Data security detection method, computer equipment and medium based on artificial intelligence
By collecting and preprocessing network data in data security detection, extracting features, establishing intelligent detection models and using blockchain storage, the problem of difficulty in taking into account efficiency and accuracy in the existing technology is solved, and a more efficient and accurate network is achieved Data security detection and protection.
Patent Information
- Application Number
- CN202410115727.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-29
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-01-29
AI Technical Summary
Current data security detection methods based on artificial intelligence are difficult to take into account efficiency and accuracy when processing large-scale and diversified network data, and have poor real-time learning results, resulting in poor performance when encountering new threats.
By collecting network data and pre-processing, extracting network data security features, establishing an intelligent data security detection model for real-time monitoring and processing, and storing data through blockchain for protection, and formulating corresponding security processing measures.
It improves the accuracy and efficiency of data processing, enhances the security detection and protection capabilities of network data, and has higher efficiency and accuracy when processing large-scale and diversified network data.
Smart Images

Figure CN117955863B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data security detection, and in particular to a data security detection method and system based on artificial intelligence. Background Art
[0002] With the rapid development of network technology, the advent of the big data era has led to an exponential growth in the amount of network data. In this context, the importance of network data security has become increasingly prominent. In recent years, data security detection methods based on artificial intelligence have become a hot topic of research. The core of this method is to use artificial intelligence algorithms to analyze and process huge network data to identify and prevent security threats. Traditional data security detection methods mostly rely on rules and signature matching, which are difficult to adapt to the challenges of new and complex attack methods. With the development of machine learning and deep learning technologies, the research on intelligent data security detection models has gradually deepened. These models can learn and identify complex data patterns, thereby effectively identifying unknown security threats. However, current methods often find it difficult to balance efficiency and accuracy when processing large-scale and diverse network data. Poor real-time learning results lead to poor performance when encountering new threats. Summary of the invention
[0003] In view of the problems existing in the above-mentioned existing artificial intelligence-based data security detection methods and systems, the present invention is proposed.
[0004] Therefore, the problem to be solved by the present invention is that the current methods often find it difficult to strike a balance between efficiency and accuracy when processing large-scale, diverse network data, and the poor real-time learning effect leads to poor performance when encountering new threats.
[0005] To solve the above technical problems, the present invention provides the following technical solutions: an artificial intelligence-based data security detection method, which includes collecting and preprocessing network data, extracting network data security features; establishing an intelligent data security detection model, monitoring network data in real time and formulating security processing measures; storing network data through blockchain and performing data security protection.
[0006] As a preferred solution of the artificial intelligence-based data security detection method described in the present invention, the collection and preprocessing of network data refers to collecting network data through network traffic sensors and performing cleaning, filtering, format conversion, filling in missing values, and unifying network data timestamps.
[0007] As a preferred solution of the artificial intelligence-based data security detection method of the present invention, wherein: the extraction of network data security features refers to using an algorithm to extract features from pre-processed network data:
[0008]
[0009] F(D) is the feature vector extracted from the data set D, n is the number of features, ω i is the weight of the i-th feature, ν ij is the importance coefficient of the i-th feature in the j-th dimension, g j (D) is the j-th dimension information extracted from the data set D, m is the number of data dimensions, and h jl is the lth coefficient of the jth dimension, D l is the lth dimension of the dataset D, α is the adjustment parameter, β l is the filter coefficient.
[0010] As a preferred solution of the artificial intelligence-based data security detection method of the present invention, wherein: the establishment of an intelligent data security detection model and real-time monitoring of network data includes the following steps:
[0011] The extracted data features are used to form training sample sets and test sample sets, and an intelligent data security detection model algorithm is constructed:
[0012]
[0013] Where S(F) is the data security score, the threshold is [0,1], a k and b k is the model parameter, F k is the kth feature extracted from the training sample set, u k is the weight of the kth feature;
[0014] Set the loss function to:
[0015]
[0016] Where q is the number of training samples, y r is the actual label value of the rth training sample, S(F r ) is the data security score of the rth training sample, F r is the feature vector of the rth training sample, λ is the regularization parameter, θ k is the model parameter of the kth feature, including a k 、b k and u k ;
[0017] Calculate the model parameter gradient and update the model parameters iteratively:
[0018]
[0019]
[0020] in is the model parameter gradient, S(F r ) about θ k The partial derivative of , η is the learning rate;
[0021] At the end of each iteration, the test sample set is used to calculate the model loss function value until the loss function value no longer decreases significantly or the predetermined number of iterations is reached, and the iteration is stopped to complete the training of the intelligent data security detection model. The intelligent data security detection model is used to monitor the network data in real time and calculate the data security score S(F). The data security score S(F) is numerically compared with the set thresholds S1 and S2 to determine the network data security, where 0<S1<S2<1;
[0022] If S(F)<S1, it means that the network data is abnormal;
[0023] If S1≤S(F)<S2, it means that there is a potential threat to the network data;
[0024] If S(F)≥S2, it means that the network data is secure.
[0025] As a preferred solution of the artificial intelligence-based data security detection method of the present invention, the formulation of security processing measures refers to formulating corresponding security processing measures according to the judgment results of the intelligent data security detection model, including:
[0026] If the network data is safe, the collection and detection of network data will continue, and the detection and judgment results will be sent to the staff for review and recording;
[0027] If there is a potential threat in the network data, an early warning notification will be sent to the staff, and the collected network data packets will be sent simultaneously to assist the staff in eliminating and correcting the potential threat data, and a processing record will be generated after the potential threat is processed;
[0028] If there are any anomalies in the network data, an alarm notification will be immediately sent to the staff, and the network data will be redirected to the security analysis sandbox. The collected network data will be isolated at the same time. The entire process of the staff's analysis of the network data to detect the cause of the anomaly will be recorded, and an anomaly elimination record will be generated after the anomaly is eliminated.
[0029] As a preferred solution of the artificial intelligence-based data security detection method described in the present invention, wherein: the data storage through blockchain refers to the collection of network data, extracted network data security features, trained model parameters, data security scores and judgment results, set thresholds and security processing measures to form a data combination package and store it through blockchain.
[0030] As a preferred solution of the artificial intelligence-based data security detection method described in the present invention, the data security protection refers to encrypting the data package after it is formed, setting access rights, and generating data access records for synchronous storage when the data package needs to be accessed.
[0031] The data security detection system based on artificial intelligence is characterized by comprising: an acquisition module, an analysis module, a processing module and a storage module;
[0032] The acquisition module is used to collect network data and pre-process the network data;
[0033] The analysis module is used to extract network data features and establish and train an intelligent data security detection model to analyze network data security;
[0034] The processing module is used to implement corresponding processing measures according to the analysis results of the network data security by the analysis module;
[0035] The storage module is used to store all data through the blockchain, and cooperate with other modules to call and supervise the data in the database.
[0036] A computer device comprises: a memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the above-mentioned artificial intelligence-based data security detection method are implemented.
[0037] A computer-readable storage medium having a computer program stored thereon, characterized in that: when the computer program is executed by a processor, the steps of the above-mentioned artificial intelligence-based data security detection method are implemented.
[0038] The beneficial effects of the present invention are as follows: the present invention collects network data and extracts feature vectors, uses the feature vectors to establish and train an intelligent data security detection model to detect network data, thereby judging the security status of network data and taking corresponding processing measures, thereby improving the accuracy and efficiency of data processing, enhancing the network data security detection and protection capabilities, and having higher efficiency and accuracy when processing large-scale and diversified network data. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0040] Figure 1The figure is a flowchart of the data security detection method based on artificial intelligence.
[0041] Figure 2 This is a schematic diagram of the structure of the data security detection system based on artificial intelligence. DETAILED DESCRIPTION
[0042] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.
[0043] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0044] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.
[0045] Example 1
[0046] Reference Figure 1 , which is the first embodiment of the present invention, and this embodiment provides a data security detection method based on artificial intelligence, and the data security detection method based on artificial intelligence includes the following steps:
[0047] S1, collect and pre-process network data to extract network data security features;
[0048] Specifically, collecting network data and preprocessing means collecting network data through network traffic sensors and performing cleaning, filtering, and format conversion to fill in missing values, as well as unifying network data timestamps.
[0049] The data collected by network traffic sensors can provide a comprehensive perspective on network behavior, which is the basis for identifying network threats and optimizing network performance. The cleaning and filtering steps can improve the quality of data and the reliability of analysis. In the field of network security, this step is critical for identifying real security threats and reducing false alarms. The unified format allows data from different sources to be compared and integrated on the same analysis platform, which is particularly important for building a comprehensive network security view. The effective filling of missing values can ensure the consistency and completeness of data analysis, thereby improving the accuracy and reliability of analysis. The unification of timestamps is crucial for tracking and analyzing the temporal relationship of network events, which helps to identify the time, duration and frequency of attacks, and analyze the time trend of network behavior.
[0050] Specifically, extracting network data security features refers to using algorithms to extract features from pre-processed network data:
[0051]
[0052] F(D) is the feature vector extracted from the data set D, n is the number of features, ω i is the weight of the i-th feature, obtained through historical data, ν ij is the importance coefficient of the i-th feature in the j-th dimension, which is used to quantify the importance of a specific feature in a specific dimension and is obtained through historical data. j (D) is the j-th dimension information extracted from the data set D, m is the number of data dimensions, and h jl is the lth coefficient of the jth dimension, determined by experiments, D l is the lth dimension of the dataset D, α is the adjustment parameter, β l is the filter coefficient, and tanh is the hyperbolic tangent function, which is used for normalization.
[0053] Using algorithms to extract features from preprocessed network data is a key step in machine learning and data analysis. This helps identify and analyze key patterns and trends in network data and provide support for network security strategies. Determining feature weights and importance coefficients through historical data helps improve the accuracy of the model. It ensures that the model pays more attention to features that are more critical to security analysis. Considering multiple dimensions of network data helps to comprehensively analyze network activities. This multi-dimensional analysis method can provide deeper insights and help to more effectively identify complex security threats. The coefficients determined through experiments can make the model more adaptable to specific network environments. This customized method improves the adaptability and flexibility of the model. The use of adjustment parameters and filter coefficients can further optimize the data processing process, reduce errors, and improve the quality of data analysis. Using the hyperbolic tangent function for data normalization can make the data processed by the algorithm more stable and consistent, which helps to improve the overall performance of the algorithm.
[0054] S2. Establish an intelligent data security detection model to monitor network data in real time and formulate security processing measures;
[0055] Specifically, establishing an intelligent data security detection model to monitor network data in real time includes the following steps:
[0056] The extracted data features are used to form training sample sets and test sample sets, and an intelligent data security detection model algorithm is constructed:
[0057]
[0058] Where S(F) is the data security score, the threshold is [0,1], a k and b k is the model parameter obtained through training, F k is the kth feature extracted from the training sample set, u k is the weight of the kth feature;
[0059] Set the loss function to:
[0060]
[0061] Where q is the number of training samples, y r is the actual label value of the rth training sample, 0 represents safety, 1 represents anomaly, S(F r ) is the data security score of the rth training sample, F r is the feature vector of the rth training sample, λ is the regularization parameter used to prevent the model from overfitting, and θ k is the model parameter of the kth feature, including a k 、b k and u k ;
[0062] Calculate the model parameter gradient and update the model parameters iteratively:
[0063]
[0064] in is the model parameter gradient, S(F r ) about θ k The partial derivative of , η is the learning rate, and it is a positive number used to control the step size of parameter update;
[0065] At the end of each iteration, the model loss function value is calculated using the test sample set until the loss function value no longer decreases significantly or reaches the predetermined number of iterations, and the iteration is stopped to complete the training of the intelligent data security detection model. The network data is monitored in real time through the intelligent data security detection model and the data security score S(F) is calculated. The data security score S(F) is numerically compared with the set thresholds S1 and S2 to determine the network data security, where 0<S1<S2<1. In this embodiment, S1 is set to 0.33 and S2 is set to 0.67;
[0066] If S(F)<S1, it means that the network data is abnormal;
[0067] If S1≤S(F)<S2, it means that there is a potential threat to the network data;
[0068] If S(F)≥S2, it means that the network data is secure.
[0069] Through data security scoring, the intelligent data security detection model can quantify the security level of network data. This quantification method provides a more detailed security status judgment than a simple "safe" or "unsafe" label, which helps to more accurately identify and deal with potential security threats. Setting different thresholds allows the system to distinguish different levels of security threats, such as "abnormal", "potential threat" and "safe". This layered risk assessment method makes security response more flexible and targeted, and helps to reduce false positives and false negatives. By using data features for training sample sets and test sample sets, the intelligent model can learn to identify complex patterns and trends related to network security. This feature-based learning method makes the model more effective in detecting new or changing security threats. By setting the loss function and using regularization parameters to prevent overfitting, the generalization ability of the model is enhanced, which improves the prediction accuracy of the model on unknown data. By calculating the gradient of the model parameters and continuously updating them, the model is continuously optimized during each iteration, which ensures that the model can adapt to new data patterns and continuously improve its security detection capabilities. By real-time monitoring and scoring of network data, the model can instantly identify abnormalities or potential threats and take necessary security measures in a timely manner, thereby effectively preventing network attacks and security risks.
[0070] Furthermore, formulating security processing measures refers to formulating corresponding security processing measures according to the judgment results of the intelligent data security detection model, including:
[0071] If the network data is safe, the collection and detection of network data will continue, and the detection and judgment results will be sent to the staff for review and recording;
[0072] If there is a potential threat in the network data, an early warning notification will be sent to the staff, and the collected network data packets will be sent simultaneously to assist the staff in eliminating and correcting the potential threat data, and a processing record will be generated after the potential threat is processed;
[0073] If there are any anomalies in the network data, an alarm notification will be immediately sent to the staff, and the network data will be redirected to the security analysis sandbox. The collected network data will be isolated at the same time. The entire process of the staff's analysis of the network data to detect the cause of the anomaly will be recorded, and an anomaly elimination record will be generated after the anomaly is eliminated.
[0074] When the data is judged to be safe, the system continues to collect and detect network data and sends the results to staff for review and recording. This continuous monitoring and recording is essential to maintaining the overall security of the network environment and provides valuable data for future analysis. When potential threats are detected, the system immediately sends an early warning notification to the staff and provides relevant data to help them quickly identify and deal with these threats. This rapid response mechanism can effectively prevent potential threats from developing into serious problems and ensure network security. When network data is identified as abnormal, the system will immediately send an alert to the staff and redirect the data to the security analysis sandbox for further analysis. At the same time, the collected network data will be isolated to prevent the spread of potential malicious activities. This process is recorded throughout to ensure that the cause of the abnormality can be accurately found and resolved. This timely exception handling and detailed recording are extremely critical to preventing network attacks and reducing damages. It not only improves the response speed and efficiency of network security, but also helps to continuously improve future security strategies and response mechanisms through detailed recording and analysis.
[0075] S3, store network data through blockchain and protect data security;
[0076] Specifically, storing network data through blockchain means forming a data package of collected network data, extracted network data security features, trained model parameters, data security scores and judgment results, set thresholds and security processing measures and storing them through blockchain.
[0077] By storing key network data and related information on the blockchain, it can be ensured that the data is not tampered with, and the integrity and reliability of the data can be improved. The encryption characteristics and decentralized storage mechanism of the blockchain provide an additional layer of security for the stored data, which is crucial for protecting sensitive network data and analysis results. The transparency and immutability of blockchain technology allow all data changes to be tracked and verified, which is very useful for data audits and compliance checks. The data stored on the blockchain can be used for further analysis and decision support, which is of great value for understanding network security trends and formulating effective strategies. The distributed nature of the blockchain makes data sharing and cooperation easier and safer, and helps to establish a cross-institutional or cross-industry network security cooperation mechanism.
[0078] Specifically, data security protection refers to encrypting the data package after it is formed, setting access permissions, and generating and synchronously storing data access records when the data package needs to be accessed.
[0079] By encrypting the data package, the sensitive information contained in it can be protected from unauthorized access and leakage, which is crucial to maintaining the confidentiality and integrity of the data, especially when processing network data containing sensitive information. By setting access permissions for the data package, the access and processing capabilities of different users to the data can be precisely controlled, which not only improves the security of the data, but also helps to comply with data protection regulations and standards. Access records are generated every time a data package is accessed, which can provide complete tracking and auditing of data access behavior, which is very useful for monitoring data usage, preventing unauthorized access and analyzing data access patterns.
[0080] Example 2
[0081] Reference Figure 2 , which is the second embodiment of the present invention, and which is different from the previous embodiment, provides a data security detection system based on artificial intelligence, characterized in that it includes an acquisition module, an analysis module, a processing module and a storage module;
[0082] The acquisition module is used to collect network data and pre-process the network data;
[0083] The analysis module is used to extract network data features and establish and train an intelligent data security detection model to analyze network data security;
[0084] The processing module is used to implement corresponding processing measures according to the analysis results of the network data security by the analysis module;
[0085] The storage module is used to store all network data through the blockchain, and cooperate with other modules to call and supervise the data in the database.
[0086] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.
[0087] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0088] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.
[0089] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0090] Example 3
[0091] This is the third embodiment of the present invention. This embodiment is different from the previous two embodiments. In order to verify the beneficial effects of the method of the present invention, the method of the present invention is compared with the prior art to demonstrate and prove the comparison results. Table 1 shows.
[0092] Table 1: Comparison table of the method of the present invention and prior art experiments
[0093]
[0094] As can be summarized in the above table, the significant innovation and advantages of the method of the present invention compared with the prior art not only improve the efficiency and accuracy of data security detection, but also improve the security and monitoring capabilities of network data by introducing threshold settings and the generation of data access records. It shows excellent performance in the field of network data security detection and effectively improves the overall security level of the network environment.
[0095] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.
Claims
1. The data security detection method based on artificial intelligence is characterized by: include, Collect and pre-process network data to extract network data security features; Establish an intelligent data security detection model to monitor network data in real time and formulate security processing measures; Use blockchain to store network data and protect data security; The network data collection and preprocessing refers to collecting network data through network traffic sensors and performing cleaning, filtering, format conversion, filling missing values, and unifying network data timestamps; Extracting network data security features refers to extracting features from pre-processed network data using an algorithm: Where F(D) is the feature vector extracted from the dataset D, n is the number of features, ω i is the weight of the i-th feature, ν ij is the importance coefficient of the i-th feature in the j-th dimension, g j (D) is the j-th dimension information extracted from the dataset D, m is the number of data dimensions, h jl is the lth coefficient of the jth dimension, D l is the lth dimension of the dataset D, α is the adjustment parameter, β l is the filter coefficient; The establishment of an intelligent data security detection model to monitor network data in real time includes the following steps: The extracted data features are used to form training sample sets and test sample sets, and an intelligent data security detection model algorithm is constructed: Where S(F) is the data security score, the threshold is [0,1], a k and b k is the model parameter, F k is the kth feature extracted from the training sample set, u k is the weight of the kth feature; Set the loss function to: Where q is the number of training samples, y r is the actual label value of the rth training sample, S(F r ) is the data security score of the rth training sample, F r is the feature vector of the rth training sample, λ is the regularization parameter, θ k is the model parameter of the kth feature; Calculate the model parameter gradient and update the model parameters iteratively: in is the model parameter gradient, S(F r ) about θ k The partial derivative of , η is the learning rate; At the end of each iteration, the model loss function value is calculated using the test sample set until the loss function value no longer decreases significantly or the predetermined number of iterations is reached. The iteration is stopped to complete the training of the intelligent data security detection model. The intelligent data security detection model is used to monitor network data in real time and calculate the data security score S(F). The data security score S(F) is numerically compared with the set thresholds S1 and S2 to judge the network data security, where 0<S1<S2<1; If S(F)<S1, it means that there is an anomaly in the network data; If S1≤S(F)<S2, it means that there is a potential threat to the network data; If S(F)≥S2, it means that the network data is secure; The storage of network data through blockchain refers to the storage of collected network data, extracted network data security features, trained model parameters, data security scores and judgment results, set thresholds and security processing measures into a data package through blockchain.
2. The artificial intelligence-based data security detection method according to claim 1, wherein: The formulation of security processing measures refers to formulating corresponding security processing measures based on the judgment results of the intelligent data security detection model, including: If the network data is safe, continue to collect and test the network data, and send the test results and judgment results to the staff for review and recording; If there is a potential threat to network data, an early warning notification will be sent to the staff, and the collected network data will be sent simultaneously to assist the staff in eliminating and correcting the potential threat data. After the potential threat is handled, a processing record will be generated; If there is an anomaly in the network data, an alarm notification will be sent to the staff immediately, and the network data will be redirected to the security analysis sandbox. The collected network data will be isolated at the same time. The entire process of the staff's analysis of the network data to detect the cause of the anomaly will be recorded, and an anomaly elimination record will be generated after the anomaly is eliminated.
3. The artificial intelligence-based data security detection method according to claim 2, characterized in that: The data security protection refers to encrypting the data package after it is formed, setting access rights, and generating and synchronously storing data access records when the data package needs to be accessed.
4. A computer device comprising: memory and processor; The memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.
5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.
Citation Information
Patent Citations
SQL statement safety detection method and device based on machine learning, equipment and medium
CN111783132A
Network security monitoring method and device based on situation awareness, equipment and medium
CN111786950A
Network data security monitoring method and system
CN116405310A
Intelligent data monitoring system and method for Internet information security
CN116723034A
Power communication equipment data anomaly detection method and system and storage medium
CN117034180A
