Personalized privacy policy generation method, system equipment and medium

By generating personalized privacy policy drafts from user privacy preference data and combining natural language processing and regulatory databases for dynamic compliance checks, this technology solves the problems of cumbersome privacy policy texts and insufficient enforcement supervision in existing technologies, achieving personalized and secure privacy protection.

CN118966181AActive Publication Date: 2024-11-15GUANGZHOU SANQI DREAM NETWORK TECH CO LTD

Patent Information

Application Number
CN202410986938.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-15
Estimated Expiration
2044-07-23

AI Technical Summary

Technical Problem

Existing privacy policies are often verbose and difficult for users to understand, and their enforcement is often inadequate, leading to data breaches or misuse. Furthermore, the privacy preferences of different users and the requirements of different industries are complex, making it difficult for existing technologies to achieve personalized privacy protection.

Method used

By acquiring user privacy preference data, we generate personalized privacy policy drafts, optimize policy texts using natural language processing and deep learning algorithms, conduct dynamic compliance checks in conjunction with regulatory databases, establish a graphical interactive interface to display data permission options and provide feedback, monitor data access behavior in real time, and conduct risk assessments and updates.

Benefits of technology

It improves the efficiency of privacy policy formulation and enforcement, enables personalized and dynamic updates of privacy policies, and enhances the security of privacy protection and user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118966181A_ABST
    Figure CN118966181A_ABST
Patent Text Reader

Abstract

The invention is suitable for the technical field of information security, and provides a personalized privacy policy generation method, which comprises the following steps: matching user privacy preference data with a preset privacy policy template to generate a privacy policy draft; scoring each term in the privacy policy draft to obtain a privacy policy text; based on a laws and regulations database, a natural language processing method is adopted, the laws and regulations database is converted into a rule engine, dynamic compliance check is conducted on the privacy policy text according to the rule engine, and a compliance evaluation report is generated; the privacy setting interaction interface is established based on the user privacy preference data, the privacy policy text and the compliance evaluation report, the personalized privacy policy text can be dynamically generated according to the privacy policy laws and regulations and the user privacy preferences, the privacy policy making and executing efficiency is greatly improved, and meanwhile good user experience is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of information security technology, and in particular, relates to a personalized privacy policy generation method, system equipment and medium. Background Art

[0002] In the modern digital age, privacy protection has become a common focus for users and enterprises. In the existing technology, regulatory frameworks and standards such as GDPR and CCPA have been established to provide basic guidance for privacy protection. The widespread application of these regulations covers many aspects, including but not limited to in-depth analysis of privacy policy texts, strict inspection of corporate compliance, and permission control for user data access and processing, thereby comprehensively strengthening the protection of personal privacy.

[0003] However, users' personalized expressions of privacy preferences are multi-dimensional and complex. For example, a financial services user may have extremely high requirements for the confidentiality of transaction data, while a social media user may be more concerned about preventing personal information from being abused. In addition, different industries such as finance and e-commerce have different legal requirements for the processing of user data, and there are significant differences in the resource investment in data processing and privacy protection between large enterprises and small and medium-sized enterprises. In terms of effectiveness, privacy policies are often complicated and difficult for users to fully understand their meaning, resulting in a discount in the actual effect of privacy protection measures. In terms of user experience, users often need to read long privacy policies, resulting in poor user experience. In terms of security, insufficient supervision of the implementation of privacy policies may lead to data leakage or abuse. Summary of the invention

[0004] The embodiments of the present application provide a personalized privacy policy generation method, system device and medium, which can solve at least one of the above-mentioned prior art problems.

[0005] In a first aspect, an embodiment of the present application provides a method for generating a personalized privacy policy, including:

[0006] Match user privacy preference data with the preset privacy policy template to generate a privacy policy draft;

[0007] Score each clause in the draft privacy policy to obtain the privacy policy text;

[0008] Based on the regulatory database, a natural language processing method is used to convert the regulatory database into a rule engine, and a dynamic compliance check is performed on the privacy policy text according to the rule engine to generate a compliance assessment report;

[0009] Based on user privacy preference data, privacy policy text and compliance assessment report, a privacy setting interactive interface is established, wherein the privacy setting interactive interface is used to graphically display options for various data permissions related to privacy settings and provide feedback information related to privacy settings.

[0010] Furthermore, matching the user privacy preference data with a preset privacy policy template to generate a privacy policy draft includes:

[0011] Obtaining the user's privacy preference data, and obtaining a privacy preference profile corresponding to the user by analyzing the privacy preference data;

[0012] Establishing a privacy policy generation model, wherein the privacy policy generation model is used to generate a preset privacy policy template according to the privacy preference profile;

[0013] Using natural language processing technology to perform semantic analysis and keyword extraction on the privacy preference data to obtain the user's privacy demand keywords;

[0014] The privacy requirement keywords are matched with the preset privacy policy template to generate a privacy policy draft.

[0015] Furthermore, the establishment of a privacy policy generation model includes:

[0016] Obtain different users' sensitivity scores for various data permissions and obtain privacy data sources;

[0017] Preprocessing the privacy data source to obtain privacy information of different users and establish privacy preference profiles of different user groups;

[0018] Obtaining an existing privacy policy text, preprocessing the existing privacy policy text, and obtaining a training data set;

[0019] Based on the Transformer architecture, a pre-trained model is constructed, and fine-tuning technology is used to input the training data set into the pre-trained model for training to generate a privacy policy generation model;

[0020] The privacy preference profiles of different user groups are input into the privacy policy generation model for distributed training to generate multiple privacy policy templates.

[0021] Furthermore, the step of scoring each clause in the draft privacy policy to obtain the privacy policy text includes:

[0022] Use deep learning algorithms to optimize the privacy policy draft and obtain the first draft of the privacy policy;

[0023] Using a graph traversal algorithm to search a privacy regulation database, marking regulatory clauses in the privacy regulation database that are related to the first draft of the privacy policy;

[0024] An expert analysis method is used to score each clause of the draft privacy policy based on the marked regulatory clauses to obtain the privacy policy text.

[0025] Furthermore, based on the regulatory database, a natural language processing method is used to convert the regulatory database into a rule engine, and a dynamic compliance check is performed on the privacy policy text according to the rule engine to generate a compliance assessment report, including:

[0026] Dynamically obtain regulatory texts in a regulatory database, pre-process the regulatory texts through natural language technology, and obtain a key database, wherein the key database is a privacy regulatory database;

[0027] Using a keyword extraction algorithm to identify privacy regulatory terms in the key database;

[0028] Using semantic analysis tools to analyze the specific context and relevance of the privacy regulatory terms in the key database to obtain semantic understanding rules of the privacy regulatory terms;

[0029] Based on the semantic understanding rules, construct logical reasoning rules, and based on the logical reasoning rules, design a rule engine;

[0030] Based on the rule engine, the privacy policy text is checked for compliance and a compliance assessment report is generated.

[0031] Furthermore, based on the user privacy preference data, the privacy policy text and the compliance assessment report, a privacy setting interactive interface is established, and the privacy setting interactive interface is used to graphically display the options of various data permissions related to the privacy setting and provide feedback information related to the privacy setting, including:

[0032] Use visual elements to intuitively display the options of various data permissions related to privacy settings;

[0033] Obtain the user's privacy setting information, and provide timely feedback information based on the privacy setting information, wherein the feedback information is used to explain the impact and risks brought about by the current privacy setting.

[0034] Furthermore, the above-mentioned method for generating a personalized privacy policy also includes:

[0035] Use unsupervised learning algorithms to establish normal data access patterns;

[0036] Monitor users' data access behaviors in real time, detect abnormal behaviors that deviate from the normal data access patterns, intercept unauthorized abnormal behaviors, perform multi-dimensional risk scoring on the abnormal behaviors, and obtain risk reports;

[0037] Prompting the user whether to update privacy settings through the risk report;

[0038] Obtain the user's updated settings for privacy settings, and regenerate the privacy policy text according to the updated settings.

[0039] In a second aspect, the present application embodiment provides a personalized privacy policy generation system, including:

[0040] Privacy policy draft generation model: used to match user privacy preference data with the preset privacy policy template to generate a privacy policy draft;

[0041] Privacy policy text generation module: used to score each clause in the privacy policy draft to obtain the privacy policy text;

[0042] Dynamic compliance check module: used to convert the regulatory database into a rule engine based on the regulatory database by using natural language processing methods, and to perform dynamic compliance check on the privacy policy text according to the rule engine to generate a compliance assessment report;

[0043] Interactive interface setting module: used to establish a privacy setting interactive interface based on user privacy preference data, privacy policy text and compliance assessment report. The privacy setting interactive interface is used to graphically display options for various data permissions related to privacy settings and provide feedback information related to privacy settings.

[0044] In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned personalized privacy policy generation method when executing the computer program.

[0045] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, including a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-mentioned personalized privacy policy generation method is implemented.

[0046] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0047] In this application, by associating the user's privacy preferences with privacy regulations and automatically generating a privacy policy text, the efficiency of privacy policy formulation and implementation is greatly improved. At the same time, through dynamic compliance checks on the privacy policy text, the privacy policy text can respond to updates to relevant privacy policies in real time, and dynamically update according to changes in the user's privacy preferences. Intelligent risk assessment and compliance checks can promptly discover and handle privacy risks, enhancing the security of privacy protection. In addition, by setting up a privacy setting interactive interface to improve user experience, it is easier for users to understand and control their privacy preferences. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0049] Figure 1 It is a flowchart of a method for generating a personalized privacy policy provided by an embodiment of the present invention;

[0050] Figure 2 It is a structural diagram of a personalized privacy policy generation system provided by an embodiment of the present invention;

[0051] Figure 3 It is a structural diagram of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0053] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0054] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0055] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0056] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0057] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0058] See also Figure 1 As shown, the present invention is a method for generating a personalized privacy policy, comprising the following steps:

[0059] S100, matching the user privacy preference data with a preset privacy policy template to generate a privacy policy draft;

[0060] In this embodiment, user privacy preference data is obtained and then matched with a preset privacy policy template to generate a privacy policy draft. The preset privacy policy template contains basic terms that comply with general laws and regulations, covering aspects such as data collection, use, storage and sharing. In addition, automatically matching with the preset privacy policy template to generate a privacy policy draft reduces the risk of human errors and omissions, ensuring that enterprises can quickly respond to changing legal and regulatory requirements and reduce legal risks.

[0061] In some embodiments, the above step S100 includes:

[0062] Obtaining the user's privacy preference data, and obtaining a privacy preference profile corresponding to the user by analyzing the privacy preference data;

[0063] Establishing a privacy policy generation model, wherein the privacy policy generation model is used to generate a preset privacy policy template according to the privacy preference profile;

[0064] Using natural language processing technology to perform semantic analysis and keyword extraction on the privacy preference data to obtain the user's privacy demand keywords;

[0065] The privacy requirement keywords are matched with the preset privacy policy template to generate a privacy policy draft.

[0066] In this embodiment, a privacy policy template library is generated through a privacy policy generation model, and the privacy policy template library includes multiple privacy policy templates.

[0067] In this embodiment, the user's privacy preference data is obtained based on the interactive data generated between the user and the personalized privacy policy generation system, and the user's sensitivity and focus on privacy protection are analyzed through the privacy preference data, and then the user is assigned to the corresponding privacy preference portrait. Specifically, through the privacy setting interaction module, the user selects the options of various data permissions related to the privacy setting, and the data collection and preprocessing technology is used to obtain the preference settings, selection behaviors and feedback information of the various data permissions selected by the user, and the user's privacy preference raw data is generated. By summarizing and sorting the privacy preference raw data, structured user privacy preference data is obtained. By extracting features and quantitatively analyzing the user's privacy preference data, a privacy focus point identification algorithm is used to obtain the user's attention to various privacy attributes, and by sorting the attention level, the user's key focus areas and sensitive preferences in privacy protection are determined, and then the privacy preference features are generated. The portrait matching algorithm is used to match the user's privacy preference features with the privacy preference portrait, and the matching degree of the user's privacy preference features and different privacy preference portraits is obtained through feature similarity calculation, and the corresponding privacy preference portrait of the user is determined according to the matching degree. Through the privacy preference portrait, the user can obtain personalized privacy preference setting suggestions.

[0068] For example, on a gaming platform, if a player's privacy preference is to share his or her gaming achievements, location data, and gaming activity records, then they can be classified as a user group with a specific privacy sharing tendency in the user privacy preference portrait. Based on the player's privacy preference portrait, a corresponding privacy policy template is generated. The privacy policy template clearly states that the player's relevant gaming activity data and location information will be obtained. At the same time, after the privacy policy text is generated based on the privacy policy template, personalized privacy preference setting suggestions will be generated based on the corresponding privacy preference portrait, prompting the user to change the corresponding privacy preference settings.

[0069] In this embodiment, according to the privacy preference data provided by the user, natural language processing technology is used to perform semantic analysis on the feedback information in the privacy preference data and the preference settings of various data permissions selected by the user, and the keywords, phrases and sentence components in the feedback information are obtained through word segmentation, part-of-speech tagging, named entity recognition and other processing to obtain the privacy demand keywords of the user's privacy preference. The TF-IDF algorithm is used to calculate the weight of the privacy preference keywords. Specifically, by analyzing the frequency of occurrence of the privacy demand keywords in the privacy preference data and the option selection in each data permission, the importance of each privacy demand keyword is obtained, and the privacy demand keywords are sorted by weight.

[0070] Specifically, the user's selection of various data permissions, including the authorization of privacy data such as location information, address book, and photos, is obtained to obtain the original data of the user's privacy preference. By preprocessing the original data of privacy preferences, the data is converted into a format suitable for analysis, such as converting text data into digital codes, and determining the location and frequency of the privacy demand keywords in the data. Natural language processing technology is used to perform word segmentation and part-of-speech tagging on the preprocessed privacy preference data to obtain keywords related to privacy needs, such as "location", "address book", "photos", etc., and the frequency of occurrence of each keyword is counted. According to the user's option selection in each data permission, different weights are assigned to each option, such as "allow" is assigned a higher weight and "deny" is assigned a lower weight, and the privacy importance score of each data permission is obtained. The weight of each privacy demand keyword is obtained by calculating the product of the frequency of occurrence of the privacy demand keyword and the corresponding data permission importance score. The higher the weight, the more important the privacy demand corresponding to the keyword. According to the weight sorting of the privacy demand keywords, a keyword list of the user's privacy demand is obtained. Keywords with high weights represent privacy demands that users attach more importance to, such as location privacy and social privacy. When generating the privacy policy text, visualization technology is used to present the clauses related to the keywords of user privacy needs in an intuitive manner. For example, the font size of keywords with higher weights is larger, and the corresponding clauses are marked with bright colors to facilitate user reference and improve user experience.

[0071] In this embodiment, the privacy preference portrait corresponding to the user is input into the privacy policy model, a privacy policy template is dynamically generated, a keyword list of the user's privacy needs and the content of the privacy policy template are obtained, and the privacy policy template is analyzed using natural language processing technology to obtain paragraphs and sentences related to the keyword list in the privacy policy template. The preliminary privacy policy content is obtained by matching the privacy demand keywords with the relevant paragraphs and sentences in the privacy policy template. According to the preliminary privacy policy content obtained by matching, the semantic analysis technology is used to optimize and supplement the content to ensure the integrity and accuracy of the privacy policy content. By formatting the optimized privacy policy content, a privacy policy draft that meets the standard format requirements is obtained.

[0072] In some embodiments, the step of establishing a privacy policy generation model includes:

[0073] Obtain different users' sensitivity scores for various data permissions and obtain privacy data sources;

[0074] Preprocessing the privacy data source to obtain privacy information of different users and establish privacy preference profiles of different user groups;

[0075] Obtaining an existing privacy policy text, preprocessing the existing privacy policy text, and obtaining a training data set;

[0076] Based on the Transformer architecture, a pre-trained model is constructed, and fine-tuning technology is used to input the training data set into the pre-trained model for training to generate a privacy policy generation model;

[0077] The privacy preference profiles of different user groups are input into the privacy policy generation model for distributed training to generate multiple privacy policy templates.

[0078] In this embodiment, a privacy preference questionnaire is designed to cover various types of data permissions such as location information, contacts, health and biometrics, ensuring that the expression is concise and clear; the questionnaire is published through an online platform, and digital recognition technology is used to ensure the uniqueness of each user's questionnaire data to avoid duplicate reporting; by obtaining privacy preference questionnaires filled out by different users, the sensitivity scores of different users to various data permissions are obtained, and then the privacy data source is obtained.

[0079] In this embodiment, a collaborative filtering algorithm is used to cluster similar user groups based on a privacy data source to obtain privacy information, and then a privacy preference portrait is established. The portrait contains the user's specific privacy needs and preference settings, which helps the system to better personalize the service. Specifically, according to the privacy data source, data preprocessing technology is used to clean, deduplicate, and normalize the original data to obtain a high-quality privacy data set. By performing feature engineering on the privacy data set, key features of user privacy preferences, such as privacy settings, privacy concerns, etc., are extracted to obtain feature vectors for collaborative filtering. A user-based collaborative filtering algorithm is used to calculate the similarity between users. According to the user's specific privacy needs and preference settings, a user similarity matrix is ​​obtained using a measurement method such as cosine similarity or Pearson correlation coefficient. According to the user similarity matrix, a clustering algorithm is used to group similar users. K-means, hierarchical clustering and other algorithms can be used to classify users with similar privacy preference characteristics by setting appropriate clustering parameters, obtain common features of different user groups, and determine the privacy preference category to which each user belongs based on these common features. According to the user characteristics of different privacy preference categories, the typical attributes of each privacy preference category in terms of privacy protection needs, concerns, sensitivity, etc. are obtained. Through attribute combination, the corresponding privacy preference portrait is obtained by using the privacy preference portrait generation algorithm. According to the user privacy portrait, a personalized recommendation algorithm is used to generate personalized privacy preference setting suggestions for each user. Through collaborative filtering and content-based recommendation technology, combined with the user's historical privacy settings and group privacy portrait, the user's personalized privacy preference portrait is obtained. The personalized privacy preference portrait is applied to the system's privacy protection and service personalization adjustment. According to the user's privacy preferences, the system's privacy policy and service parameters are dynamically adjusted to achieve accurate protection of user privacy and personalized service optimization, and enhance the user's privacy security and user experience. Continuously collect user privacy feedback and behavior data, and adjust and optimize the privacy preference portrait in real time through incremental learning and online update mechanisms. According to the changes in user privacy preferences and new privacy needs, the group privacy portrait and personalized recommendation model are dynamically updated to ensure the continuous improvement of privacy protection and service personalization.

[0080] In this embodiment, a large amount of privacy policy texts are collected from sources such as the Internet, application stores, and corporate websites, where the privacy policy texts include privacy policies and related legal documents, such as GDPR, CCPA, etc. The privacy policy texts are then classified, scored, and key information is extracted, and the corresponding data is labeled. For example, the privacy policy text can be labeled as "complete", "partially complete", or "incomplete", or key information such as data processing methods, data sharing objects, etc. can be extracted. The privacy policy text is then preprocessed, for example, by removing noise data such as HTML tags and special characters, and then processing duplicate data and abnormal data. Abnormal data includes privacy policy texts that are labeled as partially complete and incomplete, ensuring data diversity and coverage to improve the generalization ability of the model.

[0081] In this embodiment, the Transformer architecture is used as the basic framework, and a preliminary pre-trained model for privacy policy generation is constructed based on the training data set. Then, the fine-tuning technology is used to obtain the pre-trained language model as the basic model, and a model suitable for the privacy policy generation task is obtained by fine-tuning on the data in a specific field. Specifically, according to the business attributes of the privacy policy, the training data set is further input into the pre-trained model, and the fine-tuning technology is used to fine-tune the pre-trained model. Through multiple rounds of iterative optimization, the pre-trained model is gradually adapted to the privacy policy generation task, and the initial version of the privacy policy generation model is obtained.

[0082] Specifically, data enhancement technology is used to expand and transform the training data set, such as synonym replacement and sentence rewriting, to obtain more diverse training samples and improve the generalization and robustness of the model. The training data set expanded and transformed by data enhancement technology is re-input into the privacy policy generation model, and the continuous learning method is adopted to continuously fine-tune the model to make it better adapt to the characteristics and requirements of the privacy policy field, so as to obtain a privacy policy generation model with superior performance.

[0083] More specifically, we use the model evaluation and testing method to evaluate the model's generation quality, content relevance, readability and other indicators on an independent test set to determine whether the privacy policy generation model meets the expected performance requirements. Based on the evaluation results, we use the model optimization and adjustment strategy to further improve the privacy policy generation model by adjusting the model hyperparameters, optimizing the training strategy, etc., to obtain a high-quality privacy policy generation model that meets business needs.

[0084] In this embodiment, according to different privacy preference profiles, the privacy information of different users is divided into multiple training sets and test sets, and the privacy policy generation model is trained using a distributed training framework, that is, different training sets and test sets are generated for different privacy preference profiles, and the privacy policy model is trained in distributed parallel. The privacy policy model is divided into multiple node models according to the privacy preference profile, and each node model updates the corresponding privacy policy model independently without directly exchanging data. Then, the main model is updated and optimized by collecting the data of all node models to obtain the privacy policy model. Specifically, on each node model, the node model is trained using the training data set corresponding to the node model, and the node model parameters are updated by the back propagation algorithm to obtain the optimized node privacy policy model. Each node model is independently trained and updated without directly exchanging data, which is used to protect user privacy and obtain the trained node privacy policy model. Through the secure multi-party computing protocol, the parameter information of all node models in the collection is encrypted to obtain the aggregated global privacy policy model parameters. The main privacy policy model is updated using the global model parameters, and the model is evaluated on the full test set to determine whether it meets the expected performance indicators. If the expected performance is not achieved, iterative optimization continues; if it meets the requirements, the trained main privacy policy model is deployed online to generate a privacy policy template according to the user's privacy preferences.

[0085] S200, scoring each clause in the draft privacy policy to obtain a privacy policy text;

[0086] In this embodiment, each clause in the draft privacy policy is scored by experts based on relevant regulatory clauses in the privacy regulations database, so that the generated privacy policy text meets the requirements of laws and regulations and user privacy protection needs.

[0087] In some embodiments, the step S200 includes:

[0088] Use deep learning algorithms to optimize the privacy policy draft and obtain the first draft of the privacy policy;

[0089] Using a graph traversal algorithm to search a privacy regulation database, marking regulatory clauses in the privacy regulation database that are related to the first draft of the privacy policy;

[0090] An expert analysis method is used to score each clause of the draft privacy policy based on the marked regulatory clauses to obtain the privacy policy text.

[0091] In this embodiment, according to the content of the privacy policy draft, natural language processing technology is used to perform word segmentation, part-of-speech tagging, named entity recognition and other preprocessing on the privacy policy draft to obtain the semantic features of the text. Through the corpus in the privacy policy field, the word embedding algorithm such as Word2Vec is used to train the privacy policy-specific word vector model to obtain the low-dimensional dense vector representation of each word. The TextRank, LDA and other algorithms are used to extract keywords and topic models from the privacy policy draft to obtain the main content points and topic distribution of the privacy policy draft. According to the business attributes and characteristics of the privacy policy, deep learning models such as LSTM and Transformer are used to perform semantic understanding and representation learning on the privacy policy text to obtain the deep semantic features of the privacy policy draft. Through the knowledge and experience of experts in the privacy policy field, a rule base and case base for privacy policy quality assessment are constructed to obtain the objectives and constraints for privacy policy optimization. A reinforcement learning algorithm is used to take the semantic features of the privacy policy draft as the state, and the modification operation of the privacy policy draft as the action. Through imitation learning and policy iteration, a policy network for optimizing the privacy policy draft is obtained. Based on the policy network optimized by the privacy policy, the draft privacy policy is iteratively modified. Through repeated evaluation and adjustment, the quality and readability of the privacy policy are continuously improved, and finally a better draft privacy policy is obtained.

[0092] In this embodiment, based on the content of the first draft of the privacy policy, keywords involved therein are obtained, such as personal information collection, use, sharing, protection, etc., as the basis for searching the privacy law database. The privacy law database is represented as a graph structure, in which the regulatory clauses are nodes and the reference relationship between different regulatory clauses is an edge. A privacy law graph database is constructed. A breadth-first search algorithm is adopted. Starting from the keywords of the first draft of the privacy policy, the privacy law graph database is traversed to obtain the regulatory clause nodes related to the keywords. By analyzing the contents of the regulatory clause nodes, the correlation between the regulatory clause nodes and the parts of the first draft of the privacy policy is determined to obtain a correlation measurement value. According to the correlation measurement value, a threshold filtering method is adopted to obtain a set of regulatory clause nodes that are highly correlated with the first draft of the privacy policy. The highly correlated regulatory clause nodes selected are marked by adding label attributes in the privacy law graph database to obtain the relevant regulatory clauses corresponding to the first draft of the privacy policy. The marked relevant regulatory clauses are matched with the first draft of the privacy policy to obtain the parts of the first draft of the privacy policy that need to be modified and improved, and a privacy policy revision suggestion is formed. According to the privacy policy revision suggestion, the first draft of the privacy policy is iteratively optimized to ensure that it meets the latest privacy protection regulatory requirements, and finally a complete privacy policy text is generated.

[0093] In this embodiment, according to the content of the first draft of the privacy policy, the expert analysis method is used to conduct a comprehensive evaluation of the compliance, readability, completeness and other aspects of each clause, and obtain the expert's scoring results for each clause. By summarizing and analyzing the expert scoring results, the average score of each clause is obtained as a quantitative indicator of the quality of the clause. Using the regulatory clauses based on the markup as the reference standard, the similarity between each clause of the first draft of the privacy policy and the standard clauses is obtained to determine the compliance level of each clause. According to the two indicators of the average score and compliance level of the expert scoring, the comprehensive score of each clause is obtained by the weighted average method as the final evaluation result of the clause. For clauses with a comprehensive score lower than the preset threshold, the main problems are judged and modification suggestions are given to improve the overall quality of the privacy policy. Based on the above evaluation results and modification suggestions, the first draft of the privacy policy is optimized and improved to obtain a privacy policy text that meets regulatory requirements and is easy for users to understand.

[0094] S300, based on the regulatory database, using a natural language processing method, converting the regulatory database into a rule engine, performing a dynamic compliance check on the privacy policy text according to the rule engine, and generating a compliance assessment report;

[0095] In this embodiment, the existing laws and regulations are collected to form a regulatory database, which is converted into a rule engine. The privacy policy text is dynamically updated according to the update of privacy-related regulatory clauses in the regulatory database, so that the generated privacy policy text can always comply with the latest legal and regulatory requirements and user privacy protection needs.

[0096] In some embodiments, the step S300 includes:

[0097] Dynamically obtain regulatory texts in a regulatory database, pre-process the regulatory texts through natural language technology, and obtain a key database, wherein the key database is a privacy regulatory database;

[0098] Using a keyword extraction algorithm to identify privacy regulatory terms in the key database;

[0099] Using semantic analysis tools to analyze the specific context and relevance of the privacy regulatory terms in the key database to obtain semantic understanding rules of the privacy regulatory terms;

[0100] Based on the semantic understanding rules, construct logical reasoning rules, and based on the logical reasoning rules, design a rule engine;

[0101] Based on the rule engine, the privacy policy text is checked for compliance and a compliance assessment report is generated.

[0102] In this embodiment, according to business needs, the scope of the legal database to be obtained is determined. Specifically, the business-related fields are analyzed, and it is found that they mainly involve environmental protection, production safety, labor employment, etc. Therefore, the focus is on the regulations issued by the Ministry of Ecology and Environment, the Ministry of Emergency Management, the Ministry of Human Resources and Social Security and other ministries and commissions and local regulations issued by their subordinate local departments. Web crawler technology is used to collect data from the official websites of the above-mentioned ministries and commissions. By analyzing the URL rules and page structure of the website, a crawler program is written to automatically capture legal data on a regular basis. Again, the collected data is cleaned and structured, and natural language processing technology is used to perform word segmentation, part-of-speech tagging, named entity recognition, etc. on the legal text to establish a set of legal databases covering the areas required by the business.

[0103] In this embodiment, data acquisition technology is used to dynamically obtain the regulatory text in the regulatory database to obtain the original regulatory text data set. The obtained original regulatory text data set is preprocessed by natural language processing technology, including operations such as word segmentation, stop word removal, and part-of-speech tagging to obtain a preprocessed regulatory text data set. Based on the preprocessed regulatory text data set, a keyword extraction algorithm, such as TF-IDF, TextRank, etc., is used to extract keywords in the regulatory text to obtain a regulatory keyword set. The importance and relevance of the keywords are determined by performing word frequency statistics and weight calculation on the regulatory keyword set to obtain a filtered keyword set. Based on the filtered keyword set, a keyword matching algorithm is used to match regulatory text fragments containing keywords of privacy regulatory terms in the preprocessed regulatory text data set to obtain a regulatory text fragment set related to the keywords. By performing semantic analysis and correlation calculation on the regulatory text fragment set, the logical relationship and contextual connection between the regulatory text fragments are determined to obtain a semantically related regulatory text fragment set. Based on the semantically related regulatory text fragment set, a data storage technology, such as a relational database, a non-relational database, etc., is used to store the regulatory text fragments in a critical database to obtain a structured privacy regulatory database. By performing data management and maintenance on the privacy regulations database, such as data update and data backup, the accuracy, completeness and availability of the privacy regulations database are ensured, providing data support for subsequent privacy compliance analysis and risk assessment.

[0104] In this embodiment, a word segmentation algorithm is used to segment the regulations in the privacy regulation database to obtain a word list in the privacy regulation database. By constructing a privacy regulation terminology thesaurus, keywords related to privacy regulations are obtained. A keyword extraction algorithm is used to match the word list with the privacy regulation terminology thesaurus to obtain the privacy regulation terms appearing in the privacy regulation database and determine the privacy regulation attributes involved in the privacy regulation database. Natural language processing technology is used to perform semantic analysis on the key database to obtain the contextual information and relevance measurement of the privacy regulation terms in the key database, and obtain the semantic feature vector of the privacy regulation terms. By constructing a semantic understanding rule knowledge base, the semantic feature vector of the privacy regulation terms is matched with the existing rules in the knowledge base to obtain a candidate semantic understanding rule set that is semantically related to the privacy regulation terms. A sorting algorithm based on similarity calculation is used to score the relevance of the rules in the candidate semantic understanding rule set to the privacy regulation terms, and the candidate rules are sorted according to the scoring results to obtain the semantic understanding rule with the highest confidence as the optimal semantic understanding rule for the privacy regulation terms. Apply the optimal semantic understanding rules to key databases, parse and extract the semantic information of privacy regulatory terms in specific contexts, and obtain accurate semantic representations and associations of privacy regulatory terms in key databases. Based on the obtained semantic representations of privacy regulatory terms, a rule engine based on logical reasoning rules is used in combination with domain expert knowledge to judge the compliance of privacy regulatory terms in key texts and determine whether the use of the terms complies with the requirements of relevant laws and regulations on privacy protection. By generating a privacy compliance analysis report, the semantic understanding results of privacy regulatory terms, compliance judgment conclusions, and information based on legal and regulatory provisions are integrated to form a complete privacy compliance analysis result, providing a basis for subsequent privacy compliance rectification.

[0105] In this embodiment, when the regulatory text in the regulatory database is updated, the privacy regulatory terms and logical reasoning rules are updated synchronously, and then the compliance assessment report is regenerated. According to the regenerated privacy compliance assessment report, the report publishing process and notification mechanism are used to notify the relevant stakeholders of the updated compliance assessment results. Through report distribution and explanation, it is ensured that all parties understand and comply with the latest privacy regulatory requirements. At the same time, it is also convenient for users to fully understand the corresponding privacy terms and improve the user experience.

[0106] S400. Establish a privacy setting interactive interface based on user privacy preference data, privacy policy text and compliance assessment report, wherein the privacy setting interactive interface is used to graphically display options of various data permissions related to privacy settings and provide feedback information related to privacy settings.

[0107] In this embodiment, through the privacy setting interactive interface, the personalized privacy policy can be clearly displayed, and the user can know the usage of the privacy preference data in the personalized privacy policy generation system, which improves the transparency of the data processing process and helps to establish and maintain the user's trust in the personalized privacy policy generation system. At the same time, it also makes it easier for the user to understand the privacy policy text generated by the personalized privacy policy generation method more intuitively and clearly, thereby improving the comprehensibility of the privacy policy text.

[0108] In some embodiments, the step S400 includes:

[0109] Use visual elements to intuitively display the options of various data permissions related to privacy settings;

[0110] Obtain the user's privacy setting information, and provide timely feedback information based on the privacy setting information, wherein the feedback information is used to explain the impact and risks brought about by the current privacy setting.

[0111] In this embodiment, by setting visual elements in the privacy setting interactive interface, users can directly participate in the customization process of the privacy policy through options for various data permissions related to privacy settings, making the privacy policy more in line with the actual needs of users, thereby enhancing users' trust and satisfaction with privacy protection.

[0112] In this embodiment, the user's privacy setting information is obtained according to the user's operation behavior in the privacy setting interactive interface, wherein the privacy setting information includes the user's privacy preference data such as the degree of disclosure of personal information and the scope of data sharing. By analyzing the obtained user privacy setting information, the user's risk level in privacy protection is judged. The risk level can be divided into three levels: high, medium and low. Different risk levels correspond to different possibilities of privacy leakage. According to the determined user privacy risk level, a personalized feedback method is adopted to provide the user with a description of the impact of privacy settings and risk prompts. The prompt content includes the risk of data leakage that may be caused by the current privacy setting, the problem of excessive information sharing scope, etc., so as to facilitate the user to understand the privacy-related terms and improve the user experience. The user's acceptance and understanding of the feedback information are obtained, and the user is guided to adjust and optimize the privacy settings in an interactive way to help the user find the balance between privacy protection and convenience of use. According to the privacy settings adjusted by the user, the user's privacy protection level is re-evaluated to determine whether the privacy risk is reduced, and the comparison data before and after the optimization of the privacy settings is generated to intuitively display the optimization effect. The user's privacy settings are continuously tracked by regular reminders and updates to obtain the latest changes in the user's privacy protection status. When the privacy risk is found to be increased, a reminder is sent to the user in a timely manner to maintain the user's privacy security.

[0113] In some embodiments, the above-mentioned method for generating a personalized privacy policy further includes:

[0114] Use unsupervised learning algorithms to establish normal data access patterns;

[0115] Monitor users' data access behaviors in real time, detect abnormal behaviors that deviate from the normal data access patterns, intercept unauthorized abnormal behaviors, perform multi-dimensional risk scoring on the abnormal behaviors, and obtain risk reports;

[0116] Prompting the user whether to update privacy settings through the risk report;

[0117] Obtain the user's updated settings for privacy settings, and regenerate the privacy policy text according to the updated settings.

[0118] In this embodiment, data preprocessing technology is used based on server log data to obtain key attributes such as user IP, access time, and requested resources. Through data cleaning and conversion, a standardized user access behavior data set is obtained. The cluster analysis method in the unsupervised learning algorithm is used to group the acquired user access behavior data. By setting appropriate clustering parameters and similarity measurement methods, clustering results reflecting different user access patterns are obtained. According to the clustering results, the access behavior characteristics of users in each cluster are analyzed to obtain statistical information such as access frequency, access time distribution, and requested resource type. Machine learning algorithms, such as support vector machines or random forests, are used to train the user's normal data access pattern based on the statistical information in each cluster to obtain a user behavior portrait model.

[0119] In this embodiment, the user's real-time data access behavior is obtained, and through behavioral data preprocessing, key features such as access time, access frequency, access data volume, etc. are extracted to obtain the user's current access behavior feature vector. The user's current access behavior feature vector is input into the user behavior portrait model, and through model prediction, it is determined whether the current access behavior deviates from the normal access mode to obtain the abnormal behavior detection result. According to the abnormal behavior detection result, an expert knowledge base is used to conduct a risk assessment of the abnormal behavior and determine the risk level of the abnormal behavior. According to the risk level of the abnormal behavior, access control strategies such as user identity authentication and access permission control are used to intercept high-risk abnormal behaviors and prevent unauthorized data access.

[0120] In this embodiment, for user operations that are determined to be abnormal behaviors, a multi-dimensional risk assessment model is used to comprehensively consider various attributes of the behavior, such as operation sensitivity, operation risk level, user identity trust, etc., to calculate the risk score of the abnormal behavior. Based on the risk score and business impact of the abnormal behavior, a risk report is generated, which describes in detail the type, occurrence time, risk level and other information of the abnormal behavior, providing a basis for subsequent security decisions and responses. Continuously monitor user behavior data, regularly update user behavior patterns, and continuously optimize the accuracy and real-time performance of abnormal behavior detection and risk assessment through the online learning and incremental learning capabilities of machine learning algorithms, thereby improving the security protection level of the system.

[0121] In addition, through the privacy risk assessment results, it is determined whether the user's current privacy settings have the risk of leaking personal sensitive information. If there is a high risk, a personalized privacy risk report is generated. According to the user's privacy risk level and specific risk items, natural language generation technology is used to automatically generate easy-to-understand privacy risk prompts to remind users which information is at risk of leakage and the possible negative impact. Obtain the various existing privacy setting options on the platform, and intelligently recommend related privacy settings through the risk items prompted in the risk report to guide users to protect their privacy. Use visualization technology to design a vivid and intuitive privacy setting wizard interface, present the recommended privacy setting options to users, and provide convenient privacy setting methods such as one-click update to increase users' willingness to update privacy settings. Obtain user feedback on the recommended privacy settings. If the user accepts the suggestion and updates the privacy settings, it is determined that the privacy risk prompt is effective; if the user ignores the risk prompt, it is determined that the prompt method may be insufficient and needs to be further optimized in the future. By continuously tracking the user's privacy settings and platform data changes, regularly updating privacy risk reports and privacy setting recommendations for users, and dynamically adjusting risk judgment and prompt strategies based on user feedback, the intelligent level of privacy protection is continuously improved and the user's sense of gain is enhanced.

[0122] The present application provides an embodiment applied to the gaming industry. Specifically, before entering the game interface, the player needs to create a character and set a personal profile. At this point, through the personalized privacy policy generation method, the privacy setting interface will prompt the player to enter his privacy preferences, and the player can select the corresponding privacy setting options according to his privacy preferences. For example, if the player is making a privacy preference selection, he can choose whether he is willing to share his game achievements, whether he is willing to share location data or game activity records, etc.; through the player's selection of relevant privacy preference settings, the user's privacy preference data is determined, and through the privacy preference data, the player's corresponding privacy preference portrait is determined, and the privacy preference portrait is input into the privacy policy generation model to obtain a preset privacy policy template. Based on the privacy policy template and the user's privacy preference data, a personalized privacy policy text is generated, which clearly states which player data will be collected, how to use it, and the conditions for sharing during the game. For example, if the player does not want to share location information, the privacy policy will make this clear and guarantee that the information will not be collected or shared. In addition, the player's data usage is monitored in real time. For example, real-time monitoring and ensuring that the player's location information is not illegally collected or shared. If the system detects potential violations, such as unauthorized data access, it will report it immediately. If it detects potential privacy risks, such as a third party attempting to access unauthorized player data, the system will assess the severity of this behavior and take appropriate preventive or remedial measures. In addition, all data access records in the game are automatically reviewed to ensure that all data processing activities comply with the player's privacy preferences and the provisions in the privacy policy text. At the same time, a visual interface is provided in the game platform, allowing players to view feedback on how privacy preference data is used. If there are any changes to the privacy policy or abnormal data use, players will be proactively notified to ensure transparency and trust. Through this personalized privacy policy generation method, not only the efficiency of the formulation and implementation of the privacy policy is improved, but also the trust of players in the game platform is enhanced, improving the overall user experience.

[0123] See also Figure 2 As shown, the present invention also provides a personalized privacy policy generation system, the system comprising:

[0124] A privacy policy draft generation model 201: used to match user privacy preference data with a preset privacy policy template to generate a privacy policy draft;

[0125] Privacy policy text generation module 202: used to score each clause in the privacy policy draft to obtain the privacy policy text;

[0126] Dynamic compliance check module 203: used to convert the regulatory database into a rule engine based on the regulatory database by using a natural language processing method, and to perform a dynamic compliance check on the privacy policy text according to the rule engine to generate a compliance assessment report;

[0127] Interactive interface setting module 204: used to establish a privacy setting interactive interface based on user privacy preference data, privacy policy text and compliance assessment report, wherein the privacy setting interactive interface is used to graphically display options for various data permissions related to privacy settings and provide feedback information related to privacy settings.

[0128] It is understandable that if Figure 1 The contents of the embodiment of the personalized privacy policy generation method shown in the figure are applicable to the embodiment of the personalized privacy policy generation system. The functions specifically implemented by the embodiment of the personalized privacy policy generation system are similar to those in the embodiment of the personalized privacy policy generation system. Figure 1 The embodiment of the personalized privacy policy generation method shown in FIG. 1 is the same as that shown in FIG. 1 , and the beneficial effects achieved are the same as those of FIG. Figure 1 The beneficial effects achieved by the illustrated embodiment of the personalized privacy policy generation method are also the same.

[0129] It should be noted that the information interaction, execution process and other contents between the above-mentioned systems are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0130] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0131] See also Figure 3As shown, an embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, a personalized privacy policy generation method as described in any one of the above methods is implemented.

[0132] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0133] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0134] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0135] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for generating a personalized privacy policy as described in any one of the above methods is implemented.

[0136] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0137] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for generating a personalized privacy policy, characterized in that: include: Match user privacy preference data with the preset privacy policy template to generate a privacy policy draft; Score each clause in the draft privacy policy to obtain the privacy policy text; Based on the regulatory database, a natural language processing method is used to convert the regulatory database into a rule engine, and a dynamic compliance check is performed on the privacy policy text according to the rule engine to generate a compliance assessment report; Based on user privacy preference data, privacy policy text and compliance assessment report, a privacy setting interactive interface is established, wherein the privacy setting interactive interface is used to graphically display options for various data permissions related to privacy settings and provide feedback information related to privacy settings.

2. The method according to claim 1, characterized in that The user privacy preference data is matched with the preset privacy policy template to generate a privacy policy draft, including: Obtaining the user's privacy preference data, and obtaining a privacy preference profile corresponding to the user by analyzing the privacy preference data; Establishing a privacy policy generation model, wherein the privacy policy generation model is used to generate a preset privacy policy template according to the privacy preference profile; Using natural language processing technology to perform semantic analysis and keyword extraction on the privacy preference data to obtain the user's privacy demand keywords; The privacy requirement keywords are matched with the preset privacy policy template to generate a privacy policy draft.

3. The method according to claim 2, characterized in that The step of establishing a privacy policy generation model includes: Obtain different users' sensitivity scores for various data permissions and obtain privacy data sources; Preprocessing the privacy data source to obtain privacy information of different users and establish privacy preference profiles of different user groups; Obtaining an existing privacy policy text, preprocessing the existing privacy policy text, and obtaining a training data set; Based on the Transformer architecture, a pre-trained model is constructed, and fine-tuning technology is used to input the training data set into the pre-trained model for training to generate a privacy policy generation model; The privacy preference profiles of different user groups are input into the privacy policy generation model for distributed training to generate multiple privacy policy templates.

4. The method according to claim 1, characterized in that The step of scoring each clause in the draft privacy policy to obtain the privacy policy text includes: Use deep learning algorithms to optimize the privacy policy draft and obtain the first draft of the privacy policy; Using a graph traversal algorithm to search a privacy regulation database, marking regulatory clauses in the privacy regulation database that are related to the first draft of the privacy policy; An expert analysis method is used to score each clause of the draft privacy policy based on the marked regulatory clauses to obtain the privacy policy text.

5. The method according to claim 1, characterized in that Based on the regulatory database, a natural language processing method is used to convert the regulatory database into a rule engine, and a dynamic compliance check is performed on the privacy policy text according to the rule engine to generate a compliance assessment report, including: Dynamically obtain regulatory texts in a regulatory database, pre-process the regulatory texts through natural language technology, and obtain a key database, wherein the key database is a privacy regulatory database; Using a keyword extraction algorithm to identify privacy regulatory terms in the key database; Using semantic analysis tools to analyze the specific context and relevance of the privacy regulatory terms in the key database to obtain semantic understanding rules of the privacy regulatory terms; Based on the semantic understanding rules, construct logical reasoning rules, and based on the logical reasoning rules, design a rule engine; Based on the rule engine, the privacy policy text is checked for compliance and a compliance assessment report is generated.

6. The method according to claim 1, characterized in that The privacy setting interactive interface is established based on the user privacy preference data, the privacy policy text and the compliance assessment report. The privacy setting interactive interface is used to graphically display the options of various data permissions related to the privacy setting and provide feedback information related to the privacy setting, including: Use visual elements to intuitively display the options of various data permissions related to privacy settings; Obtain the user's privacy setting information, and provide timely feedback information based on the privacy setting information, wherein the feedback information is used to explain the impact and risks brought about by the current privacy setting.

7. The method according to claim 1, characterized in that The method further comprises: Use unsupervised learning algorithms to establish normal data access patterns; Monitor users' data access behaviors in real time, detect abnormal behaviors that deviate from the normal data access patterns, intercept unauthorized abnormal behaviors, perform multi-dimensional risk scoring on the abnormal behaviors, and obtain risk reports; Prompting the user whether to update privacy settings through the risk report; Obtain the user's updated settings for privacy settings, and regenerate the privacy policy text according to the updated settings.

8. A personalized privacy policy generation system, characterized in that: include: Privacy policy draft generation model: used to match user privacy preference data with the preset privacy policy template to generate a privacy policy draft; Privacy policy text generation module: used to score each clause in the draft privacy policy to obtain the privacy policy text; Dynamic compliance check module: used to convert the regulatory database into a rule engine based on the regulatory database by using natural language processing methods, and to perform dynamic compliance check on the privacy policy text according to the rule engine to generate a compliance assessment report; Interactive interface setting module: used to establish a privacy setting interactive interface based on user privacy preference data, privacy policy text and compliance assessment report. The privacy setting interactive interface is used to graphically display options for various data permissions related to privacy settings and provide feedback information related to privacy settings.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Method and system for generating privacy policy text according to APK package

    CN113254923A

  • Privacy policy content generation method and device and electronic equipment

    CN113822036A

  • Compliance risk management and control method and system, electronic equipment and storage medium

    CN116205496A

  • Software privacy compliance pre-detection method and related equipment thereof

    CN116795707A

  • Chinese privacy automatic compliance detection method and related equipment

    CN117474724A

Cited By

  • Incremental policy analysis and dynamic model updating method and system

    CN120181066A

  • Dynamic design strategy generation method, device and equipment and readable storage medium

    CN120822274A