Power marketing business-oriented data security identification monitoring method

Through the power marketing business data monitoring method based on machine learning and deep learning, the problems of inefficiency and lack of early warning in the existing technology are solved, and accurate identification and real-time monitoring of user access abnormal behaviors and sensitive data are realized, reducing data leakage Risk, providing flexible security protection and detailed logging.

CN118965359APending Publication Date: 2024-11-15STATE GRID SHANXI MARKETING SERVICE CENT
View PDF 0 Cites 5 Cited by

Patent Information

Application Number
CN202410991410.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The existing data monitoring methods for power marketing business rely on manual operations, are inefficient and difficult to deal with complex security threats. The lack of pre-warning and in-process monitoring mechanisms leads to serious challenges in data security.

Method used

Using machine learning and deep learning methods, build a user access abnormal behavior and sensitive data monitoring model, monitor user access behavior in real time, generate abnormal behavior evaluation results, and match with the preset policy library, select target policies, and realize real-time data security Monitor and respond quickly.

Benefits of technology

The system has strong intelligent identification capabilities, which can accurately identify users' access to abnormal behaviors and sensitive data, realize real-time monitoring and rapid response, reduce the risk of data leakage, provide flexible risk response strategies and detailed data processing logs, and support administrator monitoring and audit.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118965359A_ABST
    Figure CN118965359A_ABST
Patent Text Reader

Abstract

The invention discloses a power marketing business-oriented data security identification monitoring method, and belongs to the technical field of databases. Comprising the steps of 1, training an initial user access abnormal behavior monitoring model based on a constructed user access abnormal behavior knowledge base, and determining a target user access abnormal behavior recognition model; 2, monitoring user access behaviors in real time, processing abnormal behaviors, generating an abnormal behavior evaluation result, respectively matching the abnormal behavior evaluation result with each strategy in a preset abnormal strategy library, and selecting a target strategy; 3, training the sensitive data monitoring model based on the constructed data security knowledge base, determining the sensitive data monitoring model, and performing real-time monitoring; and 4, matching strategies in the sensitive data risk strategy library, and generating a processing log of corresponding sensitive data. According to the invention, the efficient data processing capability ensures that the system can still keep quick and accurate response when facing large-scale access requests, and the risk of data leakage is effectively reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of database technology, and in particular to a data security identification and monitoring method for power marketing business. Background Art

[0002] As the digital transformation of the power grid continues to develop, data has gradually become an important asset of power companies. The value it contains is not only reflected in the production process, but also plays a vital role in social services and economic development. The power marketing business involves a wide variety of data, including user data, transaction data, and operation data. The security of these data is directly related to the economic benefits, market competitiveness, and social image of the enterprise. Once the data is leaked, tampered with, or abused, it will not only lead to huge losses of corporate assets, but may also cause legal disputes and credibility crises, causing immeasurable losses to the enterprise. At the same time, as a key link in releasing the value of factors, the sharing of data resources has become an important trend. However, in various application scenarios where data is shared internally or opened to the outside world, there are phenomena such as difficulties in the security control of sensitive data. How to ensure data security while ensuring data sharing and opening has become an urgent problem for power companies. Existing monitoring methods often rely on manual operations, are inefficient, and are difficult to cope with increasingly complex security threats. In addition, the existing power marketing business monitoring lacks effective pre-warning and in-process monitoring mechanisms, which poses serious challenges to power data security.

[0003] In order to solve these problems, a data security identification and monitoring method for power marketing business is urgently needed to achieve real-time monitoring and rapid response to data security. Summary of the invention

[0004] The purpose of the present invention is to propose a data security identification and monitoring method for power marketing business, comprising the following steps:

[0005] Step 1: Train the initial user access abnormal behavior monitoring model based on the constructed user access abnormal behavior knowledge base to determine the target user access abnormal behavior recognition model;

[0006] Step 2: Monitor user access behavior in real time and handle abnormal behavior, generate abnormal behavior evaluation results and match them with each strategy in the preset abnormal strategy library, and select the target strategy;

[0007] Step 3: Train the sensitive data monitoring model based on the constructed data security knowledge base, determine the sensitive data monitoring model, and monitor in real time;

[0008] Step 4: Match the policies in the sensitive data risk policy library and generate corresponding sensitive data processing logs.

[0009] Step 1 specifically includes the following sub-steps:

[0010] Step 11: Collect user historical access data, system logs, and abnormal behavior reports;

[0011] Step 12: Build a user access abnormal behavior knowledge base based on the information collected in step 11;

[0012] Step 13: Build a user access abnormal behavior recognition model and train it;

[0013] Step 14: Verify and optimize the user access abnormal behavior recognition model in step 13 to obtain the target user access abnormal behavior recognition model.

[0014] The user's historical access data in step 11 includes access time, access content, and access frequency.

[0015] The user access abnormal behavior knowledge base in step 12 includes the user's normal access behavior pattern, abnormal behavior characteristics and preset abnormal behavior rules.

[0016] Abnormal behaviors include unauthorized access, data leakage, and suspicious commands.

[0017] Sensitive data includes customer information, transaction records, and marketing strategies.

[0018] The specific strategy for matching the sensitive data risk strategy library in step 4 is as follows: Search the abnormal strategy library for a strategy that is consistent with the abnormal behavior type and obtain a matching value; if there are multiple matching values, select the strategy with the highest matching value as the target strategy.

[0019] A data security identification and monitoring device for power marketing business, comprising:

[0020] The first training module is used to train the initial user access abnormal behavior monitoring model based on the constructed user access abnormal behavior knowledge base to determine the target user access abnormal behavior monitoring model;

[0021] The monitoring module is used to monitor user access behavior in real time and handle abnormal behavior, generate abnormal behavior evaluation results and match them with each strategy in the preset abnormal strategy library to select the target strategy;

[0022] The second training module is used to train the sensitive data monitoring model based on the constructed data security knowledge base, determine the sensitive data monitoring model, and monitor in real time;

[0023] The matching module is used to match the policies in the sensitive data risk policy library and generate corresponding sensitive data processing logs.

[0024] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, each step of a method for secure identification and monitoring of power marketing business data is implemented.

[0025] A storage medium stores a computer program, which, when executed by a processor, implements various steps in a method for secure identification and monitoring of power marketing business data.

[0026] The beneficial effects of the present invention are:

[0027] 1. This system relies on machine learning and deep learning technologies, has powerful intelligent recognition capabilities, and can accurately identify abnormal user access behaviors and sensitive data. With the growth of data volume and continuous training of models, the recognition accuracy of the system will continue to improve, and it will adaptively respond to increasingly complex network threats.

[0028] 2. The system has a real-time monitoring function, which can instantly analyze the user's access request. Once abnormal behavior or access to sensitive data is found, the corresponding processing flow will be triggered immediately. The efficient data processing capability ensures that the system can still maintain a fast and accurate response when facing large-scale access requests, effectively reducing the risk of data leakage.

[0029] 3. The risk strategy library allows administrators to flexibly configure and expand different risk response strategies according to actual needs, such as access control, security alarm triggering, secondary verification mechanism, etc. This flexibility enables the system to adapt to the security needs of different business scenarios and provide customized data security protection solutions.

[0030] 4. The data processing logs generated by the system record key information such as access request information, the type of sensitive data, the risk response strategies adopted, and the processing results in detail. These logs not only help administrators monitor and audit the security status of the system, but also provide strong evidence support when security incidents occur. In addition, the detailed nature of the logs also makes the system traceable and auditable, providing a basis for tracing and holding accountable data security. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 The present invention is a flow chart of a method for secure identification and monitoring of power marketing business data.

[0032] Figure 2 This is an architecture diagram of the data security identification and monitoring system for power marketing business according to the present invention.

[0033] Figure 3 This is a workflow diagram of the data security identification and monitoring system for power marketing business of the present invention. DETAILED DESCRIPTION

[0034] The present invention proposes a data security identification and monitoring method for power marketing business, which is further described below in conjunction with the accompanying drawings and specific embodiments.

[0035] Figure 1 A flowchart showing a method for secure identification and monitoring of power marketing business data according to an embodiment of the present invention includes the following steps:

[0036] Step 1: Train the initial user access abnormal behavior monitoring model based on the constructed user access abnormal behavior knowledge base to determine the target user access abnormal behavior monitoring model.

[0037] Specifically, the above step 1 includes:

[0038] S11. Collect user historical access data, system logs and abnormal behavior reports;

[0039] First, collect all the user's access data in the past period of time, including access time, access content, access frequency, etc. At the same time, obtain system logs to record detailed information about the user's interaction with the system. In addition, it is necessary to collect historical abnormal behavior reports to understand the types and characteristics of abnormal behaviors that have occurred in the past.

[0040] S12. Build a user access abnormal behavior knowledge base based on the collected user historical access data, system logs and abnormal behavior reports. The knowledge base will contain the user's normal access behavior patterns, abnormal behavior characteristics and preset abnormal behavior rules.

[0041] S13. Build a user access abnormal behavior recognition model and perform training;

[0042] Based on the data in the user access abnormal behavior knowledge base, the initial user access abnormal behavior recognition model is trained. During the training process, the processed data is divided into a training set and a test set. Through multiple iterative training, the model learns key features and abnormal behavior recognition rules.

[0043] Specifically, after building the data security knowledge base, the knowledge base is used as sample data to train the initial user access abnormal behavior recognition model. To build the user access abnormal behavior recognition model, the data must first be cleaned, the outliers are corrected or removed, and the missing values ​​are filled in by selecting appropriate filling methods based on the characteristics of the data and business logic, such as using the mean, median, mode, interpolation or specific business logic. Based on the diversity and complexity of the features, the model design includes two core components: one is to use neural network models such as Autoencoder, Isolation Forest, and One-Class SVM to identify abnormal behaviors to accurately determine the level of abnormal behaviors; the other is to use behavioral analysis algorithms such as sequence pattern mining and association rule mining to identify behavioral patterns to determine the specific type of abnormal behaviors. The processed data is divided into training sets and test sets. Through multiple iterative training, the model learns key features and user behavior rules from historical access record data, data security business knowledge, and expert user behavior analysis.

[0044] S14, validation and optimization of the model;

[0045] After training, the model is verified using the test set. The model is optimized and adjusted based on the verification results until the preset accuracy and recall requirements are met or the model converges. The target user access abnormal behavior recognition model finally obtained will be used for subsequent user access abnormal behavior detection tasks.

[0046] Step 2: Monitor user access behavior in real time and handle abnormal behavior, generate abnormal behavior evaluation results and match them with each strategy in the preset abnormal strategy library, and select the target strategy.

[0047] After building and training the user access abnormal behavior recognition model, it is necessary to monitor the user's access behavior in real time. The system will record and analyze each user's access, extract key features and compare them with the trained model.

[0048] When the system detects that the user's access behavior matches the abnormal behavior features in the trained model, the abnormal behavior identification mechanism will be triggered. The target risk identification model is used to extract features from the data to be identified, and the abnormal point type and abnormal point level of the user behavior to be identified are determined based on the extracted multiple features. Based on the abnormal point type and abnormal point level of the data to be identified, the user's abnormal behavior assessment result is generated.

[0049] Among them, in the abnormal policy library, the policies are classified and stored according to the abnormal behavior type to achieve efficient policy matching. The risk policy library contains processing rules and measures for different types of sensitive data, such as restricting access rights, triggering security alarms, and performing secondary verification. When the system detects abnormal behavior, it will traverse and search in the policy library according to the type of abnormal behavior. If a unique matching policy is found, the system will directly use the policy as the response plan; if there are multiple matching policies, the system will screen according to the matching value of each policy, and finally select the policy with the highest matching degree as the target policy output. The larger the matching value, the more consistent the policy is with the characteristics of the abnormal behavior, and the matched policy result is more suitable as a response plan for the behavior to be identified.

[0050] In addition, to further improve data security, the system can also record detailed information of abnormal behavior for subsequent analysis.

[0051] Step 3: Train the sensitive data monitoring model based on the constructed data security knowledge base, determine the sensitive data monitoring model, and implement real-time monitoring.

[0052] Specifically, the above step 3 includes:

[0053] S31. Collect sensitive data from power marketing business systems, including customer information, transaction records, marketing strategies, etc.

[0054] S32. Build a sensitive information identification model based on machine learning or deep learning methods. This model can accurately identify sensitive information in the data, such as electricity sales, electricity users, transaction types, etc.

[0055] Step 4: Match relevant policies in the sensitive data risk policy library and generate corresponding sensitive data processing logs.

[0056] According to the results of the sensitive information identification model, the sensitive data is processed accordingly. The risk scenario is matched with the desensitization strategy of each scenario in the strategy library to obtain the strategy matching value; if there are multiple strategy matching values, the strategy with the highest strategy matching value is selected as the target strategy, and the sensitive data is processed by the selected target strategy, and the data processing log is recorded. The target strategy processing methods include desensitization, encryption, anonymization, etc. to ensure the security and privacy of sensitive data. The data processing log will record in detail key information such as the access request information, the type of sensitive data, the risk response strategy adopted, and the processing results.

[0057] Figure 2The system architecture diagram of a data security identification and monitoring method for power marketing business according to an embodiment of the present invention is shown, which includes: a user access abnormal behavior detection module, an abnormal strategy matching module, a risk analysis module, a sensitive data marking module, a risk strategy matching module and a log generation module.

[0058] The abnormal behavior analysis module is used to analyze data access behavior and determine whether the current data access request behavior is an abnormal type. If so, the abnormal strategy matching module matches the relevant strategies in the abnormal strategy library and generates the corresponding abnormal behavior log. If it is not an abnormal behavior, the risk assessment process is executed.

[0059] The abnormal strategy matching module is used to match the abnormal behavior with each strategy in the preset abnormal strategy library, search for strategies consistent with the abnormal behavior type, and obtain the matching value; if there are multiple matching values, select the strategy with the highest matching value as the target strategy.

[0060] The risk analysis module is used to determine whether the data accessed by the current data access request contains sensitive data. If so, the sensitive data is marked by the sensitive data marking module to record the flow of sensitive data, and the risk strategy matching module matches the relevant strategies in the risk strategy library and generates the corresponding data processing log. If not, the data required by the access request is directly returned.

[0061] The data currently requested to be accessed may refer to power marketing business data, including but not limited to transaction electricity prices, electricity sales, electricity users, transaction types and other information.

[0062] The sensitive data marking module is used to mark sensitive data and record the flow of sensitive data. Sensitive marking can achieve data traceability, and can also regularly evaluate and analyze the risk control capabilities of various units in the security management of power marketing business data. Through problem characterization and responsibility positioning, it can promote relevant units to improve their risk prevention and control levels and ensure the security and integrity of business data.

[0063] The risk strategy matching module is used to match the sensitive data with the desensitizing strategies for each scenario in the preset risk strategy library to obtain the strategy matching value; if there are multiple strategy matching values, the strategy with the highest strategy matching value is selected as the target strategy.

[0064] Log generation module: The data processing log will record in detail key information such as access request information, type of sensitive data, risk response strategies adopted, and processing results.

[0065] Figure 3 This is a flow chart of the data security identification and monitoring system for power marketing business of the present invention; it includes the following steps:

[0066] Step 1: The server connector is used to receive data access requests and pass them to the abnormal behavior analysis module.

[0067] Step 2: Determine whether the current access behavior is abnormal and take corresponding measures.

[0068] By using the abnormal behavior analysis model trained by the abnormal behavior knowledge base to determine whether the current access behavior belongs to abnormal behaviors such as unauthorized access, data leakage, suspicious commands, etc., if it does, the information is passed to the abnormal policy matching module, so that it matches the abnormal behavior with each policy in the preset abnormal policy library, searches for the policy consistent with the abnormal behavior type, and obtains the matching value; if there are multiple matching values, the policy with the highest matching value is selected as the target policy, and the security event log is recorded.

[0069] Step 3: Determine whether the data accessed by the current data access request contains sensitive data.

[0070] The risk analysis model trained by using the risk identification knowledge base can determine whether there are current risks such as electricity fee and price business risks, metering and collection business risks, and customer service business risks. If so, it will determine which data is sensitive data by performing business sensitivity rating on the data, and send the processing results to the sensitive data marking module.

[0071] Step 4: Analyze the results of the risk identification module and mark sensitive data.

[0072] By analyzing the results of the risk identification module, the column where the sensitive data is located is determined, and data tags are added. Sensitive tags can be used to trace the data. The risk control capabilities of each unit in the security management of power marketing business data can be regularly evaluated and analyzed. Through problem characterization and responsibility positioning, relevant units can be promoted to improve the level of risk prevention and control to ensure the security and integrity of business data. After marking, the marked data will be sent to the data processing strategy module.

[0073] Step 5: Select a risk strategy to handle the marked sensitive data.

[0074] Through the data processing policy module, the risk scenario is matched with the desensitizing strategy of each scenario in the policy library to obtain the policy matching value; if there are multiple policy matching values, the policy with the highest policy matching value is selected as the target policy, and the sensitive data is processed through the selected target policy, and the data processing log is recorded.

[0075] This embodiment also includes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, each step of the method for secure identification and monitoring of power marketing business data is implemented.

[0076] A storage medium stores a computer program, which, when executed by a processor, implements various steps in a method for secure identification and monitoring of power marketing business data.

[0077] Aiming at the data security risk problem existing in the process of marketing data sharing, the present invention proposes a data security identification and monitoring method for power marketing business. Relying on machine learning and deep learning technology, it has powerful intelligent identification capabilities and can accurately identify abnormal user access behaviors and sensitive data. It realizes comprehensive and true log recording and analysis of user behaviors of accessing sensitive page data and performing key operations, and provides a one-stop data security protection system for marketing business application systems, including data monitoring, automatic risk warning, and active protection.

[0078] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0079] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0082] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0083] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A data security identification and monitoring method for power marketing business, characterized in that: The following steps are involved: Step 1: Train the initial user access abnormal behavior monitoring model based on the constructed user access abnormal behavior knowledge base to determine the target user access abnormal behavior recognition model; Step 2: Monitor user access behavior in real time and handle abnormal behavior, generate abnormal behavior evaluation results and match them with each strategy in the preset abnormal strategy library, and select the target strategy; Step 3: Train the sensitive data monitoring model based on the constructed data security knowledge base, determine the sensitive data monitoring model, and monitor in real time; Step 4: Match the policies in the sensitive data risk policy library and generate corresponding sensitive data processing logs.

2. The method for secure identification and monitoring of power marketing business data according to claim 1 is characterized in that: The step 1 specifically includes the following sub-steps: Step 11: Collect user historical access data, system logs, and abnormal behavior reports; Step 12: Build a user access abnormal behavior knowledge base based on the information collected in step 11; Step 13: Build a user access abnormal behavior recognition model and train it; Step 14: Verify and optimize the user access abnormal behavior recognition model in step 13 to obtain the target user access abnormal behavior recognition model.

3. The method for secure identification and monitoring of power marketing business data according to claim 2 is characterized in that: The user's historical access data in step 11 includes access time, access content, and access frequency.

4. The method for secure identification and monitoring of power marketing business data according to claim 2 is characterized in that: The user access abnormal behavior knowledge base in step 12 includes the user's normal access behavior pattern, abnormal behavior characteristics and preset abnormal behavior rules.

5. According to claim 1, the method for security identification and monitoring of power marketing business data is characterized in that: Abnormal behaviors include unauthorized access, data leakage, and suspicious commands.

6. The method for secure identification and monitoring of power marketing business data according to claim 1 is characterized in that: Sensitive data includes customer information, transaction records, and marketing strategies.

7. The method for secure identification and monitoring of power marketing business data according to claim 1 is characterized in that: The strategy in the sensitive data risk strategy library matched in step 4 is specifically as follows: searching the abnormal strategy library for a strategy consistent with the abnormal behavior type to obtain a matching value; if there are multiple matching values, selecting the strategy with the highest matching value as the target strategy.

8. A data security identification and monitoring device for power marketing business, characterized in that: include: The first training module is used to train the initial user access abnormal behavior monitoring model based on the constructed user access abnormal behavior knowledge base to determine the target user access abnormal behavior monitoring model; The monitoring module is used to monitor user access behavior in real time and handle abnormal behavior, generate abnormal behavior evaluation results and match them with each strategy in the preset abnormal strategy library to select the target strategy; The second training module is used to train the sensitive data monitoring model based on the constructed data security knowledge base, determine the sensitive data monitoring model, and monitor in real time; The matching module is used to match the policies in the sensitive data risk policy library and generate corresponding sensitive data processing logs.

9. An electronic 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, each step of the method for secure identification and monitoring of power marketing business data as described in any one of claims 1 to 7 is implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, each step of the method for secure identification and monitoring of power marketing business data as claimed in any one of claims 1 to 7 is implemented.

Citation Information

Cited By

  • Industrial information data security protection method and system based on machine learning

    CN119358007A

  • Electric power data safety monitoring method and system

    CN120524165A

  • Voltage sampling unit fault detection method and system based on surge impact analysis

    CN120559557A

  • Sensitive data identification and processing method and device based on deep learning, equipment, storage medium and program product

    CN121167391A

  • Blockchain-based method and system for tracing behavior of power marketing sensitive data

    CN122760063A