CN120409682A

CN120409682A - Method, apparatus, device and storage medium for task interaction

Info

Publication number: CN120409682A
Application number: CN202510497297.5A
Authority: CN
Inventors: 陈庆泓; 肖亦祺; 麦晋宁
Original assignee: Beijing Zitiao Network Technology Co Ltd
Current assignee: Beijing Zitiao Network Technology Co Ltd
Priority date: 2025-04-18
Filing date: 2025-04-18
Publication date: 2025-08-01

Abstract

According to an embodiment of the present disclosure, a method, apparatus, device and storage medium for task interaction are provided. The method includes: in response to a request for a task of an agent, presenting first information related to the execution process of the task in an interface for interacting with the agent, requesting task information indicating the task; in response to the suspension condition of the task being met, pausing the execution of the task; and in response to receiving an adjustment or resumption of the task in the suspended state of the task, resuming the execution of the task, wherein second information related to the execution process or execution result of the resumed task is presented in the interface. In this way, during or during the execution of the task, the user can pause and modify the execution of the task at any time to obtain results that meet their needs.

Description

Method, apparatus, device and storage medium for task interaction

Technical Field

Example embodiments of the present disclosure relate generally to the field of computers and, more particularly, relate to a method, apparatus, electronic device, computer-readable storage medium and computer program product for task interaction.

Background

With the development of information technology, more and more intelligent systems are capable of accomplishing various complex tasks based on user input. Such systems typically interact with the user in the form of a dialogue, generating response content from the user's natural language request, thereby forming a question-answer dialogue. However, in practical applications, the user's goal is often not just to obtain a sentence of answers, but rather hopes that the system will be able to complete planning and execution around a task. Therefore, how to complete the execution of a specific task based on the task target driving model and improve the structuring degree and the user controllability of the execution process becomes a concern.

Disclosure of Invention

In a first aspect of the present disclosure, there is provided a method for task interaction, comprising presenting first information related to an execution process of a task in an interface interacting with an agent in response to a request for the task of the agent, requesting task information indicating the task, causing execution of the task to be suspended in response to a suspension condition of the task being satisfied, and resuming execution of the task in response to receiving an adjustment or resumption of the task in a suspended state of the task, wherein second information related to the execution process or an execution result of the resumed task is presented in the interface.

In a second aspect of the present disclosure, there is provided an apparatus for task interaction, including a first information presentation module configured to present first information related to an execution process of a task in an interface interacting with an agent in response to a request for the task of the agent, the request indicating task information of the task, an execution suspension module configured to suspend execution of the task in response to a suspension condition of the task being satisfied, and an execution resumption module configured to resume execution of the task in response to receiving an adjustment or resumption of the task in a suspension state of the task, wherein second information related to the execution process or an execution result of the resumed task is presented in the interface.

In a third aspect of the present disclosure, an electronic device is provided. The apparatus includes at least one processor, and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. The instructions, when executed by at least one processor, 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 computer-executable instructions executable by a processor to implement the method of the first aspect.

According to a fifth aspect of the present disclosure, there is provided a computer program product comprising computer executable instructions which when executed by a processor 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 of the present disclosure may be implemented;

2A-2I illustrate schematic diagrams of example interfaces for interacting with an agent, according to some embodiments of the present disclosure;

FIG. 3 illustrates a flow chart of a process for task interaction according to some embodiments of the present disclosure;

FIG. 4 illustrates a block diagram of an apparatus for task interaction in accordance with some embodiments of the present disclosure, and

Fig. 5 illustrates a block diagram of an electronic device capable of implementing one or more embodiments of the 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 or use 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 user should be informed and authorized of the type, usage range, usage scenario, etc. of the personal information related to the present disclosure in an appropriate manner according to relevant legal regulations.

For example, in response to receiving an active request from a user, prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using personal information to the user, so that the user may autonomously select whether to provide personal information to software or hardware such as an electronic device, an application, 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, in response to receiving an active request from a user, the prompt information may be sent to the 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 personal 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.

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.

A "neural network" is a machine learning network based on deep learning. The neural network is capable of processing the input and providing a corresponding output, which generally includes an input layer and an output layer, and one or more hidden layers between the input layer and the output layer. Neural networks used in deep learning applications typically include many hidden layers, thereby increasing the depth of the network. The layers of the neural network are connected in sequence such that the output of the previous layer is provided as an input to the subsequent layer, wherein the input layer receives the input of the neural network and the output of the output layer is provided as the final output of the neural network. Each layer of the neural network includes one or more nodes (also referred to as processing nodes or neurons), each of which processes input from a previous layer.

Generally, machine learning may generally include three phases, namely a training phase, a testing phase, and an application phase (also referred to as an inference phase). In the training phase, a given model may be trained using a large amount of training data, iteratively updating parameter values until the model is able to obtain consistent inferences from the training data that meet the desired goal. By training, the model may be considered to be able to learn the association between input and output (also referred to as input to output mapping) from the training data. Parameter values of the trained model are determined. In the test phase, test inputs are applied to the trained model to test whether the model is capable of providing the correct outputs, thereby determining the performance of the model. In the application phase, the model may be used to process the actual input based on the trained parameter values, determining the corresponding output.

FIG. 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure may be implemented. In this example environment 100, an application 125 is installed in a terminal device 110. The user 140 may interact with the application 125 via the terminal device 110 and/or an attachment device of the terminal device 110.

In some embodiments, the application 125 may be downloaded and installed on the terminal device 110. In some embodiments, the application 125 may also be accessed by other means, such as by web page access, or the like. In the environment 100 of fig. 1, in response to the application 125 being launched, the terminal device 110 may present an interface 150 of the application 125.

In some embodiments, terminal device 110 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/video camera, positioning device, television receiver, radio broadcast receiver, electronic book device, gaming device, or any combination of the preceding, including accessories and peripherals for these devices, or any combination thereof. In some embodiments, terminal device 110 is also capable of supporting any type of interface to the user (such as "wearable" circuitry, etc.).

In some embodiments, terminal device 110 communicates with server 130 to enable service provisioning for application 125. The terminal device 110 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, 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. In some embodiments, terminal device 110 is also capable of supporting any type of interface to the user (such as "wearable" circuitry, etc.). The applications 125 may be various types of computing systems/servers capable of providing computing capabilities, including, but not limited to, mainframes, edge computing nodes, computing devices in a cloud environment, and so forth.

In embodiments of the present disclosure, the application 125 may provide interactive functionality with an agent. The application 125 may be dedicated to an application that provides services for an agent, or an application that is integrated with an agent (that is, may provide other functions or services in addition to an agent). Although a single application is shown in fig. 1, a plurality of applications may be installed on the terminal device 110 in practice.

In the context of the present disclosure of the present invention, intelligent agents 160-1, 160-2 the term 160-N (collectively or individually referred to as agent 160) may be deployed locally or remotely at terminal device 110. In the case of remote deployment, terminal device 110 may invoke the agent directly, or may invoke the agent via server 130.

In embodiments of the present disclosure, agent 160 may have intelligent dialog and task processing capabilities. An interface 150 is provided at the terminal device 110 that can present interactions with the agent 160. In interface 150, user 140 can enter a task request for agent 160 by entering natural language input (text input or voice input) and can also be uploaded into an online or offline file session to instruct agent 160 to assist in accomplishing various tasks.

In embodiments of the present disclosure, agent 160 may process tasks indicated by users in response to requests from users 140 during interactions with users 140. In some embodiments, during task processing, agent 160 may invoke one or more tools 165-1, 165-2, once again, as required by the task, 165-M (collectively or individually referred to as tools 165) to assist in the execution of the task and the provision of the task results. These tools 165 may be any type of tool, such as weather query tools, flight query tools, information search tools, online or offline databases, image processing tools, chart generation tools, web page production tools, and so forth.

In some embodiments, environment 100 may also include a management node for multiple agents 160-1, 160-2, that can interact with multiple agents 160-1, 160-2, 160-N. In some examples, the management node may determine a task requirement corresponding to the task request in response to the task request of the user 140. Thereafter, the management node may assign a task request to an agent 160 matching the task demand based on the task demand to request the agent 160 to perform the task. In other examples, the management node may also determine an execution plan for the task based on the task demand. The execution plan of a task may indicate one or more subtasks needed to complete the task. The management node may assign the one or more subtasks to one or more agents 160, through which the one or more agents 160 respectively perform the respective corresponding subtasks. Regarding the management node, in some examples, the management node may be implemented by one of a plurality of agents 160-1, 160-2, a.i. 160-N (in which case the agent 160 is also referred to as a management agent 160). In other examples, the management node may be implemented by a machine learning model, such as by a Language Model (LM) or a Large Language Model (LLM).

In some embodiments, agent 160 may be built based on one or more machine learning models. In some embodiments, the machine learning model on which agent 160 is based may include at least a Language Model (LM). These machine learning models include content-generative models capable of generating corresponding outputs based on model inputs. In some embodiments, a language model-based machine learning model may receive model inputs in a text modality (e.g., natural language and/or machine language) and/or model inputs in a non-text modality (e.g., image, voice, video, etc.), and may be able to derive corresponding model outputs based on the model inputs and the hint words, thereby completing execution of the task. The hint words herein are used to guide the machine learning model to generate a user query that can solve the user query indicated by the model input. In an application scenario for supporting user dialog, input from the user 140 may be provided to the machine learning model 160 as at least a portion of the model input (other portions may include prompt words). The user input is treated as a question or query request. Based on the model output, a corresponding response may be provided to the user 140.

It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and are not meant to suggest any limitation as to the scope of the disclosure.

As mentioned briefly above, a user may initiate a task request within an application. In some scenarios, a user may input task requirements in a user interface provided by an application, and the application may provide services to the user that may satisfy the task requirements according to the task requirements of the user. Conventionally, a user may initiate a question in an application providing a question-and-answer service to obtain a corresponding answer. However, by way of operation, the user is not aware of the execution process for the problem. Further, in some scenarios, after a task is initiated, a user may not control and modify the execution of the task, but may only wait for the task to be executed to completion. Alternatively, after a task is initiated, the user may choose to interrupt the current task and initiate a new task.

According to some embodiments of the present disclosure, an improved scheme for task interactions is presented. According to the scheme of the embodiment of the disclosure, if a request for a task of an agent is received, first information related to the execution process of the task is presented in an interface for interacting with the agent, and task information indicating the task is requested. In the case where the suspension condition of the task is satisfied, execution of the task is suspended. Further, if an adjustment or restoration of a task is received in a suspended state of the task, execution of the task may be restored. Accordingly, if the execution of the task is resumed, second information related to the execution course or execution result of the resumed task is presented in the interface.

In this way, by presenting the task execution process and execution result in the interface that interacts with the agent, the user can be made aware of the disassembly process and execution process of the agent for the task. Further, in the execution process or disassembly process of the task, the user can pause, adjust or resume the disassembly or the execution of the task at any time so as to obtain a result meeting the own requirements.

In this disclosure, "trigger" refers to one or more interactions of a user on a terminal device. Further, these interactions may be triggered within the same user interface/popup window or within different user interfaces/popup windows. The present disclosure is not limited in this respect.

Some embodiments of the present disclosure will be described below with reference to the accompanying drawings. For ease of understanding, examples of interfaces for interacting with an agent in some embodiments of the present disclosure will be described below with reference to fig. 2A-2I. These example interfaces may be presented by the application 125 in the terminal device 110. It should be understood that the interfaces shown in the figures are merely examples, and that various interface designs may actually exist. The individual graphical elements in the interface 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 interface 200A shown in fig. 2A may present an interactive interface 200A between the user 140 and the agent 160. In the interactive interface 200A, a request for a new task initiated by a user may be received. As shown in fig. 2A, the user may trigger a new task by triggering a "new task" control 211. In response to the triggering of the "new task" control 211, a task-specific interactive interface, such as interactive interface 200B shown in fig. 2B, is presented in interface 200A to initiate a new task in interactive interface 200B. In some embodiments, an input area 215 is also provided in interface 200A for task input, in which input area 215 a user can input a request for a task to trigger and initiate the request for a task through a "send" control 216. The input area 215 may support text input, such as entering text in a text input box, and may also support voice input, such as by triggering the voice control 217. In addition, the input area 215 may also provide an upload control 216 to support uploading attachments to indicate a user's task request. In some embodiments, interactive interface 200A also provides a task list 212 that is initiated to agent 160, task list 212 indicating various tasks that have been initiated and the status of execution of the tasks (e.g., interrupt status, in-progress status, completed status, etc.).

In some embodiments, multiple modes of operation of user 140 and agent 160 may be provided and flexible switching between the multiple modes of operation may be provided, for example, via mode switch control 218 shown in fig. 2A. In the event that a mode is triggered, a corresponding interaction region is presented to facilitate interaction of user 140 with agent 160. The interaction modes of the user 140 and the agent 160 in different operation modes are different, so that the interaction modes can be flexibly adapted to the interaction requirements in different application scenes. In some embodiments, the different modes of operation may include an automatic mode and a collaborative mode. In the automatic mode, execution of the task by agent 160 may automatically continue until the task is completed. In the coordinated mode, agent 160, upon completion of an action by the task execution, may pause the execution of the task and provide modification and confirmation options for the user to check whether the execution of the current action is in line with expectations and whether modification of the execution of the action is required. If no modification is required, upon receipt of a user confirmation, agent 160 will continue to perform the next action of the task until the task is completed.

In some embodiments, agent 160 may be in a suspended state during execution of a task. During the pause state, modification and resumption etc. options may be provided for the user to check if the execution of the current action is in line with expectations, if the execution of the action needs to be modified. Then in the event that the task is modified, the modified task may be passed to the management agent 160. Management agent 160 may assign modifications to the tasks to other agents. During task execution, user 140 may add a new task, for example, add an XX subtask. In this scenario, terminal device 110 may invoke management agent 160 to add the XX subtask. After management agent 160 receives the XX subtask, the entire task may be modified. Management agent 160 may then reassign the tasks to the various agents. In some embodiments, terminal equipment 110 may invoke an agent that may resolve the XX subtask to handle.

In some embodiments, management agent 160 may determine a prompt corresponding to additional task information indicating a modification or addition to a subtask. The Prompt may be spliced into the original Prompt as part of a System Prompt (SP) to provide contextual guidance for subsequent task execution. Alternatively or additionally, the prompt word corresponding to the additional task information is directly spliced into the task prompt word of the agent corresponding to the subtask, so that the corresponding agent can consider new context content when executing the task.

Upon triggering a request for a task of an agent, terminal device 110 presents interactive interface 200B shown in fig. 2B. A request for a user-initiated task, such as message 221, may be presented in interactive interface 200B, and task execution information may also be presented when the task is executed by the agent. The task execution information may be presented in the interactive interface 200B in the form of one or more messages. During execution of a task, agent 160 may analyze the user-initiated task request to determine task requirements to generate an execution plan for the task. The execution plan of a task may indicate one or more subtasks needed to complete the task. In order to make the user more aware of the execution of the task by the agent, a message 221 indicating the generation of the execution plan may be presented in the interactive interface 200B. After execution plan determination, a message 223 indicating the various subtasks in the execution plan (e.g., subtasks 224, 225, etc. subtasks) may be presented in the interactive interface 200B. The agent 160 then proceeds to execute the respective sub-tasks automatically or in response to a user's confirmation, and the execution of the respective sub-tasks and the execution results may be presented in the interactive interface 200B. After the execution of the entire task is completed, the execution result of the task or an access entry to the execution result may be presented in the interactive interface 200B (if the execution result needs to jump to another interface for presentation). In this way, in the whole task execution process, the user can intuitively know how the agent specifically disassembles the task demands of the user and the specific execution steps of each subtask, so that the user can conveniently confirm or adjust the task or subtask execution process, and the expected execution result is obtained.

In some embodiments, the process of determining one or more subtasks required to complete a task in the execution plan of the task based on the task request of user 140 may be implemented by a machine learning model deployed at server 130 or invoked by server 130. Further, after determining a particular task execution plan, the machine learning model may assign each sub-task to the appropriate one or more agents 160 for the particular task execution.

Alternatively or additionally, the user's task request may also be sent to the management agent 160. The process of determining one or more sub-tasks in the execution plan of a task may be implemented by management agent 160. Management agent 160 may be configured to parse the user's task request based on the user's 140 task request to determine one or more sub-tasks required to complete the task in the task's execution plan. Further, the management agents 160 may assign subtasks to the appropriate agent or agents 160 for specific task execution, and according to different task execution requirements and capabilities.

Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings. Embodiments to which the present disclosure relates may be implemented at terminal device 110. It should be noted that the operations performed by the terminal device 110 may be specifically performed by a related application (e.g., the application 120) installed on the terminal device 110. Some of the operations described with reference to terminal equipment 110 may require assistance from server 130 to complete.

In this context, the terminal device 110 deploys an application 120 supporting task processing functionality, and the user 140 may utilize the application 120 to process tasks including, but not limited to, information querying (e.g., acquisition of real-time information such as weather forecast, news digest, etc.), data processing (e.g., analysis of sales report for the XX quarter), code execution (e.g., generation and execution of simple code segments), and so forth. These are merely exemplary rows and the disclosure is not limited thereto.

In the embodiment of the present disclosure, the terminal device 110 causes execution of the task to be suspended if it is determined that the suspension condition of the task is satisfied. In some embodiments, terminal device 110 may present at least one interactive element in the interface if it is determined that a pause condition of the task is satisfied, wherein execution of the task is paused. The at least one interactive element is configured at least to adjust or resume the task in a suspended state of the task. In some scenarios, during the process of the terminal device 110 invoking the agent 160 to determine the task plan of the task and executing the task, the user 140 may pause and adjust the task at any time to obtain a result that meets the requirements of the user 140. In a scenario where the terminal device 110 is required to input additional task information or take over by the user 140, the progress of the task may be suspended and the execution of the task may be adjusted or resumed based on the next interactive operation of the user 140. In a scenario in which the execution duration of a certain subtask of a task exceeds the duration threshold, the terminal device 110 may suspend the task and adjust or resume the execution of the task based on the next interactive operation of the user 140. The above scenarios are merely exemplary, and the present disclosure is not limited in this regard. The following will describe in detail under what conditions the terminal device 110 puts the task in a suspended state and how the user 140 can interact with the agent 160 for the task in the suspended state, with reference to the accompanying drawings.

In an embodiment of the present disclosure, the terminal device 110 resumes execution of the task if an adjustment or resumption of the task is received in a suspended state of the task. Accordingly, if the terminal device 110 determines the restoration of the execution of the task, the second information related to the execution course or the execution result of the restored task may be presented in the interface. In some embodiments, terminal device 110 may determine that execution of the task is resumed based on user 140's interaction after execution of the task is suspended. Further, terminal device 110 may continue to present information related to the execution of the task or the execution result in an interface (e.g., example interface 200B).

In the following, it will be described with reference to fig. 2B to 2I under what conditions the terminal device 110 brings a task into a suspended state, and how the user 140 can interact with the agent 160 for the task in the suspended state.

In some embodiments, in the case where the terminal device 110 invokes the agent 160 to generate a task plan for a task, it may be determined that a suspension condition of the task is satisfied, thereby suspending execution of the task. Accordingly, the terminal device 110 may present task information indicating at least one sub-task indicated by the task plan in the interface. The terminal device 110 may present the first interactive element and a fifth interactive element for starting execution of the mission plan in the interface. In some embodiments, the first interactive element is used to trigger an adjustment of task information for the task in a suspended state of the task. The first interactive element may be used to receive additional task information triggering the input task, i.e. to adjust the task information of the task based on the additional task information. In some examples, at least one sub-task is determined during execution of the task. After requesting execution of a task, agent 160 may first analyze the request from the user to determine an execution plan for the task. The execution plan of the task indicates one or more subtasks included in the task.

As illustrated in example interfaces 200C-200D of fig. 2C-2D, in the event that terminal device 110 determines that a task has been disassembled into sub-tasks 223, 224, 3, 4, etc., task information 223 corresponding to each respective sub-task may be presented in the interface (e.g., example interface 200C). In such a scenario, terminal device 110 may determine that the current task is in a suspended state, and may present interactive element 231 (e.g., a "modify task" control) and interactive element 232 (e.g., a "begin task" control) in an interface (e.g., example interface 200C). The user 140 may click on the interactive element 232 to enable the terminal device 110 to begin executing the respective subtasks.

If terminal device 110 receives user 140 clicking on interactive element 231, input box 241 may be presented in an interface, such as example interface 200D. The user 140 may enter additional task information for the task in the input box 241, e.g., the user 140 may enter some modification suggestions. Although not shown in the figures, the interactive element 241 may also support other input means, such as voice input, or modification suggestions by uploading attachments, providing web page links, etc., in addition to direct input in a text input box. Subsequently, if the terminal device 110 receives additional task information input by the user 140, it may continue execution of the task using the agent 160 according to the additional task information input by the user 140 and information of the task execution process or information of the execution result that has been currently generated.

In some embodiments, terminal device 110 can also present cancel control 242 and confirm control 243 in interactive interface 200D. The cancel control 242 is used for canceling the modification process carried by the current input box 241 when the user abandons the modification operation, and returning to the presentation interface of the original mission plan. The confirmation control 243 is used to confirm the submission of the modified content after the user has completed the input.

In some embodiments, referring to the example interfaces 200B and 200E shown in fig. 2B and 2E, during execution of a task, the terminal device 110 may present a pause control 226 in the interface. If terminal device 110 receives a trigger for pause control 226, it may determine that a pause condition for the task is satisfied, thereby pausing execution of the task. That is, during execution of a task, the user 140 may click on the pause control 226 to place the task in a paused state. For example, in the process of terminal device 110 generating a mission plan, if user 140 needs to supplement some information, user 140 may click on pause control 226 to supplement such information based on interactive elements (e.g., an "input box") provided by terminal device 110. For another example, if user 140 needs to supplement some information during execution of a subtask by terminal device 110, user 140 may also click on pause control 226 to supplement such information based on interactive elements (e.g., an "input box") provided by terminal device 110. In these scenarios, terminal device 110 can present interactive element 231 (e.g., an "input box") and interactive element 252 (e.g., a "continue" control) in an interface (e.g., example interface 200E). The interactive element 252 (i.e., the second interactive element) may be used to trigger resuming execution of the task in a suspended state of the task.

In some embodiments, the terminal device 110 may resume execution of the task if additional task information is received via the first interactive element. Accordingly, the terminal device 110 may present second information related to the execution process or execution result of the restored task in the interface, wherein the second information is determined based on the additional task information and the first information. As shown in fig. 2E, the user 140 may enter the user 140's demand information in an interactive element 231 (e.g., an "input box") presented in an interface (e.g., example interface 200E) such that execution of the task is resumed. The terminal device 110, if receiving the additional task information input by the user 140, may generate the second information using the agent 160 based on the additional task information input by the user 140 and information of the task process in which the current task has been performed or information of the execution result that has been generated. Accordingly, terminal device 110 may continue to present the second information in the interface.

In some embodiments, terminal device 110 may also resume execution of the task if a trigger is received by user 140 for interactive element 252 (e.g., a "continue" control). At this time, since the user 140 does not input additional task information, second information that continues to be presented in the interface is generated by the agent 160 based on the previous first information and the execution plan of the task. In some embodiments, if terminal device 110 detects that execution of a task is suspended, an interactive element 251 (e.g., a "terminate" control) for stopping execution of the task may be presented in an interface (e.g., example interface 200E). Terminal device 110 may terminate execution of the task if a trigger is received by user 140 for interactive element 251 (e.g., a "terminate" control). Therefore, the user can interrupt, adjust or resume execution of the task at any time to obtain a result meeting the requirement of the user.

In some embodiments, agent 160 may gradually execute these subtasks based on the determined execution plan, thereby gradually completing execution of the entire task. In some embodiments, to implement human-machine collaboration and dynamic control during task execution, the controllability of the user to the agent task execution process is enhanced, and when the current action execution of the agent 160 is completed, an intermediate interaction stage may be entered. At this stage, the terminal device 110 may buffer the execution result of the current action, and suspend the automatic propulsion of the subsequent action in the task flow. The user 140 may adjust the execution of the current action, such as modifying, replacing or regenerating the execution content, at the stage of the intermediate interaction. The task interaction procedure at the intermediate interaction stage will be described below with reference to fig. 2F.

Referring to the example interface 200F shown in fig. 2F, during execution of a task, the terminal device 110 may determine that a suspension condition of the task is satisfied if it is determined that auxiliary information (i.e., additional task information) is required for a third sub-task (e.g., sub-task 261) among at least one sub-task of the task, thereby suspending execution of the task. That is, during execution of the task, the terminal device 110 may place the task in a suspended state if it determines that some additional task information needs to be collected from the user 140 (e.g., supplementing constraints, specifying desired structures, adding missing subtasks, etc.). In some embodiments, terminal device 110 may resume execution of the third sub-task if the assistance information is received. In some embodiments, if terminal device 110 determines that some additional task information needs to be collected from user 140, interactive element 231 may be provided to user 140 for obtaining auxiliary information (i.e., additional task information). In some embodiments, the interactive element 231 may be presented with information of the input box to guide the user 140 in input. After the user 140 confirms the input auxiliary information, execution of the task is resumed. In some embodiments, terminal device 110 may also present prompt 262 in the interface in association with interactive element 231 (e.g., an "input box") for prompting user 140 to input own demand information in interactive element 231 (e.g., an "input box").

In some embodiments, the terminal device 110 may resume execution of the third subtask if the assistance information is received via the first interactive element. Accordingly, the terminal device 110 may present second information related to the execution course or the execution result of the task in the interface, wherein the second information is determined based on the auxiliary information and the first information. As shown in fig. 2F, user 140 may enter demand information for user 140 in an interactive element 231 (e.g., an "input box") presented in an interface (e.g., example interface 200F) such that execution of subtask 261 is resumed. The terminal device 110, if receiving the auxiliary information input by the user 140, may generate the second information using the agent 160 based on the auxiliary information input by the user 140 and information of the task process in which the current task has been performed or information of the execution result that has been generated. Accordingly, terminal device 110 may continue to present the second information in the interface. Therefore, the terminal device 110 can interrupt the execution of the task, so that the user can choose to adjust or resume the execution of the task, thereby providing the user with the result meeting the requirement.

During execution of a task, the execution of certain subtasks included in the task may require access rights to the information source. In such a scenario, terminal device 110 may suspend execution of tasks and provide user 140 with access for authorization. Task interactions in such a scenario are described below with reference to fig. 2G.

Referring to the example interface 200G shown in fig. 2G, during execution of a task, if the terminal device 110 determines that the first sub-task (e.g., the sub-task 271) of the at least one sub-task requires access rights of an information source, it may determine that a suspension condition of the task is satisfied, thereby causing execution of the task to be suspended. That is, during execution of the task, the terminal device 110 may suspend execution of the task if it is determined that the subtask 271 requires access rights of the information source. In such a scenario, terminal device 110 may present interactive element 231 (e.g., an "immediately takeover" control) and interactive element 252 (e.g., a "skip" control) in an interface (e.g., example interface 200G). The interactive element 231 (e.g., an "immediate takeover" control) may be a portal for the authorized information sources to be accessed.

In some embodiments, the terminal device 110 may resume execution of the first subtask if it receives an access grant to the information source to be accessed. In some embodiments, terminal device 110 may present a configuration panel if a trigger for interactive element 231 (e.g., an "immediately take over" control) is received. The configuration panel may receive an access authorization to the information source to be accessed as additional task information. In some examples, user 140 may authorize information sources to be accessible to terminal device 110 through a configuration panel. For example, the user 140 may be authorized by scanning a predetermined code corresponding to the information source, by entering a cell phone number, and so forth. These are merely exemplary and the present disclosure is not limited thereto.

Further, the terminal device 110 may resume execution of the first task if an access grant is received via the configuration panel. Accordingly, the terminal device 110 may present second information related to the execution process or execution result of the restored task in the interface, wherein the second information is determined based on the information acquired from the information source and the first information. As shown in fig. 2G, user 140 may click on interactive element 231 (e.g., "immediately take over") to grant access to the information source such that execution of subtask 271 is resumed. The terminal device 110 may generate the second information using the agent 160 based on the information acquired from the information source and the information of the task process in which the current task has been performed or the information of the execution result that has been generated if it is determined that the user 140 has access to the information source for authorization. Accordingly, terminal device 110 may continue to present the second information in the interface.

In some embodiments, if the terminal device 110 receives a resume of a task in a suspended state of the task, execution of the first sub-task may be skipped and execution of a second sub-task subsequent to the first sub-task may continue. In some embodiments, the execution of the first subtask may be skipped by terminal device 110 if a trigger by user 140 for interactive element 252 (e.g., a "skip" control) is received. Accordingly, terminal device 110 continues to execute the second sub-task after the first sub-task. As with the example interface 200G shown in fig. 2G, if the user 140 clicks the interactive element 252 (e.g., a "skip" control), the terminal device 110 may be caused to skip executing the subtask 271 while continuing to execute subtasks subsequent to the subtask 271.

In some embodiments, terminal device 110 may also resume execution of the task if a trigger by user 140 for interactive element 252 (e.g., a "skip" control) is received. That is, in the event that authorization for the information is not available, some or all of the steps of the first sub-task may need to be skipped. At this time, after the execution of the task is resumed, the execution of the second sub-task after the first sub-task may be continued. The second information that continues to be presented in the interface is generated by the agent based on the previous first information and the execution of the second subtask. In some embodiments, if terminal device 110 determines that access rights to the information source are required to perform the subtask, prompt 272 for prompting the user to confirm authorization may be presented in an interface (e.g., example interface 200G). Therefore, in the process that the task is executed, the intelligent agent can call other information sources authorized by some users, so that the accuracy of the result is improved.

The terminal device 110 may also put the task in a suspended state in case the execution duration of the task and the subtasks of the task exceeds a duration threshold. The task interaction procedure in this case is described below with continued reference to fig. 2H to 2I.

In some embodiments, if the terminal device 110 determines that the execution time of the fourth sub-task of the at least one sub-task is greater than the first time threshold, it may determine that a suspension condition of the task is satisfied, thereby causing the execution of the task to be suspended. Accordingly, the terminal device 110 may present the second interactive element and a third interactive element at the interface, wherein the third interactive element is configured to trigger the execution of the stop task. As with the example interface 200H shown in fig. 2H, the terminal device 110 may leave the task in a suspended state if it is determined that the execution time of the fourth subtask (e.g., XX subtask) is greater than the first time length threshold (e.g., 30 minutes or any other suitable time length threshold).

In such a scenario, terminal device 110 may present interactive element 252 (e.g., a "continue" control) in an interface (e.g., example interface 200H) for resuming execution of the task. Terminal device 110 can present interactive element 251 (e.g., a "terminate" control) in an interface, such as example interface 200H, for triggering the execution of a stop task. In some embodiments, terminal device 110 may also present in an interface (e.g., example interface 200H) a prompt 281 for prompting user 140 that the performance of the current task exceeds a time duration threshold. In some embodiments, the terminal device 110 may stop execution of the task if it receives a trigger for stopping the task. In some embodiments, the terminal device 110 may stop execution of the task if a trigger for the third interactive element is received. That is, the user 140 may click on the interactive element 251 (e.g., a "terminate" control) to stop execution of the task.

In some embodiments, if the terminal device 110 receives a resume of the task in a suspended state of the task, execution of the task may resume to continue execution of the fourth sub-task or to start a fifth sub-task after the fourth sub-task. In some embodiments, if the terminal device 110 receives a trigger for the second interaction element, execution of the task may resume to continue to execute the fourth sub-task or to start the fifth sub-task after the fourth sub-task. Accordingly, the second information presented in the interface by the terminal device 110 is determined based on the execution process or execution result of the fourth sub-task or the fifth sub-task. As shown in fig. 2H, user 140 may click on interactive element 252 (e.g., a "continue" control) to cause execution of the task to be resumed. That is, if terminal device 110 receives user 140 clicking on interactive element 252 (e.g., a "continue" control), it may cause the fourth subtask to continue to be performed. Alternatively, if terminal device 110 receives user 140 clicking on interactive element 252 (e.g., a "continue" control), a sub-task following the fourth sub-task may be caused to be performed. If terminal device 110 receives user 140 clicking on interactive element 252 (e.g., a "continue" control), then second information may be generated by agent 160 based on information of the task process that the current task has been performed or information of the execution result that has been generated. Accordingly, terminal device 110 may continue to present the second information in the interface.

In some embodiments, terminal device 110 stops execution of the task if it is determined that the total execution time of the task is greater than the second time period threshold. In some embodiments, if the terminal device 110 determines that the total execution time of the task is greater than the second time period threshold, a sixth interactive element may be presented at the interface, where the sixth interactive element is used to trigger the opening of a new task with the agent. As with the example interface 200I shown in fig. 2I, the terminal device 110 may leave the task in a suspended state if it is determined that the total execution time of the task is greater than a second duration threshold (e.g., 1.5 hours or any other suitable duration threshold). In such a scenario, terminal device 110 may present interactive element 291 (e.g., an "open new task" control) in an interface (e.g., example interface 200I) for opening a new task with agent 160.

In some embodiments, if the terminal device 110 determines that the total execution time of the task is greater than the second time period threshold, prompt information for prompting to open a new task may be presented at the interface. As illustrated in example interface 200I of fig. 2I, terminal device 110 may present a prompt 292 in the interface (e.g., example interface 200I) for prompting user 140 that a new task with agent 160 may be initiated.

In summary, through the method and the device, the task execution process and the execution result can be presented in the interface which is interacted with the intelligent agent, so that a user can know the disassembly process and the execution process of the intelligent agent for the task. Further, in the process that the task is executed, the agent can call other information sources authorized by some users, so that the accuracy of the result is improved. In this way, in the execution process of the task, the disassembly or execution of the task can be interrupted, adjusted or resumed at any time, so that a result meeting the user requirement is provided for the user.

Fig. 3 illustrates a flow chart of a process 300 for task interaction according to some embodiments of the present disclosure. The process 300 may be implemented at the terminal device 110. The process 300 is described below with reference to fig. 1.

In block 310, the terminal device 110 presents first information related to execution of a task in an interface interacting with an agent in response to a request for the task of the agent, the request indicating task information of the task.

In block 320, the terminal device 110 causes execution of the task to be suspended in response to the suspension condition of the task being satisfied.

In block 330, the terminal device 110 resumes execution of the task in response to receiving an adjustment or resumption of the task in a suspended state of the task, wherein second information related to the execution of the resumed task or the execution result is presented in the interface.

In some embodiments, the process 300 further includes presenting at least one interactive element in the interface in response to the pause condition of the task being met, the at least one interactive element being at least configured to adjust or resume the task in a pause state of the task.

In some embodiments, the at least one interactive element comprises at least one of a first interactive element for triggering an adjustment of task information for the task in a suspended state of the task, or a second interactive element for triggering resuming execution of the task in the suspended state of the task.

In some embodiments, the interface includes a pause control during execution of the task and causing execution of the task to be paused includes causing execution of the task to be paused in response to triggering of the pause control.

In some embodiments, resuming execution of the task includes resuming execution of the task in response to receiving the adjustment to the task information, wherein the second information is determined based on the adjustment to the task information and the first information.

In some embodiments, the task includes at least one sub-task, and wherein causing execution of the task to be suspended in the interface includes causing execution of the task to be suspended during execution of the task in response to a first sub-task of the at least one sub-task requiring access to the information source.

In some embodiments, resuming execution of the task includes resuming execution of the first subtask in response to receiving an access grant to the information source to be accessed, wherein the second information is determined based on information obtained from the information source and the first information.

In some embodiments, resuming execution of the task further comprises, in response to receiving a resume of the task in a suspended state of the task, skipping execution of the first sub-task and continuing to execute a second sub-task subsequent to the first sub-task.

In some embodiments, the task includes at least one sub-task, and wherein causing execution of the task to be suspended includes determining that a suspension condition of the task is met in response to a third sub-task of the at least one sub-task requiring auxiliary information during execution of the task, causing execution of the task to be suspended.

In some embodiments, resuming execution of the task includes resuming execution of the third subtask in response to receiving the input assistance information, wherein the second information is determined based on the slave assistance information and the first information.

In some embodiments, the process 300 further includes presenting, in association with the first interactive element, a hint information in the interface, the hint information indicating a need for auxiliary information.

In some embodiments, the task includes at least one subtask and causing execution of the task to be suspended includes causing execution of the task to be suspended in response to a time of execution of a fourth subtask of the at least one subtask being greater than a first time threshold.

In some embodiments resuming execution of the task includes resuming execution of the task to continue execution of the fourth sub-task or a fifth sub-task subsequent to starting the fourth sub-task in response to receiving a resume of the task in a suspended state of the task, wherein the second information is determined based on execution of the fourth sub-task or the fifth sub-task or an execution result.

In some embodiments, the process 300 further includes stopping execution of the task in response to receiving a trigger for stopping the task.

In some embodiments, causing execution of the task to be suspended includes causing execution of the task to be suspended in response to generation of a task plan for the task, and presenting task information for at least one subtask indicated by the task plan at an interface.

In some embodiments, the process 300 further includes stopping execution of the task in response to the total execution time of the task being greater than a second time period threshold, and presenting in the interface prompt information for prompting to open a new task.

Embodiments of the present disclosure also provide corresponding apparatus for implementing the above-described methods or processes.

Fig. 4 illustrates a schematic block diagram of an apparatus 400 for task interaction, according to some embodiments of the present disclosure. The apparatus 400 may be implemented as or included in the terminal device 110. The various modules/components in apparatus 400 may be implemented in hardware, software, firmware, or any combination thereof.

As shown in fig. 4, the apparatus 400 includes a first information presentation module 410 configured to present first information related to an execution process of a task in an interface interacting with an agent in response to a request for the task of the agent, requesting task information indicating the task. The apparatus 400 further includes an execution suspension module 420 configured to cause execution of the task to be suspended in response to a suspension condition of the task being met. The apparatus 400 further comprises an execution restoration module 430 configured to resume execution of the task in response to receiving an adjustment or restoration of the task in a suspended state of the task, wherein second information related to an execution process or an execution result of the restored task is presented in the interface.

In some embodiments, the interface includes a pause control during execution of the task, and the execution pause module 420 is further configured to cause execution of the task to be paused in response to a trigger to the pause control.

In some embodiments, the execution restoration module 430 is further configured to resume execution of the task in response to receiving the adjustment to the task information, wherein the second information is determined based on the adjustment to the task information and the first information.

In some embodiments, the task includes at least one sub-task, and the execution suspension module 420 is further configured to cause execution of the task to be suspended during execution of the task in response to a first sub-task of the at least one sub-task requiring access to the information source.

In some embodiments, the execution restoration module 430 is further configured to resume execution of the first subtask in response to receiving an access authorization to the information source to be accessed, wherein the second information is determined based on the information obtained from the information source and the first information.

In some embodiments, the execution resume module 430 is further configured to skip execution of the first sub-task and continue execution of a second sub-task subsequent to the first sub-task in response to receiving a resume of the task in a suspended state of the task.

In some embodiments, the task includes at least one sub-task, and the execution suspension module 420 is further configured to determine, during execution of the task, that a suspension condition of the task is satisfied in response to a third sub-task of the at least one sub-task requiring the auxiliary information, such that execution of the task is suspended.

In some embodiments, the execution restoration module 430 is further configured to resume execution of the third subtask in response to receiving the input auxiliary information, wherein the second information is determined based on the slave auxiliary information and the first information.

In some embodiments, the apparatus 400 further comprises a prompt presentation module configured to present a prompt in the interface in association with the first interactive element, the prompt indicating a need for auxiliary information.

In some embodiments, the task includes at least one sub-task, and the execution suspension module 420 is further configured to determine that a suspension condition of the task is met, causing execution of the task to be suspended, in response to a time of execution of a fourth sub-task of the at least one sub-task being greater than a first time threshold.

In some embodiments, the execution resume module 430 is further configured to resume execution of the task to continue execution of the fourth sub-task or to start a fifth sub-task after the fourth sub-task in response to receiving a trigger for resumption of the task in a suspended state of the task, wherein the second information is determined based on an execution course or an execution result of the fourth sub-task or the fifth sub-task.

In some embodiments, the apparatus 400 further comprises an execution stopping module configured to stop execution of the task in response to receiving a trigger for stopping the task.

In some embodiments, execution suspension module 420 is further configured to cause execution of the task to be suspended in response to generation of a task plan for the task, and to present task information for at least one subtask indicated by the task plan at the interface.

In some embodiments, the prompt presentation module is further configured to stop execution of the task in response to the total execution time of the task being greater than the second time threshold, and present in the interface prompt information prompting the opening of the new task.

The elements and/or modules included in apparatus 400 may be implemented in various manners, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and/or modules may be implemented using software and/or firmware, such as machine executable instructions stored on a storage medium. In addition to or in lieu of machine-executable instructions, some or all of the units and/or modules in apparatus 400 may be implemented at least in part by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include Field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standards (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.

It will be appreciated that one or more steps of the above methods may be performed by suitable electronic devices or combinations of electronic devices. Such an electronic device or combination of electronic devices may include, for example, terminal device 110 and server 130 in fig. 1.

Fig. 5 illustrates a block diagram of an electronic device 500 in which one or more embodiments of the disclosure may be implemented. It should be understood that the electronic device 500 shown in fig. 5 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 500 shown in fig. 5 may be used to implement the terminal device 110 or the server 130 of fig. 1.

As shown in fig. 5, the electronic device 500 is in the form of a general-purpose electronic device. The components of electronic device 500 may include, but are not limited to, one or more processing units or processors 510, memory 520, storage 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 570 may be an actual or virtual processor and is capable of performing various processes according to programs stored in the memory 520. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capabilities of electronic device 500.

Electronic device 500 typically includes multiple computer storage media. Such a medium may be any available medium that is accessible by electronic device 500, including, but not limited to, volatile and non-volatile media, removable and non-removable media. The memory 520 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 device 530 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 500.

The electronic device 500 may further include additional removable/non-removable, volatile/nonvolatile storage media. Although not shown in fig. 5, 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 520 may include a computer program product 525 having one or more program modules configured to perform the various methods or acts of the various embodiments of the present disclosure.

The communication unit 540 enables communication with other electronic devices through a communication medium. Additionally, the functionality of the components of electronic device 500 may be implemented in a single computing cluster or in multiple computing machines capable of communicating over a communication connection. Thus, the electronic device 500 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 550 may be one or more input devices such as a mouse, keyboard, trackball, etc. The output device 560 may be one or more output devices such as a display, speakers, printer, etc. The electronic device 500 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 500, or with any device (e.g., network card, modem, etc.) that enables the electronic device 500 to communicate with one or more other electronic devices, as desired, via the communication unit 540. 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 method for task interaction, comprising:

In response to a request for a task of an agent, presenting first information related to an execution process of the task in an interface for interacting with the agent, the request indicating task information of the task;

In response to a suspension condition of the task being satisfied, causing execution of the task to be suspended; and

In response to receiving an adjustment or resumption of the task in the paused state, the execution of the task is resumed, wherein second information related to the execution process or execution result of the resumed task is presented in the interface.

2. The method according to claim 1, further comprising:

In response to a suspension condition of the task being met, at least one interactive element is presented in the interface, where the at least one interactive element is at least configured to adjust or resume the task in a suspended state.

3. The method according to claim 2, wherein the at least one interactive element comprises at least one of the following:

A first interactive element is used to trigger the adjustment of the task information of the task in the paused state of the task, or

The second interactive element is used to trigger the resumption of execution of the task when the task is in a paused state.

4. The method according to claim 1 , wherein the interface includes a pause control during the execution of the task, and pausing the execution of the task comprises:

In response to triggering the pause control, execution of the task is paused.

5. The method of claim 1 , wherein resuming execution of the task comprises:

In response to receiving an adjustment to the task information,

Execution of the task is resumed, wherein the second information is determined based on the adjustment to the task information and the first information.

6. The method of claim 1 , wherein the task includes at least one subtask, and wherein causing execution of the task to be suspended comprises:

During the execution of the task, in response to a first subtask of the at least one subtask requiring access rights to an information source, the execution of the task is suspended.

7. The method of claim 6, wherein resuming execution of the task comprises:

In response to receiving access authorization to the information source to be accessed, resuming execution of the first subtask,

The second information is determined based on information obtained from the information source and the first information.

8. The method according to claim 7, wherein resuming the execution of the task further comprises:

In response to receiving a resume of the task in a suspended state of the task,

skipping the execution of the first subtask, and

Continue to execute the second subtask after the first subtask.

9. The method of claim 1 , wherein the task includes at least one subtask, and wherein causing execution of the task to be suspended comprises:

During the execution of the task, in response to a third subtask of the at least one subtask requiring auxiliary information, the execution of the task is suspended.

10. The method of claim 9, wherein resuming execution of the task comprises:

In response to receiving the auxiliary information, execution of the third subtask is resumed, wherein the second information is determined based on the auxiliary information and the first information.

11. The method according to claim 9, further comprising:

Prompt information is presented in the interface in association with the first interactive element, the prompt information indicating a need for the auxiliary information.

12. The method of claim 1 , wherein the task includes at least one subtask, and causing execution of the task to be suspended comprises:

In response to an execution duration of a fourth subtask among the at least one subtask being greater than a first duration threshold, execution of the task is suspended.

13. The method of claim 12, wherein resuming execution of the task comprises:

In response to receiving a resume of the task in the paused state of the task, resuming execution of the task to continue executing the fourth subtask or starting a fifth subtask subsequent to the fourth subtask,

The second information is determined based on the execution process or execution result of the fourth subtask or the fifth subtask.

14. The method according to claim 12, further comprising:

In response to receiving a trigger to stop the task, execution of the task is stopped.

15. The method of claim 1 , wherein causing execution of the task to be suspended comprises:

In response to generating a task plan for the task,

causing execution of the task to be suspended, and

Task information of at least one subtask indicated by the task plan is presented on the interface.

16. The method according to claim 1, further comprising:

In response to the total execution time of the task being greater than a second time threshold,

stopping execution of said task, and

A prompt message for prompting to start a new task is presented in the interface.

17. A device for task interaction, comprising:

a first information presentation module configured to present, in response to a request for a task of an agent, first information related to an execution process of the task in an interface for interacting with the agent, wherein the request indicates task information of the task;

an execution suspension module configured to suspend the execution of the task in response to a suspension condition of the task being met; and

An execution recovery module is configured to resume the execution of the task in response to receiving an adjustment or resumption of the task in a paused state of the task, wherein second information related to the execution process or execution result of the resumed task is presented in the interface.

18. An electronic device comprising:

at least one processor; and

At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 16 when executed by the at least one processor.

19. A computer-readable storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions can be executed by a processor to implement the method according to any one of claims 1 to 16.

20. A computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 16.