Method and apparatus for pushing policy data

Abstract

The application discloses a policy data pushing method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: in response to a policy pushing request, obtaining a user identifier of a user to be pushed, and obtaining a user portrait attribute according to the user identifier; obtaining a policy special subject bound with the user portrait attribute according to the user portrait attribute; obtaining to-be-pushed policy data according to the association relationship between the policy special subject and the policy data, wherein the to-be-pushed policy data comprises to-be-pushed policy files and interpretation files of the to-be-pushed policy files; and performing policy data pushing based on the to-be-pushed policy files and the interpretation files of the to-be-pushed policy files. The embodiment improves the intelligent level and the individualization degree of policy data recommendation, solves the technical problems of current policy interpretation difficulty, policy reach difficulty, policy matching difficulty and policy analysis difficulty, and improves the intelligibility, applicability and implementation effect of the policy.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method and apparatus for pushing policy data. Background Technology

[0002] To better communicate the content and effects of policies, governments, departments, and institutions at all levels actively release various types of policy information. The release of policies aims to provide timely and accurate policy guidance to businesses and the public, enabling them to fully understand and utilize the benefits and opportunities offered by these policies. Through government websites and other channels, businesses and the public can easily find and obtain policy information applicable to their own needs, thereby better participating in and benefiting from policy implementation.

[0003] However, relying on users to actively search for and obtain policy information through government websites and other channels creates significant limitations in policy communication, dissemination, implementation, and feedback. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method and apparatus for pushing policy data, which can improve the intelligence and personalization of policy data recommendations, solve the existing technical problems such as difficulties in policy interpretation, policy reach, policy matching, and policy analysis, and improve the comprehensibility, applicability, and implementation effectiveness of policies.

[0005] To achieve the above objectives, according to one aspect of the present invention, a method for pushing policy data is provided, comprising: In response to a policy push request, the system obtains the user identifier of the user to be pushed to, and obtains user profile attributes based on the user identifier. Based on the user profile attributes, obtain the policy topics bound to the user profile attributes; Based on the correlation between policy topics and policy data, obtain policy data to be pushed, which includes policy documents to be pushed and interpretation documents of the policy documents to be pushed. Policy data is pushed based on the policy document to be pushed and its interpretation document.

[0006] Optionally, obtaining user profile attributes based on the user identifier includes: obtaining user profile attributes from the user profile based on the user identifier, wherein the user profile attributes include individual profile attributes and group profile attributes; wherein the individual profile attributes are obtained by constructing an individual profile based on the user's basic information and the user's historical access data to policy documents; and the group profile attributes are obtained by constructing a group profile based on the user's region and the user group characteristics of the region.

[0007] Optionally, obtaining policy topics bound to the user profile attributes based on the user profile attributes includes: obtaining policy topics bound to the user profile attributes based on a knowledge graph of the relationship between user profile attributes and policy topics. The knowledge graph of the relationship between user profile attributes and policy topics is constructed in the following ways: mining the association patterns between user profile attributes and policy topics based on user profile attributes and policy topics; calculating the similarity between user profile attributes and the attributes of each policy topic based on the attributes of user profile attributes and policy topics, obtaining the similarity between user profile attributes and each policy topic; conducting cross-analysis of policy topics based on the attributes of different policy topics and applicable users, obtaining the relationship between different policy topics; obtaining the correlation degree between user profile attributes and each policy topic based on the association patterns between user profile attributes and policy topics, the similarity between user profile attributes and each policy topic, and the relationship between different policy topics; and constructing a relationship knowledge graph based on the correlation degree between user profile attributes and each policy topic.

[0008] Optionally, the association between the policy topics and policy data is established in the following way: Keyword extraction is performed on the preset policy topics and collected policy documents to obtain keywords corresponding to each policy topic and each policy document; based on the keywords corresponding to each policy topic and each policy document, keyword vectors corresponding to each policy topic and each policy document are generated; the similarity between each policy topic and each policy document is obtained by calculating the similarity between the keyword vectors corresponding to each policy topic and each policy document; for target policy topics and target policy documents whose similarity meets a set threshold, the interpretation file of the target policy document is obtained to generate target policy data; based on the target policy topics and the target policy data, the association between the policy topics and policy data is established.

[0009] Optionally, the interpretation file of the policy document is generated in the following way: based on the policy document interpretation template, a first keyword is extracted from the policy document, wherein the policy document interpretation template defines the first keyword for performing semantic analysis of the policy document; the interpretation file of the policy document is generated according to the first keyword and a pre-built policy interpretation model; wherein the policy interpretation model is constructed in the following way: obtaining policy documents within a specified historical period, and extracting the first keyword from the policy documents according to the policy document interpretation template; generating the interpretation file of the policy document according to the first keyword; using the policy document and the interpretation file of the policy document as training samples, and training the policy interpretation model based on the training samples.

[0010] Optionally, the policy data to be pushed can be obtained based on the association between policy topics and policy data, including: obtaining the policy data to be pushed from the retrieval cluster index table corresponding to the policy topic based on the association between the policy topic and policy data.

[0011] Optionally, policy data push based on the policy document to be pushed and its interpretation file includes: in response to the policy push request being initiated by the system, obtaining the push time and push frequency of the user to be pushed, wherein the push time is determined based on the active period of the user to be pushed, and the push frequency is determined based on the user's historical access data to the policy document; and according to the push time and the push frequency, pushing the policy document to be pushed and its interpretation file to the user to be pushed through a set active push method.

[0012] Optionally, policy data push based on the policy document to be pushed and its interpretation file includes: in response to the policy push request being initiated by the user to be pushed, directly pushing the policy document to be pushed and its interpretation file to the user to push the policy data.

[0013] Optionally, the method further includes: obtaining feedback information from the user to be pushed to the policy document, and providing the feedback information to the department that issues the policy document.

[0014] According to another aspect of the present invention, a policy data push device is provided, comprising: The user information acquisition module is used to respond to policy push requests, acquire the user identifier of the user to be pushed, and acquire user profile attributes based on the user identifier; The policy topic determination module is used to obtain policy topics bound to the user profile attributes based on the user profile attributes. The push data acquisition module is used to acquire policy data to be pushed based on the correlation between policy topics and policy data. The policy data to be pushed includes policy documents to be pushed and interpretation files of the policy documents to be pushed. The policy data push module is used to push policy data based on the policy document to be pushed and its interpretation file.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the policy data push method provided in the embodiments of the present invention.

[0016] According to another aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the policy data push method provided in the embodiments of the present invention.

[0017] According to another aspect of the present invention, a computer program product is provided, including a computer program that, when executed by a processor, implements the policy data push method provided in the embodiments of the present invention.

[0018] One embodiment of the above invention has the following advantages or beneficial effects: by responding to a policy push request, obtaining the user identifier of the user to be pushed, and obtaining the user profile attributes based on the user identifier; obtaining the policy topic bound to the user profile attributes based on the user profile attributes; obtaining the policy data to be pushed based on the association between the policy topic and the policy data, the policy data to be pushed includes the policy document to be pushed and the interpretation document of the policy document to be pushed; the technical solution of pushing policy data based on the policy document to be pushed and the interpretation document of the policy document to be pushed can improve the intelligence level and personalization of policy data recommendation, solve the existing technical problems such as difficulty in policy interpretation, difficulty in policy reach, difficulty in policy matching and difficulty in policy analysis, and improve the comprehensibility, applicability and implementation effect of policies.

[0019] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0020] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein: Figure 1 This is a schematic diagram illustrating the main steps of the policy data push method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the main modules of a policy data push device according to an embodiment of the present invention; Figure 3 This is an exemplary system architecture diagram in which embodiments of the present invention can be applied; Figure 4 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0021] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0022] It should be noted that the technical solutions disclosed in this invention, regarding the collection, updating, analysis, processing, use, transmission, and storage of user personal information, all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0023] This invention aims to address current technical challenges such as difficulties in policy interpretation, policy outreach, policy matching, and policy analysis. By introducing innovative technologies, this invention aims to provide an intelligent and personalized method for policy interpretation and communication, better helping users understand and apply policy content. Simultaneously, this invention aims to build an efficient policy outreach mechanism, ensuring that policy information is accurately and promptly delivered to target users. Furthermore, this invention strives to develop an intelligent matching system capable of precisely matching applicable policy information based on user needs and characteristics. Finally, this invention also aims to provide an efficient policy analysis tool, helping governments and relevant departments quickly obtain data feedback and analysis results on policy implementation, thereby supporting policy optimization and improvement. By solving these technical problems, this invention will improve the understandability, applicability, and effectiveness of policies, promoting seamless integration between policies and users.

[0024] Figure 1 This is a schematic diagram illustrating the main steps of a policy data push method according to an embodiment of the present invention. Figure 1 As shown, the policy data push method of this embodiment mainly includes the following steps S101 to S104.

[0025] Step S101: In response to the policy push request, obtain the user identifier of the user to be pushed, and obtain the user profile attributes based on the user identifier.

[0026] According to the technical solution of the present invention, the policy push request can be triggered by the user logging in and searching for policy documents on the website where the policy documents are published, or it can be triggered periodically according to the timed triggering rules set by the system.

[0027] After triggering a policy push request, the system will obtain the user identifier of the user to be pushed to, such as the user's login information registered in the system. Then, the system will obtain user profile attributes based on the user identifier.

[0028] According to one embodiment of the present invention, obtaining user profile attributes based on user identifiers may specifically include: obtaining user profile attributes from user profiles based on user identifiers, wherein user profile attributes include individual profile attributes and group profile attributes; wherein, individual profile attributes are obtained by constructing an individual profile based on the user's basic information and the user's historical access data to policy documents; and group profile attributes are obtained by constructing a group profile based on the user's region and the characteristics of the user group in the region.

[0029] The construction of individual user profiles can be achieved through the fusion of data from multiple channels and data sources to form comprehensive and accurate user characteristics. Data acquired for user profile construction includes, for example: information provided by users during registration and basic information about individuals or enterprises issued by the government; information proactively provided by users, such as interests, work experience, and educational background; data from user-completed questionnaires, messages, and comments that provide a better understanding of their personality and needs; historical access data such as clicks, favorites, follows, and subscriptions to policy documents; and basic information obtained from the Ministry of Industry and Information Technology and other government channels, including enterprise registration information, operating status, and industry classification, etc. After acquiring the above data, the data from different channels is merged to build a unified user profile. Furthermore, the data from different channels can be pre-cleaned to ensure the accuracy and consistency of the information. After data cleaning, data analysis and modeling techniques can be used to mine user behavior patterns and characteristics, and machine learning algorithms can be used to predict users' future needs and behaviors, allowing users to be divided into different groups, establishing a user classification system, and adding tags to users, such as high-risk users, active users, and potential customers, to provide more targeted services. After the above processing, a user profile can be constructed, and the user's profile attributes can be obtained based on the user profile.

[0030] The construction of user profiles can be achieved, for example, by collecting relevant data from the city where the user resides. By creating user profiles for each city, policy document recommendations can be made more accurate. This involves integrating personal information, interests, and behavioral data of registered users in that city, and then using user profile construction methods such as machine learning and data analysis to uncover user characteristics and behavioral patterns, thus forming user profiles. This allows for the determination of user group attributes. Introducing user group characteristics into the policy recommendation process in this embodiment of the invention can optimize the recommendation algorithm. Adjusting the weights and push strategies of the recommendation model based on the characteristics of the city's user group can improve the accuracy of policy recommendations, thereby better meeting user needs.

[0031] It should be understood that the individual user profile and the user group profile in this invention can be updated by combining real-time data, thereby ensuring that the user profile remains timely and improving the accuracy of policy recommendations.

[0032] Step S102: Obtain the policy topics bound to the user profile attributes. After obtaining the user profile attributes, the bound policy topics can be obtained based on the user profile attributes.

[0033] According to one embodiment of the present invention, this step may include: obtaining policy topics bound to user profile attributes based on a knowledge graph of the relationship between user profile attributes and policy topics. The knowledge graph of the relationship between user profile attributes and policy topics is constructed in the following ways: mining the relationship patterns between user profile attributes and policy topics based on user profile attributes and policy topics; calculating the similarity between user profile attributes and the attributes of each policy topic based on the attributes of user profile attributes and policy topics, thereby obtaining the similarity between user profile attributes and each policy topic; conducting cross-analysis of policy topics based on the attributes of different policy topics and applicable users, thereby obtaining the relationship between different policy topics; obtaining the degree of association between user profile attributes and each policy topic based on the relationship patterns between user profile attributes and policy topics, the similarity between user profile attributes and each policy topic, and the relationship between different policy topics; and constructing a relationship knowledge graph based on the degree of association between user profile attributes and each policy topic.

[0034] In embodiments of this invention, machine learning algorithms, such as association rule mining and collaborative filtering, can be used to discover hidden correlation patterns between user profile attributes and policy topics, based on user profile attributes and policy topics. This allows for the mining of correlation patterns between user profile attributes and policy topics, and the generation of a first correlation score based on these patterns. Based on the attributes of user profile attributes and policy topics, considering the weights of multiple dimensions, a suitable similarity algorithm, such as cosine similarity or Jaccard similarity, is selected to calculate the similarity between user profile attributes and the attributes of each policy topic. This yields a second correlation score based on this similarity. Furthermore, cross-analysis of policy topics is conducted based on their attributes and applicable users to obtain correlations between different policy topics and to discover cross-user behaviors across different topics, thus providing a more comprehensive understanding of user interests and needs. Each policy topic can be configured with its characteristics, target audience, or applicable users during its development.

[0035] When determining the correlation between user profile attributes and policy topics based on the correlation patterns between user profile attributes and various policy topics, the similarity between user profile attributes and different policy topics, and the correlation relationships between different policy topics, the correlation score between user profile attributes and each policy topic can be calculated by combining the correlation relationships between different policy topics, as well as the first correlation score and the second correlation score between user profile attributes and each policy topic. This determines the correlation score between user profile attributes and each policy topic. Finally, a knowledge graph of correlation relationships can be constructed based on the correlation scores between user profile attributes and each policy topic.

[0036] It should be understood that this knowledge graph of relationships can maintain its timeliness by introducing real-time data and establishing a regular update and maintenance mechanism to address the dynamic changes in user attributes and topic attributes.

[0037] Furthermore, according to embodiments of the present invention, the association results between user profile attributes and various policy topics can be visualized, providing platform operators with an intuitive display of the association between users and topics. Moreover, the knowledge graph of this association can be manually intervened and adjusted by operators to improve the accuracy of matching, thereby realizing intelligent matching and association between user profile attributes and policy topics, and providing users with more personalized and accurate policy information push services.

[0038] Step S103: Based on the correlation between policy topics and policy data, obtain the policy data to be pushed. The policy data to be pushed includes the policy documents to be pushed and the interpretation documents of the policy documents to be pushed.

[0039] According to one embodiment of the present invention, the association between policy topics and policy data is established in the following manner: Keyword extraction is performed on preset policy topics and collected policy documents to obtain keywords corresponding to each policy topic and each policy document; based on the keywords corresponding to each policy topic and each policy document, keyword vectors corresponding to each policy topic and each policy document are generated; the similarity between each policy topic and each policy document is obtained by calculating the similarity between the keyword vectors corresponding to each policy topic and each policy document; for target policy topics and target policy documents whose similarity meets a set threshold, an interpretation file of the target policy document is obtained to generate target policy data; based on the target policy topics and target policy data, the association between policy topics and policy data is established.

[0040] According to embodiments of the present invention, a pre-established association between policy topics and policy data can be established. The policy topics can be set according to business scenario needs. Policy documents can be obtained from policy document publishing websites using web crawling technology, specifically including attributes such as the full text of the policy, the issuing department, the publication time, and the publication region. After obtaining the policy documents, keywords can be extracted from the policy documents using Natural Language Processing (NLP) technology, such as the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm or embedding vector extraction algorithm. Similarly, the same algorithm can be used to extract keywords from policy topics to obtain a keyword set.

[0041] Next, the keyword sets of policy topics and policy documents are converted into text vectors, with each element representing the weight of a keyword. Then, the cosine similarity formula is used to calculate the similarity between two text vectors, thereby calculating the similarity between the keyword vectors corresponding to each policy topic and the keyword vectors corresponding to each policy document, and obtaining the similarity between each policy topic and each policy document. Then, based on a set similarity threshold, for target policy topics and target policy documents whose similarity meets the set threshold, interpretation files of the target policy documents are obtained to generate target policy data; based on the target policy topics and target policy data, the association between policy topics and policy data is established.

[0042] According to one embodiment of the present invention, the interpretation file of a policy document is generated in the following manner: based on a policy document interpretation template, a first keyword is extracted from the policy document, wherein the policy document interpretation template defines the first keyword for performing semantic analysis of the policy document; the interpretation file of the policy document is generated according to the first keyword and a pre-built policy interpretation model; wherein the policy interpretation model is constructed in the following manner: obtaining policy documents within a specified historical period and extracting the first keyword from the policy document according to the policy document interpretation template; generating the interpretation file of the policy document according to the first keyword; using the policy document and the interpretation file of the policy document as training samples, and training the policy interpretation model based on the training samples.

[0043] In embodiments of the present invention, full-text keywords (i.e., first keywords) of policy documents can be extracted using NLP attribute-free methods to obtain more comprehensive semantic information. The extracted keywords may include key fields such as policy type, issuing department, effective date, and applicable users. These key fields can be defined using a policy document interpretation template.

[0044] In an embodiment of the present invention, after obtaining policy data, the policy data can be saved to a database, and a relationship table between policy data and policy topics can be established to store the policy data and policy topics in association.

[0045] According to one embodiment of the present invention, obtaining policy data to be pushed based on the association between policy topics and policy data can specifically include: retrieving the policy data to be pushed from the index table of the retrieval cluster corresponding to the policy topic, based on the association between the policy topic and policy data. To facilitate the pushing and retrieval of policy data, in this embodiment of the invention, policy data can also be stored in a retrieval cluster, such as a retrieval cluster implemented based on Elasticsearch. In Elasticsearch, an independent index table (Index) is created for each policy topic to ensure the grouping and isolation of policy data. The corresponding policy data is stored in the index table. Elasticsearch has a powerful word segmenter that supports word segmentation in multiple languages, including Chinese and English; and it can accelerate the search process and improve query performance through inverted indexes; complex queries and aggregation operations can be performed using Elasticsearch's query language. When storing policy data in Elasticsearch according to policy topics, sharding and replication can be reasonably configured to adapt to the increase in data volume. Simultaneously, a monitoring mechanism is set up to regularly check the health status of the Elasticsearch cluster and optimize and expand performance to address the query pressure that may result from increased data volume.

[0046] By storing policy data in Elasticsearch, you can take full advantage of its search and analytics engine, improve query efficiency, and enjoy its flexibility and scalability, enabling the system to better handle the management and querying needs of large amounts of policy data.

[0047] In embodiments of the present invention, policy topics and policy documents can be periodically updated and maintained by setting scheduled tasks to keep policy information up-to-date. Simultaneously, monitoring changes in keywords of policy topics and policy documents and updating matching rules in a timely manner helps to manage large amounts of policy information more effectively and improves data organization and usability.

[0048] Step S104: Push policy data based on the policy document to be pushed and its interpretation document.

[0049] According to one embodiment of the present invention, policy data push based on the policy document to be pushed and its interpretation document can specifically include: in response to a policy push request being initiated by the system, obtaining the push time and push frequency for the user to be pushed to, wherein the push time is determined based on the user's active time period and the push frequency is determined based on the user's historical access data to the policy document; and according to the push time and push frequency, pushing the policy document to be pushed and its interpretation document to the user to be pushed to through a set proactive push method. The set proactive push method includes, for example, message push, email notification, and mini-program push. In this embodiment of the present invention, a differentiated outreach strategy is designed based on user behavior data and personalized recommendation results, and message push, email notification, and other methods can be used to promptly push policy information that users may be interested in. Policy information is sent to enterprises, talents, and the public through diverse channels such as SMS and mini-programs to ensure that information can be quickly and intuitively conveyed to the target user group.

[0050] When pushing differentiated policy data to users, the timing of policy information pushes is optimized based on users' active periods, avoiding times when users are resting or unable to view information. User behavior is analyzed to optimize push frequency, ensuring the quality of information and user experience. Personalized control options for push settings are also provided, allowing users to customize push frequency and content to meet diverse needs and increase user engagement and interaction with the platform. Furthermore, a user feedback portal is provided, allowing users to provide feedback on their satisfaction and interest in the push information. Push information is adjusted based on user feedback, continuously optimizing the reach strategy and content.

[0051] According to another embodiment of the present invention, policy data push based on the policy document to be pushed and its interpretation file can specifically include: in response to the policy push request being initiated by the user to be pushed, directly pushing the policy document to be pushed and its interpretation file to the user to push the policy data. Specifically, when a user actively queries a policy document in the Elasticsearch search cluster, the policy push request can be triggered. At this time, after the policy document to be pushed and its interpretation file are determined, the policy document to be pushed and its interpretation file can be directly sent to the user to complete the policy data push.

[0052] In this embodiment, after the policy data is pushed, the policy data recommendation results can be presented to the user in a visual way through an intuitive display interface, so that the user can easily browse and understand the relevant policies and improve the user's understanding and acceptance of policy documents.

[0053] According to another embodiment of the present invention, the method for pushing policy data further includes: obtaining feedback information from users to be pushed policy documents, and providing the feedback information to the department that issues the policy documents.

[0054] According to an embodiment of the present invention, a data receipt mechanism is triggered the moment a user clicks on policy data, transmitting information such as the user's click behavior back to the policy data push system of the present invention. The system platform records relevant data such as user feedback and implementation progress, providing support for subsequent analysis. Based on the collected data, the system platform generates reports, including information on policy implementation status, investment attraction results, and talent introduction, and feeds these reports back to the government, helping the government to comprehensively understand the policy implementation and providing data support for policy adjustment and improvement. Simultaneously, a monitoring mechanism can be established to track the policy implementation in real time. Furthermore, data analysis tools can be used to deeply analyze the policy's impact and effects, providing decision-making support for the government.

[0055] Meanwhile, the system platform of this invention can also provide online customer service, consultation services, etc., to help users understand policy content and solve problems, so as to provide policy publicity and training to users through multiple channels.

[0056] Through the aforementioned functions and mechanisms, the system platform can better help enterprises, talents, and the public implement policies, improve the effectiveness of policy implementation, and provide the government with timely and accurate information on policy implementation, thereby enabling the government to formulate policies more effectively.

[0057] Figure 2 This is a schematic diagram of the main modules of a policy data push device according to an embodiment of the present invention. Figure 2As shown, the policy data push device 200 of this embodiment mainly includes a user information acquisition module 201, a policy topic determination module 202, a push data acquisition module 203, and a policy data push module 204.

[0058] The user information acquisition module 201 is used to respond to policy push requests, acquire the user identifier of the user to be pushed, and acquire user profile attributes based on the user identifier. The policy topic determination module 202 is used to obtain policy topics that are bound to user profile attributes based on user profile attributes. The push data acquisition module 203 is used to acquire the policy data to be pushed based on the relationship between policy topics and policy data. The policy data to be pushed includes the policy documents to be pushed and the interpretation documents of the policy documents to be pushed. The policy data push module 204 is used to push policy data based on the policy document to be pushed and its interpretation document.

[0059] According to an embodiment of the present invention, the user information acquisition module 201 can also be used to: acquire user profile attributes from the user profile based on the user identifier, wherein the user profile attributes include individual profile attributes and group profile attributes; wherein, the individual profile attributes are obtained by constructing an individual profile based on the user's basic information and the user's historical access data to policy documents; and the group profile attributes are obtained by constructing a group profile based on the user's region and the user group characteristics of the region.

[0060] According to another embodiment of the present invention, the policy topic determination module 202 can also be used to: obtain policy topics bound to user profile attributes based on a knowledge graph of the relationship between user profile attributes and policy topics. The knowledge graph of the relationship between user profile attributes and policy topics is constructed in the following ways: mining the relationship patterns between user profile attributes and policy topics based on user profile attributes and policy topics; calculating the similarity between user profile attributes and the attributes of each policy topic based on the attributes of user profile attributes and policy topics, and obtaining the similarity between user profile attributes and each policy topic; conducting cross-analysis of policy topics based on the attributes of different policy topics and applicable users, and obtaining the relationship between different policy topics; obtaining the degree of association between user profile attributes and each policy topic based on the relationship patterns between user profile attributes and policy topics, the similarity between user profile attributes and each policy topic, and the relationship between different policy topics; and constructing a relationship knowledge graph based on the degree of association between user profile attributes and each policy topic.

[0061] According to another embodiment of the present invention, the policy data push device 200 may further include a relationship establishment module (not shown in the figure) for establishing a relationship between policy topics and policy data. The relationship between policy topics and policy data is established in the following manner: extracting keywords from preset policy topics and collected policy documents to obtain keywords corresponding to each policy topic and keywords corresponding to each policy document; generating keyword vectors corresponding to each policy topic and keyword vectors corresponding to each policy document based on the keywords corresponding to each policy topic and keywords corresponding to each policy document; obtaining the similarity between each policy topic and each policy document by calculating the similarity between the keyword vectors corresponding to each policy topic and the keyword vectors corresponding to each policy document; obtaining the interpretation file of the target policy document to generate target policy data for target policy topics and target policy documents whose similarity meets a set threshold; and establishing a relationship between policy topics and policy data based on the target policy topics and target policy data.

[0062] According to another embodiment of the present invention, the policy data push device 200 may further include an interpretation document generation module (not shown in the figure) for generating interpretation documents of policy documents, wherein the interpretation documents of policy documents are generated in the following manner: extracting a first keyword from the policy document based on a policy document interpretation template, wherein the policy document interpretation template defines a first keyword for performing semantic analysis of the policy document; generating the interpretation documents of policy documents based on the first keyword and a pre-built policy interpretation model; wherein the policy interpretation model is constructed in the following manner: obtaining policy documents within a specified historical period and extracting a first keyword from the policy document based on the policy document interpretation template; generating the interpretation documents of policy documents based on the first keyword; using the policy document and the interpretation documents of policy documents as training samples, and training the policy interpretation model based on the training samples.

[0063] According to another embodiment of the present invention, the push data acquisition module 203 can also be used to: obtain the policy data to be pushed from the retrieval cluster index table corresponding to the policy topic according to the association between the policy topic and the policy data.

[0064] According to another embodiment of the present invention, the policy data push module 204 can also be used to: in response to a policy push request being initiated by the system, obtain the push time and push frequency of the user to be pushed to, wherein the push time is determined based on the active period of the user to be pushed to, and the push frequency is determined based on the user's historical access data to policy documents; and according to the push time and push frequency, push the policy document to be pushed and its interpretation file to the user to be pushed to through a set proactive push method. The set proactive push method includes, for example, message push, email notification, and mini-program push.

[0065] According to another embodiment of the present invention, the policy data push module 204 can also be used to: in response to the policy push request being initiated by the user to be pushed, directly push the policy document to be pushed and the interpretation file of the policy document to be pushed to the user to push the policy data.

[0066] According to another embodiment of the present invention, the policy data push device 200 may further include a feedback information collection module (not shown in the figure), which is used to obtain feedback information from users to be pushed the policy documents and to provide the feedback information to the department that issues the policy documents.

[0067] According to the technical solution of this invention, in response to a policy push request, the user identifier of the user to be pushed is obtained, and user profile attributes are obtained based on the user identifier; policy topics bound to the user profile attributes are obtained based on the user profile attributes; and policy data to be pushed is obtained based on the association between the policy topics and policy data, including policy documents to be pushed and interpretation documents of the policy documents to be pushed. This technical solution of pushing policy data based on policy documents to be pushed and interpretation documents of the policy documents to be pushed can improve the intelligence and personalization of policy data recommendations, solve existing technical problems such as difficulties in policy interpretation, policy reach, policy matching, and policy analysis, and improve the comprehensibility, applicability, and implementation effectiveness of policies.

[0068] Figure 3 An exemplary system architecture 300 is shown, in which the policy data push method or policy data push device of the present invention can be applied.

[0069] like Figure 3 As shown, system architecture 300 may include terminal devices 301, 302, and 303, a network 304, and a server 305. Network 304 serves as the medium for providing communication links between terminal devices 301, 302, and 303 and server 305. Network 304 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0070] Users can use terminal devices 301, 302, and 303 to interact with server 305 via network 304 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 301, 302, and 303, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0071] Terminal devices 301, 302, and 303 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0072] Server 305 can be a server providing various services, such as a backend management server supporting shopping websites browsed by users using terminal devices 301, 302, and 303 (this is just an example). The backend management server can respond to received policy data push requests by obtaining the user identifier of the user to be pushed to, and obtaining user profile attributes based on the user identifier; obtaining policy topics bound to the user profile attributes based on the user profile attributes; obtaining the policy data to be pushed based on the association between the policy topics and policy data, including the policy document to be pushed and its interpretation file; performing policy data push processing based on the policy document to be pushed and its interpretation file, and feeding back the processing results (e.g., target policy data to be pushed – this is just an example) to the terminal device.

[0073] It should be noted that the policy data push method provided in this embodiment of the invention is generally executed by server 305, and correspondingly, the policy data push device is generally set in server 305.

[0074] It should be understood that Figure 3 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0075] The following is for reference. Figure 4 It shows a schematic diagram of the structure of a computer system 400 suitable for implementing terminal devices or servers of the present invention. Figure 4 The terminal device or server shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0076] like Figure 4 As shown, the computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 402 or programs loaded from storage section 408 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the system 400. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0077] The following components are connected to I / O interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. Drive 410 is also connected to I / O interface 405 as needed. Removable media 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 410 as needed so that computer programs read from them can be installed into storage section 408 as needed.

[0078] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit (CPU) 401, it performs the functions defined above in the system of this invention.

[0079] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0080] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0081] The units or modules described in the embodiments of the present invention can be implemented in software or hardware. The described units or modules can also be housed in a processor; for example, a processor can be described as including a user information acquisition module, a policy topic determination module, a push data acquisition module, and a policy data push module. The names of these units or modules do not necessarily limit the specific unit or module itself. For example, the user information acquisition module can also be described as "a module for responding to a policy push request, acquiring the user identifier of the user to be pushed to, and acquiring user profile attributes based on the user identifier."

[0082] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include: in response to a policy push request, obtaining a user identifier of a user to be pushed to, and obtaining user profile attributes based on the user identifier; obtaining policy topics bound to the user profile attributes based on the user profile attributes; obtaining policy data to be pushed based on the association between the policy topics and policy data, the policy data to be pushed including a policy document to be pushed and an interpretation file of the policy document to be pushed; and pushing the policy data based on the policy document to be pushed and the interpretation file of the policy document to be pushed.

[0083] According to the technical solution of this invention, in response to a policy push request, the user identifier of the user to be pushed is obtained, and user profile attributes are obtained based on the user identifier; policy topics bound to the user profile attributes are obtained based on the user profile attributes; and policy data to be pushed is obtained based on the association between the policy topics and policy data, including policy documents to be pushed and interpretation documents of the policy documents to be pushed. This technical solution of pushing policy data based on policy documents to be pushed and interpretation documents of the policy documents to be pushed can improve the intelligence and personalization of policy data recommendations, solve existing technical problems such as difficulties in policy interpretation, policy reach, policy matching, and policy analysis, and improve the comprehensibility, applicability, and implementation effectiveness of policies.

[0084] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for pushing policy data, characterized in that, include: In response to a policy push request, the system obtains the user identifier of the user to be pushed to, and obtains user profile attributes based on the user identifier. Based on the user profile attributes, obtain the policy topics bound to the user profile attributes; Based on the correlation between policy topics and policy data, obtain policy data to be pushed, which includes policy documents to be pushed and interpretation documents of the policy documents to be pushed. Policy data is pushed based on the policy document to be pushed and its interpretation document.

2. The method according to claim 1, characterized in that, Obtaining user profile attributes based on the user identifier includes: User profile attributes are obtained from the user profile based on the user identifier, and the user profile attributes include individual profile attributes and group profile attributes. The individual profile attributes are derived from the user's basic information and the user's historical access data to policy documents. The group profile attributes are obtained by constructing a group profile based on the basic information of the user's region and the characteristics of the user group in that region.

3. The method according to claim 1 or 2, characterized in that, Based on the user profile attributes, policy topics bound to the user profile attributes are obtained, including: Based on the knowledge graph of the relationship between user profile attributes and policy topics, policy topics bound to the user profile attributes are obtained. The knowledge graph of the relationship between user profile attributes and policy topics is constructed in the following way: Based on user profile attributes and policy topics, we will explore the correlation patterns between user profile attributes and policy topics; Based on the attributes of user profiles and the attributes of policy topics, the similarity between user profile attributes and the attributes of each policy topic is calculated to obtain the similarity between user profile attributes and each policy topic. Based on the attributes and applicable users of different policy topics, cross-relationship analysis of policy topics is conducted to obtain the correlation between different policy topics; Based on the correlation patterns between user profile attributes and policy topics, the similarity between user profile attributes and various policy topics, and the correlation between different policy topics, the correlation degree between user profile attributes and various policy topics is obtained; A knowledge graph of relationships is constructed based on the correlation between the user profile attributes and various policy topics.

4. The method according to claim 1, characterized in that, The correlation between the policy topics and policy data was established in the following ways: Keyword extraction was performed on the pre-defined policy topics and the collected policy documents to obtain the keywords corresponding to each policy topic and each policy document. Based on the keywords corresponding to each policy topic and the keywords corresponding to each policy document, a keyword vector corresponding to each policy topic and a keyword vector corresponding to each policy document are generated; The similarity between each policy topic and each policy document is obtained by calculating the similarity between the keyword vectors corresponding to each policy topic and the keyword vectors corresponding to each policy document. For target policy topics and target policy documents whose similarity meets a set threshold, obtain the interpretation file of the target policy document to generate target policy data; Based on the target policy topics and the target policy data, establish the correlation between the policy topics and the policy data.

5. The method according to claim 1 or 4, characterized in that, The interpretation documents for policy documents are generated in the following ways: Based on the policy document interpretation template, a first keyword is extracted from the policy document. The policy document interpretation template defines a first keyword for performing semantic analysis of policy documents. An interpretation document of the policy document is generated based on the first keyword and a pre-built policy interpretation model; wherein, the policy interpretation model is constructed in the following manner: Retrieve policy documents within a specified historical period and extract the first keyword from the policy documents according to the policy document interpretation template; Generate an interpretation document of the policy document based on the first keyword; The policy document and its interpretation document are used as training samples to train the policy interpretation model.

6. The method according to claim 1, characterized in that, Based on the correlation between policy topics and policy data, obtain the policy data to be pushed, including: Based on the correlation between policy topics and policy data, the policy data to be pushed is obtained from the retrieval cluster index table corresponding to the policy topic.

7. The method according to claim 1, characterized in that, Policy data is pushed based on the policy document to be pushed and its interpretation document, including: In response to the policy push request being initiated by the system, the push time and push frequency of the user to be pushed are obtained, wherein the push time is determined based on the active period of the user to be pushed, and the push frequency is determined based on the historical access data of the user to the policy document; Based on the push time and the push frequency, the policy document to be pushed and its interpretation file are pushed to the user to be pushed through a set active push method.

8. The method according to claim 1, characterized in that, Policy data is pushed based on the policy document to be pushed and its interpretation document, including: In response to the policy push request being initiated by the user to be pushed to, the policy document to be pushed and its interpretation file are directly pushed to the user to push the policy data.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: Obtain feedback information from the users to be pushed to the policy document, and provide the feedback information to the department that issues the policy document.

10. A policy data push device, characterized in that, include: The user information acquisition module is used to respond to policy push requests, acquire the user identifier of the user to be pushed, and acquire user profile attributes based on the user identifier; The policy topic determination module is used to obtain policy topics bound to the user profile attributes based on the user profile attributes. The push data acquisition module is used to acquire policy data to be pushed based on the correlation between policy topics and policy data. The policy data to be pushed includes policy documents to be pushed and interpretation files of the policy documents to be pushed. The policy data push module is used to push policy data based on the policy document to be pushed and its interpretation file.

11. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-9.

12. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-9.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-9.

Images