Data security management method, device and equipment for power grid infrastructure and medium

Abstract

The invention discloses a data security management method, device and equipment for power grid infrastructure and a medium, and the method comprises the steps: obtaining a user authority level of a user in response to a viewing instruction of the user for power grid infrastructure data; according to the first power grid infrastructure data checked by the user, the encryption level of the first power grid infrastructure data is determined; based on the user permission level and the encryption level, judging whether the user meets a viewing condition; if the user conforms to the viewing condition, screening first power grid infrastructure data conforming to the user permission level and the encryption level; and if the user does not meet the viewing condition, screening second power grid infrastructure data and sending the second power grid infrastructure data to the user based on the user permission level and the first power grid infrastructure data. According to the method, the security of the power grid infrastructure data can be effectively improved, so that the data is prevented from being leaked and tampered.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of information data management, and in particular to a data security management method, device and equipment for power grid infrastructure and a medium. BACKGROUND

[0002] With the rapid development of information technology, electricity is the foundation and support for the stable development of social economy. Power data is related to people's livelihood and involves the privacy of many power users. If data misuse, leakage and other security incidents occur, it will have an adverse impact on power production, management, user service and social stability. Therefore, ensuring the security of power grid infrastructure data is of great significance to maintaining social stability.

[0003] At present, the data management method for power grid infrastructure is to establish a power grid infrastructure database, and then integrate related data in the whole cycle of power grid equipment planning, design, construction, operation, idling and scrap, and store all related data in the power grid infrastructure database. However, due to the wide range of power grid infrastructure data sources, involving multiple departments and units, data sharing between different departments and units, data management is difficult, data security is difficult to guarantee, and once the power grid infrastructure data is leaked or tampered with, it is difficult to accurately track the source of the leak due to the involvement of multiple links and multiple responsible persons, which will cause significant economic losses to the relevant departments of the power grid infrastructure. SUMMARY

[0004] The purpose of the present application is to overcome the problems of wide range of power grid infrastructure data sources, involving multiple departments and units and data sharing between different departments and units, different importance of power grid infrastructure data and different personnel access permissions, resulting in management difficulties and difficult data security, and to provide a data security management method for power grid infrastructure.

[0005] To achieve the above purpose, the technical solution of the present application is:

[0006] In a first aspect, the present application provides a data security management method for power grid infrastructure, the management method comprising:

[0007] In response to a user's viewing instruction for power grid infrastructure data, obtaining the user's user permission level;

[0008] According to the viewing instruction, identifying the first power grid infrastructure data that the user wants to view, and determining the encryption level of the first power grid infrastructure data;

[0009] Based on the user permission level and the encryption level, determining whether the user meets the viewing condition;

[0010] If the user meets the viewing condition, the first power grid infrastructure data is sent to the user;

[0011] if the user does not meet the viewing condition, filtering second power grid infrastructure data based on the user permission level and the first power grid infrastructure data to send to the user.

[0012] determining the encryption level of the first power grid infrastructure data, comprising:

[0013] obtaining the to-be-analyzed sensitivity data and the to-be-analyzed importance data of the first power grid infrastructure data;

[0014] based on the to-be-analyzed sensitivity data, performing sensitivity evaluation on the first power grid infrastructure data to determine the sensitivity of the first power grid infrastructure data;

[0015] based on the to-be-analyzed importance data, performing importance evaluation on the first power grid infrastructure data to determine the importance of the first power grid infrastructure data;

[0016] constructing a sensitivity-importance matrix through the sensitivity and the importance of the first power grid infrastructure data to determine the encryption level of the first power grid infrastructure data.

[0017] obtaining the to-be-analyzed sensitivity data of the first power grid infrastructure data, comprising: extracting sensitive words in the first power grid infrastructure data, quantizing the data category corresponding to the first power grid infrastructure data and the sensitive words to obtain a corresponding sensitive feature vector, and taking the sensitive feature vector as the to-be-analyzed sensitivity data corresponding to the first power grid infrastructure data;

[0018] obtaining the to-be-analyzed importance data of the first power grid infrastructure data, comprising: extracting important words in the first power grid infrastructure data, quantizing the data category corresponding to the first power grid infrastructure data and the important words to obtain a corresponding important feature vector, and taking the important feature vector as the to-be-analyzed importance data corresponding to the first power grid infrastructure data.

[0019] extracting sensitive words in the first power grid infrastructure data comprises:

[0020] collecting power grid design, construction, and operation related data, and classifying the data to form a plurality of categories of power grid infrastructure corpus, each category of power grid infrastructure corpus containing one category of power grid infrastructure data;

[0021] preprocessing the data in the power grid infrastructure corpus, the preprocessing comprising: removing stop words, word segmentation, part-of-speech tagging, and uniform terminology processing;

[0022] using the TF-IDF method to extract, in different categories of power grid infrastructure corpus, words with a frequency higher than a preset threshold and related to data security as candidate sensitive words for the corresponding data category.

[0023] obtaining a data category corresponding to the first power grid infrastructure data and all candidate sensitive words corresponding to the data category;

[0024] taking the sensitive words appearing in the first power grid infrastructure data as the sensitive words of the first power grid infrastructure data.

[0025] determining the sensitivity of the first power grid infrastructure data, comprising:

[0026] obtaining a data category of power grid infrastructure data and sensitive words corresponding thereto;

[0027] inputting the data category and the sensitive words into an initial neural network model to train the initial neural network model to obtain a sensitivity analysis model;

[0028] inputting the sensitive data to be analyzed of the first power grid infrastructure data into the sensitivity analysis model to obtain the sensitivity of the first power grid infrastructure data;

[0029] determining the importance of the first power grid infrastructure data, comprising:

[0030] obtaining a data category of power grid infrastructure data and important words corresponding thereto;

[0031] inputting the data category and the important words into an initial neural network model to train the initial neural network model to obtain an importance analysis model;

[0032] inputting the important data to be analyzed of the first power grid infrastructure data into the sensitivity analysis model to obtain the importance of the first power grid infrastructure data.

[0033] constructing a sensitivity-importance matrix through the sensitivity and the importance of the first power grid infrastructure data to determine the encryption level of the first power grid infrastructure data, comprising:

[0034] taking the sensitivity as the vertical axis of the sensitivity-importance matrix and taking the importance as the horizontal axis of the sensitivity-importance matrix;

[0035] constructing a matrix based on the vertical axis and the horizontal axis of the sensitivity-importance matrix;

[0036] mapping the sensitivity and the importance of the first power grid infrastructure data into the matrix, and determining the encryption level of the first power grid infrastructure data according to a preset mapping rule of the sensitivity-importance matrix and the encryption level.

[0037] filtering second power grid infrastructure data to be sent to a user based on the user permission level and the first power grid infrastructure data, comprising:

[0038] obtaining a viewing range of the user authority level;

[0039] extracting a keyword in the first power grid infrastructure data;

[0040] filtering second power grid infrastructure data based on the keyword within the viewing range;

[0041] sending the second power grid infrastructure data to the user.

[0042] In a second aspect, the present application provides a data security management device for power grid infrastructure, which is used to execute the data security management method for power grid infrastructure as described above, and specifically comprises:

[0043] a response module, configured to obtain a user authority level of a user in response to a viewing instruction of the user on power grid infrastructure data;

[0044] an encryption level determination module, configured to identify first power grid infrastructure data that the user wants to view according to the viewing instruction, and determine an encryption level of the first power grid infrastructure data;

[0045] a judgment module, configured to judge whether the user meets a viewing condition based on the user authority level and the encryption level;

[0046] a data sending module, configured to send the first power grid infrastructure data to the user when the user meets the viewing condition, and filter second power grid infrastructure data based on the user authority level and the first power grid infrastructure data to send the second power grid infrastructure data to the user when the user does not meet the viewing condition.

[0047] In a third aspect, the present application provides a data security management device for power grid infrastructure, which comprises a memory and a processor, wherein the memory is configured to store computer program codes and transmit the computer program codes to the processor;

[0048] the processor is configured to execute the data security management method for power grid infrastructure as described above according to instructions in the computer program codes.

[0049] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program; the computer program is executed by a processor to implement steps in the data security management method for power grid infrastructure as described above.

[0050] Compared with the prior art, the present application can effectively prevent unauthorized users from accessing sensitive or confidential information by determining whether the user meets the viewing conditions through the user's permission level and the encryption level of the data. And dynamically filter and provide data according to the user's permission and data encryption level. For users who do not meet the viewing conditions, the system can automatically filter and provide other data suitable for their permission level, improving the flexibility and convenience of data use. At the same time, users will only see the data they have the right to view, which avoids users from being exposed to information they do not need or should not see, thereby reducing confusion and unnecessary interference. Not only enhances the security of data, but also improves the flexibility and efficiency of data management, optimizes the user experience, and promotes the compliance of the organization. It is of great significance to protect the sensitive information of power grid infrastructure projects, ensure the safe use of data, and support the overall business objectives of the organization. BRIEF DESCRIPTION OF DRAWINGS

[0051] Figure 1 is a flowchart of a data security management method for power grid infrastructure provided by an embodiment of the present application.

[0052] Figure 2 is a schematic diagram of a sensitivity-importance matrix provided by an embodiment of the present application.

[0053] Figure 3 is a structural schematic diagram of a data security management device for power grid infrastructure provided by an embodiment of the present application.

[0054] Figure 4 is a structural schematic diagram of a data security management device for power grid infrastructure provided by an embodiment of the present application. DETAILED DESCRIPTION

[0055] The present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0056] In order to solve the technical problems existing in the related art, an embodiment of the present application provides a data security management method for power grid infrastructure, please refer to Figure 1 , comprising:

[0057] S110, in response to a user's viewing instruction for power grid infrastructure data, obtaining the user's user permission level;

[0058] S120, according to the viewing instruction, identifying the first power grid infrastructure data that the user wants to view, and determining the encryption level of the first power grid infrastructure data;

[0059] S130, based on the user permission level and the encryption level, determining whether the user meets the viewing conditions;

[0060] S140, if the user meets the viewing condition, screening the first power grid infrastructure data meeting the user permission level and encryption level, and sending the screened first power grid infrastructure data to the user;

[0061] If the user does not meet the viewing condition, based on the user permission level and the first power grid infrastructure data, screening the second power grid infrastructure data and sending it to the user.

[0062] First, in response to the user's viewing instruction of the power grid infrastructure data, the user's permission level is obtained. After the system receives the user's instruction to view the power grid infrastructure data, the system needs to verify the user's identity first, which can be obtained through the relevant information of the user's login account. After verifying the user's identity, the user's permission level is obtained. The user permission level is a predefined level or role, such as "administrator", "advanced user", "ordinary user" and so on, each level or role corresponds to different data access permissions. According to the user's permission level, it is checked whether the user has the right to view the requested power grid infrastructure data.

[0063] Secondly, according to the first power grid infrastructure data viewed by the user, the encryption level of the first power grid infrastructure data is determined. In this embodiment, the first power grid infrastructure data is the power grid infrastructure data viewed by the user, that is, the system receives the user's request to view specific power grid infrastructure data, and identifies the specific power grid infrastructure data item that the user wants to view according to the content of the request. The system queries the database or configuration file to obtain the encryption level information of the data item. The encryption level of the data item is determined according to the sensitivity, importance and potential security risk of the data. For example, data involving business secrets or personal privacy may have a higher encryption level. The encryption level can be an identifier, such as "confidential", "secret", "public" and so on, and then the encryption level of the first power grid infrastructure data is determined.

[0064] Next, based on the user's permission level and encryption level, determine whether the user meets the viewing conditions. First, the system needs to obtain the current user's permission level, which is completed through user identity authentication and access control system. The system will assign the corresponding permission level according to the user's identity (such as username, role, position, etc.). Then, the system needs to determine the encryption level of the power grid infrastructure data that the user wants to view, which can be achieved by querying data metadata or access control list (ACL), which clearly marks the sensitivity and encryption requirements of the data. Compare the user's permission level with the encryption level of the data to determine whether the user meets the viewing conditions. If the user's permission level is higher than or equal to the required permission level of the data's encryption level, the system determines that the user meets the viewing conditions and allows the user to view the data. If the user's permission level is lower than the required permission level of the data's encryption level, the system determines that the user does not meet the viewing conditions and denies the user's viewing request. At the same time, the system can return an error message to the user or prompt the user to contact the administrator to obtain higher access permissions.

[0065] If the user meets the viewing conditions, filter the first power grid infrastructure data that meets the user's permission level and encryption level. Specifically, when the user meets the viewing conditions, the system determines the range of power grid infrastructure data that needs to be filtered according to the user's request, including specific regions, time ranges, project types, etc. Within the data range, the system filters out data items that meet the user's permission level and encryption level by using the user's permission level and encryption level as filtering conditions. The filtered data items are sorted (for example, by time, project name, etc.) and the first data item is selected as the result and returned to the user. If the power grid infrastructure data is stored in a database, the filtering can be achieved through an SQL query statement. The query statement should include the comparison conditions of the user's permission level and encryption level, as well as the sorting and selection of the first result logic.

[0066] If the user does not meet the viewing conditions, filter the second power grid infrastructure data based on the user's permission level and the first power grid infrastructure data and send it to the user. Specifically, if the user's permission level is lower than the required permission level of the first power grid infrastructure data, or the data encryption level is higher than the user's viewable range, it is determined that the user does not meet the viewing conditions. Then, based on the user's permission level, determine the criteria for filtering the second power grid infrastructure data, including factors such as data sensitivity and importance. In the database, search for other power grid infrastructure data within the user's permission level viewable range based on the keywords in the first power grid infrastructure data, and sort the searched power grid infrastructure data based on the keywords. The data can be sorted according to the update time, relevance factors, etc. The first data item after sorting is selected as the second power grid infrastructure data, which is sent to the user.

[0067] By judging whether the user meets the viewing conditions through the user's permission level and the data encryption level, unauthorized users can be effectively prevented from accessing sensitive or confidential information. And according to the user's permission and data encryption level, data is dynamically filtered and provided; at the same time, for users who do not meet the viewing conditions, the system can automatically filter and provide other data suitable for their permission level, improving the flexibility and convenience of data use. In this mode, users will only see the data they have the right to view, avoiding users from accessing information they do not need or should not see, thereby reducing confusion and unnecessary interference, enhancing the security of data, improving the flexibility and efficiency of data management, optimizing user experience, and promoting the compliance of the organization. It is of great significance to protect the sensitive information of power grid infrastructure projects, ensure the safe use of data, and support the overall business objectives of the organization.

[0068] In one embodiment of the present embodiment, the data security management method for power grid infrastructure further comprises:

[0069] S210, all power grid infrastructure data is obtained, and the power grid infrastructure data is filtered to determine the confidentiality level corresponding to the power grid infrastructure data;

[0070] S220, based on the confidentiality level, selecting the corresponding encryption algorithm to encrypt the data and determining the encryption level of the data;

[0071] S230, according to the encryption level, set the access permission range.

[0072] All power grid infrastructure data can be obtained by using the internal information system of the power enterprise, such as data center, ERP system, etc. to query the basic data of power grid infrastructure project. After obtaining the power grid infrastructure data, it needs to be filtered to determine the confidentiality level corresponding to the power grid infrastructure data, which can be judged in terms of sensitivity and importance of data. Since the power grid infrastructure data may involve sensitive information such as trade secrets or personal privacy, the data needs to be classified and managed according to its importance and sensitivity. For example, data related to national security needs to take more stringent security measures; for enterprise internal trade secrets, it can be circulated within a certain range, but needs to be marked as "internal material, pay attention to save".

[0073] Based on the degree of confidentiality, select the corresponding encryption algorithm to encrypt the data, determine the encryption level of the data, that is, according to the degree of confidentiality of the power grid infrastructure data, select the corresponding encryption algorithm, for example, high-level confidential data uses high-level encryption algorithm, and medium-level confidential data uses medium-level encryption algorithm. Suitable for highly sensitive data, such as state secrets, trade secrets, etc., use high-level encryption algorithm (such as AES-256) and long key length, and implement strict key management and access control. The medium-level encryption algorithm is suitable for general sensitive data, such as enterprise internal work secrets, uses medium-strength encryption algorithm (such as AES-128) and appropriate key length, and implements basic key management and access control. Low-level encryption is suitable for non-sensitive data or scenarios requiring lower security, which can use weaker encryption algorithms or shorter key lengths, but still needs to ensure basic data integrity and confidentiality.

[0074] Next, according to the encryption level, set the access permission range, the encryption level includes low-level encryption, medium-level encryption and high-level encryption. Low-level encryption is suitable for non-sensitive data or scenarios requiring lower security. Medium-level encryption is suitable for general sensitive data, such as enterprise internal work secrets. High-level encryption is suitable for highly sensitive data, such as state secrets, trade secrets, etc. The access permission range of low-level encryption can be to allow enterprise internal employees or specific partners to access, which requires simple identity verification, such as username and password. The access permission range of medium-level encryption can be to limit access permission to employees in specific departments or positions, which requires more stringent identity verification, such as multi-factor authentication, and for external partners, may need to sign a confidentiality agreement and limit access time and range. The access permission range of high-level encryption can be strictly limited to a small number of core employees or senior management. For external access, strict approval process and monitoring measures may be required, and in some cases, external access may be completely prohibited.

[0075] By accurately identifying the data confidentiality, enhancing the pertinence of data encryption, clearly defining the access permission range, promoting the compliance of data management, and improving the flexibility and scalability of data processing, it provides a strong guarantee for the security management of power grid infrastructure data.

[0076] The encryption level of the first power grid infrastructure data provided by the embodiment can be obtained according to its sensitivity and importance, in an embodiment of the embodiment, the encryption level of the first power grid infrastructure data is determined according to the first power grid infrastructure data viewed by the user, including:

[0077] S310, based on the first power grid infrastructure data, obtaining the first power grid infrastructure data to be analyzed sensitive data and to be analyzed important data;

[0078] S320, performing sensitivity evaluation on the first power grid infrastructure data based on the to-be-analyzed sensitivity data, to determine the sensitivity of the first power grid infrastructure data;

[0079] S330, performing importance evaluation on the first power grid infrastructure data based on the to-be-analyzed importance data, to determine the importance of the first power grid infrastructure data;

[0080] S340, constructing a sensitivity-importance matrix by the sensitivity and the importance of the first power grid infrastructure data, to determine the encryption level of the first power grid infrastructure data.

[0081] The to-be-analyzed sensitivity data and the to-be-analyzed importance data of the first power grid infrastructure data are obtained respectively. In this embodiment, the to-be-analyzed sensitivity data is a comprehensive feature vector formed after quantitative processing of the "data category" and "sensitive word" of the power grid infrastructure data. The comprehensive feature vector is composed of sensitive words and data category features.

[0082] The power grid infrastructure data can be divided into multiple data categories corresponding to sensitive words according to data dimensions, such as device-related data categories, construction-related data categories, and project management-related data categories. The sensitive words can be automatically extracted based on the data categories, that is, for different data categories, high-frequency appearing and data security related words are automatically extracted from historical data using text mining technology. For example, "substation coordinates" appear frequently in design drawings and are related to security risks, and will be automatically identified as sensitive words. Words related to key power facilities such as "main substation" and "dispatching center", as well as "user number" and words related to address identification, will also be automatically identified as sensitive words due to the involvement of private information.

[0083] For different data categories, high-frequency appearing and data security related words can be automatically extracted from historical power grid infrastructure data as sensitive words using text mining technology. In an implementation manner of this embodiment, the extraction of sensitive words in the first power grid infrastructure data includes the steps in S311 to S315.

[0084] S311, collecting historical power grid design, construction, and operation and maintenance related data, and classifying the data to form multiple categories of power grid infrastructure corpus. Each power grid infrastructure corpus of a category contains power grid infrastructure data of the category. The categories of the power grid infrastructure data include device-related data, construction-related data, and project management-related data.

[0085] S312, preprocessing the data in the power grid infrastructure corpus, which includes removing stop words, word segmentation, part-of-speech tagging, and uniform term processing. For example, "substation coordinates" is standardized to a uniform format and expression.

[0086] S313, using the TF-IDF method, extracting the words with a frequency higher than a preset threshold and related to data security from the power grid infrastructure corpus of different categories as candidate sensitive words of the corresponding data category.

[0087] TF-IDF (Term Frequency-Inverse Document Frequency) is a widely used weighting statistical method in the field of information retrieval and text mining, which is used to evaluate the importance of a word to a specific document set or a document in a corpus. Its core idea is to combine term frequency (TF) and inverse document frequency (IDF) to quantify the local importance of a word in a document and the global scarcity of a word in a corpus, so as to extract and weight the keywords.

[0088] S314, obtaining the data category corresponding to the first power grid infrastructure data and all candidate sensitive words corresponding to the data category;

[0089] S315, taking the sensitive words appearing in the first power grid infrastructure data as the sensitive words of the first power grid infrastructure data.

[0090] In this embodiment, the to-be-analyzed importance data can reflect a set of information reflecting the close degree of association between the first power grid infrastructure data and the safe operation of the power grid. The to-be-analyzed importance data is also a comprehensive feature vector formed after the "data category" and "important word" of the power grid infrastructure data are quantitatively processed. According to the data dimension of the power grid infrastructure data, the power grid infrastructure data is divided into multiple data categories, such as equipment-related data category, construction-related data category, etc. Each data category has its corresponding important word. The important word can be realized by word frequency statistics from multiple data categories corresponding to the important word. Specifically, the candidate important word in each data category can be extracted by an OCR (Optical Character Recognition) model, or the candidate important word in each data category can be extracted by presetting the important word. The frequency of each candidate important word is calculated, and the important word with a frequency greater than a threshold is selected to obtain the important word corresponding to each data category. For any first power grid infrastructure data, its data category and important word are obtained, and the data category and important word are concatenated to construct a comprehensive feature vector corresponding to the important word, i.e. the to-be-analyzed importance data.

[0091] In one embodiment of this embodiment, obtaining the to-be-analyzed sensitivity data of the first power grid infrastructure data includes: extracting the sensitive words in the first power grid infrastructure data, and obtaining the corresponding sensitive feature vector after quantitatively processing the data category and sensitive words corresponding to the first power grid infrastructure data. The sensitive feature vector is taken as the to-be-analyzed sensitivity data corresponding to the first power grid infrastructure data.

[0092] Subsequently, based on the to-be-analyzed sensitivity data, sensitivity evaluation is performed on the first power grid infrastructure data to determine the sensitivity of the first power grid infrastructure data. Specifically, the to-be-analyzed sensitivity data obtained previously is input into the trained sensitivity analysis model to determine the sensitivity of the first power grid infrastructure data, wherein the trained sensitivity analysis model is trained by using multiple data categories and sensitive words, that is, the data categories and corresponding sensitive words are used as training samples, and the training samples are labeled to determine the corresponding known sensitivity, such as high, medium, and low. The model learns the feature rules of the training samples to learn how to determine the sensitivity according to the data categories and sensitive words, and finally obtains the trained sensitivity analysis model. For example, the data category of safety emergency + the keyword of large-area power outage plan corresponds to high sensitivity, and the data category of ordinary construction log + the keyword of daily attendance record corresponds to low sensitivity. The sensitivity of the first power grid infrastructure data is determined by using the trained sensitivity analysis model.

[0093] In an embodiment of the present embodiment, obtaining the to-be-analyzed importance data of the first power grid infrastructure data includes extracting important words in the first power grid infrastructure data, and obtaining corresponding important feature vectors after quantizing the data categories and important words corresponding to the first power grid infrastructure data, and taking the important feature vectors as the to-be-analyzed importance data corresponding to the first power grid infrastructure data.

[0094] Subsequently, based on the to-be-analyzed importance data, importance evaluation is performed on the first power grid infrastructure data to determine the importance of the first power grid infrastructure data. Specifically, the to-be-analyzed importance data obtained previously is input into the trained sensitivity analysis model to determine the importance of the first power grid infrastructure data. In the present embodiment, the importance of the first power grid infrastructure data includes the data category of economic benefit, that is, the data category and important words corresponding to the economic benefit are input into the trained importance analysis model to determine the importance of the first power grid infrastructure data. The trained importance analysis model is trained by using multiple data categories and important words, that is, the data categories and corresponding important words are used as training samples, and the training samples are labeled to determine the corresponding known importance, and the model learns the feature rules of the training samples to learn how to determine the importance according to the data categories and important words, and finally obtains the trained importance analysis model.

[0095] Then, a sensitivity-importance matrix is constructed by the sensitivity and importance of the first power grid infrastructure data to determine the encryption level of the first power grid infrastructure data. In the embodiment, the sensitivity of the first power grid infrastructure data includes device location sensitivity, user privacy sensitivity and power grid topology sensitivity, and the importance of the first power grid infrastructure data includes the importance of the region where the power grid device is located. Specifically, the importance of the region where the power grid device is located includes population density, economic activity and power grid hub geographic location in the region where the power grid device is located.

[0096] In one implementation of the embodiment, the sensitivity-importance matrix is constructed by the sensitivity and importance of the first power grid infrastructure data to determine the encryption level of the first power grid infrastructure data, which specifically includes the following steps:

[0097] The device location sensitivity, user privacy sensitivity and power grid topology sensitivity are analyzed by the analytic hierarchy process to determine the assigned weight, and the assigned weight, device location sensitivity, user privacy sensitivity and power grid topology sensitivity are used for weighted summation calculation to obtain a comprehensive sensitivity score;

[0098] According to the population density index, economic activity and power grid hub geographic location index in the region where the power grid device is located, the population density index, economic activity index and power grid hub status index are quantitatively processed to obtain a population density score, an economic activity score and a power grid hub status score. The comprehensive importance score is calculated according to the population density score, the economic activity score and the power grid hub status score;

[0099] The sensitivity-importance matrix is plotted with the comprehensive sensitivity score as the vertical coordinate and the comprehensive importance score as the horizontal coordinate;

[0100] The region where the comprehensive importance score and the comprehensive sensitivity score both exceed the preset importance score and the preset sensitivity score is regarded as a high sensitivity-high importance region, and the first power grid infrastructure data located in the region is encrypted by using a high-level encryption algorithm;

[0101] The region where the comprehensive importance score exceeds the preset importance score and the comprehensive sensitivity score does not exceed the preset sensitivity score is regarded as a high sensitivity-low importance region, and the first power grid infrastructure data located in the region is encrypted by using a secondary encryption algorithm;

[0102] The region where the comprehensive importance score does not exceed the preset importance score and the comprehensive sensitivity score exceeds the preset sensitivity score is regarded as a low sensitivity-high importance region, and the first power grid infrastructure data located in the region is encrypted by using a secondary encryption algorithm;

[0103] The region where the comprehensive importance score does not exceed the preset importance score and the comprehensive sensitivity score does not exceed the preset sensitivity score is regarded as a low-sensitivity region-low-importance region, and a three-level encryption algorithm is used to encrypt the first power grid infrastructure data located in the region. The encryption strength of the three-level encryption algorithm is less than that of the two-level encryption algorithm, and the encryption strength of the two-level encryption algorithm is less than that of the high-level encryption algorithm.

[0104] In the embodiment, the sensitivity of the first power grid infrastructure data includes device location sensitivity, user privacy sensitivity, and power grid topology sensitivity. The device location sensitivity is associated with the geographical location of the power grid device (such as a backbone substation or a dispatch center). The closer the device is to the backbone substation, the wider the influence range, and the higher the device location sensitivity. The user privacy sensitivity is associated with the user identity information quantification features contained in the data, such as user number, power consumption habit, address identifier, etc. The power grid topology sensitivity is obtained by analyzing the connectivity and critical path importance of the device node in the power grid topology structure. If the node is in a critical link or has a low redundancy characteristic in the topology structure, its topology sensitivity is higher. The importance of the first power grid infrastructure data includes the importance of the region where the power grid device is located. For example, if a certain region is a key industrial zone or a hospital, a communication hub, the data importance level of the region is higher.

[0105] After obtaining the device location sensitivity, the user privacy sensitivity, and the power grid topology sensitivity, the analytic hierarchy process is used to analyze the device location sensitivity, the user privacy sensitivity, and the power grid topology sensitivity to determine the distribution weights of the device location sensitivity, the user privacy sensitivity, and the power grid topology sensitivity. The weighted sum of the device location sensitivity, the user privacy sensitivity, and the power grid topology sensitivity is calculated according to the distribution weights.

[0106] In the embodiment, the analytic hierarchy process is used to distribute the weights of the sensitivity. Specifically, the device location sensitivity, the user privacy sensitivity, and the power grid topology sensitivity are used as sensitivity evaluation indexes. Then, the analytic hierarchy process is used to compare the three indexes pairwise, establish a judgment matrix, and calculate the characteristic vectors of the indexes to determine their relative weights, so as to obtain the distribution weights of the device location sensitivity, the user privacy sensitivity, and the power grid topology sensitivity. After the weights are determined, the sensitivity score values corresponding to the indexes are obtained, and the weighted sum of the sensitivity scores is calculated according to the distribution weights to obtain the comprehensive sensitivity score.

[0107] The population density, economic activity and power grid hub geographical position of the region where the power grid equipment is located are determined, and the population density, economic activity and power grid hub position score are quantitatively processed to obtain the population density score, economic activity score and power grid hub position score. In this embodiment, the population density, economic activity and power grid hub geographical position of the region where the power grid equipment is located can be determined by calling a geographic information system (GIS) and a statistical database. The population density is used to represent the concentration of personnel distribution in the region, reflecting the key position of the equipment in the power grid topology. Then, the population density, economic activity and power grid hub geographical position are quantitatively processed. Specifically, the population density is obtained by normalizing the obtained regional population data, using the maximum and minimum standardization method to map the population density values of different regions to a preset score interval. The economic activity score is obtained by weighting the multi-dimensional data of the regional power load intensity, industrial power consumption proportion and commercial energy consumption frequency, and combining the preset economic activity evaluation model. The power grid hub position score is obtained by quantifying the node connectivity, power flow concentration and power supply range of the power grid topology through a topological centrality analysis algorithm. Through the above quantitative process, the regional social characteristics and power grid structure characteristics can be unified and quantified, providing input parameters for subsequent calculation of the comprehensive sensitivity score based on the analytic hierarchy process to determine the distribution weight and weighted summation. Thus, the quantitative and comparable evaluation of the sensitivity level of the region where the power grid equipment is located is realized.

[0108] Then, the comprehensive importance score is calculated according to the population density score, economic activity score and power grid hub position score, that is, the population density score, economic activity score and power grid hub position score are added to obtain the comprehensive importance score. The comprehensive importance score is used to represent the overall importance level of the region in social influence, power supply and demand and power grid structure, providing quantitative basis for subsequent sensitivity calculation, safety classification and resource scheduling strategy.

[0109] The calculated comprehensive sensitivity score is used as the vertical coordinate, and the comprehensive importance score is used as the horizontal coordinate. The sensitivity-importance matrix is plotted in the two-dimensional coordinate system. That is, each power grid infrastructure data corresponds to a data point, and the vertical coordinate value represents the comprehensive sensitivity level of the power grid infrastructure data, and the horizontal coordinate value represents the comprehensive importance level of the power grid infrastructure data. By analyzing the position distribution of different data points in the matrix, the power grid infrastructure data can be divided into different categories, such as high sensitivity and high importance, high sensitivity and low importance, low sensitivity and high importance, and low sensitivity and low importance. The sensitivity-importance matrix can intuitively reflect the distribution characteristics of the power grid infrastructure data in safety sensitivity and comprehensive importance, providing quantitative basis and decision support for subsequent safety protection strategy formulation, operation and maintenance resource allocation and priority determination.

[0110] In other embodiments, the sensitivity level of the first power grid infrastructure data can also be divided into three levels: high, medium, and low, and the specific division criteria can be developed according to the actual situation and needs of the project; the importance level of the first power grid infrastructure data can also be divided into three levels: core, important, and general, and the division criteria are similar to the sensitivity dimension. Taking the sensitivity and importance dimensions as the horizontal and vertical coordinates of the matrix, a two-dimensional matrix is formed, and each cell of the matrix represents a specific combination of sensitivity and importance, such as "high sensitivity-core importance". According to the security requirements and resource limitations of the project, the encryption level is divided into different levels, such as high-level encryption, medium-level encryption, low-level encryption, or no encryption, and the selection of the encryption level should consider the sensitivity and importance of the data, as well as the cost, complexity, and impact on system performance of the encryption technology. For data with high sensitivity and core importance, high-level encryption technology should be used to ensure the security and confidentiality of the data. For data with high sensitivity but low importance, or data with high importance but low sensitivity, medium-level encryption technology can be used to balance security requirements and resource limitations. For data with low sensitivity and importance, low-level encryption or no encryption can be used to reduce costs and impact on system performance. According to the sensitivity and importance of the data, the data is classified into the corresponding cells of the matrix. For data in different cells, specific encryption strategies are developed, including the selection of encryption algorithms, the management of encryption keys, the storage and transmission of encrypted data, etc. For example, the high sensitivity-high importance area can use the AES-256 encryption algorithm to encrypt the data, and use the hardware security module (HSM) to store the encryption key to ensure the security of the key. During data transmission, the TLS1.3 protocol is used for encrypted transmission, and strict two-factor authentication and the principle of least privilege are implemented for data access. The high sensitivity-medium importance area can use the RSA-2048 encryption algorithm, and the key management system is used for key management, and the key is replaced regularly. The role-permission model is set for data access control, different roles (such as operation and maintenance personnel, management personnel) have different data access permissions, and detailed access logs are recorded for auditing. IPSec VPN is used for encrypted channel transmission during transmission. The low sensitivity-low importance area can use the 3DES encryption algorithm, and the key is stored in the database encryption field. Access control is based on user group-permission allocation, and user groups are divided according to departments or projects. During transmission, the SSL protocol (newer version) is used for basic encryption transmission, and data integrity verification (such as MD5 or SHA-256 hash verification) is enabled. The preset sensitivity score and the preset importance score in this embodiment can be determined according to the actual situation.

[0111] The encryption level of the first power grid infrastructure data is determined by constructing a sensitivity-importance matrix, which not only improves the security of the data and the utilization efficiency of the encryption resources, but also optimizes the system performance, improves the decision efficiency, and has strong adaptability, and is of great significance for protecting the data security of the power grid infrastructure project.

[0112] In an implementation of the embodiment, the sensitivity of the first power grid infrastructure data is determined based on the sensitive data to be analyzed, and the sensitivity of the first power grid infrastructure data is determined based on the sensitive data to be analyzed.

[0113] S410, obtaining the data category of the power grid infrastructure data and the sensitive words corresponding thereto;

[0114] S420, inputting the data category and the sensitive words corresponding thereto into an initial neural network model to train the initial neural network model and obtain a sensitivity analysis model;

[0115] S430, inputting the sensitive data to be analyzed of the first power grid infrastructure data into the sensitivity analysis model to obtain the sensitivity of the first power grid infrastructure data.

[0116] In the embodiment, part of the data in the entire power grid infrastructure data is selected as a training set, the data category of the power grid infrastructure data in the training set is obtained, and the sensitive words corresponding thereto are obtained. When the training set data is made, the related sensitive words can also be obtained through a pre-set database, for example, the sensitive words of the power grid equipment parameter class data are equipment model (such as transformer model, circuit breaker specification), equipment operation parameter (such as voltage level, current capacity, insulation level), equipment position coordinate (such as substation longitude and latitude, power tower GPS coordinate), equipment maintenance log (such as fault record, maintenance period), and the sensitive words of the power grid equipment parameter class data are equipment model, equipment operation parameter, equipment position coordinate, and equipment maintenance log. The sensitive words of the network topology and system architecture class are network topology graph (such as power communication network structure, SCADA system architecture), IP address / port configuration (such as RTU, IED device communication address), protocol type (such as IEC 60870-5-104, DNP3 protocol configuration), system interface description (such as interaction interface with dispatching center and new energy station), and the sensitive words of the network topology and system architecture class are the above sensitive words.

[0117] Subsequently, the data category and sensitive word are input into the initial neural network model to train the initial neural network model to obtain the trained sensitivity analysis model, that is, a model capable of automatically analyzing the sensitivity of power grid infrastructure data is constructed by a machine learning method. Specifically, first, the data category, for example, the classification of power grid infrastructure data (such as device parameters, network topology, user power consumption data, etc.) and the key words or phrases related to the sensitivity (such as "device coordinates", "control instruction", "user power consumption", etc.) are input into the initial neural network model, wherein each piece of data needs to be labeled with its sensitivity as a label for supervised learning. Next, the model is trained by the labeled data (input text + sensitivity label) to learn to identify the sensitivity features from the text to obtain the trained sensitivity analysis model.

[0118] After obtaining the sensitive words of the first power grid infrastructure data, the sensitive words and the "data category" corresponding to the sensitive words are spliced to construct a comprehensive feature vector, and finally a comprehensive feature vector of the sensitive data to be analyzed is obtained. The feature vector can be used as the input of the neural network model for identification, and then used for sensitivity analysis of the power grid infrastructure data. The sensitive data to be analyzed is input into the trained sensitivity analysis model to determine the sensitivity of the first power grid infrastructure data. The sensitive data to be analyzed is a comprehensive feature vector formed after the "data category" and "sensitive words" of the power grid infrastructure data are quantitatively processed. The comprehensive feature vector is composed of sensitive word quantitative features and data category features. The data category features are determined by the standardized coding (such as one-hot coding, category identification, etc.) of the "data category" (such as device parameters, network topology, construction log, etc.); the sensitive word quantitative features are determined by the quantification of the "sensitive words" (such as device model, substation coordinates, voltage level, etc.). The sensitive word quantitative features can be determined by using the feature word frequency weight method. The frequency of the sensitive word appearing in the data is counted (such as the high-frequency appearance of "substation coordinates" in design drawings). According to the statistical frequency of the sensitive word, a weight value is assigned to each sensitive word, which can be determined according to the actual situation to measure its sensitivity in the data. The word frequency is used to measure the ratio of the number of times the word appears in the data to the total number of words in the data. In this embodiment, the sensitive words can be automatically extracted based on the data category, that is, for different data categories, the text mining technology is used to automatically extract high-frequency appearing and data security related words from historical data, such as "substation coordinates" in design drawings. The high-frequency association with security risks is automatically identified as a sensitive word. The trained sensitivity analysis model is a model trained by a large amount of historical power grid infrastructure data. During the training process, the model analyzes the relationship between different sensitive data to be analyzed and the actual power grid infrastructure results (such as cost overrun, construction delay time, engineering quality grade, etc.), thereby determining the internal law between the sensitive data to be analyzed and the sensitivity. In this embodiment, the trained sensitivity analysis model is a neural network model; when the sensitive words and data types are used as inputs and the sensitivity label is used as a training label, the model will mine the deep features related to the sensitivity in these input data through a large amount of data training. The sensitive data to be analyzed is input into the trained model. The model will process the index values of the input according to its internal algorithm and the "memorized" rules. Through a series of calculations, the sensitivity result of the first power grid infrastructure data is output. The sensitivity result can be a quantitative value, and the sensitivity level is determined according to the quantitative value, such as high, medium and low.

[0119] Through the above steps, the data security management efficiency can be improved, the manual intervention in sensitive degree evaluation can be reduced, and the data processing efficiency can be significantly improved. The model can quickly process a large amount of data, meet the high throughput demand of power grid enterprises, significantly improve the data security management level, and provide strong support for the construction and operation of smart power grids.

[0120] In an implementation form of the embodiment, based on the to-be-analyzed importance data, importance evaluation is performed on the first power grid infrastructure data to determine the importance degree of the first power grid infrastructure data, including:

[0121] S510, obtaining important words corresponding to a data category of the power grid infrastructure data;

[0122] S520, inputting the data category and the important words into an initial neural network model to train the initial neural network model and obtain a trained importance degree analysis model;

[0123] S530, inputting the to-be-analyzed importance data into the trained importance degree analysis model to determine the importance degree of the first power grid infrastructure data.

[0124] In the embodiment, the important words corresponding to the data category of the power grid infrastructure data can be obtained through a preset database. Specifically, important words related to the category of the power grid infrastructure data (such as device parameters, network topology, user power consumption data, etc.) are extracted. The specific extraction method has been described above, and will not be repeated here.

[0125] Subsequently, the plurality of data categories and the important words corresponding thereto are input into an initial neural network model to train the initial neural network model and obtain a trained importance degree analysis model. The data with labeled importance degrees is input into the initial neural network model to train the initial neural network model, so that the initial neural network model can identify importance degree features and judge importance degree levels from the input data. The input layer includes important words, the hidden layer extracts features through a full connection layer, and the output layer outputs importance degree classification results, thereby obtaining the trained importance degree analysis model.

[0126] Next, the to-be-analyzed importance data is input into the trained importance degree analysis model to determine the importance degree of the first power grid infrastructure data. That is, the trained neural network model is used to predict the importance degree of the power grid infrastructure data. Specifically, the to-be-analyzed importance data corresponding to the first power grid infrastructure data is input into the trained importance degree analysis model, and the model returns the predicted importance degree.

[0127] In this embodiment, the importance data to be analyzed is a comprehensive feature vector formed after the quantification of the "data category" and "important word" of the power grid infrastructure data. The comprehensive feature vector of the importance data to be analyzed is composed of data category features and important word quantification features. The data category features can be determined by standardized coding of the "data category", and the comprehensive feature vector can be obtained by string splicing of the data category and the corresponding important word. By taking the data category of the power grid infrastructure data and the corresponding important word as input, the model can learn the importance pattern of different categories of data in the project. For example, equipment procurement cost, maintenance cost and other data reflect the economic importance of equipment. By taking the data category features and important words as input, the model can evaluate the importance of the data in combination with the economic value of the data, and the importance label in the training data provides supervision information for model training.

[0128] By evaluating the importance of the first power grid infrastructure data based on the importance data to be analyzed and automatically evaluating based on the neural network model, the evaluation accuracy can be significantly improved, the evaluation can be automated, the resource allocation can be optimized, the decision-making scientificity can be improved, and the data value mining can be promoted. These effects are of great significance for the operation management and decision-making of power grid enterprises.

[0129] In one embodiment of the present embodiment, the sensitivity-importance matrix is constructed by the sensitivity and the importance of the first power grid infrastructure data, and the encryption level of the first power grid infrastructure data is determined, comprising:

[0130] S610, taking the sensitivity as the vertical axis of the sensitivity-importance matrix, and taking the importance as the horizontal axis of the sensitivity-importance matrix;

[0131] S620, constructing a matrix based on the vertical axis and the horizontal axis of the sensitivity-importance matrix;

[0132] S630, mapping the sensitivity and the importance of the first power grid infrastructure data into the matrix, and determining the encryption level of the first power grid infrastructure data according to a preset mapping rule of the sensitivity-importance matrix and the encryption level.

[0133] Figure 2 A schematic diagram of a sensitivity-importance matrix provided by the present embodiment is shown in Figure 2 The horizontal axis is high importance and low importance, and the vertical axis is high sensitivity and low sensitivity.

[0134] Firstly, sensitivity is taken as the vertical axis of the sensitivity-importance matrix, and importance is taken as the horizontal axis of the sensitivity-importance matrix, to obtain the to-be-analyzed sensitivity data and the to-be-analyzed importance data, wherein the sensitivity is usually used to measure the degree of response of a system or model to the change of an input parameter. In the sensitivity-importance matrix, the sensitivity as the vertical axis represents the sensitivity degree of different power infrastructure data in the power grid, and the importance as the horizontal axis represents the importance degree of different data in the power grid. Through the sensitivity-importance matrix, the performance of different data points in the two dimensions of sensitivity and importance can be intuitively seen, so that the security level thereof can be comprehensively evaluated.

[0135] In this embodiment, the matrix is constructed based on the vertical axis and the horizontal axis of the sensitivity-importance matrix. Specifically, according to different combinations of the sensitivity and the importance, the matrix can be divided into four quadrants, the first quadrant is high sensitivity-high importance, the second quadrant is low sensitivity-high importance, the third quadrant is low sensitivity-low importance, and the fourth quadrant is high sensitivity-low importance. The sensitivity and the importance of the first power infrastructure data are mapped into the matrix to determine the encryption level of the first power infrastructure data. Specifically, the sensitivity and the importance of the first power infrastructure data are mapped into the matrix, the sensitivity of the first power infrastructure data is evaluated to determine the sensitivity level thereof, and the importance of the first power infrastructure data is evaluated to determine the quadrant in which the first power infrastructure data is located in the sensitivity-importance matrix, and then the encryption level of the first power infrastructure data is determined. Subsequently, a mapping rule of the sensitivity-importance matrix to the encryption level is formulated. For example, high sensitivity-high importance is strong encryption, low sensitivity-high importance and high sensitivity-low importance are weak encryption, and low sensitivity-low importance is no encryption, and then the encryption level of the first power infrastructure data is determined.

[0136] The sensitivity-importance matrix is constructed based on the sensitivity and the importance, and the encryption level of the first power infrastructure data is determined accordingly, so that the data security can be systematically evaluated, the encryption level can be accurately determined, the data security management efficiency can be improved, the data protection awareness can be enhanced, the data security changes can be flexibly responded to, and the decision making can be supported.

[0137] In one of the implementation manners of this embodiment, based on the user permission level and the first power infrastructure data, the second power infrastructure data is filtered and sent to the user, including:

[0138] S710, obtaining a viewing range of the user permission level;

[0139] S720, extracting a keyword in the first power infrastructure data;

[0140] S730, filtering second power infrastructure data based on the keyword within the viewing range;

[0141] S740, sending the second power grid infrastructure data to the user.

[0142] First, the viewing range of the user's authority level is obtained, the authority level of the user is queried, the authority level is associated with the user role or user group, and is stored in the user management database of the system. According to the authority level of the user, the range of power grid infrastructure data that the user can view is determined, including specific projects, regions, equipment types or data categories, etc.

[0143] Secondly, the keywords of the first power grid infrastructure data are determined. Specifically, first, the content of the first power grid infrastructure data is determined, including the theme of the data, the field involved, the related project or equipment, etc. On the basis of understanding the data content, the key information in the data is identified. According to the key information, the keywords that can represent the characteristics of these data are extracted. The keywords should be concise, clear and representative, and can accurately reflect the core content of the data. After extracting the keywords, it is necessary to verify them to ensure their accuracy and effectiveness. The rationality of the keywords can be verified by comparing them with the data content or by asking experts in the relevant field to review them.

[0144] Within the viewing range, the second power grid infrastructure data is filtered based on the keywords. Specifically, according to the authority level of the user, the range of power grid infrastructure data that the user can access is determined, including specific projects, regions, equipment types or data categories, etc. Then, the user inputs the keywords for filtering based on the previous query data of the user, which are related to the second power grid infrastructure data that the user wants to find. Within the determined viewing range, the system starts searching for data matching the keywords, involving checking each record in the database to see if it contains the keywords specified by the user. The system collects all matching data records to form a filtered result set, which contains all second power grid infrastructure data within the viewing range and meets the keyword search conditions, and sorts the filtered results, such as by relevance, time order or other user-specified criteria.

[0145] The second power grid infrastructure data is sent to the user. Specifically, it can be sent to the user through API interface call (for user system integration) or directly displayed on the user interface. The system needs to define a set of API interfaces for integration with the user system. Then, the system may sort the filtered results, such as by relevance, time order or other user-specified criteria, and display the sorted results to the user, usually through a user-friendly interface.

[0146] By combining the user permission level and the keywords of the first power grid infrastructure data to filter and send the second power grid infrastructure data, the data security, accuracy and user experience are enhanced, the resource utilization is optimized, the customized demand is supported, and the data sharing and cooperation are promoted.

[0147] In summary, the embodiment of the present application provides a data security management method for power grid infrastructure, which not only enhances the data security, but also improves the flexibility and efficiency of data management, optimizes the user experience, and has important significance for protecting sensitive information of power grid infrastructure projects, ensuring safe use of data, and supporting overall business objectives of an organization.

[0148] According to the method described in the above embodiment, the present embodiment will be further described from the perspective of a data security management device for power grid infrastructure. The device can be implemented as an independent entity or integrated in an electronic device such as a terminal. Please refer to Figure 3 , Figure 3 is a structural schematic diagram of the data security management device for power grid infrastructure provided by the embodiment of the present application. The device comprises:

[0149] A response module is configured to obtain a user permission level of a user in response to a viewing instruction of the user on power grid infrastructure data.

[0150] An encryption level determination module is configured to determine an encryption level of the first power grid infrastructure data according to the viewed first power grid infrastructure data of the user.

[0151] A judgment module is configured to judge whether the user meets a viewing condition based on the user permission level and the encryption level.

[0152] A data sending module is configured to send the first power grid infrastructure data to the user when the user meets the viewing condition, and filter second power grid infrastructure data based on the user permission level and the first power grid infrastructure data and send the second power grid infrastructure data to the user when the user does not meet the viewing condition.

[0153] In addition, Figure 4 is a structural schematic diagram of the data security management device for power grid infrastructure provided by the embodiment of the present application. As shown in Figure 4 , the device comprises a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned data security management method for power grid infrastructure are implemented.

[0154] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions or controlled by instructions related hardware, which can be stored in a computer readable storage medium and loaded and executed by a processor. For this purpose, the embodiments of the present application provide a computer readable storage medium, wherein a plurality of instructions are stored, which can be executed by a processor to implement the steps in the above data security management method for power grid infrastructure.

[0155] Generally, computer instructions to implement the methods of the present application can be carried in any combination of one or more computer readable media. Computer readable media, such as, but not limited to, memory, both volatile and non-volatile computer readable media, could be used. By way of example, and not limitation, computer readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of computer readable instructions or data structures and that can be accessed by a computer. Also, functional computer readable instructions can be loaded into a computer, other programmable data processing apparatus, or other device to cause a series of operations to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions of the embodiments of the application.

[0156] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments of the present application, electronic mail (email) can be utilized as the

[0157] Although the embodiments of the present application have been shown and described above, it should be understood by those skilled in the art that the above embodiments are exemplary and cannot be interpreted as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A data security management method for power grid infrastructure, characterized in that, The management method comprises: In response to a user's viewing instruction of power grid infrastructure data, obtaining the user's user authority level; According to the viewing instruction, identify the first power grid infrastructure data that the user wants to view, determine the encryption level of the first power grid infrastructure data; Based on the user authority level and the encryption level, determine whether the user meets the viewing condition; If the user meets the viewing condition, send the first power grid infrastructure data to the user; If the user does not meet the viewing condition, based on the user authority level and the first power grid infrastructure data, filter the second power grid infrastructure data and send it to the user.

2. The data security management method for power grid infrastructure according to claim 1, characterized in that, Determine the encryption level of the first power grid infrastructure data, comprising: Obtain the to-be-analyzed sensitivity data and the to-be-analyzed importance data of the first power grid infrastructure data; Based on the to-be-analyzed sensitivity data, sensitivity evaluation is performed on the first power grid infrastructure data to determine the sensitivity of the first power grid infrastructure data; Based on the to-be-analyzed importance data, importance evaluation is performed on the first power grid infrastructure data to determine the importance of the first power grid infrastructure data; Construct a sensitivity-importance matrix through the sensitivity and importance of the first power grid infrastructure data to determine the encryption level of the first power grid infrastructure data.

3. The data security management method for power grid infrastructure of claim 2, wherein, Obtaining the to-be-analyzed sensitivity data of the first power grid infrastructure data comprises: extracting sensitive words in the first power grid infrastructure data, quantifying the data category corresponding to the first power grid infrastructure data and the sensitive words to obtain the corresponding sensitive feature vector, and taking the sensitive feature vector as the to-be-analyzed sensitivity data corresponding to the first power grid infrastructure data; Obtaining the to-be-analyzed importance data of the first power grid infrastructure data comprises: extracting important words in the first power grid infrastructure data, quantifying the data category corresponding to the first power grid infrastructure data and the important words to obtain the corresponding important feature vector, and taking the important feature vector as the to-be-analyzed importance data corresponding to the first power grid infrastructure data.

4. The data security management method for power grid infrastructure of claim 3, wherein, Extracting sensitive words in the first power grid infrastructure data comprises: Collecting power grid design, construction and operation related data, and classifying the data to form a plurality of categories of power grid infrastructure corpus, each category of power grid infrastructure corpus containing a category of power grid infrastructure data; Pretreatment of the data in the power grid infrastructure corpus, the pretreatment comprising: stop word removal, word segmentation, part-of-speech tagging, and unified term processing; Using the TF-IDF method, extract the words with frequency higher than a preset threshold and related to data security as candidate sensitive words of the corresponding data category in different categories of power grid infrastructure corpus; Obtain the data category corresponding to the first power grid infrastructure data and all candidate sensitive words corresponding to the data category; The sensitive words appearing in the first power grid infrastructure data are taken as the sensitive words of the first power grid infrastructure data.

5. The data security management method for power grid infrastructure of claim 4, wherein, Determine the sensitivity of the first power grid infrastructure data, comprising: Obtain the data category of the power grid infrastructure data and the sensitive words corresponding thereto; inputting the data category and the sensitive word into an initial neural network model to train the initial neural network model, and obtaining a sensitivity analysis model; inputting the first power grid infrastructure data to be analyzed into the sensitivity analysis model to obtain the sensitivity of the first power grid infrastructure data; determining the importance of the first power grid infrastructure data, comprising: obtaining the data category of the power grid infrastructure data and the corresponding important word; inputting the data category and the important word into an initial neural network model to train the initial neural network model, and obtaining an importance analysis model; inputting the first power grid infrastructure data to be analyzed into the sensitivity analysis model to obtain the sensitivity of the first power grid infrastructure data.

6. The data security management method for power grid infrastructure of claim 2, wherein, constructing a sensitivity-importance matrix through the sensitivity and the importance of the first power grid infrastructure data, and determining the encryption level of the first power grid infrastructure data, comprising: taking the sensitivity as the vertical axis of the sensitivity-importance matrix and taking the importance as the horizontal axis of the sensitivity-importance matrix; constructing a matrix based on the vertical axis and the horizontal axis of the sensitivity-importance matrix; mapping the sensitivity and the importance of the first power grid infrastructure data into the matrix, and determining the encryption level of the first power grid infrastructure data according to a preset mapping rule of the sensitivity-importance matrix and the encryption level.

7. The data security management method for power grid infrastructure of claim 1, wherein, filtering second power grid infrastructure data to be sent to the user based on the user permission level and the first power grid infrastructure data, comprising: obtaining the viewing range of the user permission level; extracting the key word in the first power grid infrastructure data; filtering second power grid infrastructure data based on the key word within the viewing range; sending the second power grid infrastructure data to the user.

8. A data security management device for power grid infrastructure, characterized by, The device is used to execute the data security management method for power grid infrastructure as claimed in any one of claims 1 to 7, and specifically comprises: a response module, configured to obtain the user permission level of the user in response to a viewing instruction of the user on the power grid infrastructure data; an encryption level determination module, configured to identify the first power grid infrastructure data that the user wants to view according to the viewing instruction, and determine the encryption level of the first power grid infrastructure data; a judgment module, configured to judge whether the user meets the viewing condition based on the user permission level and the encryption level; a data sending module, configured to send the first power grid infrastructure data to the user when the user meets the viewing condition, and filter second power grid infrastructure data to be sent to the user based on the user permission level and the first power grid infrastructure data when the user does not meet the viewing condition.

9. A data security management device for power grid infrastructure, characterized by, a memory and a processor, wherein the memory is configured to store computer program code and transmit the computer program code to the processor; the processor is configured to execute the data security management method for power grid infrastructure as claimed in any one of claims 1 to 8 according to the instructions in the computer program code.

10. A computer storable medium having stored therein a computer program, characterized in that The computer program is executed by the processor to implement the data security management method for power grid infrastructure as claimed in any one of claims 1 to 7.

Images