Content compliance detection method and device and readable storage medium

Abstract

The invention relates to a content compliance detection method and device. The method comprises the steps of collecting original data and performing data preprocessing; rules input by a front-end user are obtained, basic information is stored, the effect of the user rules is evaluated, and the priority of the user rules is dynamically adjusted; collecting rule use data and user behavior data, and integrating to form a data set; classifying the users, and dynamically updating the user portraits in real time according to the newest behaviors and scores of the users; classifying the rules according to rule functions and compliance fields, and generating a recommendation rule list according to the use frequency, the accuracy rate and the false alarm rate of the rules and the matching degree with the user portrait; and continuously optimizing the priority of the rule and the recommendation strategy according to user feedback, and generating a detection report. Through the modular design and the intelligent technology, efficient, accurate and compliant detection of commercialized Wiki tool content is realized, the development and maintenance cost of enterprises is reduced, and the data security management level is improved.

Description

Technical Field

[0001] The present application belongs to the field of data management technology, and in particular, relates to a detection method, device, electronic device and computer-readable storage medium based on content compliance of a commercial Wiki tool. Background Art

[0002] With the rapid development of information technology, enterprises are increasingly relying on knowledge management and collaboration tools. Commercial Wiki tools (such as Confluence) are widely used in multiple business scenarios such as project management, technical support, and knowledge sharing due to their efficient knowledge management and collaboration functions. Such tools significantly improve team collaboration efficiency and the accuracy of information transmission by centrally storing and organizing documents, specifications, and processes within the enterprise. However, with the continuous expansion of enterprise scale and the increase in business complexity, existing commercial Wiki tools have gradually exposed many shortcomings in meeting specific needs, especially in content compliance detection.

[0003] 1. Limitations of retrieval requirements

[0004] Existing commercial Wiki tools usually provide basic full-text search functions, allowing users to search for relevant content by keywords. However, faced with the complex needs of enterprises in content compliance testing, the search capabilities of these tools seem to be insufficient, as shown in the following:

[0005] Diversity of compliance standards: When companies conduct content compliance testing, they often need to conduct detailed checks based on multiple compliance standards to ensure that documents do not contain sensitive information such as personal data, login credentials, corporate secrets, etc. The simple keyword search of existing tools cannot meet the multi-level and multi-dimensional compliance testing needs.

[0006] Insufficient detection accuracy: Traditional keyword searches are easily affected by linguistic phenomena such as synonyms and polysemous words, resulting in high false positive and false negative rates, making it difficult to achieve high-precision content review.

[0007] Lack of automated detection: Most commercial Wiki tools lack automated compliance detection capabilities and are unable to implement regular, batch content scanning. Relying on manual review is not only inefficient but also prone to human omissions.

[0008] 2. High development and maintenance costs

[0009] To make up for the shortcomings of existing tools in content compliance detection, enterprises usually adopt the following two methods:

[0010] Relying on tool vendors for customized development: Enterprises need to cooperate with tool providers to customize functions. This method is not only time-consuming and costly, but also has the risk of being unable to quickly respond to changes in the enterprise's business after customized development, making it difficult for enterprises to adjust and respond in a timely manner when faced with new compliance requirements.

[0011] Internally developed solutions: Some companies with strong technical capabilities choose to develop content compliance detection tools on their own. However, this requires a lot of manpower and material resources for research and development and maintenance, and the speed of technology updates cannot keep up with the rapidly changing compliance requirements, resulting in insufficient sustainability and scalability of the system.

[0012] 3. The urgency of content compliance management

[0013] In the context of globalization and digital transformation, enterprises are facing increasingly stringent laws, regulations and compliance requirements. Content compliance management is not only related to the data security and intellectual property protection of enterprises, but also directly affects the legal liability and market reputation of enterprises. Therefore, developing an efficient, automated and flexible content compliance detection tool has become an important issue that enterprises need to solve urgently.

[0014] In summary, the existing technologies have the following deficiencies in content compliance detection:

[0015] Low degree of automation: Most tools rely on manual review or simple keyword matching and lack intelligent detection methods, making it difficult to achieve efficient and accurate content review.

[0016] Poor scalability: Existing systems often require cumbersome system upgrades or redevelopment when faced with new compliance standards or complex testing requirements, and lack flexible expansion capabilities.

[0017] Limited detection accuracy: Existing tools have difficulty achieving high-precision keyword extraction and sensitive information identification when processing structured or semi-structured text data.

[0018] In view of the above-mentioned shortcomings of existing technologies, enterprises urgently need a solution that can flexibly adapt to different compliance requirements, automatically perform content detection, and have high detection accuracy and good scalability. Summary of the invention

[0019] In response to the above problems, this application proposes a new content compliance detection method and device. This application aims to achieve efficient and accurate compliance detection of the content of commercial Wiki tools through modular design and intelligent technology, thereby reducing the company's development and maintenance costs in content management, improving data security management levels, and ensuring that corporate operations comply with legal and regulatory requirements.

[0020] In summary, this application performs compliance testing on the content of commercial Wiki tools, using concurrent processing technology and advanced data cleaning methods to significantly improve the efficiency and accuracy of data collection and processing. At the same time, the flexible rule storage mechanism supports complex detection logic combinations, enhancing the adaptability and scalability of the system. In addition, through intelligent recommendations based on the frequency of rule use, the user's rule configuration process is optimized, and the overall intelligence and automation level of detection is improved. These features enable this application to have higher accuracy and a wider range of applications in content compliance testing, surpassing existing keyword-based detection methods.

[0021] In order to achieve the above objectives, this application provides the following technical solutions:

[0022] A first aspect of the present application provides a content compliance detection method, comprising:

[0023] Collect raw data from data sources and perform data preprocessing on the collected data;

[0024] Obtain the rules entered by the front-end user, store the basic information of the user rules, evaluate the effect of the user rules, and dynamically adjust the priority of the user rules;

[0025] Collect rule usage data and user behavior data and integrate them into a data set for rule evaluation;

[0026] Categorize users and dynamically update user profiles in real time based on their latest behaviors and ratings;

[0027] Classify rules according to their functions and compliance areas, generate a list of recommended rules based on the frequency of use, accuracy, false positive rate and matching degree of the rules with the user profile, display the recommended rules on the front-end interface, and allow users to adopt, ignore or modify the rule configuration;

[0028] Collect user feedback data, continuously optimize the priority and recommendation strategies of rules based on user feedback, and generate detection reports.

[0029] Optionally, in the method of the present application, the content compliance detection method is a retrieval and compliance management detection method implemented for Wiki system data.

[0030] Optionally, in the method of the present application, the data source includes: a database, a file system, an API;

[0031] When the data source is a database, first complete the database connection settings by configuring the database's JDBC connection string, database name, user name, and password;

[0032] The data preprocessing includes: cleaning, format conversion and standardization processing; the cleaning includes: removing invalid characters and deduplicating duplicate records.

[0033] Optionally, in the method of the present application, multi-threading technology is used when collecting raw data from the data source, and data is captured from the data source concurrently by configuring the thread pool, and non-blocking data reading is achieved by adjusting the thread pool size and combining asynchronous I / O methods.

[0034] Optionally, in the method of the present application, a rule table is used to store basic information of user rules, and the basic information of the user rules includes: rule name, rule description, priority, type, enable / disable status, creation time, last update time, version number and last update user;

[0035] The following three evaluation indicators are used to evaluate the effectiveness of user rules:

[0036] Usage frequency: the total number of times each rule is triggered;

[0037] Accuracy: After each rule detection is completed, the user will give an overall score to the execution effect of the rule, and select "accurate" or "inaccurate". The accuracy rate is the proportion of the rule marked as "accurate" in the user's score;

[0038] False alarm rate: After each rule detection is completed, the user will give an overall score on the execution effect of the rule, selecting "accurate" or "inaccurate". The false alarm rate is the proportion of the rule marked as "inaccurate" in the user's score;

[0039] Dynamically adjusting the priority of user rules includes the following mechanisms:

[0040] Weighting mechanism: Using a weighted average method, the score weight decays exponentially over time, and the most recent score has a higher weight;

[0041] Dynamic adjustment mechanism: The priority of the rules is dynamically adjusted according to the scoring results. When the accuracy of the rule is higher than a certain threshold and the false alarm rate is lower than a certain threshold, the system automatically increases its priority.

[0042] Optionally, in the method of the present application, the rule usage data includes: usage frequency, last usage time, accuracy rate and false alarm rate;

[0043] The user behavior data includes: operation records, rule configuration, detection execution, feedback annotation, search keywords and frequency.

[0044] Optionally, in the method of the present application, classifying users includes:

[0045] (1) User Behavior Analysis

[0046] Operation record analysis: Analyze user operation behaviors and determine user preferences for different compliance areas and rule types;

[0047] Search behavior analysis: Identify content topics and compliance requirements that users are interested in based on their search behavior;

[0048] (2) User interest preference identification

[0049] Rating-based preference identification: Identify the user's approval of different types of rules based on the user's rating of the rules;

[0050] Compliance field preference identification: Identify the compliance fields that users tend to focus on based on their operation records and rating results;

[0051] (3) User classification

[0052] Based on the clustering algorithm, users are classified into different compliance demand categories according to their rule usage characteristics, operation behavior characteristics and interest area characteristics.

[0053] Optionally, in the method of the present application, the rules are divided into the following categories according to their functions: keyword filtering, pattern matching, range checking, and data integrity checking;

[0054] Rules are divided into the following categories based on compliance areas: content review, data privacy, financial compliance, and legal and regulatory compliance.

[0055] A second aspect of the present application provides a content compliance detection device, including:

[0056] Data acquisition module: responsible for acquiring data from multiple data sources, supporting multiple data access methods and high-concurrency processing; the data sources include: database, file system, API;

[0057] Data preprocessing module: responsible for cleaning, format conversion and standardization of collected data to ensure data consistency;

[0058] Rule engine module: realizes automatic detection and optimization of rules through rule management and version control;

[0059] Intelligent recommendation module: realizes intelligent recommendation based on analysis of rule indicators, user behavior data and user portraits;

[0060] Automatic detection and task scheduling module: executes compliance detection tasks through timed scheduling and real-time triggering;

[0061] Result analysis and feedback module: used to generate compliance test reports, store historical records, and support the processing of user feedback;

[0062] User management and authority control module: implements dynamic control of user authority and operation audit to ensure system security.

[0063] Optionally, in the device of the present application, each module works in collaboration through a standard interface and data stream, including:

[0064] The data acquisition module obtains raw data from various data sources and passes the data to the data preprocessing module; the data preprocessing module cleans, converts the format and standardizes the data;

[0065] The rule engine module executes the compliance detection rules configured by the user, wherein the compliance detection rules are derived from efficient rules defined by the user or recommended by the system;

[0066] The automated detection and task scheduling module is responsible for managing the execution of tasks, supporting scheduled scheduling, real-time triggering, and event-based dynamic detection;

[0067] The intelligent recommendation module generates a personalized recommendation rule list based on the analysis of rule indicators, user behavior data and user portraits; the rule indicators include: usage frequency, accuracy, and false alarm rate; the user behavior data includes: operation records and search behavior;

[0068] The result analysis and feedback module generates compliance detection reports. Users rate the effectiveness of rule execution. Feedback data is used to dynamically adjust the priority of rules and update the scores through weighted average or time decay mechanisms, forming a closed-loop optimization process for rules.

[0069] The user management and permission control module uses role permission control to ensure that each user's operations are in line with the preset permission range and that all operations have audit records.

[0070] A third aspect of the present application provides an electronic device, comprising: a memory and a processor;

[0071] Memory: used to store computer programs;

[0072] Processor: used to execute the computer program to implement the steps of the aforementioned content compliance detection method.

[0073] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the aforementioned content compliance detection method are implemented.

[0074] Finally, the present application also provides a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program codes for executing the aforementioned content compliance detection method.

[0075] In summary, this application has made many improvements and innovations to the existing compliance detection technology, mainly including:

[0076] (1) Rule effect evaluation mechanism based on user ratings

[0077] This application introduces a simple and easy-to-use rule scoring mechanism. After each test, the user scores the overall performance of the rule as "accurate" or "inaccurate", thereby dynamically evaluating the accuracy and false positive rate of the rule. This method greatly reduces the complexity of the user's operation, and can quickly collect feedback data to support rule optimization and intelligent recommendation.

[0078] (2) Rule version management and rollback mechanism

[0079] This application supports version management of rules. A new version will be created for each rule update, and historical versions will be retained for backtracking and comparison. Users can view change records and roll back to a specific version to ensure the flexibility and maintainability of rule configuration.

[0080] (3) Closed-loop feedback and optimized dynamic adjustment mechanism

[0081] This application has designed a closed-loop process of continuous optimization, using user feedback data to dynamically adjust the priority of rules and recommendation strategies. With the accumulation of user feedback, the detection accuracy and recommendation quality of the system can be continuously improved.

[0082] (4) User portrait construction based on multi-dimensional data integration

[0083] This application integrates multiple data sources (such as operation records, search behaviors, and rule usage data) to build a user profile that reflects the user's compliance needs. It also combines clustering algorithms to classify users and supports personalized rule recommendations and intelligent adjustments.

[0084] (5) Enable / disable and prioritize rule engines

[0085] This application rule can be flexibly enabled or disabled, and the priority can be dynamically adjusted according to the frequency of use, scoring results, etc. to meet the needs of different detection tasks.

[0086] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the techniques indicated in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0088] Figure 1 This is a structural diagram of the content compliance detection device according to an embodiment of the present application.

[0089] Figure 2 A schematic diagram of the working process of a content compliance detection device according to an embodiment of the present application.

[0090] Figure 3 A schematic diagram of the implementation process of a content compliance detection method according to an embodiment of the present application. DETAILED DESCRIPTION

[0091] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0092] The term "including" and its variations used in this document are open inclusions, i.e., "including but not limited to"; the term "based on" means "at least partly based on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments".

[0093] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless the context clearly indicates otherwise, it should be understood as "one or more".

[0094] Figure 1 The figure shows an intelligent content compliance detection device proposed in this application.

[0095] Figure 2 The following is the workflow of the detection device of this application. The device integrates multiple functional modules such as data collection, data preprocessing, rule engine and intelligent recommendation, automated detection and task scheduling, result analysis and feedback, and user management and authority control. The core goal of this device is to achieve high efficiency and accuracy of compliance detection through automated processes, intelligent recommendation mechanisms and user feedback optimization.

[0096] The device of the present application adopts a modular design, each module performs its own duties, and together completes the closed-loop process of data collection, processing, detection, analysis and feedback. The modules work together through standard interfaces and data streams. The device includes:

[0097] Data acquisition module: responsible for acquiring data from multiple data sources (such as databases, file systems, APIs, etc.), supporting multiple data access methods and high-concurrency processing.

[0098] Data preprocessing module: cleans, converts and standardizes the collected data to ensure data consistency and high quality.

[0099] Rule engine module: realizes automatic detection and optimization of rules through rule management and version control.

[0100] Intelligent recommendation module: realizes intelligent recommendation based on the analysis of rule indicators, user behavior data and user portraits.

[0101] Automated detection and task scheduling module (hereinafter referred to as the detection scheduling module): executes compliance detection tasks through timed scheduling and real-time triggering.

[0102] Result analysis and feedback module: Generates compliance test reports, stores historical records, and supports the processing of user feedback.

[0103] User management and authority control module: implements dynamic control of user authority and operation audit to ensure system security.

[0104] The device composed of the above modules implements the content compliance detection method disclosed in this application when running. The collaborative working mode of the above modules is described in detail below:

[0105] (1) Collaboration between data acquisition module and data preprocessing module

[0106] The data acquisition module obtains raw data from various data sources and passes the data to the data preprocessing module, which cleans and standardizes the data to ensure the accuracy of subsequent tests and the processability of the data.

[0107] (2) Collaboration between the rule engine module, intelligent recommendation module, and detection scheduling module

[0108] The rule engine module works with the detection scheduling module to execute user-configured compliance detection rules. The rules can come from user-defined or system-recommended efficient rules. The detection scheduling module is responsible for managing the execution of tasks and supports timed scheduling, real-time triggering, and event-based dynamic detection. The storage and management of rules include version control and enable / disable status management to ensure that the rules are flexible and available.

[0109] The intelligent recommendation module generates a personalized list of recommended rules based on multiple indicators such as rule usage frequency, accuracy, false alarm rate, and analysis of user behavior data (such as operation records, search behavior) and user portraits. The system supports classification management of rules (such as functional classification, compliance field classification, source classification, etc.) and displays them on the front end for users to adopt or modify.

[0110] (3) Closed-loop optimization of result analysis and user feedback

[0111] After the detection is completed, the system automatically generates a compliance detection report, and users can score the effectiveness of rule execution. Feedback data is used to dynamically adjust the priority of rules, and update the score through weighted average, time decay and other mechanisms to form a closed-loop optimization process for rules. In addition, user portraits will be updated in real time based on the latest behavioral data to ensure the relevance and accuracy of recommended rules.

[0112] (4) Security assurance of user management and authority control

[0113] The user management and permission control module ensures that each user's operations are within the preset permission range through role permission control. All operations are audited to prevent unauthorized behavior and ensure system security.

[0114] Figure 3 A content compliance detection method provided by the present application is shown, comprising the following steps:

[0115] Collect raw data from data sources and perform data preprocessing on the collected data;

[0116] Obtain the rules entered by the front-end user, store the basic information of the user rules, evaluate the effect of the user rules, and dynamically adjust the priority of the user rules;

[0117] Collect rule usage data and user behavior data and integrate them into a data set for rule evaluation;

[0118] Categorize users and dynamically update user profiles in real time based on their latest behaviors and ratings;

[0119] Classify rules according to their functions and compliance areas, generate a list of recommended rules based on the frequency of use, accuracy, false positive rate and matching degree of the rules with the user profile, display the recommended rules on the front-end interface, and allow users to adopt, ignore or modify the rule configuration;

[0120] Collect user feedback data, continuously optimize the priority and recommendation strategies of rules based on user feedback, and generate detection reports.

[0121] In order to better understand the technical solution of this application, its implementation process is further described in detail with the following business scenario examples. This example is a compliance detection method for achieving comprehensive retrieval and compliance management of internal Wiki system data of an enterprise, including:

[0122] Step 1: In this implementation, a MySQL database of a certain enterprise Wiki system is connected as the data source. The database connection settings are completed by configuring the database's JDBC connection string, database name, user name, and password.

[0123] Step 2: Use multi-threading technology to collect data from the database. Configure the thread pool to concurrently grab data from the database, adjust the thread pool size to improve collection efficiency, and combine asynchronous I / O technology (asynchronous input / output technology) to achieve non-blocking data reading.

[0124] Step 3: After collecting the data, clean the data and convert its format. Use regular expressions to remove invalid characters and deduplicate duplicate records.

[0125] Step 4: User rule storage configuration. The backend obtains the frontend user input rules, and the system uses the rule table to store the basic information of the user search rules, including rule_id, rule name, rule description, priority, type, status (enabled / disabled), creation time, last update time, version number, and last update user, etc. The rule table structure is shown in Table 1 below:

[0126] Table 1 Rule table structure

[0127]

[0128] Step 5: Evaluate the effectiveness of user rules and dynamically adjust the priority of rules. First, use three indicators (frequency of use, accuracy, and false positive rate) to evaluate the effectiveness, and then dynamically adjust the priority of rules.

[0129] The indicators are described as follows:

[0130] Usage Count: This counts the total number of times a rule is triggered, reflecting the breadth of use of the rule in the system. A rule with a higher usage frequency usually means that the rule is more widely used in user detection tasks.

[0131] Accuracy: After each rule check is completed, the user can give an overall score for the execution effect of the rule, choosing "accurate" or "inaccurate". Accuracy is the proportion of all scores marked as "accurate". This indicator is used to measure the accuracy of the rule. For example, if a rule is scored 20 times and 15 of them are "accurate", the accuracy is 75%.

[0132] False Positive Rate: The false positive rate is the proportion of all scores marked as "inaccurate" and is used to evaluate the reliability of the rule. For example, if a rule is scored 20 times and 5 of them are "inaccurate", the false positive rate is 25%.

[0133] The adjustment priority mechanism is described as follows:

[0134] Weighting mechanism: To reflect the latest ratings, a weighted average approach can be used, with more recent ratings having higher weights. For example, the rating weights can decay exponentially over time, giving the latest ratings a greater impact.

[0135] Dynamically adjust the priority: The system dynamically adjusts the priority of the rule based on the scoring results. When the accuracy of the rule is higher than a certain threshold (such as 80%) and the false alarm rate is lower than a certain threshold (such as 20%), the system will automatically increase its priority.

[0136] Step 6: Collect and integrate rule usage data and user behavior data. This includes collecting rule usage data (usage frequency, last usage time, accuracy, and false positive rate) and user behavior data (rule configuration, detection execution, feedback annotation, search keywords and frequency) to form a data set for rule evaluation to support rule effect evaluation and recommendation generation.

[0137] Step 7: Classify users. The following are the classification steps:

[0138] 1. User behavior analysis

[0139] Operation record analysis: Analyze users’ operation behaviors in the system (such as rule configuration, detection execution frequency, etc.) to reflect users’ preferences for different compliance areas and rule types.

[0140] Search behavior analysis: Identify content topics and compliance requirements that users are interested in based on their search keywords, search frequency, and other data.

[0141] 2. Identification of user interest preferences

[0142] Rating-based preference identification: Based on the user's rating of the rule (accurate / inaccurate), the user's approval of different types of rules is identified. The rule type frequently marked as "accurate" will be regarded as the user's preference.

[0143] Compliance area preference identification: Based on the user's operation records and scoring results, identify the compliance areas that the user tends to pay attention to (such as data privacy, financial compliance, etc.).

[0144] 3. User classification

[0145] Classification based on clustering algorithms: Use K-means or hierarchical clustering algorithms to classify users into different compliance demand categories based on their rule usage characteristics, operation behavior characteristics, and interest area characteristics. For example, one category of users may be mainly concerned about data privacy, while another category of users may be concerned about financial compliance.

[0146] 4. Dynamic update of user portraits

[0147] Real-time feedback adjustment: The system dynamically updates the user profile based on the user’s latest behavior and ratings to maintain the relevance and accuracy of the recommendations.

[0148] Step 8: Classify search rules. According to the function of the rules, they are divided into different categories, such as keyword filtering, pattern matching, range verification, and data integrity detection. According to the compliance field, they are divided into content review, data privacy, financial compliance, and legal and regulatory compliance.

[0149] Step 9: Recommend rules to users. Generate a list of recommended rules by comprehensively considering the frequency of use, accuracy, false positive rate and matching degree of the rules with the user profile. Display the recommended rules on the front-end interface and allow users to adopt, ignore or modify the rule configuration.

[0150] Step 10: Collect user feedback data and continuously optimize the rule priority and recommendation strategy based on user feedback.

[0151] Step 11: Generate test report and process user feedback.

[0152] Step 12: Make modifications based on the detailed description of the violation and modification suggestions provided by the system.

[0153] The flow charts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the apparatus, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0154] The names of messages or data exchanged between multiple modules in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or data.

[0155] Furthermore, an embodiment of the present application also discloses an electronic device, including: a memory and a processor;

[0156] The memory is used to store a computer program, and the processor is used to run the computer program to implement the steps of the above-mentioned content compliance detection method.

[0157] It is understandable that, in addition to the memory and the processor, the electronic device may also include an input device such as a keyboard, an output device such as a display, and a communication module. The input device, the output device, and the communication module communicate with the processor via an I / O interface (i.e., an input / output interface).

[0158] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0159] Furthermore, the present application also discloses a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can perform each step of the content compliance detection method disclosed in the present application.

[0160] In the context of the present disclosure, a computer-readable storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A readable storage medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0161] In particular, according to an embodiment of the present disclosure, the process described in the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processing device, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0162] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), etc.

[0163] Although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Certain features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination.

[0164] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0165] Those skilled in the art should also understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for detecting content compliance, characterized in that: The method comprises: Collect raw data from data sources and perform data preprocessing on the collected data; Obtain the rules entered by the front-end user, store the basic information of the user rules, evaluate the effect of the user rules, and dynamically adjust the priority of the user rules; Collect rule usage data and user behavior data and integrate them into a data set for rule evaluation; Categorize users and dynamically update user profiles in real time based on their latest behaviors and ratings; Classify rules according to their functions and compliance areas, generate a list of recommended rules based on the frequency of use, accuracy, false positive rate and matching degree of the rules with the user profile, display the recommended rules on the front-end interface, and allow users to adopt, ignore or modify the rule configuration; Collect user feedback data, continuously optimize the priority and recommendation strategies of rules based on user feedback, and generate detection reports.

2. The method according to claim 1, characterized in that The content compliance detection method is a retrieval and compliance management detection method implemented for Wiki system data.

3. The method according to claim 1, characterized in that The data sources include: database, file system, API; When the data source is a database, first complete the database connection settings by configuring the database's JDBC connection string, database name, user name, and password; The data preprocessing includes: cleaning, format conversion and standardization processing; the cleaning includes: removing invalid characters and deduplicating duplicate records.

4. The method according to claim 1, characterized in that Multi-threading technology is used when collecting raw data from the data source. Data is fetched from the data source concurrently by configuring the thread pool. Non-blocking data reading is achieved by adjusting the thread pool size and combining asynchronous I / O methods.

5. The method according to claim 1, characterized in that The rule table is used to store basic information of user rules, including rule name, rule description, priority, type, enabled / disabled status, creation time, last updated time, version number, and last updated user; The following three evaluation indicators are used to evaluate the effectiveness of user rules: Usage frequency: the total number of times each rule is triggered; Accuracy: After each rule detection is completed, the user will give an overall rating of the execution effect of the rule, selecting "accurate" or "inaccurate". The accuracy rate is the proportion of the rule marked as "accurate" in the user rating; False alarm rate: After each rule detection is completed, the user will give an overall score on the execution effect of the rule, selecting "accurate" or "inaccurate". The false alarm rate is the proportion of the rule marked as "inaccurate" in the user's score; Dynamically adjusting the priority of user rules includes the following mechanisms: Weighting mechanism: Using a weighted average method, the score weight decays exponentially over time, and the most recent score has a higher weight; Dynamic adjustment mechanism: The priority of the rules is dynamically adjusted according to the scoring results. When the accuracy of the rule is higher than a certain threshold and the false alarm rate is lower than a certain threshold, the system automatically increases its priority.

6. The method according to claim 1, characterized in that The rule usage data includes: usage frequency, last usage time, accuracy rate and false alarm rate; The user behavior data includes: operation records, rule configuration, detection execution, feedback annotation, search keywords and frequency.

7. The method according to claim 1, characterized in that The user classification includes: (1) User Behavior Analysis Operation record analysis: Analyze user operation behaviors and determine user preferences for different compliance areas and rule types; Search behavior analysis: Identify content topics and compliance requirements that users are interested in based on their search behavior; (2) User interest preference identification Rating-based preference identification: Identify the user's approval of different types of rules based on the user's rating of the rules; Compliance field preference identification: Identify the compliance fields that users tend to focus on based on their operation records and rating results; (3) User classification Based on the clustering algorithm, users are classified into different compliance demand categories according to their rule usage characteristics, operation behavior characteristics and interest area characteristics.

8. The method according to claim 1, characterized in that The rules are divided into the following categories according to their functions: keyword filtering, pattern matching, range checking, and data integrity checking; Rules are divided into the following categories based on compliance areas: content review, data privacy, financial compliance, and legal and regulatory compliance.

9. A content compliance detection device, characterized in that: The device comprises: Data acquisition module: responsible for acquiring data from multiple data sources, supporting multiple data access methods and high-concurrency processing; the data sources include: database, file system, API; Data preprocessing module: responsible for cleaning, format conversion and standardization of collected data to ensure data consistency; Rule engine module: realizes automatic detection and optimization of rules through rule management and version control; Intelligent recommendation module: realizes intelligent recommendation based on analysis of rule indicators, user behavior data and user portraits; Automatic detection and task scheduling module: executes compliance detection tasks through timed scheduling and real-time triggering; Result analysis and feedback module: used to generate compliance test reports, store historical records, and support the processing of user feedback; User management and authority control module: implements dynamic control of user authority and operation audit to ensure system security.

10. The device according to claim 9, characterized in that The modules work together through standard interfaces and data flows, including: The data acquisition module obtains raw data from various data sources and passes the data to the data preprocessing module; the data preprocessing module cleans, converts the format and standardizes the data; The rule engine module executes the compliance detection rules configured by the user, wherein the compliance detection rules are derived from efficient rules defined by the user or recommended by the system; The automated detection and task scheduling module is responsible for managing the execution of tasks, supporting scheduled scheduling, real-time triggering, and event-based dynamic detection; The intelligent recommendation module generates a personalized recommendation rule list based on the analysis of rule indicators, user behavior data and user portraits; the rule indicators include: usage frequency, accuracy, and false alarm rate; the user behavior data includes: operation records and search behavior; The result analysis and feedback module generates compliance detection reports. Users rate the effectiveness of rule execution. Feedback data is used to dynamically adjust the priority of rules and update the scores through weighted average or time decay mechanisms, forming a closed-loop optimization process for rules. The user management and permission control module uses role permission control to ensure that each user's operations are in line with the preset permission range and that all operations have audit records.

Images