CN119441568A - Enterprise information retrieval method, device and electronic device based on knowledge engine - Google Patents
Enterprise information retrieval method, device and electronic device based on knowledge engine Download PDFInfo
- Publication number
- CN119441568A CN119441568A CN202510025422.2A CN202510025422A CN119441568A CN 119441568 A CN119441568 A CN 119441568A CN 202510025422 A CN202510025422 A CN 202510025422A CN 119441568 A CN119441568 A CN 119441568A
- Authority
- CN
- China
- Prior art keywords
- policy
- information
- retrieval
- sub
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本申请提供一种基于知识引擎的企业信息检索方法、装置和电子设备，涉及信息检索领域。该方法中，获取用户输入的待检索需求，待检索需求包括制度检索需求和政策检索需求；根据制度检索需求和政策检索需求在预设的大模型知识引擎上进行信息爬取，得到初始制度信息和初始政策信息；对初始制度信息和初始政策信息分别进行分解，得到多个子检索项目，通过进行信息分解，方便对信息进行管理，以便后续准确推荐；对各个子检索项目进行相关性计算，得到关联分析，通过进行关联分析，能够推荐出关联的制度和政策，为用户检索提供便利，实现较为容易的信息获取；根据关联分析进行信息检索推荐，得到检索结果，能够推荐出符合用户输入需求的信息。
The present application provides a method, device and electronic device for enterprise information retrieval based on a knowledge engine, and relates to the field of information retrieval. In the method, the user inputs a to-be-retrieved demand, which includes a system retrieval demand and a policy retrieval demand; information crawling is performed on a preset large model knowledge engine according to the system retrieval demand and the policy retrieval demand, and initial system information and initial policy information are obtained; the initial system information and the initial policy information are respectively decomposed to obtain multiple sub-search items, and by performing information decomposition, it is convenient to manage the information for subsequent accurate recommendation; the relevance of each sub-search item is calculated to obtain an association analysis, and by performing the association analysis, the associated system and policy can be recommended, which provides convenience for user retrieval and realizes easier information acquisition; information retrieval recommendation is performed according to the association analysis, and the retrieval results are obtained, and information that meets the user input requirements can be recommended.
Description
Technical Field
The application relates to the field of information retrieval, in particular to an enterprise information retrieval method and device based on a knowledge engine and electronic equipment.
Background
Along with the expansion of the enterprise scale, the complete enterprise internal management system can optimize the enterprise internal flow, define responsibility division and improve the cooperation efficiency. Meanwhile, the enterprise can be ensured to operate efficiently on the premise of compliance by timely knowing and adapting to external policy changes, so that the acquisition and updating of the enterprise internal management system and external policy information become increasingly important. At present, most enterprises still adopt a traditional document management mode to store and retrieve the system and the policy, and intelligent retrieval cannot be realized, so that a user is difficult to acquire the required system or policy.
Disclosure of Invention
The application provides an enterprise information retrieval method and device based on a knowledge engine and electronic equipment, which can conduct intelligent retrieval and can easily acquire corresponding systems and policies.
The technical scheme of the embodiment of the application is as follows:
in a first aspect, an embodiment of the present application provides a knowledge engine-based enterprise information retrieval method, where the method includes:
acquiring a requirement to be searched input by a user, wherein the requirement to be searched comprises a system searching requirement and a policy searching requirement, and the requirement to be searched is voice searching;
according to the system retrieval requirements and the policy retrieval requirements, information crawling is carried out on a preset large model knowledge engine to obtain initial system information and initial policy information;
decomposing the initial system information and the initial policy information respectively to obtain a plurality of sub-search items;
Carrying out correlation calculation on each sub-search item to obtain correlation analysis;
And carrying out information retrieval recommendation according to the association analysis to obtain a retrieval result, wherein the retrieval result is a voice answer corresponding to the voice retrieval.
In the technical scheme, the requirements to be searched, which are input by a user, are acquired, wherein the requirements to be searched comprise system searching requirements and policy searching requirements, the requirements to be searched are voice searching, corresponding system or policy is recommended automatically and conveniently through acquiring corresponding requirements to be searched, information crawling is conducted on a preset large model knowledge engine according to the system searching requirements and the policy searching requirements, initial system information and initial policy information are obtained, information crawling is conducted automatically through the large model knowledge engine, corresponding information can be timely acquired, newer and more comprehensive system and policy information can be obtained, the initial system information and the initial policy information are respectively decomposed to obtain a plurality of sub-searching items, information is conveniently managed through information decomposition so that follow-up accurate recommendation can be conducted, relevance calculation is conducted on each sub-searching item to obtain relevance analysis, relevant system and relevant policy can be recommended conveniently through conducting relevance analysis, information retrieval recommendation is achieved according to the relevance analysis, the retrieval result is obtained, voice searching is corresponding voice searching answer, information meeting the user input requirements can be obtained conveniently, and the user can conveniently search by adopting a quick searching mode.
In some embodiments of the application, the sub-search term includes a plurality of system sub-terms and a plurality of policy sub-terms;
and performing correlation calculation on each sub-search item to obtain correlation analysis, wherein the correlation analysis comprises the following steps:
Carrying out feature map processing on each system sub-item to obtain a system feature sub-map;
performing feature map processing on each policy sub-item to obtain a policy feature sub-map;
and correlating the system characteristic subgraph with the policy characteristic subgraph to obtain the correlation analysis.
In the technical scheme, the feature map processing is carried out on the system sub-item and the policy sub-item respectively to obtain the system feature sub-image and the policy feature sub-image, then the system feature sub-image and the policy feature sub-image are associated to obtain the association analysis, and the association relation between the features can be calculated more clearly by calculating the feature sub-image so as to carry out the retrieval recommendation later.
In some embodiments of the present application, the associating the system feature sub-graph with the policy feature sub-graph to obtain the association analysis includes:
calculating the similarity of each system feature node in the system feature subgraph and the policy feature node in the policy feature subgraph to obtain similarity;
Calculating the relevance of the system characteristic subgraph and the policy characteristic subgraph by using a preset relevance rule to obtain relevance, wherein the relevance rule is obtained by extracting the relation between a historical system and a historical policy;
and carrying out weighted calculation on the similarity and the relevance to obtain the relevance analysis.
In the technical scheme, the related system and policy can be searched by calculating the similarity of the system characteristic subgraph and the policy characteristic subgraph and calculating by using the association rule and then weighting calculation, so that the complexity of searching and screening is simplified.
In some embodiments of the present application, the decomposing the initial system information and the initial policy information to obtain a plurality of sub-search items includes:
Classifying the initial system information according to each department in the enterprise to obtain department retrieval sub-items;
Dividing the department retrieval sub-items according to functions and role authorities to obtain a plurality of system sub-items;
dividing the initial policy information according to the business scope of the enterprise to obtain a plurality of policy sub-projects;
And combining each system sub-item and each policy sub-item into a plurality of sub-search items.
In the technical scheme, the initial system information is classified according to each department, and a plurality of system sub-items are obtained by dividing according to functions and roles, so that the system can be managed, the search is convenient, and the search result is easy to obtain. The initial policy information is divided through the business scope of the enterprise to obtain a plurality of policy sub-items, so that the policy is managed, and the policies associated with the enterprise can be easily searched later.
In some embodiments of the present application, the information retrieval recommendation is performed according to the association analysis, to obtain a retrieval result, including:
Selecting a corresponding system characteristic node with the association analysis value larger than a preset threshold value as a system association node according to the association analysis, and selecting a corresponding policy characteristic node with the association analysis value larger than the preset threshold value as a policy association node;
and connecting the system corresponding to the system association node with the policy corresponding to the policy association node, and recommending the connected result to obtain a retrieval result.
According to the technical scheme, screening is carried out according to the association analysis, and the screened system and policy are recommended after being connected, so that a search result is obtained, the associated system and policy can be obtained, and the search requirement of a user can be met.
In some embodiments of the present application, the information retrieval recommendation is performed according to the association analysis, to obtain a retrieval result, including:
responding to the retrieval screening operation of the user, and screening the association analysis to obtain a screened association analysis;
and matching the filtered association analysis with the operation record of the user in the enterprise to generate the search result.
In the technical scheme, through user-defined screening operation, personalized retrieval of the user can be realized, corresponding retrieval results are obtained, and the retrieval requirements of the user are met.
In some embodiments of the present application, after the obtaining the requirement to be retrieved input by the user, the method further includes:
verifying the role of the user, and verifying the authority of the user under the condition that the role of the user is a member of an item group to obtain access authority;
Under the condition that the access rights are a plurality of access rights, determining the requirement to be searched input by the user as a parallel search requirement;
And under the condition that the access authority is non-parallel access, determining the requirement to be searched input by the user as a single search requirement.
In the technical scheme, the security of retrieval can be ensured by verifying the roles and then verifying the access right after determining the roles as the members of the project group. And under the condition of having access rights, the parallel search requirement and the single search requirement are determined, so that parallel search can be realized, and the diversity search requirement is met.
In a second aspect, an embodiment of the present application provides an enterprise information retrieval device based on a knowledge engine, the device including:
the system comprises a data acquisition module, a voice search module and a data processing module, wherein the data acquisition module is used for acquiring a to-be-searched demand input by a user, and the to-be-searched demand comprises a system search demand and a policy search demand, wherein the to-be-searched demand is voice search;
The data searching module is used for crawling information on a preset large model knowledge engine according to the system searching requirement and the policy searching requirement to obtain initial system information and initial policy information;
The data decomposition module is used for respectively decomposing the initial system information and the initial policy information to obtain a plurality of sub-search items;
The correlation calculation module is used for carrying out correlation calculation on each sub-search item to obtain correlation analysis;
And the retrieval recommendation module is used for carrying out information retrieval recommendation according to the association analysis to obtain a retrieval result, wherein the retrieval result is a voice answer corresponding to the voice retrieval.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, a user interface, a communication bus, and a network interface, where the processor, the memory, the user interface, and the network interface are respectively connected to the communication bus, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory, so that the electronic device performs the method according to any one of the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing instructions that, when executed, perform the method of any one of the first aspects provided above.
In summary, one or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
1. The method comprises the steps of acquiring a requirement to be searched, which is input by a user, wherein the requirement to be searched comprises a system searching requirement and a policy searching requirement, the requirement to be searched is voice searching, corresponding systems or policies are recommended automatically and conveniently by acquiring the corresponding requirement to be searched, information crawling is conducted on a preset large model knowledge engine according to the requirement to be searched to obtain initial system information and initial policy information, the information crawling is conducted automatically through the large model knowledge engine, corresponding information can be timely acquired, newer and more comprehensive system and policy information can be obtained, the initial system information and the initial policy information are respectively decomposed to obtain a plurality of sub-search items, information is conveniently managed by means of information decomposition so as to be recommended accurately and conveniently, relevance calculation is conducted on each sub-search item to obtain relevance analysis, the relevant systems and policies can be recommended to be conveniently used for user searching, information retrieval recommendation is conducted according to relevance analysis, and retrieval results are obtained according to the relevance analysis, the voice searching corresponding voice searching answer can be recommended, the information meeting the requirement can be conveniently searched, and the user can conveniently search and the user can be conveniently and quickly achieved by adopting a user mode. Therefore, the method and the device effectively solve the problem that the user is difficult to acquire the required system or policy because the intelligent retrieval cannot be realized in the related technology.
2. And performing association matching on the association analysis and the historical operation record of the user, so that the recommended retrieval result meets the retrieval requirement of the user.
3. By judging the roles and the authorities of the users, corresponding system and policy recommendation can be performed according to the retrieval authorities of the users, and safety control is realized.
Drawings
FIG. 1 is a flow diagram of a knowledge engine based enterprise information retrieval method in accordance with an embodiment of the application;
FIG. 2 is a schematic flow chart showing a sub-step of step S300 in FIG. 1;
FIG. 3 is a schematic flow chart of a sub-step of step S400 in FIG. 1;
FIG. 4 is a schematic flow chart showing a sub-step of step S430 in FIG. 3;
FIG. 5 is a schematic flow chart showing a sub-step of step S500 in FIG. 1;
FIG. 6 is a schematic diagram of an enterprise information retrieval device based on a knowledge engine, in accordance with an embodiment of the application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments.
In describing embodiments of the present application, words such as "for example" or "for example" are used to mean serving as examples, illustrations, or descriptions. Any embodiment or design described herein as "such as" or "for example" in embodiments of the application should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "or" for example "is intended to present related concepts in a concrete fashion.
In the description of embodiments of the application, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating an indicated technical feature. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
The embodiment of the application provides a knowledge engine-based enterprise information retrieval method, a knowledge engine-based enterprise information retrieval device, electronic equipment and a readable storage medium, wherein the knowledge engine-based enterprise information retrieval method firstly obtains requirements to be retrieved input by a user, and the requirements to be retrieved comprise system retrieval requirements and policy retrieval requirements, wherein the requirements to be retrieved are voice retrieval, and the corresponding requirements to be retrieved are obtained, so that the subsequent automatic recommendation of corresponding systems or policies is facilitated; the method comprises the steps of carrying out information crawling on a preset large model knowledge engine according to system retrieval requirements and policy retrieval requirements to obtain initial system information and initial policy information, carrying out information crawling automatically through the large model knowledge engine, timely obtaining corresponding information, further obtaining newer and more comprehensive system and policy information, respectively decomposing the initial system information and the initial policy information to obtain a plurality of sub-retrieval items, carrying out information decomposition to facilitate information management so as to facilitate accurate subsequent recommendation, carrying out correlation calculation on each sub-retrieval item to obtain correlation analysis, carrying out correlation analysis to enable recommended relevant system and policy to facilitate user retrieval, carrying out information retrieval recommendation according to the correlation analysis to obtain retrieval results, wherein the retrieval results are voice answers corresponding to voice retrieval, and can recommend information meeting user input requirements, so that retrieval is convenient and quick for users.
It should be noted that, the knowledge engine-based enterprise information retrieval method is applied to the medical industry and the system and policy retrieval of enterprises associated with the medical industry, and can also be applied to the system and policy retrieval of other industries. In the medical industry, clinical trial research and medication standards are various, and the knowledge engine-based enterprise information retrieval method can help users to quickly retrieve corresponding systems and standards, so that the users can conveniently check at any time.
The technical scheme provided by the embodiment of the application is further described below with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a flowchart of an enterprise information retrieval method based on a knowledge engine according to an embodiment of the present application. The knowledge engine-based enterprise information retrieval method is applied to the knowledge engine-based enterprise information retrieval device, and is executed by the electronic device or a processor in the readable storage medium, and comprises the steps of S100, S200, S300, S400 and S500.
Step S100, obtaining a requirement to be searched input by a user, wherein the requirement to be searched comprises a system searching requirement and a policy searching requirement, and the requirement to be searched is voice searching.
In one embodiment, the requirements to be searched include a system search requirement and a policy search requirement, wherein the system search requirement is a search requirement of relevant system of each department in the enterprise, and the policy search requirement is a requirement of relevant policy of corresponding department in the enterprise development and a requirement of relevant policy of medical industry. First, the user logs in the information retrieval engine, and the user can input the requirement to be retrieved, for example, the medication standard system, the medication policy specification and the like of the clinical test can be retrieved. The requirement to be searched for input can be only a system searching requirement, can be only a policy searching requirement, and can also comprise a system searching requirement and a policy searching requirement. According to the input of the user, the input mode of the user can select a voice input mode or a text input mode, for example, a voice input mode is taken as an example, a voice input button can be clicked, and the user can describe the requirement. And acquiring the requirement to be searched input by a user through the front-end and back-end transfer functions of the search engine, so as to facilitate the subsequent automatic recommendation of corresponding systems or policies.
In one embodiment, after obtaining the requirement to be searched input by the user, the enterprise information searching method based on the knowledge engine further comprises, but is not limited to, verifying the role of the user, verifying the authority of the user to obtain the access authority when the role of the user is a member of the project group, and determining the requirement to be searched input by the user to be a parallel searching requirement when the access authority is a member with a plurality of access authorities.
Specifically, the roles of the users are verified, whether the roles are members of the corresponding departments or not is checked, and the corresponding system of the corresponding departments can be checked only if the users are members of the corresponding parts. The policy information is automatically crawled and sorted and then divided into corresponding departments, and can be checked after the role verification is passed. And under the condition that the role of the user is a project group member, verifying the authority of the user to obtain the access authority. The method is characterized in that the project group members can execute different test projects in parallel, and the access rights of users are verified for different project systems and standards to determine whether to perform parallel search. Under the condition that the access rights are provided with a plurality of access rights, the user is indicated to have retrieval requirements of a plurality of systems and policies, the to-be-retrieved requirements input by the user are determined to be parallel retrieval requirements, and information acquisition is carried out on the parallel retrieval requirements by utilizing multiple threads, so that the processing efficiency is improved. Through the authority verification, safety control is performed, and data safety is realized.
In another embodiment, after obtaining the requirement to be searched input by the user, the enterprise information searching method based on the knowledge engine further comprises, but is not limited to, verifying the role of the user, verifying the authority of the user to obtain the access authority when the role of the user is a member of the project group, and determining the requirement to be searched input by the user to be a single searching requirement when the access authority is non-parallel access.
Specifically, firstly, verifying a user role, checking whether the role is a member of a corresponding department, and only if the user is a member of the corresponding department, checking the corresponding system and the divided policy of the corresponding department. And under the condition that the role of the user is a project group member, verifying the authority of the user to obtain the access authority. The method is characterized in that the project group members can execute different test projects in parallel, and the access authority of the user is verified according to different project systems and standards, and under the condition that the access authority is non-parallel access, the user is indicated to have no retrieval requirements of a plurality of systems and policies, the to-be-retrieved requirement input by the user is determined to be a single retrieval requirement, and the single retrieval requirement is subjected to information acquisition by utilizing a single thread so as to save resources. Through the authority verification, safety control is performed, and data safety is realized.
Step S200, information crawling is carried out on a preset large model knowledge engine according to the system retrieval requirement and the policy retrieval requirement, and initial system information and initial policy information are obtained.
In an embodiment, a preset large model knowledge engine integrates a file storage library of a department system, professional knowledge bases of various industries and policy information obtained from official websites, authoritative media, professional research institutions and the like, has massive data, digs knowledge through an industry large model, and adopts manual screening to form data which can be crawled. By automatically crawling information on the large model knowledge engine, corresponding information can be obtained in time, and newer system and policy information can be obtained so as to control the research direction of clinical tests. The method comprises the steps of firstly determining a target and a range to be crawled according to a system retrieval requirement and a policy retrieval requirement, and for crawling of a department system, searching a file storage library of the department system or searching related system information of related enterprises of the industry from a professional knowledge base of each industry to obtain initial system information. The crawling of the policy information can be achieved by mining corresponding information from each public institution through industry big model mining, so as to obtain initial policy information. The information crawling is performed through the large model knowledge engine, so that corresponding information can be timely obtained, and newer and more comprehensive system and policy information can be obtained. The industrial large model is realized based on technologies such as P-Tuning and LoRa, and the effect of tasks is improved on the basis of a small amount of calculation force, so that the cost of calculation resources can be saved.
And step S300, decomposing the initial system information and the initial policy information respectively to obtain a plurality of sub-search items.
As shown in fig. 2, the initial system information and the initial policy information are decomposed respectively to obtain a plurality of sub-search items, including but not limited to the following steps:
and step S310, classifying the initial system information according to each department in the enterprise to obtain department retrieval sub-items.
In one embodiment, the initial system information and the initial policy information crawled in step S200 are subjected to information arrangement, so that the relevant data can be easily retrieved later. The initial system information is firstly classified according to each department in the enterprise, and because the system of each department is different, for example, emergency departments, clinical research departments and the like exist in clinic, the system of each clinic department is different, and the department retrieval sub-items are obtained by classifying according to the departments, so that the corresponding system can be divided, excessive time waste during retrieval and searching is avoided, and convenience is provided for system acquisition.
It should be noted that, the system information in each department may be repeated or different, and the corresponding access authority for different system information is higher, and after the access verification, the corresponding system can be searched and checked. For the same system information, each department personnel accesses the corresponding system information through the department interface, so that the retrieval efficiency can be accelerated.
Step S320, dividing the department retrieval sub-items according to the functions and the role rights to obtain a plurality of system sub-items.
In an embodiment, since different user roles have different access rights, and the system of each item reference in the same department may also be different, after division according to the department, division is performed on the department search sub-items according to the functions and role rights, so as to obtain multiple system sub-items. Through dividing, the information is convenient to manage, and subsequent quick retrieval and recommendation are facilitated.
In clinical experiments, the functions refer to drug administration standards, execution standard systems of different experiments and the like which are referenced in project implementation, and role authorities can be group owners and members in project group members, wherein the group owners have higher access authorities than the members. The system division is carried out according to different projects, so that the system of other projects can be prevented from being checked, the safety is ensured, and the search and inquiry can be facilitated. And after the division is carried out according to the role authorities, the access of a system is limited, for example, the members do not need to search some contents which can be reduced by the group owner authorities, so that the time is saved, convenience is brought to the search of users, and easier information acquisition is realized.
Step S330, dividing the initial policy information according to the business scope of the enterprise to obtain a plurality of policy sub-items.
In one embodiment, in a clinical trial, the initial policy information includes approval process, fund subsidy, tax, etc., and the business scope is obtained according to registration information of the medical institution, and the business scope of the enterprise can be obtained by reading the enterprise information registration. And establishing a connection between the initial policy information and the business scope of the enterprise, dividing the initial policy information to obtain a plurality of policy sub-items, thereby providing convenience for user retrieval and facilitating easier information acquisition. The policy may be guided to match with the enterprise operation scope through a preset matching algorithm to establish a correlation, where the preset matching algorithm may be a natural language processing algorithm, for example, a word segmentation algorithm, a deep learning algorithm, and the like.
It should be noted that, since the policy information may be updated continuously, the initial policy information is acquired according to a preset time, and a relationship between the acquired initial policy information and the business scope is established. Policy information associated with the initial policy information may also be updated based on previous policies to conserve resources.
Step S340, each system sub-item and each policy sub-item are combined into a plurality of sub-search items.
In an embodiment, according to each system sub-item obtained in step S320 and each policy sub-item obtained in step S330, the system sub-items are all used as sub-search items, and form an item group set, which is beneficial to follow-up search recommendation according to the sub-search items.
And step S400, performing correlation calculation on each sub-search item to obtain correlation analysis.
In one embodiment, the sub-search items comprise a plurality of system sub-items and a plurality of policy sub-items, and as shown in fig. 3, correlation calculation is performed on each sub-search item to obtain a correlation analysis, including but not limited to the following steps:
And step S410, performing feature map processing on each system sub-item to obtain a system feature sub-map.
In an embodiment, for each system sub-item, keyword recognition is performed by using a graph neural network to obtain system keyword features, the system keyword features are used as nodes, association relation extraction is performed according to each system sub-item to obtain the association between the system keyword features, a system feature sub-graph is established so as to facilitate subsequent calculation of the association between the sub-graphs, and association analysis is performed. For each system sub-item, the relation among the system sub-items can be extracted by using the graphic neural network, and the relation among the system sub-items can be established.
Step S420, processing the feature map of each policy sub-item to obtain a policy feature sub-image.
In an embodiment, for each policy sub-item, keyword recognition is performed by using a graph neural network to obtain policy keyword features, the policy keyword features are used as nodes, association relation extraction is performed according to each policy sub-item to obtain a relationship between the policy keyword features, and a policy feature sub-graph is established so as to facilitate the relationship between subsequent calculation sub-graphs to perform association analysis. For each policy sub-item, the relationship between each policy sub-item can be extracted by using the graph neural network, and the relationship between each policy sub-item can be established.
And step S430, associating the system feature subgraph with the policy feature subgraph to obtain association analysis.
In an embodiment, according to the system feature subgraph obtained in step S410 and the policy feature subgraph obtained in step S420, a relationship between feature graphs is established, and association analysis is obtained, so that subsequent retrieval is facilitated.
As shown in fig. 4, the system feature subgraph and the policy feature subgraph are associated to obtain an association analysis, including but not limited to the following steps:
step S431, calculating the similarity between each system feature node in the system feature subgraph and the policy feature node in the policy feature subgraph to obtain the similarity.
In an embodiment, similarity between each system feature node in the system feature sub-graph and the policy feature node in the policy feature sub-graph is calculated by using a preset keyword matching algorithm, so as to obtain similarity, and the similarity is represented by a similarity degree value so as to facilitate subsequent relevance calculation. By carrying out similarity association calculation, the associated system and policy can be recommended, convenience is brought to user retrieval, and easier information acquisition is realized. The preset keyword matching algorithm may be the longest common substring matching algorithm, or may be a character string matching algorithm.
Step S432, calculating the relevance of the system characteristic subgraph and the policy characteristic subgraph by using a preset relevance rule to obtain relevance, wherein the relevance rule is obtained by extracting the relation between a historical system and a historical policy.
In an embodiment, the preset association rule is obtained by extracting a relationship between a history system and a history policy, where the history system is an old system adopted by the enterprise or a system adopted by an enterprise similar to the enterprise. The history policy is a previously published old policy or a policy related to the policy. The history system and the history policy are obtained by crawling from the internet by utilizing a crawler technology, and the data volume is large. According to the acquired history system and history policy, firstly, data preprocessing is carried out on the history system and the history policy, wherein the data preprocessing comprises data cleaning, data conversion, standardization processing and the like. And then, respectively carrying out feature map processing on the processed history system and history policy to obtain a history system feature map corresponding to the history system and a history policy feature map corresponding to the history policy. And training the initial association rule by using a large number of historical system feature graphs and historical policy feature graphs to obtain a trained association rule, namely a preset association rule. And calculating the relevance of the system characteristic subgraph and the policy characteristic subgraph by using a preset relevance rule to obtain relevance, wherein the relevance is expressed in a numerical form so as to carry out subsequent relevance analysis calculation. By carrying out the relevance calculation, the relevant system and policy can be recommended, convenience is brought to the user retrieval, and easier information acquisition is realized. The preset association rule may be a mutual information algorithm, a covariance matrix, a deep learning model, and the like. Since there are a plurality of the system feature map and the policy feature map, there are a plurality of the obtained correlations.
And step S433, weighting calculation is carried out on the similarity and the relevance to obtain relevance analysis.
In an embodiment, the similarity is obtained according to step S431, and the similarity values are first sorted, which may be arranged in ascending order or descending order, and selected. Illustratively, the similarity values are arranged in descending order, and a preset number of similarity values arranged in front are selected to perform weighted calculation with the relevance. The preset number is the same as the association number. And then carrying out weighted calculation on the similarity and the relevance, and respectively endowing the similarity and the relevance with corresponding weights, wherein the weights are obtained according to experience of professionals and are not described in detail herein, and the weight is used for adjusting the proportion occupied by the similarity and the relevance so as to obtain the relevance analysis. The correlation analysis is also represented by a numerical form, and the larger the numerical value is, the stronger the correlation is indicated. So that the subsequent retrieval recommends the retrieval results meeting the requirements.
And S500, carrying out information retrieval recommendation according to the association analysis to obtain a retrieval result, wherein the retrieval result is a voice answer corresponding to voice retrieval.
As shown in fig. 5, the information retrieval recommendation is performed according to the association analysis, and the retrieval result is obtained, which includes but is not limited to the following steps:
Step S510, selecting corresponding system feature nodes with the association analysis value larger than a preset threshold value as system association nodes according to the association analysis, and selecting corresponding policy feature nodes with the association analysis value larger than the preset threshold value as policy association nodes.
In an embodiment, since the association analysis is represented in a numerical form, that is, an association analysis value, according to the association analysis obtained in step S400, a corresponding system feature node with an association analysis value greater than a preset threshold is selected as a system association node, which indicates that the system information corresponding to the system association node meets the search requirement of the user, and a corresponding policy feature node with an association analysis value greater than the preset threshold is selected as a policy association node, which indicates that the policy information corresponding to the policy association node meets the search requirement of the user, so as to be recommended later. The preset threshold is set by a professional according to experience, and will not be described here.
Under the condition that a plurality of correlation analysis values are larger than a preset threshold value, a system feature node and a policy feature node corresponding to the maximum correlation analysis value in the correlation analysis values are selected.
In another embodiment, in the case that the association analysis value is less than or equal to the preset threshold, the association analysis values are ranked, illustratively, in a descending order, and then the system feature nodes corresponding to the association analysis values of N before the ranking in the association analysis values are selected as the system association nodes, and the corresponding policy feature nodes are selected as the policy association nodes.
Step S520, connecting the system corresponding to the system association node with the policy corresponding to the policy association node, and recommending the connected result to obtain the retrieval result.
In an embodiment, according to the system association node and the policy association node obtained in step S510, the system corresponding to the system association node and the policy corresponding to the policy association node are connected in character strings, that is, the system and the policy are combined into a record, the connected result is recommended to obtain a search result, and information meeting the input requirement of the user can be recommended, so that the search and the search are convenient.
When the search requirements are parallel, the search results corresponding to the search requirements are displayed in a table form for the user to view. In the case of a single search requirement, it may also be presented in tabular form, with only one record in the table.
In one embodiment, information retrieval recommendation is performed according to the association analysis to obtain retrieval results, including but not limited to, responding to a retrieval screening operation of a user, screening the association analysis to obtain a screened association analysis, and matching the screened association analysis with an operation record of the user in an enterprise to generate the retrieval results.
In some possible embodiments of the present application, the user may also select to search the system and policy, and may also perform conditional restriction on the recommended search result. And responding to the retrieval screening operation of the user, and screening the association analysis to obtain the screened association analysis. Illustratively, when the search screening operation of the user is to view only the search system or only the search policy, the system or the policy is screened out, and the association analysis after screening is system analysis or policy analysis. Because the user has the operation record in the enterprise, the operation record of the user in the enterprise can be read, the operation record is matched with the screened association analysis, the screened association analysis can be matched with the operation record of the user in the enterprise, a partial character matching algorithm can be adopted, and a search result is generated, and the search result meets the search requirement of the user more.
It should be noted that, the search result is presented to the user in a voice manner, and is presented in a dialogue manner on the front-end page, so that the user can use the search function easily and quickly.
As shown in fig. 6, an embodiment of the present application provides an enterprise information retrieval device 100 based on a knowledge engine, where the enterprise information retrieval device 100 based on a knowledge engine obtains a requirement to be retrieved input by a user through a data obtaining module 110, the requirement to be retrieved includes a system retrieval requirement and a policy retrieval requirement, the requirement to be retrieved is voice retrieval, the requirement to be retrieved is beneficial to follow-up automatic recommendation of corresponding systems or policies through obtaining the corresponding requirement to be retrieved, then information crawling is performed on a preset large model knowledge engine according to the system retrieval requirement and the policy retrieval requirement through a data searching module 120, initial system information and initial policy information are obtained, information crawling is performed automatically through the large model knowledge engine, corresponding information can be timely obtained, and newer and more comprehensive system and policy information can be obtained, the initial system information and the initial policy information can be decomposed respectively by a data decomposing module 130, a plurality of sub-retrieval items are obtained, the information is managed through information decomposition, so that the follow-up accurate recommendation can be performed, the relevance calculation is performed on each sub-retrieval item through adopting a relevance calculation module 140, relevance analysis is obtained, relevance analysis is performed, the relevance analysis is enabled, the relevance information can be obtained, the user can be easily obtained, and the user can easily obtain a recommendation by using a recommendation result, and the recommendation function is convenient to obtain by using a recommendation, and the recommendation result is recommended, and the user can easily, and the retrieval result is recommended by using a user.
It should be noted that, the data acquisition module 110 is connected to the data search module 120, the data search module 120 is connected to the data decomposition module 130, the data decomposition module 130 is connected to the correlation calculation module 140, and the correlation calculation module 140 is connected to the retrieval recommendation module 150. The knowledge engine-based enterprise information retrieval method is applied to the knowledge engine-based enterprise information retrieval device 100, the knowledge engine-based enterprise information retrieval device 100 obtains the to-be-retrieved requirements input by a user, the to-be-retrieved requirements comprise system retrieval requirements and policy retrieval requirements, the to-be-retrieved requirements are voice retrieval, corresponding system or policy is recommended automatically after corresponding to the to-be-retrieved requirements are obtained, information crawling is conducted on a preset large model knowledge engine according to the system retrieval requirements and the policy retrieval requirements, initial system information and initial policy information are obtained, information crawling is conducted automatically through the large model knowledge engine, corresponding information can be obtained timely, newer and more comprehensive system and policy information can be obtained, the initial system information and the initial policy information are respectively decomposed, a plurality of sub-retrieval items are obtained, the information is conveniently managed through information decomposition so as to be recommended accurately later, correlation analysis is obtained through correlation analysis on each sub-retrieval item, the correlation retrieval system and policy can be recommended conveniently, information retrieval is achieved for the user, information retrieval is achieved easily, the corresponding voice retrieval result can be conveniently searched by adopting a recommendation mode, and the voice retrieval function is conveniently achieved, and the user can be conveniently searched by adopting a recommendation function.
It should be further noted that, when the apparatus provided in the foregoing embodiment implements the functions thereof, only the division of the foregoing functional modules is used as an example, in practical application, the foregoing functional allocation may be implemented by different functional modules, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the embodiments of the apparatus and the method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the embodiments of the method are detailed in the method embodiments, which are not repeated herein.
The application also discloses electronic equipment. Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 500 may include at least one processor 501, at least one network interface 504, a user interface 503, a memory 505, and at least one communication bus 502.
Wherein a communication bus 502 is used to enable connected communications between these components.
The user interface 503 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 503 may further include a standard wired interface and a standard wireless interface.
The network interface 504 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.
Wherein the processor 501 may include one or more processing cores. The processor 501 connects various parts throughout the server using various interfaces and lines, performs various functions of the server and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 505, and invoking data stored in the memory 505. Alternatively, the processor 501 may be implemented in at least one hardware form of digital signal Processing (DIGITAL SIGNAL Processing, DSP), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 501 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like, the GPU is used for rendering and drawing contents required to be displayed by the display screen, and the modem is used for processing wireless communication. It will be appreciated that the modem may not be integrated into the processor 501 and may be implemented by a single chip.
The Memory 505 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 505 comprises a non-transitory computer readable medium (non-transitory computer-readable storage medium). Memory 505 may be used to store instructions, programs, code sets, or instruction sets. The memory 505 may include a stored program area that may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, etc., and a stored data area that may store data related to the various method embodiments described above, etc. The memory 505 may also optionally be at least one storage device located remotely from the processor 501. Referring to fig. 7, an operating system, a network communication module, a user interface module, and an application program of an enterprise information retrieval method based on a knowledge engine may be included in a memory 505 as a computer storage medium.
In the electronic device 500 shown in fig. 7, the user interface 503 is primarily used to provide an input interface for a user to obtain data entered by the user, while the processor 501 may be used to invoke an application in the memory 505 that stores a knowledge engine based enterprise information retrieval method, which when executed by the one or more processors 501, causes the electronic device 500 to perform the method as in one or more of the embodiments described above. It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all of the preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as a division of units, merely a division of logic functions, and there may be additional divisions in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in whole or in part in the form of a software product stored in a memory, comprising several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method of the various embodiments of the present application. The memory includes various media capable of storing program codes, such as a USB flash disk, a mobile hard disk, a magnetic disk or an optical disk.
The above are merely exemplary embodiments of the present disclosure and are not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure.
This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.
Claims (10)
1. A knowledge engine-based enterprise information retrieval method, the method comprising:
acquiring a requirement to be searched input by a user, wherein the requirement to be searched comprises a system searching requirement and a policy searching requirement, and the requirement to be searched is voice searching;
according to the system retrieval requirements and the policy retrieval requirements, information crawling is carried out on a preset large model knowledge engine to obtain initial system information and initial policy information;
decomposing the initial system information and the initial policy information respectively to obtain a plurality of sub-search items;
Carrying out correlation calculation on each sub-search item to obtain correlation analysis;
And carrying out information retrieval recommendation according to the association analysis to obtain a retrieval result, wherein the retrieval result is a voice answer corresponding to the voice retrieval.
2. The method of claim 1, wherein the sub-search items comprise a plurality of system sub-items and a plurality of policy sub-items;
and performing correlation calculation on each sub-search item to obtain correlation analysis, wherein the correlation analysis comprises the following steps:
Carrying out feature map processing on each system sub-item to obtain a system feature sub-map;
performing feature map processing on each policy sub-item to obtain a policy feature sub-map;
and correlating the system characteristic subgraph with the policy characteristic subgraph to obtain the correlation analysis.
3. The method of claim 2, wherein said correlating said institutional feature sub-graph with said policy feature sub-graph to obtain said correlation analysis comprises:
calculating the similarity of each system feature node in the system feature subgraph and the policy feature node in the policy feature subgraph to obtain similarity;
Calculating the relevance of the system characteristic subgraph and the policy characteristic subgraph by using a preset relevance rule to obtain relevance, wherein the relevance rule is obtained by extracting the relation between a historical system and a historical policy;
and carrying out weighted calculation on the similarity and the relevance to obtain the relevance analysis.
4. The method of claim 1, wherein the decomposing the initial system information and the initial policy information to obtain a plurality of sub-search items comprises:
Classifying the initial system information according to each department in the enterprise to obtain department retrieval sub-items;
Dividing the department retrieval sub-items according to functions and role authorities to obtain a plurality of system sub-items;
dividing the initial policy information according to the business scope of the enterprise to obtain a plurality of policy sub-projects;
And combining each system sub-item and each policy sub-item into a plurality of sub-search items.
5. The method of claim 1, wherein the performing information retrieval recommendation according to the association analysis, to obtain a retrieval result, comprises:
Selecting a corresponding system characteristic node with the association analysis value larger than a preset threshold value as a system association node according to the association analysis, and selecting a corresponding policy characteristic node with the association analysis value larger than the preset threshold value as a policy association node;
and connecting the system corresponding to the system association node with the policy corresponding to the policy association node, and recommending the connected result to obtain a retrieval result.
6. The method of claim 1, wherein the performing information retrieval recommendation according to the association analysis, to obtain a retrieval result, comprises:
responding to the retrieval screening operation of the user, and screening the association analysis to obtain a screened association analysis;
and matching the filtered association analysis with the operation record of the user in the enterprise to generate the search result.
7. The method of claim 1, wherein after the obtaining the user-entered need to be retrieved, the method further comprises:
verifying the role of the user, and verifying the authority of the user under the condition that the role of the user is a member of an item group to obtain access authority;
Under the condition that the access rights are a plurality of access rights, determining the requirement to be searched input by the user as a parallel search requirement;
And under the condition that the access authority is non-parallel access, determining the requirement to be searched input by the user as a single search requirement.
8. An enterprise information retrieval device based on a knowledge engine, the device comprising:
The system comprises a data acquisition module (110) for acquiring requirements to be searched, which are input by a user, wherein the requirements to be searched comprise system searching requirements and policy searching requirements, and the requirements to be searched are voice searching;
The data searching module (120) is used for crawling information on a preset large model knowledge engine according to the system searching requirement and the policy searching requirement to obtain initial system information and initial policy information;
The data decomposition module (130) is used for respectively decomposing the initial system information and the initial policy information to obtain a plurality of sub-search items;
The relevance calculating module (140) is used for carrying out relevance calculation on each sub-search item to obtain relevance analysis;
and the retrieval recommendation module (150) is used for carrying out information retrieval recommendation according to the association analysis to obtain a retrieval result, wherein the retrieval result is a voice answer corresponding to the voice retrieval.
9. An electronic device comprising a processor (501), a memory (505), a user interface (503), a communication bus (502) and a network interface (504), the processor (501), the memory (505), the user interface (503) and the network interface (504) being respectively connected to the communication bus (502), the memory (505) being for storing instructions, the user interface (503) and the network interface (504) being for communicating to other devices, the processor (501) being for executing the instructions stored in the memory (505) for causing the electronic device (500) to perform the method according to any of claims 1-7.
10. A computer readable storage medium storing instructions which, when executed, perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510025422.2A CN119441568A (en) | 2025-01-08 | 2025-01-08 | Enterprise information retrieval method, device and electronic device based on knowledge engine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510025422.2A CN119441568A (en) | 2025-01-08 | 2025-01-08 | Enterprise information retrieval method, device and electronic device based on knowledge engine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119441568A true CN119441568A (en) | 2025-02-14 |
Family
ID=94529373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510025422.2A Pending CN119441568A (en) | 2025-01-08 | 2025-01-08 | Enterprise information retrieval method, device and electronic device based on knowledge engine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119441568A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111210198A (en) * | 2019-12-30 | 2020-05-29 | 广州高企云信息科技有限公司 | Information delivery method and device and server |
| WO2022016561A1 (en) * | 2020-07-22 | 2022-01-27 | 江苏宏创信息科技有限公司 | Ai modeling system and method for policy profiling based on big data |
| CN115203357A (en) * | 2022-07-27 | 2022-10-18 | 海南绿境高科环保有限公司 | Information retrieval and information index updating method, device, equipment and medium |
| CN116467291A (en) * | 2023-03-10 | 2023-07-21 | 北京无代码科技有限公司 | Knowledge graph storage and search method and system |
| CN118069822A (en) * | 2024-01-25 | 2024-05-24 | 中国电信股份有限公司 | Recommendation method, recommendation device, recommendation equipment and storage medium |
| CN118245671A (en) * | 2024-03-14 | 2024-06-25 | 广东省华南技术转移中心有限公司 | Automatic extraction and recommendation method and system of science and technology policy information based on web crawler |
| CN118349701A (en) * | 2024-02-26 | 2024-07-16 | 深圳市绿联科技股份有限公司 | Information retrieval recommendation method, device, electronic equipment, storage equipment and system |
-
2025
- 2025-01-08 CN CN202510025422.2A patent/CN119441568A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111210198A (en) * | 2019-12-30 | 2020-05-29 | 广州高企云信息科技有限公司 | Information delivery method and device and server |
| WO2022016561A1 (en) * | 2020-07-22 | 2022-01-27 | 江苏宏创信息科技有限公司 | Ai modeling system and method for policy profiling based on big data |
| CN115203357A (en) * | 2022-07-27 | 2022-10-18 | 海南绿境高科环保有限公司 | Information retrieval and information index updating method, device, equipment and medium |
| CN116467291A (en) * | 2023-03-10 | 2023-07-21 | 北京无代码科技有限公司 | Knowledge graph storage and search method and system |
| CN118069822A (en) * | 2024-01-25 | 2024-05-24 | 中国电信股份有限公司 | Recommendation method, recommendation device, recommendation equipment and storage medium |
| CN118349701A (en) * | 2024-02-26 | 2024-07-16 | 深圳市绿联科技股份有限公司 | Information retrieval recommendation method, device, electronic equipment, storage equipment and system |
| CN118245671A (en) * | 2024-03-14 | 2024-06-25 | 广东省华南技术转移中心有限公司 | Automatic extraction and recommendation method and system of science and technology policy information based on web crawler |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102222081B (en) | The model of personage is applied to Search Results | |
| CN112199512B (en) | Method, device, equipment and storage medium for constructing event map for scientific and technological services | |
| US11941714B2 (en) | Analysis of intellectual-property data in relation to products and services | |
| US11803927B2 (en) | Analysis of intellectual-property data in relation to products and services | |
| CN102243647A (en) | Extracting higher-order knowledge from structured data | |
| KR102559806B1 (en) | Method and Apparatus for Smart Law Precedent Search Technology and an Integrated Law Service Technology Based on Machine Learning | |
| CN107844533A (en) | A kind of intelligent Answer System and analysis method | |
| CN115714002B (en) | Depression risk detection model training method, depressive symptom early warning method and related equipment | |
| CN118350968B (en) | Intelligent processing method and system for realizing case law examination based on deep learning | |
| EP4575822A1 (en) | Data source mapper for enhanced data retrieval | |
| US20210004918A1 (en) | Analysis Of Intellectual-Property Data In Relation To Products And Services | |
| CN120412984B (en) | Large-model-based enterprise intelligent diagnosis method, system, equipment and medium | |
| CN120429414B (en) | A technology development situation awareness system and method | |
| CN118095270B (en) | A method, device, electronic device and storage medium for constructing a logic analysis diagram | |
| Zhao et al. | State and tendency: an empirical study of deep learning question&answer topics on Stack Overflow | |
| Ataman et al. | Transforming large-scale participation data through topic modelling in urban design processes | |
| CN112052365A (en) | Cross-border scene portrait construction method and device | |
| CN119441499B (en) | Construction method, device and equipment of financial event map | |
| CN119441568A (en) | Enterprise information retrieval method, device and electronic device based on knowledge engine | |
| Butcher | Contract Information Extraction Using Machine Learning | |
| CN110909777B (en) | A multi-dimensional feature map embedding method, device, equipment and medium | |
| Reese et al. | Java: Data science made easy | |
| CN114780730B (en) | Automatic analysis method and device for relationship types in knowledge graph construction process | |
| CN118132818B (en) | Tourist area resource assessment method based on image difference | |
| CN119830896B (en) | Data intelligence intelligent analysis method based on LLM large language model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20250214 |