Secondary encryption power grid data communication method and device
By using convolutional neural networks and large models to filter power grid field data and combining them with national cryptographic algorithms for secondary encryption, the problems of power grid data communication efficiency and security have been solved, and efficient and secure power grid data transmission has been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-04
- Publication Date
- 2026-04-03
AI Technical Summary
Existing power grid data encryption algorithms face the risk of brute-force attacks. Complex encryption algorithms consume high computational resources and time, resulting in low communication efficiency and making it difficult to meet the power grid's rapid response requirements.
A method combining convolutional neural networks and large models is adopted to determine the content access level based on the query request, filter the power grid field data to be encrypted, ensure security and efficiency through double encryption, and use the national cryptographic algorithm for encryption processing.
It improves the efficiency of power grid data communication, reduces encryption redundancy, ensures communication security, and meets the data security requirements of the power grid system in the process of intelligent operation and maintenance.
Smart Images
Figure CN121792121A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of information security technology, and in particular to a method and apparatus for secondary encryption of power grid data communication. Background Technology
[0002] With the development of smart grids, data communication between various power grid systems and devices has become more frequent, and the amount of power grid data that needs to be transmitted is constantly increasing. In order to ensure the data security of the power grid system during intelligent operation and maintenance, it is necessary to study the security and privacy of this data during transmission.
[0003] Existing secure data transmission methods for power grids have several shortcomings: traditional data encryption algorithms are vulnerable to brute-force attacks, and their security gradually decreases with increasing computing power, allowing them to be cracked through exhaustive methods or inherent weaknesses in the encryption algorithm itself. While more complex encryption algorithms offer higher security, they require extensive computation during encryption and decryption, consuming significant computing resources and time, resulting in low efficiency in encrypted communication. This is particularly pronounced in scenarios involving the large-scale, real-time secure transmission of power grid data, which clearly cannot meet the needs of rapidly evolving power grid transmission. Furthermore, current methods for securely processing power grid data typically involve multiple encryptions of all data, resulting in numerous complex calculations. This adds unnecessary time to both the encryption process at the sending end and the decryption process at the receiving end, further reducing data transmission efficiency and failing to effectively meet the rapid response requirements of the power grid. Therefore, improving the encryption process for power grid data to ensure both communication efficiency and security, thereby guaranteeing data security during intelligent operation and maintenance of the power grid system, remains a pressing technical problem that needs to be addressed. Summary of the Invention
[0004] This application provides a secondary encryption method and apparatus for power grid data communication to solve the technical problem that existing encryption methods for power grid data cannot meet the requirements of communication efficiency and security.
[0005] According to a first aspect of the embodiments of this application, a secondary encryption power grid data communication method is provided, comprising: Based on the current query request, the content access level is determined, and based on the content access level and the query results to be sent, multiple power grid field data are determined; wherein, the query results are obtained based on the current query request; each power grid field data includes the user's identity identifier and the user's electricity address; Based on a convolutional neural network, features are extracted from the multiple power grid field data, and based on the feature extraction results, the set of encrypted sites for each power grid field data is derived by combining the large model. Based on the preset first national cryptographic algorithm, combined with the set of encryption points, each power grid field data is encrypted to obtain the first ciphertext corresponding to each power grid field data, and each first ciphertext is replaced in the power grid field data corresponding to the query result to obtain the first sending content; Based on the preset second national cryptographic algorithm, the first sent content and the set of encryption points for each power grid field data are sequentially concatenated and encrypted as a whole to obtain the second sent content, which is then sent to the query requester.
[0006] This application first determines the content access level based on the current query request, and then determines multiple power grid field data based on the query results obtained from the current query request. This allows for pre-screening of power grid field data to be encrypted based on the current query request, avoiding the encryption of all power grid data as in existing technologies. This avoids the waste of computing resources and time caused by encryption redundancy and improves the efficiency of power grid data communication. Furthermore, it extracts features from multiple power grid field data based on a convolutional neural network and derives an encryption point set using a large model. This further narrows down the encryption range in the power grid field data to be encrypted, further avoiding encryption redundancy and improving the efficiency of power grid data communication. By combining the features of the data to be encrypted with a large model, it can accurately determine the encryption points, avoiding encryption point errors and ensuring the security of power grid data communication. Finally, it encrypts and replaces the first transmission content based on the first national cryptographic algorithm and then encrypts and transmits the first transmission content and the encryption point set of each power grid field data based on the second national cryptographic algorithm. This double encryption ensures data security while reducing encryption density, thereby improving the communication efficiency of power grid data and meeting the communication security requirements of power grid data.
[0007] In some embodiments of this application, the query result includes multiple query field data; determining the multiple power grid field data based on the content access level and the query result to be sent specifically includes: Based on the content access level, a field matching list is determined, and based on the field matching list, it is matched with the multiple query field data to obtain multiple first-class field data; Based on the multiple primary field data, each field data to be filtered is filtered to obtain multiple secondary field data; wherein, the field data to be filtered is the query field data other than the multiple primary field data among the multiple query field data; Based on the multiple Class I field data and the multiple Class II field data, multiple power grid field data are obtained.
[0008] This application first determines a field matching list based on the content access level, then matches multiple Class I field data. It can first determine some field data to be encrypted based on the field matching rules, and then filter the query field data other than Class I field data based on multiple Class I fields. It can determine some field data to be encrypted that is not recognized by the field matching rules but meets the encryption requirements, thereby accurately determining multiple power grid field data to be encrypted. This avoids encryption errors and reduces encryption redundancy, ensuring the communication efficiency and communication security requirements of power grid data.
[0009] In some embodiments of this application, the step of filtering each field data to be filtered based on the plurality of primary field data to obtain a plurality of secondary field data specifically includes: Based on the multiple single-class field data, a single-class classifier is constructed using a single-classification algorithm; Each field data to be filtered is input into the field single classifier to obtain the field classification result corresponding to each field data to be filtered. Based on the field classification results corresponding to each field to be filtered, the data of each field to be filtered is filtered to obtain multiple second-category field data.
[0010] This application first constructs a field single classifier based on multiple primary field data and a single classification algorithm. Then, it filters each field data to be filtered using the field single classifier to obtain multiple secondary field data. Based on the characteristics of the primary field data, it can determine the field data that is not identified by the field matching rules but meets the encryption requirements, thereby accurately determining multiple power grid field data to be encrypted and ensuring the communication security requirements of power grid data.
[0011] In some embodiments of this application, the step of extracting features from the multiple power grid field data based on a convolutional neural network, and deriving the set of encrypted sites for each power grid field data based on the feature extraction results and a large model, specifically includes: Each power grid field data is segmented into words and its features are extracted based on a convolutional neural network to obtain multiple segmented field features corresponding to each power grid field data. Based on a pre-defined large model, multiple segmented field features corresponding to each power grid field data are filtered. The filtering is based on the semantic influence order, and the set of encryption sites for each power grid field data is determined according to the filtering results.
[0012] This application first segments each power grid field data into words and extracts features through a convolutional neural network to obtain multiple segmented field features corresponding to each power grid field data. Then, based on a large language model and combined with semantic influence order, the segmented field features are filtered to determine the set of encryption sites. This can determine the corresponding encryption sites according to the features of the power grid field data, avoid encryption site errors, and ensure the security of power grid data communication.
[0013] In some embodiments of this application, the step of filtering multiple segmented field features corresponding to each power grid field data based on a preset large model, filtering according to the semantic influence order, and determining the set of encryption sites for each power grid field data based on the filtering results, specifically includes: Based on the features of multiple word segmentation fields corresponding to each power grid field data, construct multiple first word segmentation combinations corresponding to each power grid field data; Based on the pre-set large model, according to the semantic influence of the first word segmentation combination on the corresponding power grid field data from high to low, all the first word segmentation combinations of each power grid field data are filtered to obtain several second word segmentation combinations of each power grid field data. Based on the union of all second word combinations for each power grid field data, determine the encryption sites of multiple encrypted word segments for each power grid field data, and based on the encryption sites of multiple encrypted word segments for each power grid field data, determine the encryption site set for each power grid field data.
[0014] This application first constructs multiple first word segmentation combinations based on the multiple word segmentation field features of each power grid field data. Then, it combines a large model to filter all first word segmentation combinations of each power grid field data. During the filtering, the first word segmentation combinations are filtered according to the semantic influence order, resulting in several second word segmentation combinations of each power grid field data. Then, the corresponding encryption site set is determined by the union of all second word segmentation combinations of each power grid field data. This can accurately filter word segmentation combinations and determine encryption sites based on the semantic influence order related to encryption, avoid encryption site errors, and ensure the security of power grid data communication.
[0015] According to a second aspect of the embodiments of this application, a power grid data communication device with secondary encryption is provided, including a field data determination module, an encryption point derivation module, a primary encryption replacement module, and a secondary encryption transmission module; The field data determination module is used to determine the content access level based on the current query request, and to determine multiple power grid field data based on the content access level and the query results to be sent; wherein, each power grid field data includes a user identity identifier and a user electricity address; the query results are obtained based on the current query request; The encryption site derivation module is used to extract features from the multiple power grid field data based on a convolutional neural network, and derive the encryption site set for each power grid field data based on the feature extraction results and a large model. The first encryption and replacement module is used to encrypt each power grid field data based on a preset first national cryptographic algorithm and a set of encryption points, to obtain a first ciphertext corresponding to each power grid field data, and to replace each first ciphertext in the power grid field data corresponding to the query result to obtain the first transmission content; The secondary encryption sending module is used to sequentially concatenate and encrypt the first sending content and the encryption point set of each power grid field data based on a preset second national cryptographic algorithm to obtain the second sending content, and then send the second sending content to the query requester.
[0016] In some embodiments of this application, the query result includes multiple query field data; the field data determination module includes a field matching submodule, a field filtering submodule, and a field integration submodule; The field matching submodule is used to determine a field matching list based on the content access level, and to match the field matching list with the multiple query field data to obtain multiple first-class field data. The field filtering submodule is used to filter each field data to be filtered based on the plurality of primary field data to obtain a plurality of secondary field data; wherein, the field data to be filtered is the query field data other than the plurality of primary field data among the plurality of query field data; The field integration submodule is used to obtain multiple power grid field data based on the multiple first-class field data and the multiple second-class field data.
[0017] In some embodiments of this application, the field filtering submodule includes a single classifier construction unit, a field data classification unit, and a field data filtering unit; The single classifier construction unit is used to construct a field single classifier based on the multiple class-aspect data and a single classification algorithm. The field data classification unit is used to input each field data to be filtered into the field single classifier to obtain the field classification result corresponding to each field data to be filtered. The field data filtering unit is used to filter each field data according to the field classification result corresponding to each field data to be filtered, so as to obtain multiple second-class field data.
[0018] In some embodiments of this application, the encrypted site derivation module includes a field feature extraction submodule and a large model derivation submodule; The field feature extraction submodule is used to segment each power grid field data into words and extract features based on a convolutional neural network to obtain multiple segmented field features corresponding to each power grid field data. The large model derivation submodule is used to filter multiple segmented field features corresponding to each power grid field data based on a preset large model. The filtering is based on the semantic influence order, and the set of encryption sites for each power grid field data is determined according to the filtering results.
[0019] In some embodiments of this application, the large model derivation submodule includes a word segmentation and combination construction unit, a word segmentation and combination filtering unit, and an encryption site determination unit; The word segmentation combination construction unit is used to construct multiple first word segmentation combinations corresponding to each power grid field data based on the multiple word segmentation field features corresponding to each power grid field data. The word segmentation combination filtering unit is used to filter all first word segmentation combinations of each power grid field data according to the semantic influence of the first word segmentation combination on the corresponding power grid field data from high to low based on a preset large model, so as to obtain several second word segmentation combinations of each power grid field data. The encryption site determination unit is used to determine the encryption sites of multiple encryption segments of each power grid field data based on the union of all second word combinations of each power grid field data, and to determine the encryption site set of each power grid field data based on the encryption sites of multiple encryption segments of each power grid field data.
[0020] This application first determines the content access level based on the current query request, and then determines multiple power grid field data based on the query results obtained from the current query request. This allows for pre-screening of power grid field data to be encrypted based on the current query request, avoiding the encryption of all power grid data as in existing technologies. This avoids the waste of computing resources and time caused by encryption redundancy and improves the efficiency of power grid data communication. Furthermore, it extracts features from multiple power grid field data based on a convolutional neural network and derives an encryption point set using a large model. This further narrows down the encryption range in the power grid field data to be encrypted, further avoiding encryption redundancy and improving the efficiency of power grid data communication. By combining the features of the data to be encrypted with a large model, it can accurately determine the encryption points, avoiding encryption point errors and ensuring the security of power grid data communication. Finally, it encrypts and replaces the first transmission content based on the first national cryptographic algorithm and then encrypts and transmits the first transmission content and the encryption point set of each power grid field data based on the second national cryptographic algorithm. This double encryption ensures data security while reducing encryption density, thereby improving the communication efficiency of power grid data and meeting the communication security requirements of power grid data. Attached Figure Description
[0021] Figure 1 This is a flowchart illustrating a secondary encryption power grid data communication method according to certain embodiments of this application. Figure 2 This is a module structure diagram of a secondary encrypted power grid data communication device shown in some embodiments of this application. Detailed Implementation
[0022] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below in conjunction with the accompanying drawings are exemplary and are only used to explain some embodiments of this application, and should not be construed as limiting the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments shown in this application without inventive effort are within the protection scope of this application.
[0023] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, unless otherwise explicitly specified, "a plurality of" or "several" means two or more.
[0024] Existing power grid data security transmission schemes have several shortcomings: (1) Traditional data encryption algorithms used for data transmission are vulnerable to brute-force attacks, and their security gradually decreases as computing performance increases; (2) More complex data encryption algorithms offer higher security for data transmission, but encryption and decryption require extensive computation, wasting significant computing resources and time, resulting in low encryption communication efficiency and failing to meet the demand for large-volume real-time secure transmission of power grid data; (3) Existing power grid data security transmission typically involves multiple encryptions of all data, inevitably encrypting some data that does not affect data security, leading to encryption redundancy. Combined with the complex computations resulting from multiple encryptions, this adds unnecessary time to both encryption and decryption, thereby reducing data transmission efficiency and failing to meet the demand for rapid power grid response. Therefore, how to improve the encryption process of power grid data to ensure communication efficiency and security, and thus guarantee data security of the power grid system during intelligent operation and maintenance, remains a pressing technical problem to be solved in the current technology.
[0025] Based on the above technical background, please refer to Figure 1 This application provides a secondary encryption method for power grid data communication, including steps S101 to S104, each step of which is as follows: Step S101: Determine the content access level based on the current query request, and determine multiple power grid field data based on the content access level and the query results to be sent; wherein, the query results are obtained based on the current query request; each power grid field data includes the user identity identifier and the user's electricity address.
[0026] In some embodiments of this application, when determining the content access level based on the current query request, the content access level can be determined by rule matching based on the identity identifier of the queryer in the current query request, or by semantic understanding based on the request content in the current query request.
[0027] In some embodiments of this application, the query result includes multiple query field data; determining the multiple power grid field data based on the content access level and the query result to be sent specifically includes: Based on the content access level, a field matching list is determined, and based on the field matching list, it is matched with the multiple query field data to obtain multiple first-class field data; Based on the multiple primary field data, each field data to be filtered is filtered to obtain multiple secondary field data; wherein, the field data to be filtered is the query field data other than the multiple primary field data among the multiple query field data; Based on the multiple Class I field data and the multiple Class II field data, multiple power grid field data are obtained.
[0028] In some embodiments of this application, when determining the field matching list based on the content access level, it is preferable to determine the field matching list by means of preset rule matching.
[0029] This application first determines a field matching list based on the content access level, then matches multiple Class I field data. It can first determine some field data to be encrypted based on the field matching rules, and then filter the query field data other than Class I field data based on multiple Class I fields. It can determine some field data to be encrypted that is not recognized by the field matching rules but meets the encryption requirements, thereby accurately determining multiple power grid field data to be encrypted. This avoids encryption errors and reduces encryption redundancy, ensuring the communication efficiency and communication security requirements of power grid data.
[0030] In some embodiments of this application, the step of filtering each field data to be filtered based on the plurality of primary field data to obtain a plurality of secondary field data specifically includes: Based on the multiple single-class field data, a single-class classifier is constructed using a single-classification algorithm; Each field data to be filtered is input into the field single classifier to obtain the field classification result corresponding to each field data to be filtered. Based on the field classification results corresponding to each field to be filtered, the data of each field to be filtered is filtered to obtain multiple second-category field data.
[0031] In some embodiments of this application, the single-classification algorithm for constructing a single-class classifier can be a OneClassSVM in unsupervised learning algorithms, or an Autoencoder in deep learning algorithms.
[0032] Generally, unlike binary classifiers which use both positive and negative samples for training, single classifiers are trained with only one class of samples (positive or negative). This means that when predicting input data, a single classifier will directly classify input samples that do not belong to the same class as the training samples as "no," unlike binary classification which classifies positive samples as "yes" and negative samples as "no." Therefore, single classifiers can still stably predict input data even in scenarios with only one class of samples or where the number of samples from the two classes differs significantly. Specifically, if the classification result of the field to be filtered is "no," the corresponding field to be filtered is removed; otherwise, it is retained. The final binary field data consists of the field to be filtered that has a classification result of "yes."
[0033] This application first constructs a field single classifier based on multiple primary field data and a single classification algorithm. Then, it filters each field data to be filtered using the field single classifier to obtain multiple secondary field data. Based on the characteristics of the primary field data, it can determine the field data that is not identified by the field matching rules but meets the encryption requirements, thereby accurately determining multiple power grid field data to be encrypted and ensuring the communication security requirements of power grid data.
[0034] Step S102: Based on the convolutional neural network, feature extraction is performed on the multiple power grid field data, and based on the feature extraction results, the set of encrypted sites for each power grid field data is derived by combining the large model.
[0035] In some embodiments of this application, the step of extracting features from the multiple power grid field data based on a convolutional neural network, and deriving the set of encrypted sites for each power grid field data based on the feature extraction results and a large model, specifically includes: Each power grid field data is segmented into words and its features are extracted based on a convolutional neural network to obtain multiple segmented field features corresponding to each power grid field data. Based on a pre-defined large model, multiple segmented field features corresponding to each power grid field data are filtered. The filtering is based on the semantic influence order, and the set of encryption sites for each power grid field data is determined according to the filtering results.
[0036] In some embodiments of this application, the convolutional neural network may be a CNN or an improved model thereof, with a preferred embodiment being a CNN.
[0037] This application first segments each power grid field data into words and extracts features through a convolutional neural network to obtain multiple segmented field features corresponding to each power grid field data. Then, based on a large language model and combined with semantic influence order, the segmented field features are filtered to determine the set of encryption sites. This can determine the corresponding encryption sites according to the features of the power grid field data, avoid encryption site errors, and ensure the security of power grid data communication.
[0038] In some embodiments of this application, the step of filtering multiple segmented field features corresponding to each power grid field data based on a preset large model, filtering according to the semantic influence order, and determining the set of encryption sites for each power grid field data based on the filtering results, specifically includes: Based on the features of multiple word segmentation fields corresponding to each power grid field data, construct multiple first word segmentation combinations corresponding to each power grid field data; Based on the pre-set large model, according to the semantic influence of the first word segmentation combination on the corresponding power grid field data from high to low, all the first word segmentation combinations of each power grid field data are filtered to obtain several second word segmentation combinations of each power grid field data. Based on the union of all second word combinations for each power grid field data, determine the encryption sites of multiple encrypted word segments for each power grid field data, and based on the encryption sites of multiple encrypted word segments for each power grid field data, determine the encryption site set for each power grid field data.
[0039] In some embodiments of this application, when constructing multiple first word segmentation combinations for each power grid field data, each combination among the full combinations of multiple word segmentation field features corresponding to each power grid field data can be used as a first word segmentation combination.
[0040] In some embodiments of this application, the large model includes, but is not limited to, Wenxin Yiyan, Tongyi Qianwen, Xunfei Xinghuo, Deepseek, GPT-4, Kimi, or an open-source model finely tuned by Lora, with Deepseek being the preferred embodiment.
[0041] In some embodiments of this application, when filtering all first word segmentation combinations to obtain several second word segmentation combinations, a sequential sequence of first word segmentation combinations is first constructed according to their semantic influence from high to low. The filtering method can be to select several first word segmentation combinations located at the beginning of the sequential sequence, or to remove a certain percentage of first word segmentation combinations located at the end of the sequential sequence and then select the remaining first word segmentation combinations. Preferably, the number of second word segmentation combinations should not exceed 5.
[0042] The reason for considering determining the encryption points of multiple encrypted words based on the union of all second word segmentation combinations is that several second word segmentation combinations of the current power grid field data are obtained by filtering multiple first word segmentation combinations. The solution space formed by all first word segmentation combinations is the full combination of all word segmentation field features of the current power grid field data. Therefore, some word segmentation field features in the first / second word segmentation combinations may overlap with one or more word segmentation field features of other first / second word segmentation combinations. Thus, the union of all second word segmentation combinations can eliminate the overlap of word segmentation field features. Moreover, one word segmentation field feature corresponds to one encrypted word of the current power grid field data. Therefore, the encryption points of multiple encrypted words corresponding to the current power grid field data can be determined based on the union of all second word segmentation combinations, ensuring the accuracy and effectiveness of encryption.
[0043] This application first constructs multiple first word segmentation combinations based on the multiple word segmentation field features of each power grid field data. Then, it combines a large model to filter all first word segmentation combinations of each power grid field data. During the filtering, the first word segmentation combinations are filtered according to the semantic influence order, resulting in several second word segmentation combinations of each power grid field data. Then, the corresponding encryption site set is determined by the union of all second word segmentation combinations of each power grid field data. This can accurately filter word segmentation combinations and determine encryption sites based on the semantic influence order related to encryption, avoid encryption site errors, and ensure the security of power grid data communication.
[0044] Step S103: Based on the preset first national cryptographic algorithm and combined with the encryption point set, encrypt each power grid field data to obtain the first ciphertext corresponding to each power grid field data, and replace each first ciphertext in the power grid field data corresponding to the query result to obtain the first transmission content.
[0045] In some embodiments of this application, the first national cryptographic algorithm may be the SM1 algorithm or the SM4 algorithm, preferably the SM4 algorithm.
[0046] Step S104: Based on the preset second national cryptographic algorithm, the first transmission content and the set of encryption points of each power grid field data are sequentially concatenated and encrypted as a whole to obtain the second transmission content, and the second transmission content is sent to the query requester.
[0047] In some embodiments of this application, the second national cryptographic algorithm may be the SM1 algorithm, the SM4 algorithm, the SM2 or SM9 algorithm, or the SM3 algorithm, with the SM3 algorithm being preferred.
[0048] This application first determines the content access level based on the current query request, and then determines multiple power grid field data based on the query results obtained from the current query request. This allows for pre-screening of power grid field data to be encrypted based on the current query request, avoiding the encryption of all power grid data as in existing technologies. This avoids the waste of computing resources and time caused by encryption redundancy and improves the efficiency of power grid data communication. Furthermore, it extracts features from multiple power grid field data based on a convolutional neural network and derives an encryption point set using a large model. This further narrows down the encryption range in the power grid field data to be encrypted, further avoiding encryption redundancy and improving the efficiency of power grid data communication. By combining the features of the data to be encrypted with a large model, it can accurately determine the encryption points, avoiding encryption point errors and ensuring the security of power grid data communication. Finally, it encrypts and replaces the first transmission content based on the first national cryptographic algorithm and then encrypts and transmits the first transmission content and the encryption point set of each power grid field data based on the second national cryptographic algorithm. This double encryption ensures data security while reducing encryption density, thereby improving the communication efficiency of power grid data and meeting the communication security requirements of power grid data.
[0049] For a method corresponding to the one described above, please refer to [link to relevant documentation]. Figure 2 The present application provides a secondary encryption power grid data communication device, including a field data determination module 210, an encryption point derivation module 220, a primary encryption replacement module 230, and a secondary encryption transmission module 240. The field data determination module 210 is used to determine the content access level based on the current query request, and to determine multiple power grid field data based on the content access level and the query results to be sent; wherein, each power grid field data includes a user identity identifier and a user electricity address; the query results are obtained based on the current query request; The encryption site derivation module 220 is used to extract features from the multiple power grid field data based on a convolutional neural network, and derive the encryption site set for each power grid field data based on the feature extraction results and a large model. The encryption and replacement module 230 is used to encrypt each power grid field data based on a preset first national cryptographic algorithm and a set of encryption points, to obtain a first ciphertext corresponding to each power grid field data, and to replace each first ciphertext in the power grid field data corresponding to the query result to obtain the first transmission content. The secondary encryption sending module 240 is used to sequentially concatenate and encrypt the first sending content and the encryption point set of each power grid field data based on a preset second national cryptographic algorithm to obtain the second sending content, and then send the second sending content to the query requester.
[0050] In some embodiments of this application, the query result includes multiple query field data; the field data determination module 210 includes a field matching submodule, a field filtering submodule, and a field integration submodule; The field matching submodule is used to determine a field matching list based on the content access level, and to match the field matching list with the multiple query field data to obtain multiple first-class field data. The field filtering submodule is used to filter each field data to be filtered based on the plurality of primary field data to obtain a plurality of secondary field data; wherein, the field data to be filtered is the query field data other than the plurality of primary field data among the plurality of query field data; The field integration submodule is used to obtain multiple power grid field data based on the multiple first-class field data and the multiple second-class field data.
[0051] In some embodiments of this application, the field filtering submodule includes a single classifier construction unit, a field data classification unit, and a field data filtering unit; The single classifier construction unit is used to construct a field single classifier based on the multiple class-aspect data and a single classification algorithm. The field data classification unit is used to input each field data to be filtered into the field single classifier to obtain the field classification result corresponding to each field data to be filtered. The field data filtering unit is used to filter each field data according to the field classification result corresponding to each field data to be filtered, so as to obtain multiple second-class field data.
[0052] In some embodiments of this application, the encrypted site derivation module 220 includes a field feature extraction submodule and a large model derivation submodule; The field feature extraction submodule is used to segment each power grid field data into words and extract features based on a convolutional neural network to obtain multiple segmented field features corresponding to each power grid field data. The large model derivation submodule is used to filter multiple segmented field features corresponding to each power grid field data based on a preset large model. The filtering is based on the semantic influence order, and the set of encryption sites for each power grid field data is determined according to the filtering results.
[0053] In some embodiments of this application, the large model derivation submodule includes a word segmentation and combination construction unit, a word segmentation and combination filtering unit, and an encryption site determination unit; The word segmentation combination construction unit is used to construct multiple first word segmentation combinations corresponding to each power grid field data based on the multiple word segmentation field features corresponding to each power grid field data. The word segmentation combination filtering unit is used to filter all first word segmentation combinations of each power grid field data according to the semantic influence of the first word segmentation combination on the corresponding power grid field data from high to low based on a preset large model, so as to obtain several second word segmentation combinations of each power grid field data. The encryption site determination unit is used to determine the encryption sites of multiple encryption segments of each power grid field data based on the union of all second word combinations of each power grid field data, and to determine the encryption site set of each power grid field data based on the encryption sites of multiple encryption segments of each power grid field data.
[0054] This application first determines the content access level based on the current query request, and then determines multiple power grid field data based on the query results obtained from the current query request. This allows for pre-screening of power grid field data to be encrypted based on the current query request, avoiding the encryption of all power grid data as in existing technologies. This avoids the waste of computing resources and time caused by encryption redundancy and improves the efficiency of power grid data communication. Furthermore, it extracts features from multiple power grid field data based on a convolutional neural network and derives an encryption point set using a large model. This further narrows down the encryption range in the power grid field data to be encrypted, further avoiding encryption redundancy and improving the efficiency of power grid data communication. By combining the features of the data to be encrypted with a large model, it can accurately determine the encryption points, avoiding encryption point errors and ensuring the security of power grid data communication. Finally, it encrypts and replaces the first transmission content based on the first national cryptographic algorithm and then encrypts and transmits the first transmission content and the encryption point set of each power grid field data based on the second national cryptographic algorithm. This double encryption ensures data security while reducing encryption density, thereby improving the communication efficiency of power grid data and meeting the communication security requirements of power grid data.
[0055] It should be understood that the apparatus provided in the embodiments of this application corresponds to the aforementioned method. The secondary encryption power grid data communication apparatus provided in the embodiments of this application can implement the secondary encryption power grid data communication method provided in any embodiment of this application.
[0056] Adaptively, embodiments of this application also provide a computer device and a computer-readable storage medium.
[0057] The computer device includes: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor; The processor executes the computer program to implement a secondary encryption power grid data communication method according to this application.
[0058] The computer-readable storage medium stores multiple instructions adapted for loading by a processor to execute a secondary encrypted power grid data communication method according to this application.
[0059] The above description represents some embodiments of this application, providing a further detailed explanation of the purpose, technical solution, and beneficial effects of this application. It should be understood that the above-described embodiments of this application should not be construed as limiting this application. In particular, any changes, modifications, equivalent substitutions, and variations made by those skilled in the art within the spirit and principles of this application should be included within the scope of protection of this application.
Claims
1. A secondary encryption method for power grid data communication, characterized in that, include: Based on the current query request, the content access level is determined, and based on the content access level and the query results to be sent, multiple power grid field data are determined; wherein, the query results are obtained based on the current query request; each power grid field data includes the user's identity identifier and the user's electricity address; Based on a convolutional neural network, features are extracted from the multiple power grid field data, and based on the feature extraction results, the set of encrypted sites for each power grid field data is derived by combining the large model. Based on the preset first national cryptographic algorithm, combined with the set of encryption points, each power grid field data is encrypted to obtain the first ciphertext corresponding to each power grid field data, and each first ciphertext is replaced in the power grid field data corresponding to the query result to obtain the first sending content; Based on the preset second national cryptographic algorithm, the first sent content and the set of encryption points for each power grid field data are sequentially concatenated and encrypted as a whole to obtain the second sent content, which is then sent to the query requester.
2. The secondary encryption power grid data communication method according to claim 1, characterized in that, The query results include multiple query field data; the determination of multiple power grid field data based on the content access level and the query results to be sent specifically includes: Based on the content access level, a field matching list is determined, and based on the field matching list, it is matched with the multiple query field data to obtain multiple first-class field data; Based on the multiple primary field data, each field data to be filtered is filtered to obtain multiple secondary field data; wherein, the field data to be filtered is the query field data other than the multiple primary field data among the multiple query field data; Based on the multiple Class I field data and the multiple Class II field data, multiple power grid field data are obtained.
3. The secondary encryption power grid data communication method according to claim 2, characterized in that, The step of filtering each field data to be filtered based on the multiple primary field data to obtain multiple secondary field data specifically includes: Based on the multiple single-class field data, a single-class classifier is constructed using a single-classification algorithm; Each field data to be filtered is input into the field single classifier to obtain the field classification result corresponding to each field data to be filtered. Based on the field classification results corresponding to each field to be filtered, the data of each field to be filtered is filtered to obtain multiple second-category field data.
4. The secondary encryption power grid data communication method according to claim 1, characterized in that, The process involves extracting features from the multiple power grid field data using a convolutional neural network, and then deriving the set of encrypted sites for each power grid field data based on the feature extraction results and a large model. Specifically, this includes: Each power grid field data is segmented into words and its features are extracted based on a convolutional neural network to obtain multiple segmented field features corresponding to each power grid field data. Based on a pre-defined large model, multiple segmented field features corresponding to each power grid field data are filtered. The filtering is based on the semantic influence order, and the set of encryption sites for each power grid field data is determined according to the filtering results.
5. The secondary encryption power grid data communication method according to claim 4, characterized in that, The process involves using a pre-defined large model to filter multiple segmented field features corresponding to each power grid field data. The filtering is based on the semantic influence order, and the set of encryption points for each power grid field data is determined according to the filtering results. Specifically, this includes: Based on the features of multiple word segmentation fields corresponding to each power grid field data, construct multiple first word segmentation combinations corresponding to each power grid field data; Based on the pre-set large model, according to the semantic influence of the first word segmentation combination on the corresponding power grid field data from high to low, all the first word segmentation combinations of each power grid field data are filtered to obtain several second word segmentation combinations of each power grid field data. Based on the union of all second word combinations for each power grid field data, determine the encryption sites of multiple encrypted word segments for each power grid field data, and based on the encryption sites of multiple encrypted word segments for each power grid field data, determine the encryption site set for each power grid field data.
6. A secondary encryption power grid data communication device, characterized in that, It includes a field data determination module, an encryption point derivation module, a primary encryption replacement module, and a secondary encryption transmission module; The field data determination module is used to determine the content access level based on the current query request, and to determine multiple power grid field data based on the content access level and the query results to be sent; wherein, each power grid field data includes a user identity identifier and a user electricity address; the query results are obtained based on the current query request; The encryption site derivation module is used to extract features from the multiple power grid field data based on a convolutional neural network, and derive the encryption site set for each power grid field data based on the feature extraction results and a large model. The first encryption and replacement module is used to encrypt each power grid field data based on a preset first national cryptographic algorithm and a set of encryption points, to obtain a first ciphertext corresponding to each power grid field data, and to replace each first ciphertext in the power grid field data corresponding to the query result to obtain the first transmission content; The secondary encryption sending module is used to sequentially concatenate and encrypt the first sending content and the encryption point set of each power grid field data based on a preset second national cryptographic algorithm to obtain the second sending content, and then send the second sending content to the query requester.
7. The power grid data communication device with secondary encryption according to claim 6, characterized in that, The query results include multiple query field data; the field data determination module includes a field matching submodule, a field filtering submodule, and a field integration submodule; The field matching submodule is used to determine a field matching list based on the content access level, and to match the field matching list with the multiple query field data to obtain multiple first-class field data. The field filtering submodule is used to filter each field data to be filtered based on the plurality of primary field data to obtain a plurality of secondary field data; wherein, the field data to be filtered is the query field data other than the plurality of primary field data among the plurality of query field data; The field integration submodule is used to obtain multiple power grid field data based on the multiple first-class field data and the multiple second-class field data.
8. A secondary encryption power grid data communication device according to claim 7, characterized in that, The field filtering submodule includes a single classifier construction unit, a field data classification unit, and a field data filtering unit; The single classifier construction unit is used to construct a field single classifier based on the multiple class-aspect data and a single classification algorithm. The field data classification unit is used to input each field data to be filtered into the field single classifier to obtain the field classification result corresponding to each field data to be filtered. The field data filtering unit is used to filter each field data according to the field classification result corresponding to each field data to be filtered, so as to obtain multiple second-class field data.
9. A secondary encryption power grid data communication device according to claim 6, characterized in that, The encrypted site derivation module includes a field feature extraction submodule and a large model derivation submodule; The field feature extraction submodule is used to segment each power grid field data into words and extract features based on a convolutional neural network to obtain multiple segmented field features corresponding to each power grid field data. The large model derivation submodule is used to filter multiple segmented field features corresponding to each power grid field data based on a preset large model. The filtering is based on the semantic influence order, and the set of encryption sites for each power grid field data is determined according to the filtering results.
10. A secondary encryption power grid data communication device according to claim 9, characterized in that, The large model derivation submodule includes a word segmentation and combination construction unit, a word segmentation and combination filtering unit, and an encryption site determination unit; The word segmentation combination construction unit is used to construct multiple first word segmentation combinations corresponding to each power grid field data based on the multiple word segmentation field features corresponding to each power grid field data. The word segmentation combination filtering unit is used to filter all first word segmentation combinations of each power grid field data according to the semantic influence of the first word segmentation combination on the corresponding power grid field data from high to low based on a preset large model, so as to obtain several second word segmentation combinations of each power grid field data. The encryption site determination unit is used to determine the encryption sites of multiple encryption segments of each power grid field data based on the union of all second word combinations of each power grid field data, and to determine the encryption site set of each power grid field data based on the encryption sites of multiple encryption segments of each power grid field data.