Information security protection method and system applied to electronic information platform

Abstract

The invention relates to the technical field of information security, and particularly discloses an information security protection method and system applied to an electronic information platform, and the method comprises the steps: collecting information data, evaluating the reliability of a data source based on a Bayesian network model, analyzing the structural integrity of the information data through an auto-encoder algorithm, and calculating a comprehensive accuracy coefficient; based on an accuracy evaluation result, extracting a data exception rate and an access exception frequency, training a decision tree model in combination with historical data, establishing a risk prediction model, and dynamically calculating a risk coefficient; according to the real-time change of the risk coefficient, generating defense strategies such as data correction, access control, flow limitation and high-risk operation isolation, and re-evaluating the risk coefficient and data accuracy of the platform after execution; potential risks can be identified, various security threats can be flexibly handled, data loss and security vulnerabilities are reduced, and the stability and the anti-risk capability of an electronic information platform are improved.

Description

Technical Field

[0001] The present invention relates to the field of information security technology, and in particular to an information security protection method and system applied to an electronic information platform. Background Art

[0002] With the continuous advancement of informatization and digitalization, electronic information platforms have become an important tool for various industries to conduct business and data management. These platforms integrate multiple functional modules, such as data storage, information exchange and access control, to provide users with convenient services. However, with the expansion of the scope of use of electronic information platforms, the security threats they face are becoming more complex, including data tampering, information leakage, access anomalies and network attacks. In addition, the quality of information data directly affects the stability and reliability of the platform. For example, the credibility of the data source, the integrity of the data structure and the accuracy of the data quality all determine the platform's ability to respond to risks. Therefore, how to effectively evaluate data quality and take protective measures against potential threats has become a key technical problem in ensuring the security of electronic information platforms.

[0003] The prior art has the following deficiencies: Existing electronic information platform security protection technologies mainly focus on traditional static rule detection and anomaly analysis based on single features. Although these methods can identify known threats to a certain extent, they are often unable to cope with complex security issues. First, the existing technology lacks a comprehensive analysis of the credibility of the data source, making it difficult to accurately assess the reliability of the data source, resulting in data quality problems that are difficult to cure. Secondly, when detecting the integrity of the data structure, the existing methods usually use fixed template matching or simple verification, which cannot effectively adapt to the characteristics of data diversity and dynamic changes. In addition, the comprehensive evaluation of data quality lacks systematicity, focusing only on a single dimension, such as data source or data format, and failing to conduct accuracy analysis from multiple angles. More importantly, the existing technology has limitations in risk prediction and defense strategy formulation. It usually uses static or predefined rules, and it is difficult to dynamically adjust the defense priority according to real-time risk changes, resulting in limited security protection effects and difficulty in responding to rapidly changing security threats and complex attack scenarios. Summary of the invention

[0004] The purpose of the present invention is to provide an information security protection method and system applied to an electronic information platform to solve the problems in the above background.

[0005] The purpose of the present invention can be achieved through the following technical solutions: The information security protection method applied to the electronic information platform includes the following steps: S1: Collect information data from the electronic information platform, analyze the credibility of the data source, and evaluate the reliability of the data source based on the analysis results; The information data includes: user data, system operation data and access control data; S2: Collect information data from the electronic information platform, analyze the structural integrity of the information data, and evaluate the integrity of the information data through historical comparison and data structure integrity; S3: Conduct a comprehensive analysis of the reliability of data sources and the integrity of information data, analyze the accuracy of information data quality, and extract accurate information data based on the analysis results; S4: Based on accurate information data, extract data anomaly rate and access anomaly frequency, establish a risk prediction model, and conduct risk prediction on the electronic information platform; S5: Based on the prediction results, dynamically generate defense strategies, including methods of data correction, strengthening access control, limiting abnormal traffic and isolating high-risk operations. After executing the defense strategy, re-evaluate the platform risk factor and data accuracy to optimize the defense effect.

[0006] As a further solution of the present invention: the information data collected from the electronic information platform, the credibility of the data source is analyzed, and the reliability of the data source is evaluated according to the analysis result, which specifically includes: Collect information data from the electronic information platform in real time, calculate the reliability coefficient of the information data based on the credibility analysis of the data source, and use it to evaluate the reliability of the data source; The process of obtaining the reliability coefficient is as follows: Identify data sources and assign initial trust parameters to each data source, where the trust of each data source is Represents the reliability of the data source, where Indicates the index of the data source. is a positive integer greater than 0: Take each data source as a node in the Bayesian network and build a Bayesian network that represents the dependency relationship between data sources. If the reliability of the data source is affected by external conditions, the external conditions serve as the parent node in the Bayesian network: The external conditions include: network environment and hardware status; For each data source node Set the prior probability distribution , indicating the data source The initial trust level of , Represents the data source The initial trust The standard deviation of confidence is: Based on the actual data observed, construct the likelihood function , indicating a given data source When the reliability of the observation data" Probability: According to Bayes' theorem, by observing the data Update the reliability of the data source and calculate the posterior probability, that is, the reliability of each data source given the observed data The updated reliability after , the calculation expression is: : In the formula, Represents the marginal likelihood of the data, which is calculated by summing the reliability of all data sources. The calculation expression is: : In the formula, Indicates the total number of data sources: According to the posterior probability , calculate the reliability coefficient of each data source, the calculation expression is: : In the formula, Indicates The reliability coefficient of the data source.

[0007] As a further solution of the present invention: the information data collected from the electronic information platform, the structural integrity of the information data is analyzed, and the integrity of the information data is evaluated through historical comparison and data structural integrity, specifically including: Collect information data from the electronic information platform in real time, analyze the structural integrity of the information data, calculate the integrity coefficient based on the analysis results through historical comparison and data structure integrity, and use it to evaluate the integrity of the information data; The process of obtaining the integrity coefficient is as follows: The real-time data collected by the electronic information platform is represented as the input data set : High-dimensional input data Mapping to low-dimensional latent space , the calculation expression is: : In the formula, represents the encoded low-dimensional representation, The encoder weight matrix, represents the bias vector of the encoder, Represents the activation function: The representation of the implicit space Reconstructing back to the original space, the calculation expression is: : In the formula, Represents the reconstructed data, represents the decoder weight matrix, Represents the bias vector of the decoder: The model parameters are optimized by minimizing the reconstruction error, and the loss function is: : In the formula, represents the overall loss, represents the number of data points, represents the total number of data points, Indicates Items of data, Indicates Reconstructed data: For each piece of data, the reconstruction error is calculated, and the calculation expression is: : in, Indicates Reconstruction error of the data: The integrity coefficient of each piece of data is calculated based on the reconstruction error. The calculation expression is: : In the formula, Indicates The integrity coefficient of the data, represents the error normalization parameter.

[0008] As a further solution of the present invention: the comprehensive analysis of the reliability of the data source and the integrity of the information data, and the analysis of the accuracy of the information data quality, specifically includes: Obtain the reliability coefficient and integrity coefficient of the information data, perform normalized calculations on the reliability coefficient and integrity coefficient of the information data, and calculate the accuracy coefficient to evaluate the accuracy of the information data.

[0009] As a further solution of the present invention: the extraction of accurate information data specifically includes: Determine whether the accuracy coefficient is greater than or equal to a preset threshold. If so, it means that the data quality of the corresponding information data is accurate, and the information data is extracted. If not, it means that the data quality of the corresponding information data is inaccurate, and the information data is corrected.

[0010] As a further solution of the present invention: based on accurate information data, extracting data anomaly rate and access anomaly frequency, and establishing a risk prediction model, specifically includes: By analyzing the historical data of the electronic information platform, the reliability coefficient, integrity coefficient, accuracy coefficient, access anomaly frequency and data anomaly rate are calculated as training data to train the risk assessment model. The risk assessment model in the present invention is a decision tree model, and the construction process is: Through the historical data of the electronic information platform, the reliability coefficient, completeness coefficient, accuracy coefficient, access anomaly frequency and data anomaly rate are extracted as input features to construct a data set; The information gain statistical method is used to select features to ensure that the input features accurately predict the risk coefficient; Through the recursive splitting process, the decision tree is constructed. When splitting nodes, information gain is used as the metric, and the features that reduce data uncertainty are selected as splitting features; At each layer of decision tree nodes, calculate the current feature pair output target Contribution to optimizing the splitting rule: The output target is a risk factor; The tree height and leaf node size of the decision tree are tuned according to the training data; Use cross-validation to evaluate the model and use pruning techniques to reduce overfitting; Set the pruning threshold and decide whether to prune based on the difference between the training error and the validation error; According to the trained decision tree model, the risk coefficient of each data point is output.

[0011] As a further solution of the present invention: the risk prediction of the electronic information platform specifically includes: According to the output results of the risk prediction model, the risk coefficient is calculated, and the calculation expression is: Based on the structure of the decision tree model and the weighted value of the input features, a calculation formula for the risk coefficient is designed. The calculation expression is: : In the formula, , , , , Represents the weight coefficient determined by decision tree training, reflecting the influence of each feature on the final risk factor, and satisfies , Indicates the risk factor: in, represents the data reliability coefficient, represents the data integrity coefficient, represents the accuracy coefficient, Indicates the abnormal frequency of data access. The maximum access exception frequency of the data, represents the number of data points, Indicates Abnormal rate of data: Determine whether the risk factor is greater than or equal to the preset threshold. If so, issue a risk warning. If not, continue real-time monitoring.

[0012] As a further solution of the present invention: the dynamically generating a defense strategy according to the prediction result specifically includes: Based on real-time calculated risk factor , combined with the current security status of the platform , calculate the defense priority through the defense priority calculation expression : The defense priority calculation expression is: : In the formula, Indicates the defense priority. and Indicates the preset scale factor: The safety status includes the presence of risk and the absence of risk; Update defense priorities based on changes in real-time data; Based on the calculated defense priorities and in combination with specific risk types, the following different defense strategies are designed, including: If the risk factor contains data accuracy issues, data correction measures will be automatically initiated; If the risk factor shows that the platform access is frequently abnormal, enable the access control policy; If the risk factor shows that there are abnormal patterns in network traffic, the traffic restriction mechanism is activated; After executing the defense strategy, the effectiveness of the defense strategy is evaluated by monitoring the risk factor and data accuracy of the platform in real time.

[0013] Information security protection systems applied to electronic information platforms include: A data collection and data reliability assessment module, which collects information data from the electronic information platform, analyzes the credibility of the data source, and assesses the reliability of the data source based on the analysis results; A data integrity assessment module, which collects information data from the electronic information platform, analyzes the structural integrity of the information data, and assesses the integrity of the information data through historical comparison and data structural integrity; A data accuracy assessment module, which performs a comprehensive analysis on the reliability of the data source and the integrity of the information data, analyzes the accuracy of the information data quality, and extracts accurate information data based on the analysis results; A risk prediction module, which extracts data anomaly rate and access anomaly frequency based on accurate information data, establishes a risk prediction model, and performs risk prediction on the electronic information platform; A dynamic defense module dynamically generates defense strategies based on prediction results, including methods for data correction, enhanced access control, limiting abnormal traffic, and isolating high-risk operations. After executing the defense strategy, the platform risk factor and data accuracy are re-evaluated to optimize the defense effect.

[0014] Beneficial effects of the present invention: (1) The present invention uses a comprehensive application of Bayesian network models, autoencoder algorithms and decision tree models to deeply mine and evaluate the data quality and security of electronic information platforms. In the credibility analysis of data sources, the reliability coefficient of the data source is quantified and updated, and the accuracy of the data source evaluation is effectively improved by dynamically adjusting the trust parameters. At the same time, through deep learning processing of data structure integrity, not only can the missing or damaged parts in the data be accurately identified and repaired, but the data integrity evaluation of the platform can also be further optimized by minimizing the reconstruction error. Combined with the risk prediction function of the decision tree model, the present invention can construct a comprehensive risk assessment model based on input features of multiple dimensions including: reliability coefficient, integrity coefficient and accuracy coefficient, automatically identify potential security threats and quantify risk coefficients. This efficient and intelligent risk identification and early warning mechanism can not only reveal the security risks existing in the platform in advance, but also dynamically adjust the defense strategy based on real-time monitoring, thereby significantly reducing the probability of data loss, information leakage and other security vulnerabilities, and providing a comprehensive, accurate and efficient data security protection solution for electronic information platforms; (2) The present invention innovatively adopts an intelligent method of dynamically generating defense strategies, which can flexibly adjust the protection priority to cope with the diverse security threats faced by the platform according to the risk coefficient and security status calculated in real time. Under the guidance of the risk prediction results, the present invention designs a highly targeted defense mechanism, including data correction, access control, traffic restriction, and isolation of high-risk operations. Among them, through automated data correction means, data integrity and accuracy problems caused by collection or transmission are repaired; through precise access control strategies, abnormal access behaviors are interrupted to avoid malicious attacks and unauthorized operations; through the dynamic mechanism of limiting abnormal traffic, potential network attack risks can be quickly curbed. After the defense strategy is executed, the present invention introduces a closed-loop mechanism of real-time evaluation and optimization to further calibrate the risk coefficient and data accuracy of the platform. This dynamic and adaptive protection system can not only significantly improve the overall security of the electronic information platform, but also enhance its stability and risk resistance in complex and changing environments, ensuring that the platform can still operate efficiently and maintain data integrity and reliability when facing potential threats. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below in conjunction with the accompanying drawings.

[0016] Figure 1 It is a flowchart of the specific steps of the information security protection method applied to the electronic information platform of the present invention; Figure 2 It is a flowchart of the information security protection system applied to the electronic information platform in the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] See also Figure 1 As shown, the present invention is an information security protection method applied to an electronic information platform, comprising the following steps: S1: Collect information data from the electronic information platform, analyze the credibility of the data source, and evaluate the reliability of the data source based on the analysis results; The information data includes: user data, system operation data and access control data; S2: Collect information data from the electronic information platform, analyze the structural integrity of the information data, and evaluate the integrity of the information data through historical comparison and data structure integrity; S3: Conduct a comprehensive analysis of the reliability of data sources and the integrity of information data, analyze the accuracy of information data quality, and extract accurate information data based on the analysis results; S4: Based on accurate information data, extract data anomaly rate and access anomaly frequency, establish a risk prediction model, and conduct risk prediction on the electronic information platform; S5: Based on the prediction results, dynamically generate defense strategies, including methods of data correction, strengthening access control, limiting abnormal traffic and isolating high-risk operations. After executing the defense strategy, re-evaluate the platform risk factor and data accuracy to optimize the defense effect.

[0019] In S1, information data from the electronic information platform is collected, the credibility of the data source is analyzed, and the reliability of the data source is evaluated based on the analysis results, including: Collect information data from the electronic information platform in real time, calculate the reliability coefficient of the information data based on the credibility analysis of the data source, and use it to evaluate the reliability of the data source; The process of obtaining the reliability coefficient is as follows: Identify data sources and assign initial trust parameters to each data source, where the trust of each data source is , represents the reliability of the data source, where Indicates the index of the data source. is a positive integer greater than 0: Take each data source as a node in the Bayesian network and build a Bayesian network that represents the dependency relationship between data sources. If the reliability of the data source is affected by external conditions, the external conditions serve as the parent node in the Bayesian network. The external conditions include: network environment and hardware status; For each data source node Set the prior probability distribution , indicating the data source The initial trust level of , Represents the data source The initial trust Represents the standard deviation of confidence: Based on the actual data observed, construct the likelihood function , indicating that a given data source When the reliability of the observation data Probability: According to Bayes' theorem, by observing the data Update the reliability of the data source and calculate the posterior probability , that is, each data source has a given observation data The updated reliability after , the calculation expression is: : In the formula, Represents the marginal likelihood of the data, which is calculated by summing the reliability of all data sources. The calculation expression is: : In the formula, Indicates the total number of data sources: According to the posterior probability , calculate the reliability coefficient of each data source, the calculation expression is: : In the formula, Indicates Reliability coefficients of data sources: It should be noted that the reliability coefficient of the information data source reflects the reliability of the source of the data, and the larger the value of the reliability coefficient, the higher the corresponding data reliability.

[0020] In S2, the information data of the electronic information platform is collected, and the structural integrity of the information data is analyzed. The integrity of the information data is evaluated through historical comparison and data structure integrity, including: Collect information data from the electronic information platform in real time, analyze the structural integrity of the information data, calculate the integrity coefficient based on the analysis results through historical comparison and data structure integrity, and use it to evaluate the integrity of the information data; The process of obtaining the integrity coefficient is as follows: The real-time data collected by the electronic information platform is represented as the input data set : High-dimensional input data Mapping to low-dimensional latent space , the calculation expression is: : In the formula, represents the encoded low-dimensional representation, The encoder weight matrix, represents the bias vector of the encoder, Represents the activation function: The representation of the implicit space Reconstructing back to the original space, the calculation expression is: : In the formula, Represents the reconstructed data, represents the decoder weight matrix, Represents the bias vector of the decoder: The model parameters are optimized by minimizing the reconstruction error, and the loss function is: : In the formula, represents the overall loss, represents the number of data points, represents the total number of data points, Indicates Items of data, Indicates Reconstructed data: For each piece of data, the reconstruction error is calculated, and the calculation expression is: : in, Indicates Reconstruction error of the data: The integrity coefficient of each piece of data is calculated based on the reconstruction error. The calculation expression is: : In the formula, Indicates The integrity coefficient of the data, Represents the error normalization parameter: It should be noted that the data integrity coefficient reflects the data integrity of the information data when it is collected, and the larger the value of the data integrity coefficient is, the higher the corresponding data integrity is.

[0021] In S3, the reliability of data sources and the integrity of information data are comprehensively analyzed, the accuracy of information data quality is analyzed, and accurate information data is extracted based on the analysis results, including: Obtaining the reliability coefficient and integrity coefficient of the information data, performing normalized calculation processing on the reliability coefficient and integrity coefficient of the information data, and calculating the accuracy coefficient for evaluating the accuracy of the information data; The calculation expression of the accuracy coefficient is: : In the formula, and is the preset scale factor, and and All are greater than 0, e represents the logarithm of the base of a natural number, represents the reliability coefficient of the data, Indicates the integrity coefficient of the data, Represents the accuracy coefficient of the data.

[0022] It should be noted that the accuracy coefficient of data reflects the accuracy of the data quality of the information data, and when the value of the accuracy coefficient of data is larger, the corresponding data quality accuracy is higher.

[0023] In S4, based on accurate information data, the data anomaly rate and access anomaly frequency are extracted to establish a risk prediction model to predict the risk of the electronic information platform, including: By analyzing the historical data of the electronic information platform, the reliability coefficient, integrity coefficient, accuracy coefficient, access anomaly frequency and data anomaly rate are calculated as training data to train the risk assessment model. The risk assessment model in the present invention is a decision tree model, and the construction process is: Through the historical data of the electronic information platform, the reliability coefficient, completeness coefficient, accuracy coefficient, access anomaly frequency and data anomaly rate are extracted as input features to construct a data set; The information gain statistical method is used to select features to ensure that the input features accurately predict the risk coefficient; Through the recursive splitting process, the decision tree is constructed. When splitting nodes, information gain is used as the metric, and the features that reduce data uncertainty are selected as splitting features; At each layer of decision tree nodes, calculate the current feature pair output target Contribution,optimizing the splitting rules; The output target is a risk factor; The tree height and leaf node size of the decision tree are tuned according to the training data; Use cross-validation to evaluate the model and use pruning techniques to reduce overfitting; Set the pruning threshold and decide whether to prune based on the difference between the training error and the validation error; According to the trained decision tree model, the risk coefficient of each data point is output; According to the output results of the risk prediction model, the risk coefficient is calculated, and the calculation expression is: Based on the structure of the decision tree model and the weighted value of the input features, a calculation formula for the risk coefficient is designed. The calculation expression is: : In the formula, , , , , Represents the weight coefficient determined by decision tree training, reflecting the influence of each feature on the final risk factor, and satisfies , Indicates the risk factor: in, represents the data reliability coefficient, represents the data integrity coefficient, represents the accuracy coefficient, Indicates the abnormal frequency of data access. The maximum access exception frequency of the data, represents the number of data points, Indicates Abnormal rate of data: Determine whether the risk factor is greater than or equal to the preset threshold. If so, issue a risk warning. If not, continue real-time monitoring.

[0024] It should be noted that the risk coefficient reflects the security level of the information data, and when the value of the risk coefficient is larger, the corresponding information data has a lower data security level.

[0025] In S5, based on the prediction results, defense strategies are dynamically generated, including methods for data correction, strengthening access control, limiting abnormal traffic, and isolating high-risk operations. After executing the defense strategy, the platform risk factor and data accuracy are re-evaluated to optimize the defense effect, including: Based on real-time calculated risk factor , combined with the current security status of the platform , calculate the defense priority through the defense priority calculation expression : The defense priority calculation expression is: : In the formula, Indicates the defense priority. and Indicates the preset scale factor: The safety status includes the presence of risk and the absence of risk; Update defense priorities based on changes in real-time data; Based on the calculated defense priorities and in combination with specific risk types, the following different defense strategies are designed, including: If the risk factor contains data accuracy issues, data correction measures will be automatically initiated; If the risk factor shows that the platform access is frequently abnormal, enable the access control policy; If the risk factor shows that there are abnormal patterns in network traffic, the traffic restriction mechanism is activated; After executing the defense strategy, the effectiveness of the defense strategy is evaluated by monitoring the risk factor and data accuracy of the platform in real time.

[0026] See also Figure 2 As shown, the information security protection system applied to the electronic information platform includes: A data collection and data reliability assessment module, which collects information data from the electronic information platform, analyzes the credibility of the data source, and assesses the reliability of the data source based on the analysis results; A data integrity assessment module, which collects information data from the electronic information platform, analyzes the structural integrity of the information data, and assesses the integrity of the information data through historical comparison and data structural integrity; A data accuracy assessment module, which performs a comprehensive analysis on the reliability of the data source and the integrity of the information data, analyzes the accuracy of the information data quality, and extracts accurate information data based on the analysis results; A risk prediction module, which extracts data anomaly rate and access anomaly frequency based on accurate information data, establishes a risk prediction model, and performs risk prediction on the electronic information platform; A dynamic defense module dynamically generates defense strategies based on prediction results, including methods for data correction, enhanced access control, limiting abnormal traffic, and isolating high-risk operations. After executing the defense strategy, the platform risk factor and data accuracy are re-evaluated to optimize the defense effect.

[0027] The working principle of the present invention is: by collecting various types of information data of the platform and conducting a comprehensive analysis thereof, potential security risks are timely identified and defense strategies are automatically generated. First, user data, system operation data and access control data of the platform are collected in real time, and the credibility of the data source is analyzed. The reliability coefficient of each data source is calculated through the Bayesian network model to evaluate the credibility of the data source; then, the integrity of the information data is evaluated through historical comparison and data structure integrity analysis, and the integrity coefficient of the data is further calculated; then, the reliability coefficient and the integrity coefficient are combined to calculate the accuracy coefficient of the data and evaluate the accuracy of the data quality; on this basis, the data anomaly rate and access anomaly frequency are extracted, and the decision tree model is used for risk prediction to calculate the risk coefficient; finally, based on the risk prediction results, a defense strategy is dynamically generated, including data correction, access control enhancement, traffic restriction and high-risk operation isolation. After executing the defense strategy, the platform will re-evaluate the risk coefficient and data accuracy in real time to optimize the defense effect. The present invention comprehensively considers the reliability of data sources, data integrity and accuracy, combines risk prediction models and intelligent defense strategy generation, improves the security protection capabilities of electronic information platforms, and promptly responds to and mitigates potential security threats, thereby ensuring the long-term stable operation of the platform and data security.

[0028] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0029] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0030] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0031] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0032] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An information security protection method applied to an electronic information platform, characterized in that: The following steps are involved: 1S1: Collect information data from the electronic information platform, analyze the credibility of the data source, and evaluate the reliability of the data source based on the analysis results; The information data includes: user data, system operation data and access control data; S2: Collect information data from the electronic information platform, analyze the structural integrity of the information data, and evaluate the integrity of the information data through historical comparison and data structure integrity; S3: Conduct a comprehensive analysis of the reliability of data sources and the integrity of information data, analyze the accuracy of information data quality, and extract accurate information data based on the analysis results; S4: Based on accurate information data, extract data anomaly rate and access anomaly frequency, establish a risk prediction model, and conduct risk prediction on the electronic information platform; S5: Based on the prediction results, dynamically generate defense strategies, including methods of data correction, strengthening access control, limiting abnormal traffic and isolating high-risk operations. After executing the defense strategy, re-evaluate the platform risk factor and data accuracy to optimize the defense effect.

2. The information security protection method applied to the electronic information platform according to claim 1 is characterized in that: The information data collected from the electronic information platform is analyzed for the credibility of the data source, and the reliability of the data source is evaluated based on the analysis results, specifically including: Collect information data from the electronic information platform in real time, calculate the reliability coefficient of the information data based on the credibility analysis of the data source, and use it to evaluate the reliability of the data source; The process of obtaining the reliability coefficient is as follows: Identify data sources and assign initial trust parameters to each data source, where the trust of each data source is , represents the reliability of the data source, where Indicates the index of the data source. is a positive integer greater than 0; Take each data source as a node in the Bayesian network and build a Bayesian network that represents the dependency relationship between data sources. If the reliability of the data source is affected by external conditions, the external conditions serve as the parent node in the Bayesian network. The external conditions include: network environment and hardware status; For each data source node Set the prior probability distribution , indicating the data source The initial trust level of , Represents the data source The initial trust represents the standard deviation of trust; Based on the actual data observed, construct the likelihood function , indicating that a given data source When the reliability of the observation data The probability of According to Bayes' theorem, by observing the data Update the reliability of the data source and calculate the posterior probability , that is, each data source has a given observation data The updated reliability after , the calculation expression is: ； In the formula, Represents the marginal likelihood of the data, which is calculated by summing the reliability of all data sources. The calculation expression is: ： In the formula, Represents the marginal likelihood of the data, which is calculated by summing the reliability of all data sources. The calculation expression is: ： In the formula, Indicates the total number of data sources: According to the posterior probability , calculate the reliability coefficient of each data source, the calculation expression is: ： In the formula, Indicates The reliability coefficient of the data source.

3. The information security protection method applied to the electronic information platform according to claim 1 is characterized in that: The information data collected from the electronic information platform is analyzed for structural integrity of the information data, and the integrity of the information data is evaluated through historical comparison and data structural integrity, specifically including: Collect information data from the electronic information platform in real time, analyze the structural integrity of the information data, calculate the integrity coefficient based on the analysis results through historical comparison and data structure integrity, and use it to evaluate the integrity of the information data; The process of obtaining the integrity coefficient is as follows: The real-time data collected by the electronic information platform is represented as the input data set : High-dimensional input data Mapping to low-dimensional latent space , the calculation expression is: ： In the formula, represents the encoded low-dimensional representation, The encoder weight matrix, represents the bias vector of the encoder, Represents the activation function: The representation of the implicit space Reconstructing back to the original space, the calculation expression is: ： In the formula, represents the overall loss, represents the number of data points, represents the total number of data points, Indicates Items of data, Indicates Reconstructed data: For each piece of data, the reconstruction error is calculated, and the calculation expression is: ： in, Indicates Reconstruction error of the data: The integrity coefficient of each piece of data is calculated based on the reconstruction error. The calculation expression is: ： In the formula, Indicates The integrity coefficient of the data, represents the error normalization parameter.

4. The information security protection method applied to the electronic information platform according to claim 1 is characterized in that: The above-mentioned comprehensive analysis of the reliability of data sources and the integrity of information data, and analysis of the accuracy of information data quality, specifically includes: Obtain the reliability coefficient and integrity coefficient of the information data, perform normalized calculations on the reliability coefficient and integrity coefficient of the information data, and calculate the accuracy coefficient to evaluate the accuracy of the information data.

5. The information security protection method applied to the electronic information platform according to claim 1 is characterized in that: The extraction of accurate information data specifically includes: Determine whether the accuracy coefficient is greater than or equal to a preset threshold. If so, it means that the data quality of the corresponding information data is accurate, and the information data is extracted. If not, it means that the data quality of the corresponding information data is inaccurate, and the information data is corrected.

6. The information security protection method applied to the electronic information platform according to claim 1 is characterized in that: Based on accurate information data, the data anomaly rate and access anomaly frequency are extracted to establish a risk prediction model, which specifically includes: By analyzing the historical data of the electronic information platform, the reliability coefficient, integrity coefficient, accuracy coefficient, access anomaly frequency and data anomaly rate are calculated as training data to train the risk assessment model. The risk assessment model in the present invention is a decision tree model, and the construction process is: Through the historical data of the electronic information platform, the reliability coefficient, completeness coefficient, accuracy coefficient, access anomaly frequency and data anomaly rate are extracted as input features to construct a data set; The information gain statistical method is used to select features to ensure that the input features accurately predict the risk coefficient; Through the recursive splitting process, the decision tree is constructed. When splitting nodes, information gain is used as the metric, and the features that reduce data uncertainty are selected as splitting features; At each layer of decision tree nodes, calculate the current feature pair output target Contribution to optimizing the splitting rule: The output target is a risk factor; The tree height and leaf node size of the decision tree are tuned according to the training data; Use cross-validation to evaluate the model and use pruning techniques to reduce overfitting; Set the pruning threshold and decide whether to prune based on the difference between the training error and the validation error; According to the trained decision tree model, the risk coefficient of each data point is output.

7. The information security protection method applied to the electronic information platform according to claim 1 is characterized in that: The risk prediction of the electronic information platform specifically includes: According to the output results of the risk prediction model, the risk coefficient is calculated, and the calculation expression is: Based on the structure of the decision tree model and the weighted value of the input features, a calculation formula for the risk coefficient is designed. The calculation expression is: ： In the formula, , , , , Represents the weight coefficient determined by decision tree training, reflecting the influence of each feature on the final risk factor, and satisfies , represents the risk factor: in, represents the data reliability coefficient, represents the data integrity coefficient, represents the accuracy coefficient, represents the abnormal access frequency of data, and the maximum abnormal access frequency of data. represents the number of data points, Indicates Abnormal rate of data: Determine whether the risk factor is greater than or equal to the preset threshold. If so, issue a risk warning. If not, continue real-time monitoring.

8. The information security protection method applied to the electronic information platform according to claim 1 is characterized in that: The dynamically generating defense strategy according to the prediction result specifically includes: Based on real-time calculated risk factor , combined with the current security status of the platform , calculate the defense priority through the defense priority calculation expression : The defense priority calculation expression is: ： In the formula, Indicates the defense priority. and Indicates the preset scale factor: The safety status includes the presence of risk and the absence of risk; Update defense priorities based on changes in real-time data; Based on the calculated defense priorities and in combination with specific risk types, the following different defense strategies are designed, including: If the risk factor contains data accuracy issues, data correction measures will be automatically initiated; If the risk factor shows that the platform access is frequently abnormal, enable the access control policy; If the risk factor shows that there are abnormal patterns in network traffic, the traffic restriction mechanism is activated; After executing the defense strategy, the effectiveness of the defense strategy is evaluated by monitoring the risk factor and data accuracy of the platform in real time.

9. An information security protection system applied to an electronic information platform, characterized in that: The information security protection method applied to an electronic information platform as claimed in any one of claims 1 to 8 comprises: A data collection and data reliability assessment module, which collects information data from the electronic information platform, analyzes the credibility of the data source, and assesses the reliability of the data source based on the analysis results; A data integrity assessment module, which collects information data from the electronic information platform, analyzes the structural integrity of the information data, and assesses the integrity of the information data through historical comparison and data structural integrity; A data accuracy assessment module, which performs a comprehensive analysis on the reliability of the data source and the integrity of the information data, analyzes the accuracy of the information data quality, and extracts accurate information data based on the analysis results; A risk prediction module, which extracts data anomaly rate and access anomaly frequency based on accurate information data, establishes a risk prediction model, and performs risk prediction on the electronic information platform; A dynamic defense module dynamically generates defense strategies based on prediction results, including methods for data correction, enhanced access control, limiting abnormal traffic, and isolating high-risk operations. After executing the defense strategy, the platform risk factor and data accuracy are re-evaluated to optimize the defense effect.

Images