CN119473084A

CN119473084A - Method, device, equipment and storage medium for template creation

Info

Publication number: CN119473084A
Application number: CN202411534695.1A
Authority: CN
Inventors: 周鹏; 张家伟; 吴晓媛; 陈开济; 柴炳旭; 唐词伟; 乔阳; 胡逸夫; 郑祥宇; 李政
Original assignee: Beijing Zitiao Network Technology Co Ltd
Current assignee: Beijing Zitiao Network Technology Co Ltd
Priority date: 2024-10-30
Filing date: 2024-10-30
Publication date: 2025-02-18

Abstract

Embodiments of the present disclosure provide a template creation method, apparatus, device, and storage medium to create a target template for document generation. In the method, a template creation indication for a target template is received. The structure information of the target template is presented, the structure information indicating the document structure generated based on the template creation instruction. A target template is created based at least on corresponding configuration information of one or more document portions included by the target template. According to the scheme of the present disclosure, first, the structure of a template is generated according to the creation requirement. The creator of the template is allowed to configure the various parts to be included in the document, i.e. fine tuning of the template by the creator is allowed. In this way, it can be ensured that the generated template is compatible with the creator's expectations, thereby improving the efficiency with which the template user generates documents.

Description

Method, apparatus, device and storage medium for template creation

Technical Field

Example embodiments of the present disclosure relate generally to the field of computers and, more particularly, relate to methods, apparatuses, devices, and computer-readable storage media for template creation.

Background

Currently, machine learning models can be utilized to generate text content. By training on a large amount of text data, machine learning models learn language rules and patterns, enabling automatic generation of new text content. Such machine learning models have been widely used in the fields of content authoring, data analysis, etc., thereby providing users with convenient and efficient text generation services.

Disclosure of Invention

In a first aspect of the present disclosure, a method of template creation is provided. The method includes receiving a template creation indication for a target template for document generation, presenting structural information of the target template, the structural information indicating a document structure generated based on the template creation indication, and creating the target template based at least on corresponding configuration information of one or more document parts included in the target template.

In a second aspect of the present disclosure, an apparatus for template creation is provided. The apparatus includes a receiving module configured to receive a template creation indication for a target template for document generation, a presenting module configured to present structural information of the target template, the structural information indicating a document structure generated based on the template creation indication, and a creating module configured to create the target template based at least on corresponding configuration information of one or more document parts included in the target template.

In a third aspect of the present disclosure, an electronic device is provided. The apparatus includes at least one processing unit, and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. The instructions, when executed by at least one processing unit, cause the apparatus to perform the method of the first aspect.

In a fourth aspect of the present disclosure, a computer-readable storage medium is provided. The computer readable storage medium has stored thereon a computer program executable by a processor to implement the method of the first aspect.

It should be understood that what is described in this section of the disclosure is not intended to limit key features or essential features of the embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The above and other features, advantages and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, wherein like or similar reference numerals denote like or similar elements, in which:

FIG. 1 illustrates a schematic diagram of an example environment in which embodiments in accordance with the present disclosure may be implemented;

FIG. 2 illustrates a schematic diagram of an example interface for initiating template creation, according to some embodiments of the present disclosure;

FIG. 3 illustrates a schematic diagram of an example interface for presenting structural information, according to some embodiments of the present disclosure;

FIG. 4A illustrates a schematic diagram of an example interface for presenting selected data sources, according to some embodiments of the present disclosure;

FIG. 4B illustrates a schematic diagram of an example interface for updating content description information, according to some embodiments of the present disclosure;

FIG. 5 illustrates a schematic diagram of an example interface for selecting a knowledge base, in accordance with some embodiments of the disclosure;

FIG. 6 illustrates a schematic diagram of an entry interface for a user to specify a data object, according to some embodiments of the disclosure;

FIG. 7 illustrates a schematic diagram of an example interface for skill selection, according to some embodiments of the present disclosure;

FIG. 8 illustrates a schematic diagram of an example interface for configuring dependencies, according to some embodiments of the disclosure;

FIG. 9A illustrates a schematic diagram of one example of an entry interface for receiving document preview information in accordance with some embodiments of the present disclosure;

FIG. 9B illustrates a schematic diagram of another example of an entry interface for receiving document preview information in accordance with some embodiments of the present disclosure;

FIG. 9C illustrates a schematic diagram of one example of an interface for presenting a preview document in accordance with some embodiments of the present disclosure;

FIG. 9D illustrates a schematic diagram of another example of an interface for presenting a preview document in accordance with some embodiments of the present disclosure;

FIG. 10 illustrates a flowchart of an example process of template creation, according to some embodiments of the present disclosure;

FIG. 11 shows a schematic block diagram of an example apparatus for template creation in accordance with some embodiments of the present disclosure, and

Fig. 12 illustrates a block diagram of an electronic device capable of implementing various embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been illustrated in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather, these embodiments are provided so that this disclosure will be more thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

In describing embodiments of the present disclosure, the term "comprising" and its like should be taken to be open-ended, i.e., including, but not limited to. The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions are also possible below.

In this context, unless explicitly stated otherwise, performing a step "in response to a" does not mean that the step is performed immediately after "a", but may include one or more intermediate steps.

It will be appreciated that the data (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) involved in the present technical solution should comply with the corresponding legal regulations and the requirements of the relevant regulations.

It will be appreciated that prior to using the technical solutions disclosed in the embodiments of the present disclosure, the relevant users, which may include any type of rights subjects, such as individuals, enterprises, groups, etc., should be informed and authorized by appropriate means of the types of information, usage ranges, usage scenarios, etc. involved in the present disclosure according to relevant legal regulations.

For example, in response to receiving an active request from a user, prompt information is sent to the relevant user to explicitly prompt the relevant user that the operation requested to be performed will need to obtain and use information to the relevant user, so that the relevant user may autonomously select whether to provide information to software or hardware such as an electronic device, an application program, a server, or a storage medium that performs the operation of the technical solution of the present disclosure according to the prompt information.

As an alternative but non-limiting implementation manner, in response to receiving an active request from a relevant user, the prompt information may be sent to the relevant user, for example, in a popup window, where the prompt information may be presented in a text manner. In addition, a selection control for the user to select to provide information to the electronic device in a 'consent' or 'disagreement' manner can be carried in the popup window.

It will be appreciated that the above-described notification and user authorization process is merely illustrative and not limiting of the implementations of the present disclosure, and that other ways of satisfying relevant legal regulations may be applied to the implementations of the present disclosure. The starting of the related functions of the digital assistant, the acquired data, the processing and storage modes of the data and the like of the embodiment of the disclosure should all obtain the advanced authorization of the user and other rights subjects associated with the user, and should conform to the relevant laws and regulations and agreements of protocol rules among the rights subjects.

As used herein, the term "model" may learn the association between the respective inputs and outputs from training data so that, for a given input, a corresponding output may be generated after training is completed. The generation of the model may be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs through the use of multiple layers of processing units. The neural network model is one example of a deep learning-based model. The "model" may also be referred to herein as a "machine learning model," "machine learning network," or "learning network," which terms are used interchangeably herein.

As used in text, the term "document" refers to material used to record information. In some embodiments, the document may be an electronic document in any suitable format, such as a document in a web page, a word document, a Portable Document Format (PDF) document, and so forth. In embodiments of the present disclosure, a document may have any suitable type of content, including but not limited to text, tables, pictures, formulas, and the like.

As used herein, the term "document section" may refer to a portion of a document that is used to organize content. The document parts may have different granularities depending on the specific implementation. For example, the document portion may be a chapter. As another example, the document portion may be a paragraph. Further, although all are referred to as document parts, a plurality of document parts in the same document may have a hierarchy. For example, one document portion may be the next level of another document portion. The document portion may have a title, a body, and optionally auxiliary text (e.g., notes, footnotes, etc.). In particular, if document part a is the next level of document part B, document part a may be considered as at least part of the body of document part B.

As used herein, a "document template" or "template" may refer to an electronic, computer-processable file that describes how a document is generated.

As briefly described above, the machine learning model may be applied to the fields of content authoring, data analysis, and the like. In one approach, a service provider may provide services such as document generation to users (e.g., enterprise users) by means of a machine learning model. In this approach, the machine learning model freely generates documents from knowledge learned by itself. However, in some scenarios (e.g., in enterprise user-oriented scenarios), users may have similar or uniform requirements for a certain type of document. In such a scenario, if the machine learning model is free to generate documents, the user may take more time and effort to modify the generated documents. This undoubtedly reduces the efficiency of document generation.

In view of the above, embodiments of the present disclosure provide a template creation scheme to create a target template for document generation. In this scenario, a template creation indication for a target template is received. The structure information of the target template is presented, the structure information indicating the document structure generated based on the template creation instruction. A target template is created based at least on corresponding configuration information of one or more document portions included by the target template.

As will be more clearly understood from the following description, according to the scheme of the present disclosure, the structure of a template is first generated according to the creation requirement. The creator of the template may use the configuration generated according to the creation requirements, or may configure the various parts to be included in the document, i.e. allow the creator to make fine adjustments to the template. In this way, it can be ensured that the generated template is compatible with the creator's expectations, thereby improving the efficiency with which the template user generates documents.

Example Environment

FIG. 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure may be implemented. The environment 100 relates to an application management platform 110 that may support the creation of applications and/or the running of applications. In some embodiments, the portion of the application management platform 110 that is used to support application creation may also be referred to as an application creation portion. In some embodiments, the portion of the application management platform 110 that is used to support application execution may also be referred to as an application execution portion.

As shown, the application creation section may provide the user 105 with a creation and release environment for the application. The user 105 may be referred to as an application creation user, creator. In some embodiments, the application creation portion may be a low code platform that provides a collection of tools for application creation. The application creation part can support visual development of various applications, so that a developer can skip the process of manual coding, and the development period and cost of the applications are quickened. The application creation portion may support any suitable platform for a user to develop one or more types of applications, and may include, for example, an application platform-based, i.e., service (aPaaS) platform. The platform can support the user to develop the application with high efficiency, and realize the operations of application creation, application function adjustment and the like.

The application creation portion may be deployed locally to the terminal device of the user 105 and/or may be supported by a server device. For example, a terminal device of user 105 may run a client with an application creation portion that may support user interactions with the application creation portion provided by the server. In the case where the application creation section runs locally at the user's terminal device, the user 105 can interact directly with the local application creation section using the terminal device. In the case where the application creation section operates on the server side device, the server side device may realize service provision to the client side operating in the terminal device based on the communication connection with the terminal device. The application creation section may present the corresponding interface 130 to the user 105 based on the operation of the user 105 to output to the user 105 and/or receive information related to application creation from the user 105.

In some embodiments, the application creation section may be associated with a corresponding database in which data or information required for the application creation process supported by the application creation section is stored. For example, the database may store codes and description information and the like corresponding to the respective functional modules constituting the application. The application creation section may also perform operations such as calling, adding, deleting, updating, etc. on the function modules in the database. The database may also store operations that are performed on different functional blocks. For example, in a scenario in which an application is to be created, the application creation section may call corresponding function blocks from the database to build the application.

In an embodiment of the present disclosure, the user 105 may create the target application 120 on the application creation section as needed and issue the target application 120. The target application 120 may be published to any suitable application running portion as long as the application running portion is capable of supporting the running of the target application 120. After release, the target application 120 may be available for operation by one or more end users 145. The end user 145 may operate the target application 120 through an associated terminal device 146 and in turn interact with the application management platform 110. End user 145 may be referred to as an end user of target application 120. In some embodiments, the target application 120 may include or be implemented as a digital assistant 122.

The digital assistant 122 may be configured with intelligent dialog capabilities. In the example shown in FIG. 1, digital assistant 122 may be integrated within target application 120 as part of target application 120 to assist in performing task processing within target application 120. In other examples, digital assistant 122 may be configured as a stand-alone application, such as a web application or other type of application. In such an example, the digital assistant 122 may be considered the same application as the target application 120. The digital assistant 122 is provided to assist the user in various task processing needs for different applications, scenarios. During interaction with the digital assistant 122, the user enters an interaction message, and the digital assistant 122 provides a reply message in response to the user input. In general, the digital assistant 122 is capable of supporting a user to input questions in natural language and perform tasks and provide replies based on understanding and logical reasoning capabilities of the natural language input.

In some embodiments, digital assistant 122 may interact with end user 145 as a contact. For example, digital assistant 122 may be implemented in an Instant Messaging (IM) application. Digital assistant 122 may interact with end user 145 in a single chat session with end user 145. In some embodiments, digital assistant 122 may interact with multiple users in a group chat session that includes multiple users.

For each end user 145, the client of the application run section may present various interfaces of the target application 120 in the client interface. In the example of FIG. 1, an end user 145 is shown interacting with window 142 of digital assistant 122, such as a conversation window with digital assistant 122. End user 145 may enter a session message in the session window and target application 120 may determine a reply message to digital assistant 122 based on the created configuration information and present to the user in interactive window 142. In some embodiments, depending on the configuration of the target application 120, the interaction message with the target application 120 may include a multimodal form of message, such as a text message (e.g., natural language text), a voice message, an image message, a video message, and so forth.

Similar to the application creation section, the application execution section may be deployed locally to the terminal device of each end user 145 and/or may be supported by a server device. For example, the terminal device of end user 145 may run a client having an application running portion that may support user interaction with the application running portion provided by the server. In the case where the application run-time portion is running locally at the user's terminal device, the end user 145 may interact directly with the local application run-time portion using the terminal device. In the case where the application running section runs on the server device, the server device may realize service provision to the client running in the terminal device based on the communication connection with the terminal device. The application execution portion may present the corresponding application page to the end user 145 based on the operation of the end user 145 to output to the end user 145 and/or receive information related to application usage from the end user 145.

In some embodiments, the implementation of at least a portion of the functionality of the target application 120, and/or the implementation of at least a portion of the functionality of the digital assistant 122 in the target application 120, may be implemented based on a machine learning model (simply referred to as a model). One or more models 155, such as the capabilities of the models 155, may be invoked during creation or execution of the target application 120. In the target application 120, the digital assistant 122 may utilize the model 155 to understand the user input and respond to the user input based on the output of the model 155, e.g., provide a reply to the user input.

In the creation process, testing of the target application 120 by the application management platform 110 requires the use of the model 155 to determine that the results of the operation of the target application 120 are expected. During execution, the application execution portion may need to utilize model 155 to determine a response result to a user in response to different operation requests by the user of target application 120.

Although shown as being independent of the application management platform 110, one or more models 155 may run on the application management platform 110, or other remote servers. In some embodiments, the model 155 may be a machine learning model, a deep learning model, a neural network, or the like. In some embodiments, the model may be based on a Language Model (LM). The language model can have question-answering capability by learning from a large number of corpora. Model 155 may also be based on other suitable models.

In some embodiments, the target application 120 may provide authoring functionality, e.g., the target application 120 may be an authoring application or may include authoring components. Such authoring functionality may be implemented by means of one or more models 155, and thus may also be referred to as "smart authoring". In some embodiments, the user 105 may generate or create a document template for authoring through the application management platform 110. The created document template may be distributed to end users 145 of the target application 120. In some embodiments, the application management platform 110 may support a template creation mode from scratch. For example, the user 105 may input a requirement for a template that is desired to be generated to initiate the template creation process. In some embodiments, the application management platform 110 may support a template creation schema based on an existing document (also referred to as a template or reference document). For example, the user 105 may specify an existing document to initiate the template creation process.

In some embodiments, end user 145 may write, i.e., generate, a document through target application 120. The application management platform 110 may support various suitable document generation modes. In some embodiments, the application management platform 110 may support a template-based document generation schema. For example, end user 145 may generate a document using templates created and distributed by user 105. In some embodiments, the application management platform 110 may support a document generation schema based on existing documents. For example, end user 145 may designate an existing document as a reference to generate the target document. In some embodiments, the application management platform 110 may support a document generation schema from scratch. For example, end user 145 may input a requirement for a document desired to be generated to initiate the document generation process.

The application management platform 110 may run on an appropriate electronic device. The electronic device herein may be any type of device having computing capabilities, including a terminal device or a server device. The terminal device may be any type of mobile terminal, fixed terminal, or portable terminal, including a mobile handset, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, media computer, multimedia tablet, personal Communication System (PCS) device, personal navigation device, personal Digital Assistant (PDA), audio/video player, digital camera/camcorder, positioning device, television receiver, radio broadcast receiver, electronic book device, game device, or any combination of the preceding, including accessories and peripherals for these devices, or any combination thereof. The server devices may include, for example, computing systems/servers, such as mainframes, edge computing nodes, computing devices in a cloud environment, and so forth. In some embodiments, the application management platform 110 may be implemented based on cloud services.

It should be understood that the structure and function of environment 100 are described for illustrative purposes only and are not meant to suggest any limitation as to the scope of the disclosure. For example, while a single user interacting with the application creation section and a single user interacting with the application execution section are illustrated, in practice multiple users may access the application management platform 110 to each create a digital assistant, and each digital assistant may be used to interact with multiple users.

Some example embodiments of the present disclosure will be described in detail below with reference to examples of the accompanying drawings. It should be understood that the pages shown in the drawings are merely examples, and that various page designs may actually exist. Individual graphical elements in a page may have different arrangements and different visual representations, one or more of which may be omitted or replaced, and one or more other elements may also be present. Embodiments of the disclosure are not limited in this respect.

The processes described in the embodiments of the present disclosure may be implemented on an application management platform, a terminal device on which the application management platform is installed, and/or a server corresponding to the application management platform. In the examples below, the description is from the perspective of an application management platform, such as application management platform 110 shown in FIG. 1, for discussion purposes. The user interface presented by the application management platform 110 may be presented via the terminal device of the user 145 and the application management platform 110 may receive user input via the terminal device of the user 145. In some embodiments, user 145 is an end user of target application 120. It should be appreciated that the user interface presented by the application management platform 110 may also be presented via the terminal device of the user 105, and that the application management platform 110 may also receive user input via the terminal device of the user 105. In some embodiments, the user 105 is a creator, manager, or maintainer of the target application 120.

Example interactions

Fig. 2-9D illustrate example interfaces according to some embodiments of the present disclosure. Interfaces 200-900D may be provided by application management platform 110 shown in fig. 1, for example.

The user 105 creates a document template for document generation through the target application 120. The template creation indication is used to indicate the template that the user desires to generate. For example, the template creation indication may include a template identification of the target template (e.g., a template name or number for distinguishing the template). The template creation indication may include template description information for the target template, the template description information representing a user's generation requirements for the target template (such as a genre of the target template, document content corresponding to the target template, an application scenario of the target template, etc.). The template creation indication may also include a reference data source that may be used in the target template generation process. The reference data sources include internal data (e.g., an internal knowledge base of the organization in which the user 105 is located), public data (e.g., data that may be obtained through an internet search), and data objects specified by the user 105 (e.g., local documents or online documents uploaded by the user 105), among others. In some embodiments, the template creation indication may also include a template hierarchy or the like, e.g., outline hierarchy (such as layer 2, layer 3).

FIG. 2 illustrates a schematic diagram of an example interface 200 for initiating template creation, according to some embodiments of the present disclosure. As shown in fig. 2, an interface 200 for obtaining a template creation instruction is presented at the terminal device of the user 105. The application management platform 110 may obtain a template creation indication entered by the user 105 through the presented interface 200. As shown in fig. 2, interface 200 includes various interface elements to obtain template creation requirements. For example, FIG. 2 shows a template generation control 210, an entry 211 for obtaining template identification information, an entry 212 for obtaining template description information, an entry 213 for selecting a knowledge base, an entry 214 for setting template layer numbers, and so forth. The template identification component 211 is for receiving a template identification. The template description information component 212 provides the user with the requirements for generating the target template. The knowledge base selection portal 213 allows the user to select a knowledge base to which the creation template and document generation refer. Template layer progression component 214 is used to determine the hierarchy of the generated target template. If the template generation control 210 is opened, the application management platform 110 initiates a template creation process to generate a target template based on the template creation instruction acquired by the instruction acquisition component 210.

The provision of the target creation indication via the interface element described with reference to fig. 2 is merely exemplary and is not intended to be limiting in any way. The user 105 may give the template creation indication in various suitable ways. In some embodiments, the user 105 may provide the template creation indication by way of voice input or text input, and the template creation indication entered by the user 105 may be in the form of natural language. In this way, the goal creation process can be further simplified, improving the goal creation efficiency and the user's use experience. It should be understood that this is merely an exemplary function and is not intended to be limiting in any way.

In some embodiments, in response to user 105 initiating a template creation process, application management platform 110 creates a document structure (e.g., outline of the template) that indicates the generation of the target template based on the retrieved template. Illustratively, the target application 120 may determine the outline of the target template from the acquired template description information and template hierarchy information using a machine learning model (which may be, for example, a generic language model or a trained outline generation model). For example, the template description information indicates that the generated target template is for an industry analysis report, and the template layer number in the template creation indication is 2. The generated template outline at least comprises the contents of industry background, industry current analysis, industry growth trend and the like, and the template outline is divided into two layers. The number of levels of the outline in the template outline generated by the target application 120 is determined based on the user input. Illustratively, the outline creation model may be a language model. The template creation instruction may be provided to the outline generation model in the form of a hint word to generate a corresponding template outline. The outline may include one or more document parts (e.g., paragraphs or chapters of a document).

After generating the document structure of the target template, the document structure is presented to the user 105. FIG. 3 illustrates a schematic diagram of an example interface 300 for presenting selected data sources, according to some embodiments of the present disclosure. In interface 300, user 105 may view the document structure of the target template to further improve the user's engagement of the template generation process. Meanwhile, the application management platform 110 may also obtain feedback information of the user on the document structure of the template, so as to adjust the document structure of the template according to the user's desire. In this way, the generated document structure can be made more satisfactory to the user's expectations and the quality of the target template can be improved. Illustratively, the application management platform 110 may utilize the interface 300 to obtain feedback information of the user. As shown in fig. 3, the interface 300 includes a navigation area 310 and an editing area 320. In addition, the interface 300 also includes a "return" control for returning to a previous interface, a "template settings" control 330 for regenerating the target template, and a document preview control 340.

Navigation information about the structure of the document is presented in the navigation area 310. The user 105 can quickly view the document structure through the navigation information presented by the navigation area. As shown in FIG. 3, navigation items respectively corresponding to the document parts are presented in navigation area 310, e.g., navigation item 330 corresponds to the document part "industry development overview". The user 105 may change the portion of the document presented by the editing region 320 by a trigger (e.g., click, etc.) to the navigation region 310. Illustratively, the application management platform, in response to a user trigger for a target navigation item in the navigation area, presents a document portion corresponding to the target navigation item in the editing area 320. For example, the document portion may be presented in an edit item of the document portion.

The edit section 320 is used to obtain user 105 interaction with respect to the document structure to adjust the document structure of the template according to user desires. As shown in FIG. 3, editable items corresponding to one or more document portions included in the target template are presented in the editing area 320. The user 105 may configure the corresponding document portion by interacting with the editable items in the editing area 320. If a user selection operation is received for any of the editable items in the edit section 320 (e.g., clicking on the editable item), one or more interface elements for the portion of the document corresponding to the editable item are presented in the area corresponding to the editable item. For example, in FIG. 2, a modification configuration entry 321 for editing a document portion, a delete control 322 for deleting the document portion is shown.

In the example of fig. 3, interface 300 includes interface elements (such as editable items, etc.) in an edit area for interacting with user 105, through which the user modifies the structure and configuration of the template. Alternatively or additionally, in some embodiments, the interface may include or be associated with a text or voice input portal. The text or voice input portal is for receiving text editing instructions or voice editing instructions provided by the user 105. The text editing indication or the speech editing indication may be an indication in natural language. The application management platform 110 is responsive to the user provided indication in the form of natural language and updates the configuration information of the document portion based on an understanding of the natural language indication.

In some embodiments, the user 105 may input an update indication for a certain document portion to the target application 120 through the editing region 320. The application management platform 110 updates the structural information (such as text format, text hierarchy, etc.) of the template according to the update instruction. For example, the user 105 inputs an update instruction indicating a change in the position of the target document portion, and the application management platform 110 changes the position of the target document portion according to the update instruction, thereby updating the structural information of the target.

Illustratively, the user may change the position of the document portion by an operation of dragging the editable item. For example, section "industry chain analysis" in FIG. 3 is dragged under section "industry consumer behavior analysis" to change the structural information of the template. The user can click on the editable item "industry chain analysis" and change the hierarchy of the document part in the popped modification menu.

In some embodiments, the application management platform 110 determines the corresponding configuration information for the document portion included by the target template based on the user's 105 interactions with the presented structural information. The interactive operations of the user 105 may include, for example, selection operations (i.e., selection of any editable item), input operations (i.e., input into the interface 300). For document information presented by interface 300, user 105 provides a configuration indication through the presented editing region 320. The application management platform 110 determines configuration information corresponding to each document part based on the configuration instruction provided by the user. Illustratively, for the first document portion, the user 105 may provide configuration information to the application management platform 110 via an editable item corresponding to the first document portion. The configuration information may include a reference data source corresponding to each document part, document description information, dependencies between a plurality of document parts, and the like.

FIG. 4A illustrates a schematic diagram of an example interface 400A for presenting selected data sources, according to some embodiments of the present disclosure. As shown in fig. 4A, any editable item in interface 400A has a modification configuration entry 321 and a delete control 322 corresponding thereto. For any editable item, its corresponding modification configuration entry 321 may be in a hidden state. In response to a user's 105 selection operation of an editable item corresponding to a first portion of a document in the editing area 320 (e.g., clicking on the editable item, or moving a cursor to the editable item, etc.), a modification configuration entry 321 corresponding to the editable item is presented in the interface 400A.

The application management platform 110 may present the data sources for which the respective document portions have been configured to the user so that the user 105 can determine the data source configuration status of the document, improving the template creation efficiency. In some embodiments, the application management platform 110 presents to the user 105 a data source for which the target document portion has been configured in response to a data source view request by the user 105 for the target document portion. The data source configured by the target document portion will be used to generate the content of the target document portion. The target document portion for which the data source viewing request is directed may be any document portion in the target template or the target template as a whole.

As shown in fig. 4A, a data source query control 323 is presented in a corresponding region of the editable item of the editing area 320. The icon of the data source query control 323 can include an identification of the configured data source. The user 105 provides a data source query request to the application management platform 110 through interaction (e.g., a click operation, etc.) with the data source query control 323. The application management platform 110 presents the data source presentation area 410 to the user in response to a data source query request for the target document portion. In the data source presentation area 410, different kinds of data sources may be presented in categories. For example, the data source presentation area 410 includes a first area 411 for presenting a knowledge base (e.g., pet industry analysis knowledge base, integrated market analysis knowledge base) and data objects specified by the user 105 (e.g., documents uploaded by the user 105) and a second area 412 for presenting a common data source (e.g., internet web site links). Illustratively, in the data source presentation area 410, brief description information of the data source may also be presented for use in determining the content of the configured data source.

In some embodiments, to facilitate user configuration, the application management platform 110 may present information to the user 105 of a candidate knowledge base including target templates. The candidate knowledge base may include a knowledge base that has access rights to a set of users to which the user 105 belongs (e.g., a knowledge base maintained by an organization in which the user 105 belongs). Further, a knowledge base related to the template creation requirement may be selected as a candidate knowledge base from all knowledge bases having access rights based on the template creation requirement. The presented information of the candidate knowledge base includes an identification of the candidate knowledge base, a summary description of the knowledge base, and the like.

In some embodiments, the application management platform 110 may provide a target creation service to a plurality of members within an organization. In order to ensure the security of internal data, different data access rights need to be provided for different members within an organization. For any member within the A organization, the portion of the internal knowledge base and internal knowledge about the A organization in the application management platform 110 cannot be used as a reference data source for the target template. For example, if the member does not have access to knowledge base B, knowledge base B cannot serve as a reference data source for the target template created by the member. Accordingly, the application management platform 110, upon receiving the knowledge configuration indication sent by the user 105, first determines the data access rights of the user 105. Based on the data access rights of the user 105, data and knowledge that can be applied to the templates created by the user 105 are determined. The user 105 is then presented with information including candidate knowledge bases available for the target templates to facilitate user selection.

In some embodiments, the content description information generated by the machine learning model may not accurately reflect the user's desire for the document portion. Thus, the user 105 can make adjustments to the content description information. The application management platform 110 may update the content description information based on the received user input for the content description information. Fig. 4B illustrates a schematic diagram of an update interface 400B for content description information, according to some embodiments of the present disclosure. As shown in fig. 4B, the interface 400B includes a paragraph configuration area 420, a document preview control 340, an entry 421 for obtaining content description information of a document portion, a content generation control 422, and a dynamic generation control 423. The application management platform 110 may receive content description information provided by the user 105 through the portal 421. As shown in FIG. 4B, preference settings control 424 and data source configuration control 425 may also be included in interface 400B. Preference setting control 424 is used to set paragraph lengths, line styles, and the like in the document part configuration information. The data source configuration control 425 is used to receive an indication of the configuration of the data source by the user 105. Illustratively, if the user 105 considers that the currently configured data source of the target document portion is not sufficiently comprehensive, generating the content of the target document portion based on the currently configured data source is of poor quality and cannot meet the expectations. The user may send a data source configuration request to the application management platform 110 to update the data source of the target document portion configuration by interacting with respect to the data source configuration control 425 (e.g., clicking on the data source configuration control 425).

For example, the application management platform 110 may present an interface for acquiring data and knowledge to the user 105 in response to a data source configuration request sent by the user 105. The interface includes at least an entry for receiving data to obtain data uploaded by a user or a specified knowledge base. In some embodiments, the application management platform 110 may provide different interfaces for the user 105 to receive different types of data sources uploaded by the user 105, respectively. Fig. 5 illustrates a schematic diagram of a knowledge base presentation interface 500, in accordance with some embodiments of the present disclosure. The application management platform 110 can present a knowledge base selection interface to the user in response to the user 105 interacting with the data source configuration control 425. As shown in fig. 5, included in interface 500 are an entry 510 for specifying a data object, an entry 520 for adding skills in target application 120, an entry 530 for configuring dependencies between different document parts, and an entry 540 for configuring data and knowledge (i.e., determining a target knowledge base for generating document part content), and the like. The user 105 may configure the data source for the document portion through different portals. Illustratively, the application management platform 110 presents to the user 105 at an interface 500 (which is, for example, a panel) a plurality of candidate knowledge bases available for the target templates in response to user selection of the portal 540. The user 105 may select the candidate repository as the target repository by appropriate operations (e.g., checking a selection box before the candidate repository). The application management platform 110 determines a target knowledge base based on the selection operation of the user 105. Accordingly, configuration information for the first document portion is determined based on the target knowledge base. That is, it is determined that the application management platform 110 will refer to the target knowledge base, generating the content of the first document portion. In some embodiments, the application management platform 110 may also generate target templates based on other reference data sources.

Fig. 6 illustrates a schematic diagram of an entry interface 600 for a user to specify a data object, according to some embodiments of the disclosure. As shown in FIG. 6, in response to a user selection of portal 510, the user is presented with an interface 600 (which may be, for example, a panel) that includes portals for specifying different types of data objects. In this example, an entry 610 for uploading local files, an entry 620 for adding a uniform resource location system (uniform resource locator, URL), and an entry 630 for adding text are included in the interface 600. The user 105 may provide different types of local profiles to the application management platform 110 by operating different portals.

Fig. 7 illustrates a schematic diagram of an example interface 700 for skill selection, according to some embodiments of the present disclosure. As shown in fig. 7, in response to a user selection of an entry 520, the user is presented with an interface 700 (which may be a panel, for example) that includes entries for specifying different skills. Options 710 through 750 for one or more skills created by target application 120 are presented in interface 700. The user 105 may select skills through the interface 700. In this way, the selected skills may be utilized in the process of end user 145 generating a document using the target template after the target template is published. In the case where the target template is created in the target application, the skills that can be selected may be skills configured or created in the target application. Skills may also be referred to as functions, which are configured to perform predetermined tasks.

In some embodiments, to ensure logical continuity between multiple document portions in a template generated by the application management platform 110, to improve document quality, the user 105 may configure interdependencies between the different document portions. The dependency relationship between different document parts includes an association relationship having one or more logics. For example, the different document portions may be in a side-by-side relationship, a causal relationship, a conditional relationship, or the like. In generating a document based on a template having a dependency relationship, a document part is regenerated after its dependent document part is generated, and the content of its dependent document part is used as a reference material. For example, the user 105 may make the second document part dependent on the first document part via the configuration information. In generating a document using the template, the content of the first document portion will be generated before the second document portion. The content of the first document part is used as a reference data source for the second document part. It will be appreciated that any document portion may only depend on the preamble portion in the document structure.

In some embodiments, the subject content of the document part that is relied upon by the target document part (i.e., the subject content that is relied upon) will be used to generate the subject content of the target document part (i.e., the target subject content). The type of dependency between documents will affect how the subject content being relied upon is used in the target subject content generation process. For example, if the target document portion is in a juxtaposition with the dependent document portion, the dependent subject content will only serve as a reference and will not appear in the target subject content. If the target document portion is causal to the relied document portion, the relied subject content will serve as a data source for generating the target subject content.

In some embodiments, the target subject content may be generated using a machine learning model. The application management platform 110 provides hint information to the machine learning model based on the subject content and the dependency of the target document portion to obtain an output of the machine learning model. Based on the dependency relations of different types among the document parts, the application management platform can generate prompt information of different types so as to improve the output quality of the machine learning model. For example, if the target document portion is in a juxtaposition with the relied document portion, the hint information instructs the model to generate target subject content having a juxtaposition in accordance with the relied subject content. If the target document portion is causal to the relied document portion, the hint information instructs the model to generate causal target subject content from the relied subject content. Then, based on the output of the machine learning model, the body content of the second document portion is determined. In this way, it is ensured that the content of the dependent document part will be perceived by the target document part, avoiding the generation of duplicate, non-self consistent content in the document.

FIG. 8 illustrates a schematic diagram of an example interface 800 for configuring dependencies, according to some embodiments of the disclosure. As shown in FIG. 8, the application management platform 110 presents options 810 through 840 in the interface 800 for other document parts in the target template in response to a relationship configuration indication by the user 105 for any document part. The user 105 may determine the target document portion on which the generation of the current document portion will depend by operating (e.g., checking a selection box preceding the target document portion).

To further ensure that the generated templates are used to generate documents, the generated documents may be in agreement with the desires of the user 105 by configuring content description information for each document portion. The content description information indicates a generation requirement (i.e., user desire) for the body content of the document portion. In some embodiments, the content description information may be generated based on the template creation indication. Illustratively, the content description information in the template creation instruction is provided to the machine learning model to generate corresponding content description information. The content description information may include information on the content, genre, and paragraph length of the document part. In some embodiments, the document generated based on the created target template may not meet the expectations of the user 105. Thus, to improve the quality of the created target templates, the application management platform 110 may support the debugging of the configuration information of the templates by the creator of the templates (e.g., the user 105). For example, the preview document may be presented to the user based on the created target template to enable the user to more accurately evaluate whether the target template meets the expectations. The application management platform 110 presents the preview document to the user 105 in response to receiving the document preview information. The document preview information may include document generation requirements to indicate a user's desire for a document to be generated. The document generation requirements may be information entered by the user or information generated based on the template creation instruction. In some embodiments, the document preview information can also include supplemental material for generating the preview document, such as user-specified data objects, user-entered text, internet public data, and the like. The application management platform 110 may generate the preview document in combination with the data source in the target template and the supplemental material indicated by the document preview information to make the preview document more desirable to the user. In some embodiments, different types of supplemental material may be acquired separately using different interfaces in order to facilitate the user 105's input of the supplemental material.

FIG. 9A illustrates a schematic diagram of one example of an entry interface 900A for receiving document preview information in accordance with some embodiments of the present disclosure. As shown in FIG. 9A, a document preview control 340 and an entry 910 for obtaining document preview information are included in interface 900A. The application management platform 110 presents the portal 910 and corresponding navigation information to the user in response to the user's 105 selection of the document preview control. The user 105 may provide document preview information to the application management platform 110 through interaction with the portal 910. Further, portal 910 includes a portal 911 for obtaining text, a portal 912 for receiving links (e.g., internet addresses), a portal 913 for receiving user-specified data objects (e.g., local documents or online documents, etc.), and a document generation control 914. The user 105 may designate different types of supplemental material through entries 911 through 913, respectively.

In some embodiments, the data sources currently configured by the target template can be presented to the user, so that the user can know the data sources currently configured, and the document preview efficiency is improved. FIG. 9B illustrates a schematic diagram of another example of an entry interface 900B for receiving document preview information in accordance with some embodiments of the present disclosure. As shown in FIG. 9B, the user 105 is presented with the target template or the data sources for which the selected document portions in the target template have been configured in the data source presentation area 915. If the user 105 confirms that the material that needs replenishment does not appear in the data source presentation area 915, the replenishment material is provided to the application management platform 110 via the portal 910. Illustratively, the data source presentation area may present the configured data sources to the user 105 in the form of a thumbnail.

The application management platform 110, upon receiving the document preview information for the target template, initiates a process of generating a preview document in response to selection of the document generation control by the user 105. The application management platform 110 generates a corresponding preview document based on the received document preview information and the target template. The generated preview document is then presented to the user in order for the user to determine the target template and the desired variance based on the preview document. FIG. 9C illustrates a schematic diagram of one example of an interface 900C for presenting a preview document in accordance with some embodiments of the present disclosure. As shown in FIG. 9C, the application management platform 110 generates a preview document in response to a user 105 selecting a document generation control. The preview document is then presented to the user 105 in the editing area 320 of the interface 900A. The preview document includes each document portion of the target template and content corresponding to each document portion.

In some embodiments, if the generated preview document differs significantly from the user's desired, the user 105 may update the configuration information corresponding to the target document portion in the target template. For example, content description information corresponding to the target document portion is updated or a data source or the like on which the target document portion depends to generate content is updated. FIG. 9D illustrates a schematic diagram of another example of an interface 900D for presenting a preview document in accordance with some embodiments of the present disclosure. As shown in fig. 9D, a preview document is presented in the editing area 320 in the interface 900D. The application management platform 110 presents an entry 321, a delete control 322, and a data source query control 323 corresponding to each document portion for modifying the configuration of the target document portion in the editing zone 320 to obtain an update instruction of the user for the target document portion. In some embodiments, the application management platform 110 may present the entries 321 corresponding to respective document portions, or may present the entries 321 corresponding to selected document portions in response to a user's 105 selection of a document portion. In some embodiments, the application management platform 110 may also present configuration information corresponding to the document portion for viewing by the user. As shown in FIG. 9D, in response to a user's 105 selection of a target document portion, the data sources upon which the content of the document portion is to be generated are presented in the data source presentation area 410 corresponding to the target document portion. To facilitate the user 105 in determining the quality of the updated template, the application management platform 110 may regenerate the preview document after the user 105 updates the configuration information. Thus, the quality of the target template is determined based on the regenerated preview document.

In some embodiments, if the user 105 does not perform an update operation on the configuration information of all document parts, or performs a plurality of update operations on the configuration information corresponding to a certain document part. The application management platform 110 needs to frequently generate the full text of the preview document, which causes inconvenience to the user 105. Thus, in some embodiments, only preview content corresponding to a portion of a document portion may be generated. As shown in FIG. 4B, the user 105 may also control the application management platform 110 to generate content corresponding to a document portion via the content generation control 422 corresponding to the document portion. The application management platform 110 presents corresponding content in response to the preview indication entered by the user 105. The user 105 views the presented content, further modifying the configuration information of the document portion based on the differences in the desire for the document and the presented content. Then, based on the modified configuration information, the content corresponding to the document portion is generated again.

In some embodiments, if the currently created target template is widely spaced from what is expected by the user 105, more configuration information needs to be modified, which can affect the efficiency with which the user creates the target template. Thus, the user 105 may discard the current template and create a new target template. Illustratively, the user 105 may select the template setup control 330 to send an indication to the application management platform 110 to recreate the target template. The application management platform 110 presents the interface 200 to the user to reacquire the template creation indication for creating the target template in response to the user selecting the template setting control 330.

In some embodiments, if the created target template can meet the user's expectations, the user 105 may export the created target template through an export control. The exported templates may be provided to other users within the organization to facilitate the user's generation of corresponding target documents via the templates. For example, the exported templates may be published within the target application for selection and use by end users of the target application.

In some embodiments, the application management platform 110 may support dynamic generation (also referred to as depth generation). A header is dynamically generated that indicates the portion of the document that was dynamically generated during the document generation process. In the case of dynamic generation, the title of the document part is generated in real time from the retrieved information. As shown in fig. 4B, for a document portion, the corresponding dynamically generated control 423 for that document portion is opened by the user 105. Accordingly, the application management platform 110 receives an indication that dynamic generation is enabled for the document part and takes this indication as part of the document part configuration information. Thus, one or more sub-portions included in the document portion will be dynamically determined in the document generation. In other words, the sub-portion (e.g., the title thereof) under the document portion is not included in the target template. For example, which primary products under the primary heading are related to the retrieved content of the document generation process, are not in the template.

Example procedure

Fig. 10 illustrates a flowchart of an example process 1000 of a template creation method according to some embodiments of the present disclosure. Process 1000 may be implemented at application management platform 110. Process 1000 is described below with reference to fig. 1.

As shown in FIG. 10, at block 1010, the application management platform 110 receives a template creation indication for a target template for document generation.

In some embodiments, the template creation indication includes at least one of a template identification of the target template, template description information for the target template, the template description information indicating a generation requirement of the target template, one or more candidate knowledge bases for the target template, or a hierarchy that the target template has.

At block 1020, the application management platform 110 presents structural information of the target template, the structural information indicating a document structure generated based on the template creation indication.

In some embodiments, presenting the structural information of the target template includes presenting an edit region for the document structure, and wherein the respective configuration information for the one or more document portions is determined based at least in part on an edit indication associated with the edit region.

In some embodiments, presenting the structural information of the target template further includes presenting navigation information about the document structure, the navigation information including one or more navigation items respectively corresponding to the one or more document portions, and in response to triggering of a navigation item of the one or more navigation items, updating the edit section to present the document portion corresponding to the triggered navigation item.

In some embodiments, the structural information is determined by providing hints information for document structure generation to the machine learning model based on the template creation indication to obtain an output of the machine learning model and determining the structural information based on the output of the machine learning model.

At block 1030, the application management platform 110 creates a target template based at least on corresponding configuration information for one or more document parts included in the target template.

In some embodiments, determining respective configuration information for one or more document portions includes receiving a knowledge configuration indication for a first document portion of the one or more document portions, presenting information regarding one or more candidate repositories available for a target template in response to the knowledge configuration indication, and determining that generation of the first document portion is to reference the target repository as at least a portion of the configuration information for the first document portion in response to selection of the target repository of the one or more candidate repositories.

In some embodiments, determining respective configuration information for one or more document portions includes receiving a relationship configuration indication for a second document portion of the one or more document portions, presenting information regarding at least one document portion of the one or more document portions in response to the relationship configuration indication, and determining that the second document portion has a dependency relationship with a target document portion of the at least one document portion as at least a portion of the configuration information for the second document portion in response to selection of the target document portion.

In some embodiments, the body content of the second document portion is generated by providing hint information to the machine learning model based on the body content and the dependency of the target document portion to obtain an output of the machine learning model in response to the configuration information of the second document portion indicating that the second document portion has a dependency with the target document portion, and determining the body content of the second document portion based on the output of the machine learning model.

In some embodiments, the dependencies include associations with one or more logics.

In some embodiments, determining respective configuration information for one or more document portions includes receiving a configuration edit indication for a third document portion of the one or more document portions, presenting content description information for the third document portion in response to the configuration edit indication, the content description information indicating a generation requirement for body content of the third document portion and generated based on the template creation indication using a machine learning model, and updating the content description information as at least a portion of the configuration information for the third document portion based on user input for the content description information.

In some embodiments, determining the respective configuration information for the one or more document portions includes receiving an indication that dynamic generation is enabled for a fifth document portion of the one or more document portions as part of the configuration information for the fifth document portion such that one or more sub-portions included in the fifth document portion are to be dynamically determined in the document generation.

In some embodiments, process 1000 further includes receiving document preview information for the target template, the document preview information indicating document generation requirements based on the target template, and presenting preview content generated separately for one or more document portions using the machine learning model based on the document preview information.

In some embodiments, process 1000 further includes receiving a configuration update indication for a fourth document portion in response to presentation of preview content of the fourth document portion of the one or more document portions, and updating configuration information for the fourth document portion based on the configuration update indication.

In some embodiments, process 1000 further includes receiving interactions for the structural information, and determining corresponding configuration information for the one or more document portions based on the interactions for the structural information.

In some embodiments, process 1000 further includes receiving an update indication for a sixth document portion of the one or more document portions, the update indication indicating at least a change in the document structure for the sixth document portion, and presenting updated structural information based on the update indication.

Example apparatus and apparatus

Embodiments of the present disclosure also provide corresponding apparatus for implementing the above-described methods or processes. Fig. 11 illustrates a schematic block diagram of an example apparatus 1100 for template creation, according to some embodiments of the disclosure. The apparatus 1100 may be implemented as or included in the application management platform 110. The various modules/components in apparatus 1100 may be implemented in hardware, software, firmware, or any combination thereof.

As shown in FIG. 11, the apparatus 1100 includes a receiving module 1110 configured to receive a template creation indication for a target template for document generation. A presentation module 1120 configured to present structural information of the target template, the structural information indicating a document structure generated based on the template creation instruction. A creation module 1130 configured to create a target template based at least on corresponding configuration information of the one or more document parts included in the target template.

In some embodiments, the presentation module 1120 is further configured to present an edit section for the document structure, and wherein the respective configuration information for the one or more document portions is determined based at least in part on an edit indication associated with the edit section.

In some embodiments, the presentation module 1120 is further configured to present navigation information about the document structure, the navigation information including one or more navigation items respectively corresponding to the one or more document portions, and in response to a trigger for a navigation item of the one or more navigation items, update the editing region to present the document portion corresponding to the triggered navigation item.

In some embodiments, the rendering module 1120 is further configured to provide hints information for document structure generation to a machine learning model based on the template creation indication to obtain an output of the machine learning model, and to determine the structure information based on the output of the machine learning model.

In some embodiments, the creation module 1130 is further configured to receive a knowledge configuration indication for a first document portion of the one or more document portions, to present information regarding one or more candidate repositories available for the target template in response to the knowledge configuration indication, and to determine that the generation of the first document portion is to refer to the target repository as at least part of the configuration information for the first document portion in response to selection of the target repository of the one or more candidate repositories.

In some embodiments, the creation module 1130 is further configured to receive a relationship configuration indication for a second document portion of the one or more document portions, to present information regarding at least one document portion of the one or more document portions in response to the relationship configuration indication, and to determine that the second document portion has a dependency relationship with a target document portion of the at least one document portion in response to a selection of the target document portion as at least a portion of the configuration information for the second document portion.

In some embodiments, the creation module 1130 is further configured to provide hint information to a machine learning model based on the subject content of the target document portion and the dependency relationship to obtain an output of the machine learning model in response to the configuration information of the second document portion indicating that the second document portion has a dependency relationship with the target document portion, and determine the subject content of the second document portion based on the output of the machine learning model.

In some embodiments, the creation module 1130 is further configured to receive a configuration edit indication for a third document portion of the one or more document portions, to present content description information for the third document portion in response to the configuration edit indication, the content description information indicating a generation requirement for subject content of the third document portion and being generated based on the template creation indication using a machine learning model, and to update the content description information as at least a portion of the configuration information for the third document portion based on user input for the content description information.

In some embodiments, the creation module 1130 is further configured to receive an indication that dynamic generation is enabled for a fifth document part of the one or more document parts as part of the configuration information for the fifth document part such that one or more sub-parts included in the fifth document part are to be dynamically determined in the document generation.

In some embodiments, the apparatus 1100 further includes a preview content rendering module configured to receive document preview information for the target template, the document preview information indicating document generation requirements based on the target template, and render preview content generated separately for the one or more document portions using a machine learning model based on the document preview information.

In some embodiments, the apparatus 1100 further includes a configuration information update module configured to receive a configuration update indication for a fourth document part of the one or more document parts in response to presentation of preview content of the fourth document part, and update configuration information for the fourth document part based on the configuration update indication.

In some embodiments, the apparatus 1100 further includes a configuration information determination module configured to receive interactions for the structural information, and determine corresponding configuration information for the one or more document portions based on the interactions for the structural information.

In some embodiments, apparatus 1100 further comprises a structural information determination module configured to receive an update indication for a sixth document part of the one or more document parts, the update indication indicating at least a change in the document structure for the sixth document part, and to present the updated structural information based on the update indication.

Fig. 12 illustrates a block diagram of an electronic device capable of implementing various embodiments of the present disclosure. As shown in fig. 12, the electronic device 1200 is in the form of a general-purpose electronic device. Components of electronic device 1200 may include, but are not limited to, one or more processors or processing units 1210, memory 1220, storage 1230, one or more communication units 1240, one or more input devices 1250, and one or more output devices 1260. The processing unit 1210 may be an actual or virtual processor and is capable of executing various processes according to programs stored in the memory 1220. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capabilities of electronic device 1200.

Electronic device 1200 typically includes a number of computer storage media. Such a medium may be any available media that is accessible by electronic device 1200 and includes, but is not limited to, volatile and non-volatile media, removable and non-removable media. The memory 1220 may be volatile memory (e.g., registers, cache, random Access Memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage 1230 may be a removable or non-removable media and may include machine-readable media such as flash drives, magnetic disks, or any other media that may be capable of storing information and/or data and that may be accessed within electronic device 1200.

The electronic device 1200 may further include additional removable/non-removable, volatile/nonvolatile storage media. Although not shown in fig. 12, a magnetic disk drive for reading from or writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data medium interfaces. Memory 1220 may include a computer program product 1225 having one or more program modules configured to perform the various methods or acts of the various embodiments of the disclosure.

The communication unit 1240 enables communication with other electronic devices through a communication medium. Additionally, the functionality of the components of the electronic device 1200 may be implemented in a single computing cluster or in multiple computing machines capable of communicating over a communications connection. Thus, the electronic device 1200 may operate in a networked environment using logical connections to one or more other servers, a network Personal Computer (PC), or another network node.

The input device 1250 may be one or more input devices such as a mouse, keyboard, trackball, etc. The output device 1260 may be one or more output devices such as a display, speakers, printer, etc. The electronic device 1200 may also communicate with one or more external devices (not shown), such as storage devices, display devices, etc., with one or more devices that enable a user to interact with the electronic device 1200, or with any device (e.g., network card, modem, etc.) that enables the electronic device 1200 to communicate with one or more other electronic devices, as desired, via the communication unit 1240. Such communication may be performed via an input/output (I/O) interface (not shown).

According to an exemplary implementation of the present disclosure, a computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the method described above is provided. According to an exemplary implementation of the present disclosure, there is also provided a computer program product tangibly stored on a non-transitory computer-readable medium and comprising computer-executable instructions that are executed by a processor to implement the method described above.

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus, devices, and computer program products implemented according to the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer readable program instructions may be provided to a processing unit of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various implementations of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The foregoing description of implementations of the present disclosure has been provided for illustrative purposes, is not exhaustive, and is not limited to the implementations disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various implementations described. The terminology used herein was chosen in order to best explain the principles of each implementation, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand each implementation disclosed herein.

Claims

1. A template creation method, comprising:

Receiving a template creation instruction for a target template, wherein the target template is used for generating a document;

presenting structural information of the target template, the structural information indicating a document structure generated based on the template creation indication, and

The target template is created based at least on corresponding configuration information of one or more document parts included by the target template.

2. The method of claim 1, further comprising:

Receiving an interaction for the structural information, and

Based on the interactions for the structural information, respective configuration information for the one or more document portions is determined.

3. The method of claim 1, wherein presenting structural information of the target template comprises:

an edit section for the document structure is presented, and wherein respective configuration information for the one or more document portions is determined based at least in part on an edit indication associated with the edit section.

4. The method of claim 3, wherein presenting structural information of the target template further comprises:

presenting navigation information about the document structure, the navigation information including one or more navigation items corresponding to the one or more document portions, respectively, and

In response to a trigger for a navigation item of the one or more navigation items, the edit section is updated to present a document portion corresponding to the triggered navigation item.

5. The method of claim 1, wherein determining respective configuration information for the one or more document portions comprises:

receiving a knowledge configuration indication for a first document part of the one or more document parts;

presenting information about one or more candidate knowledge bases available for the target template in response to the knowledge configuration indication, and

In response to selection of a target knowledge base of the one or more candidate knowledge bases, it is determined that generation of the first document portion is to reference the target knowledge base as at least a portion of configuration information for the first document portion.

6. The method of claim 1, wherein determining respective configuration information for the one or more document portions comprises:

Receiving a relationship configuration indication for a second document part of the one or more document parts;

Presenting information about at least one of the one or more document parts in response to the relationship configuration indication, and

In response to selection of a target document portion of the at least one document portion, determining that the second document portion has a dependency relationship with the target document portion as at least a portion of configuration information for the second document portion.

7. The method of claim 6, wherein the body content of the second document portion is generated by:

Providing prompt information to a machine learning model based on the subject content of the target document portion and the dependency relationship to obtain an output of the machine learning model in response to the configuration information of the second document portion indicating that the second document portion has the dependency relationship with the target document portion, and

Based on the output of the machine learning model, body content of the second document portion is determined.

8. The method of claim 6, wherein the dependency comprises an association with one or more logics.

9. The method of claim 1, wherein determining respective configuration information for the one or more document portions comprises:

Receiving a configuration edit instruction for a third document portion of the one or more document portions;

In response to the configuration editing indication, presenting content description information for the third document portion, the content description information indicating generation requirements for the body content of the third document portion and generated using a machine learning model based on the template creation indication, and

Based on user input for the content description information, the content description information is updated as at least a portion of the configuration information of the third document portion.

10. The method of claim 1, further comprising:

Receiving document preview information for the target template, the document preview information indicating document generation requirements based on the target template, and

Based on the document preview information, preview content generated separately for the one or more document portions using a machine learning model is presented.

11. The method of claim 10, further comprising:

Receiving a configuration update indication for a fourth document portion of the one or more document portions in response to presentation of preview content of the fourth document portion, and

Based on the configuration update indication, configuration information for the fourth document part is updated.

12. The method of claim 1, wherein determining respective configuration information for the one or more document portions comprises:

an indication is received that dynamic generation is enabled for a fifth document part of the one or more document parts as part of configuration information for the fifth document part such that one or more sub-parts included in the fifth document part are to be dynamically determined in document generation.

13. The method of claim 1, wherein the template creation indication comprises at least one of:

the template identification of the target template,

Template description information for the target template, the template description information indicating generation requirements of the target template,

One or more candidate knowledge bases for the target templates, or

The target template has a hierarchy.

14. The method of claim 1, further comprising:

Receiving an update indication for a sixth document part of the one or more document parts, the update indication indicating at least a change in the document structure of the sixth document part, and

Based on the update indication, the updated structural information is presented.

15. The method of claim 1, wherein the structural information is determined by:

providing a machine learning model with hints information for document structure generation based on the template creation instruction to obtain an output of the machine learning model, and

The structural information is determined based on an output of the machine learning model.

16. An apparatus for template creation, comprising:

A receiving module configured to receive a template creation indication for a target template, the target template for document generation;

A presentation module configured to present structural information of the target template, the structural information indicating a document structure generated based on the template creation instruction, and

A creation module configured to create the target template based at least on respective configuration information of one or more document parts included by the target template.

17. An electronic device, comprising:

At least one processing unit, and

At least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, which when executed by the at least one processing unit, cause the electronic device to perform the method of any one of claims 1 to 15.

18. A computer readable storage medium having stored thereon a computer program executable by a processor to implement the method of any of claims 1 to 15.