User Data Protection Method for Cross-provincial and Cross-regional Power Trading Platform

Abstract

The present application relates to the technical field of data processing, and particularly to a user data protection method for a cross-provincial and cross-regional power trading platform. The method includes: analyzing the relationship between trading attributes and trading behaviors through user data in the cross-provincial and cross-regional power trading platform, and constructing trading privacy sensitivity by combining the differences between the trading attributes of different users; constructing the user trading correlation degree of each type of power trading data of each user based on the correlation relationship between the same type of power trading data of different users in the power trading platform; obtaining the necessary trading attributes of each user based on the trading privacy sensitivity and the user trading correlation degree, and encrypting the user data based on the necessary trading attributes in combination with multiple encryption algorithms, reducing the leakage risk of user data in the cross-provincial and cross-regional power trading platform when being accessed by adopting a single key generation strategy, and improving the security of user data access.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and specifically relates to a method for protecting user data of a cross-provincial and cross-regional power trading platform. Background Art

[0002] A cross-provincial and cross-regional power trading platform generally refers to a platform that provides services for power trading behaviors occurring between regional or provincial power grids formed under the responsibility of each operating entity. During the period when a user completes a power transaction through the cross-provincial and cross-regional power trading platform according to power demand, the cross-provincial and cross-regional power trading platform usually retains the user data throughout the period, including: transaction contracts, user information, transaction amounts, user units, authorization documents, etc. These user data not only help the cross-provincial and cross-regional power trading platform to perform power dispatching and trading quickly and accurately, but also involve the protection of user privacy information.

[0003] Since a large amount of different types of user data is stored in the cross-provincial and cross-regional power trading platform and a large number of power transactions are carried out, it is necessary to achieve encrypted protection of data without leaking information. Due to the different sensitivities and importance of different types of user data on the cross-provincial and cross-regional power trading platform, and the different access permissions of different users to the cross-provincial and cross-regional power trading platform, when using Attribute-Based Encryption (ABE) to encrypt user data, the impact of different types of data on user attributes is ignored, and a single key generation strategy makes the user data in the cross-provincial and cross-regional power trading platform have a leakage risk when being accessed. Summary of the Invention

[0004] To solve the above technical problems, this application provides a method for protecting user data of a cross-provincial and cross-regional power trading platform to solve the existing problems.

[0005] The method for protecting user data of a cross-provincial and cross-regional power trading platform of this application adopts the following technical solutions:

[0006] An embodiment of this application provides a method for protecting user data of a cross-provincial and cross-regional power trading platform, and the method includes the following steps:

[0007] Collect various power trading data of each user during each transaction in the power trading platform, including the transaction power consumption of the user;

[0008] Construct the weight coefficients between the transaction power consumption of each user and the rest of various power trading data based on the correlation between the transaction power consumption of each user and the rest of various power trading data; based on the differences between the same type of power trading data of all users, combine the weight coefficients to construct the transaction privacy sensitivity of the rest of various power trading data of each user except the transaction power consumption;

[0009] Construct the user transaction correlation degree of each type of power transaction data of each user based on the correlation between the same type of power transaction data of different users.

[0010] Determine the necessity degree of the transaction attributes of various power transaction data other than the transaction power for each user based on the transaction privacy sensitivity and the user transaction correlation degree; construct the necessary transaction attribute set for each user based on the necessity degree of the transaction attributes of the various power transaction data other than the transaction power for each user.

[0011] Based on the necessary transaction attribute set of each user, combined with the encryption algorithm, encrypt and protect the data of each user.

[0012] In one embodiment, the process of obtaining the weight coefficient is as follows:

[0013] Take the various power transaction data at the preset number of transactions of each user as the various historical transaction data of each user; for each user, take all types of historical power transaction data of the user as the input of the partial correlation analysis algorithm, where the transaction power is used as the dependent variable and the other various power transaction data are used as independent variables, and the output is the correlation coefficient between the transaction power of the user and the other various power transaction data, denoted as the weight coefficient.

[0014] In one embodiment, the process of obtaining the transaction privacy sensitivity is as follows:

[0015] Denote the set composed of the same type of power transaction data at the most recent transaction of all users as the transaction attribute set, so as to obtain the respective transaction attribute sets of all users.

[0016] For each transaction attribute set, take all elements in the transaction attribute set as the input of the clustering algorithm, and denote the output clustering clusters as the respective first clustering clusters of the transaction attribute set.

[0017] Construct the transaction privacy sensitivity of various power transaction data other than the transaction power for each user based on the number of elements in the first clustering cluster and the weight coefficient.

[0018] In one embodiment, the expression of the transaction privacy sensitivity is:

[0019] , where represents the transaction privacy sensitivity of the j-th type of power transaction data other than the transaction power of user i, N represents the total number of users, represents the number of elements in the first clustering cluster where the j-th type of power transaction data other than the transaction power of user i is located, represents the weight coefficient between the transaction power of user i and the j-th type of power transaction data other than the transaction power.

[0020] In one embodiment, the process of obtaining the user transaction correlation degree is as follows:

[0021] Obtain the transaction attribute sequences of each user; for each first clustering cluster of each transaction attribute set, obtain the Euclidean distance between each element in the first clustering cluster and the clustering center, and calculate the Kendall correlation coefficient between the transaction attribute sequences of each user in the first clustering cluster and each other user; construct the user transaction correlation degree of each type of power transaction data of each user based on the Euclidean distance and the Kendall correlation coefficient.

[0022] In one embodiment, the transaction attribute sequence is: a sequence composed of all types of power transaction data at the time of the most recent transaction of each user.

[0023] In one embodiment, the expression of the user transaction correlation degree is:

[0024] , where in the formula, represents the user transaction correlation degree of the j-th type of power transaction data other than the transaction power of user i; represents the Euclidean distance of the j-th type of power transaction data of user i; represents the Kendall correlation coefficient between user i and the m-th user in the first clustering cluster where the j-th type of power transaction data of user i is located; represents the number of elements in the first clustering cluster where the j-th type of power transaction data of user i is located; is a positive number preset by humans.

[0025] In one embodiment, the transaction attribute necessity degree is: the sum value of the normalized value of the transaction privacy sensitivity of each type of power transaction data other than the transaction power of each user and the normalized value of the user transaction correlation degree.

[0026] In one embodiment, the process of obtaining the necessary transaction attribute set is:

[0027] Calculate the average value of the transaction privacy sensitivities of all power transaction data of each user as the necessary segmentation threshold; regard the power transaction data of each user whose transaction privacy sensitivity is greater than or equal to the necessary segmentation threshold as the necessary transaction attributes of each user, and regard the set composed of all necessary transaction attributes of each user as the necessary transaction attribute set of each user.

[0028] In one embodiment, the process of encrypting and protecting the data of each user is:

[0029] Taking the set of necessary transaction attributes of each user as the input of the attribute encryption algorithm, the output is the first ciphertext of each user's data and the initial key; taking the initial key and the preset encryption policy as the input of the key-policy based encryption algorithm, the output is the second ciphertext and the user private key; when each user's data is transmitted, the data is encrypted through the first ciphertext and the second ciphertext of each user, and the data is decrypted through the user private key of each user.

[0030] The present application has at least the following beneficial effects:

[0031] The present application analyzes the relationship between transaction attributes and transaction behaviors and the differences between the transaction attributes of different users through the user data in the cross-provincial and cross-regional power trading platform, constructs the transaction privacy sensitivity of various power trading data of each user, which considers the contribution degree of the user's transaction attributes to the transaction behavior and the differences between user needs and consumption habits, and improves the accuracy of the sensitivity analysis of various user transaction attributes to the transaction behavior; constructs the user transaction correlation degree of each kind of power trading data of each user based on the correlation relationship between the same kind of power trading data of different users in the power trading platform, and analyzes the influence degree of different transaction attributes on the transaction behaviors between users; constructs the necessary degree of transaction attributes of various power trading data of each user based on the transaction privacy sensitivity and the user transaction correlation degree, obtains the necessary transaction attributes of each user, and encrypts the user data based on the necessary transaction attributes in combination with the AES algorithm and the CP-ABE algorithm, reducing the leakage risk of the user data in the cross-provincial and cross-regional power trading platform when being accessed by adopting a single key generation strategy, and improving the security of user data access. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0033] Figure 1 It is a flowchart of the user data protection method for the cross-provincial and cross-regional power trading platform provided by the present application;

[0034] Figure 2 It is a schematic diagram of the acquisition process of the user transaction correlation degree. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] To further elaborate on the technical means and effects adopted by this application to achieve the intended invention purpose, the following describes in detail the specific implementation manner, structure, features, and effects of the user data protection method for the cross-provincial and cross-regional power trading platform proposed according to this application in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs.

[0037] The following specifically describes the specific solution of the user data protection method for the cross-provincial and cross-regional power trading platform provided by this application in combination with the accompanying drawings.

[0038] A user data protection method for the cross-provincial and cross-regional power trading platform provided by an embodiment of this application.

[0039] Specifically, the following user data protection method for the cross-provincial and cross-regional power trading platform is provided. Please refer to Figure 1 , and this method includes the following steps:

[0040] Step S1, collect various power trading data of each user during each transaction in the power trading platform, including the transaction power consumption of the user.

[0041] Obtain various power trading data of each user during each transaction in the cross-provincial and cross-regional power trading platform. The power trading data of the user includes user type, transaction power consumption, transaction unit price, transaction time, maximum power load, minimum power load, power consumption category, and contract type. Among them, the user type refers to power generation enterprises, power sales companies, electricity users, etc., the power consumption category refers to industrial electricity, commercial electricity, residential electricity, etc., and the contract type refers to long-term trading contracts, temporary trading contracts, etc.

[0042] Perform data cleaning on all the obtained user data, and delete the data with incomplete information and duplicates.

[0043] Step S2, construct the weight coefficients between the transaction power consumption of each user and the rest of the various power trading data based on the correlation between the transaction power consumption of each user and the rest of the various power trading data; based on the differences between the same kind of power trading data of all users, combine the weight coefficients to construct the transaction privacy sensitivity of the rest of the various power trading data of each user except the transaction power consumption.

[0044] As an important hub of the regional power grid, the power trading platform conducts a large number of power trading activities at all times. Behind these trading activities, there are many different user entities, and the trading content also varies greatly. Different users have different access rights on the power trading platform. For example, electricity sales companies need to conduct transactions with multiple power users. Power users can only view their own transaction records, while electricity sales companies can view the transaction records of all power users they trade with. Therefore, in order to ensure the security of user data, it is necessary to encrypt the user data in the cross-provincial and cross-regional power trading platform. However, the traditional attribute-based encryption method adopts a single key generation strategy, ignoring the different impacts of different types of data on user attributes, resulting in a risk of leakage during data access.

[0045] (1) There are different trading behaviors in the power trading platform, such as temporary trading, short-term trading, long-term trading, etc. Behind each trading behavior, there are corresponding trading attributes, such as transaction amount, transaction type, role of the trading entity, etc. There are significant differences between the trading behaviors of different users, and there are also large differences in the contribution degrees of the trading attributes of different users to the trading results. For example, the transaction amount reflects the behavior patterns of large and medium-sized enterprises and small users; the transaction type, such as long-term trading, temporary trading, etc., directly affects the stability of power dispatching; the role of the trading entity, such as power generation enterprises, electricity sales companies, electricity users, etc., determines the sensitivity of its data security.

[0046] Therefore, taking user i as an example, obtain various power trading data when user i has the most recent g transactions as the various historical power trading data of user i. Preferably, in the embodiments of the present application, the value of g is set to 100. As other embodiments of the present application, the implementer can set the value of g according to the actual situation. Take all the various historical power trading data of user i as the input of the partial correlation analysis algorithm. Among them, take the transaction power as the dependent variable, and take the rest of the various power trading data as the independent variables, analyze the correlation coefficient between the transaction power and the rest of the various power trading data, and the output is the correlation coefficient between the transaction power of user i and the rest of the various power trading data, denoted as the weight coefficient. The larger the weight coefficient, the greater the contribution degree of the power trading data corresponding to the weight coefficient to the transaction of user i. Among them, the partial correlation analysis is a well-known technology, and the specific process will not be elaborated.

[0047] (2) Further, there are significant differences in the sensitivity of transaction attributes of different users on the power trading platform to privacy protection. Such differences mainly stem from the specific needs, consumption habits of users, and their role positioning in the power market. For example, the electricity price strategy of an electricity sales company is directly related to its market competitiveness and commercial interests. Therefore, the unit price of electricity in such transactions is often regarded as a trade secret, and there are often significant differences in the electricity unit prices among different electricity sales companies. For ordinary electricity users, the differences in their electricity prices are relatively small. Therefore, the sensitivity of electricity prices in terms of privacy protection is relatively low. However, there are significant differences in the electricity trading frequency, electricity trading amount, and electricity load conditions, which can reflect their living habits and thus have a relatively high privacy sensitivity. Therefore, by analyzing the differences in various electricity trading data among different users, the transaction privacy sensitivity of each type of electricity trading data for each user is constructed, specifically as follows:

[0048] Obtain the electricity trading data of each user at the time of their most recent transaction on the power trading platform. Denote the set composed of the a-th type of electricity trading data of all users at the time of their most recent transaction as the a-th transaction attribute set , thus obtaining the various transaction attribute sets of all users. For each transaction attribute set, take all the elements in the transaction attribute set as the input of the AP (affinity propagation) clustering algorithm, and denote the output clustering clusters as the respective first clustering clusters of the transaction attribute set. Among them, the AP clustering algorithm is a well-known technology, and the specific process will not be elaborated here.

[0049] It should be noted that for the clustering of all elements in the transaction attribute set, the implementer can also use other clustering algorithms to cluster all elements in the transaction attribute set, and this application does not make specific restrictions.

[0050] The smaller the number of elements in the first clustering cluster where the a-th type of electricity trading data of user i is located, the more likely it is that the a-th type of electricity trading data of user i has a relatively high privacy sensitivity for user i.

[0051] (3) Based on the above analysis, construct the transaction privacy sensitivity of various electricity trading data of user i except for the transaction electricity volume, and the expression is:

[0052] , where in the formula, represents the transaction privacy sensitivity of the j-th type of electricity trading data of user i except for the transaction electricity volume, N represents the total number of users, represents the number of elements in the first clustering cluster where the j-th type of the said other electricity trading data of user i is located, represents the weight coefficient between the transaction electricity volume of user i and the j-th type of the said other electricity trading data.

[0053] The greater the weight coefficient of the remaining j - th type of power trading data of user i, the more important the attribute of this type of power trading data of user i is, and this attribute can more affect the trading behavior of user i, and thus the trading privacy sensitivity is greater; the fewer the number of users in the clustering cluster where this type of power trading data of user i is located, the greater the difference between user i and other users in this type of power trading data, indicating that this type of power trading data can more reflect the unique power trading characteristics of user i, and the higher the sensitivity degree of user i to this type of power trading data, indicating that this type of power trading data is more likely to be a sensitive trading attribute of user i, and thus the value of the trading privacy sensitivity is greater.

[0054] Step S3: Construct the user trading correlation degree of each type of power trading data of each user based on the correlation situation between the same type of power trading data of different users; determine the trading attribute necessity of each type of power trading data other than the trading power quantity of each user based on the trading privacy sensitivity and the user trading correlation degree; construct the necessary trading attribute set of each user based on the trading attribute necessity of the remaining various types of power trading data of each user.

[0055] The trading behaviors between different users in the power trading platform form a complex network, and there are interdependent and supportive relationships between each trading entity. However, due to factors such as different demands of different users and changes in market strategies, different trading attributes in the power trading platform affect the trading behaviors between users to varying degrees.

[0056] Analyze the influence degree of different trading attributes on the correlation between users, and construct the user trading correlation degree of each type of power trading data of each user, specifically:

[0057] (1) Denote the sequence composed of all types of power trading data at the most recent transaction of each user as the trading attribute sequence of each user; for each first clustering cluster of each trading attribute set, obtain the Euclidean distance between each element in the first clustering cluster and the clustering center, and at the same time, calculate the Kendall correlation coefficient between each user and the trading attribute sequences of each user in its first clustering cluster. The calculations of both the Euclidean distance and the Kendall correlation coefficient are well - known techniques, and the specific process will not be elaborated. The greater the Euclidean distance and the smaller the Kendall correlation coefficient, the weaker the correlation relationship between each user and other users in its first clustering cluster, and this type of power trading data is more likely to be a non - core trading attribute of this user.

[0058] (2) Based on the above analysis, calculate the user trading correlation degree of each type of power trading data other than the trading power quantity of each user, and the expression is:

[0059] , where in the formula, Denotes the user transaction correlation degree of the j-th type of power transaction data other than the transaction power of user i; Denotes the Euclidean distance of the j-th type of power transaction data other than the above-mentioned of user i; Denotes the Kendall correlation coefficient between user i and the m-th user in the first clustering cluster where the j-th type of power transaction data other than the above-mentioned of user i is located; Denotes the number of elements in the first clustering cluster where the j-th type of power transaction data other than the above-mentioned of user i is located; Is a positive number preset by humans, and its function is to prevent the denominator from being zero. Preferably, in the embodiments of the present application, The value of is set to 0.01. As other embodiments of the present application, the implementer can set the value according to the actual situation.

[0060] Therefore, when the influence degree of the j-th type of power transaction data other than the transaction power of user i in the power trading platform on the transaction behavior between users is relatively large, after clustering according to this type of power transaction data in the power trading platform, user i and other users in the first clustering cluster where it is located are more similar in this type of power transaction data, that is, user i is closer to the central position in the first clustering cluster, and the Euclidean distance of this type of power transaction data of user i is smaller; at the same time, the influence degree of this type of power transaction data on the transaction behavior of user i is greater, and using this type of power transaction data for clustering can more effectively gather users with similar transaction behaviors together, and the calculated Kendall correlation coefficient between user i and the transaction attributes of other users in the clustering cluster where it is located is larger; furthermore, the user transaction correlation degree of this type of attribute of user i is greater, indicating that the influence degree of this type of power transaction data of user i on the transaction behavior between users is greater.

[0061] (3) For each user in the power trading platform, calculate the transaction attribute necessity of each user's various power transaction data other than the transaction power according to the transaction privacy sensitivity and the user transaction correlation degree, and the expression is:

[0062] , where in the formula, Is the transaction attribute necessity of the j-th type of power transaction data other than the transaction power of user i, Denotes the transaction privacy sensitivity of the j-th type of power transaction data other than the above-mentioned of user i, Denotes the user transaction correlation degree of the j-th type of power transaction data other than the above-mentioned of user i, Is a normalization function.

[0063] Calculate the average value of the transaction privacy sensitivities of all the power transaction data of each user as the necessary segmentation threshold; use the power transaction data of each user with a transaction privacy sensitivity greater than or equal to the necessary segmentation threshold as the necessary transaction attributes of each user, and use the set composed of all the necessary transaction attributes of each user as the necessary transaction attribute set of each user.

[0064] Step S4: Based on the necessary transaction attribute sets of each user, combine an encryption algorithm to encrypt and protect the data of each user.

[0065] Use the necessary transaction attribute set of each user in the power trading platform as the input of the AES algorithm to encrypt the data of each user, and the output is the first ciphertext and the initial key of the data of each user. Use the initial key and the encryption policy as the input of the CP-ABE (Ciphertext-Policy Attribute-Based Encryption) algorithm for encryption, and the output is the second ciphertext and the user private key. Preferably, in the embodiment of the present application, the BSW scheme is adopted for the encryption policy. As other embodiments of the present application, the implementer can set the encryption policy according to the actual situation. Among them, the ASE algorithm, the CP-ABE algorithm, and the BSW scheme are all well-known technologies, and the specific processes will not be elaborated. Encrypt the data during the data transmission of each user through the first ciphertext and the second ciphertext of each user, and decrypt the data through the user private key of each user, so as to realize the protection of user data. Among them, the data encryption and decryption technologies are well-known technologies, and the specific processes will not be elaborated.

[0066] It should be noted that for the encryption of user data based on necessary transaction attributes, the present application only provides one encryption method. There are many existing encryption methods, and the implementer can also use other encryption algorithms for encryption, and the present application does not make specific restrictions. For the acquisition of the second ciphertext, the present application only provides one method for obtaining the ciphertext. There are many existing methods for obtaining the ciphertext, and the implementer can also use other encryption algorithms to obtain the second ciphertext, and the present application does not make specific restrictions.

[0067] The schematic diagram of the acquisition process of the user transaction correlation degree is as Figure 2 shown.

[0068] In summary, in the embodiments of the present application, the relationship between transaction attributes and transaction behaviors and the differences between the transaction attributes of different users are analyzed through user data in the cross-provincial and cross-regional power trading platform, and the transaction privacy sensitivity of various power trading data of each user is constructed. It takes into account the contribution degree of the user's transaction attributes to the transaction behavior and the differences between user needs and consumption habits, and improves the accuracy of the sensitivity analysis of various user transaction attributes to the transaction behavior; based on the correlation relationship between the same power trading data of different users in the power trading platform, the user transaction correlation degree of each power trading data of each user is constructed, and the influence degree of different transaction attributes on the transaction behavior between users is analyzed; based on the transaction privacy sensitivity and the user transaction correlation degree, the transaction attribute necessity of various power trading data of each user is constructed, the necessary transaction attributes of each user are obtained, and the user data is encrypted based on the necessary transaction attributes in combination with the AES algorithm and the CP-ABE algorithm, reducing the leakage risk of user data in the cross-provincial and cross-regional power trading platform when being accessed by using a single key generation strategy, and improving the security of user data access.

[0069] It should be noted that the above sequence of the embodiments of the present application is only for description and does not represent the advantages or disadvantages of the embodiments. And the above specific embodiments of the present application have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0070] Each embodiment in the present application is described in a progressive manner. The same or similar parts between each embodiment can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

[0071] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; modifying the technical solutions recorded in the foregoing embodiments, or equivalently replacing some of the technical features, does not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of each embodiment of the present application, and should all be included in the protection scope of the present application.

Claims

1. A user data protection method for an inter-provincial and inter-regional power trading platform, characterized in that: The method comprises the following steps: Collect various power transaction data of each user in the power trading platform, including the user's transaction power; Based on the correlation between the transaction power of each user and other various power transaction data, a weight coefficient between the transaction power of each user and other various power transaction data is constructed; based on the differences between the same power transaction data of all users, combined with the weight coefficient, the transaction privacy sensitivity of various power transaction data other than the transaction power of each user is constructed; Based on the correlation between the same type of power transaction data of different users, a user transaction correlation of each type of power transaction data of each user is constructed; based on the transaction privacy sensitivity and the user transaction correlation, the transaction attribute necessity of various power transaction data of each user other than the transaction amount is determined; based on the transaction attribute necessity of the various other power transaction data of each user, a necessary transaction attribute set of each user is constructed; Based on the necessary transaction attribute set of each user, the encryption algorithm is used to encrypt and protect the data of each user; The process of encrypting and protecting each user's data is as follows: The necessary transaction attribute set of each user is used as the input of the attribute encryption algorithm, and the output is the first ciphertext and initial key of each user's data; the initial key and the preset encryption strategy are used as the input of the encryption algorithm based on the key strategy, and the output is the second ciphertext and the user's private key; when each user's data is transmitted, the data is encrypted by the first ciphertext and the second ciphertext of each user, and the data is decrypted by the user's private key.

2. The user data protection method for an inter-provincial and inter-regional power trading platform according to claim 1, characterized in that: The process of obtaining the weight coefficient is as follows: The various electricity trading data of each user at the time of a preset number of transactions are used as the various historical trading data of each user; for each user, all kinds of historical electricity trading data of the user are used as the input of the partial correlation analysis algorithm, wherein the trading electricity is used as the dependent variable, and the other various electricity trading data are used as independent variables, and the output is the correlation coefficient between the user's trading electricity and the other various electricity trading data, which is recorded as the weight coefficient.

3. The user data protection method for an inter-provincial and inter-regional power trading platform according to claim 1, characterized in that: The process of obtaining the transaction privacy sensitivity is as follows: The set of the same type of power transaction data of all users at the most recent transaction is recorded as a transaction attribute set, thereby obtaining each transaction attribute set of all users; For each transaction attribute set, all elements in the transaction attribute set are used as inputs of the clustering algorithm, and each output cluster is recorded as each first cluster of the transaction attribute set; Based on the number of elements in the first cluster and the weight coefficient, the transaction privacy sensitivity of various power transaction data of each user except the transaction amount is constructed.

4. The user data protection method for an inter-provincial and inter-regional power trading platform according to claim 3, characterized in that: The expression of the transaction privacy sensitivity is: , where represents the transaction privacy sensitivity of the jth type of electricity transaction data of user i except the transaction amount, N represents the total number of users, represents the number of elements in the first cluster where the remaining j-th type of electricity transaction data of user i is located, Represents the weight coefficient between the transaction power of user i and the remaining j-th type of power transaction data.

5. The user data protection method for an inter-provincial and inter-regional power trading platform according to claim 3, characterized in that: The process of obtaining the user transaction correlation is as follows: Obtain the transaction attribute sequence of each user; for each first cluster of each transaction attribute set, obtain the Euclidean distance between each element in the first cluster and the cluster center, and calculate the Kendall correlation coefficient between the transaction attribute sequence of each user in the first cluster and each other user; based on the Euclidean distance and the Kendall correlation coefficient, construct the user transaction correlation of each type of power transaction data of each user.

6. The user data protection method for the inter-provincial and inter-regional power trading platform according to claim 5, characterized in that: The transaction attribute sequence is a sequence consisting of all types of power transaction data of each user at the time of the most recent transaction.

7. The user data protection method for an inter-provincial and inter-regional power trading platform according to claim 5, characterized in that: The expression of the user transaction correlation is: , where Indicates the user transaction correlation of the jth type of power transaction data of user i except the transaction power; The Euclidean distance representing the remaining j-th type of electricity transaction data of user i; represents the kendall correlation coefficient between user i and the mth user in the first cluster where the remaining jth type of power transaction data of user i is located; Represents the number of elements in the first cluster where the remaining j-th type of electricity transaction data of user i is located; A positive number is preset artificially.

8. The user data protection method for an inter-provincial and inter-regional power trading platform according to claim 1, characterized in that: The transaction attribute necessity is: the sum of the normalized transaction privacy sensitivity value of each type of electricity transaction data of each user except the transaction amount and the normalized value of the user transaction correlation.

9. The user data protection method for an inter-provincial and inter-regional power trading platform according to claim 1, characterized in that: The process of obtaining the necessary transaction attribute set is as follows: The average transaction privacy sensitivity of all power transaction data of each user is calculated as the necessary segmentation threshold; the power transaction data of each user whose transaction privacy sensitivity is greater than or equal to the necessary segmentation threshold is taken as the necessary transaction attribute of each user, and the set of all necessary transaction attributes of each user is taken as the necessary transaction attribute set of each user.

Images