Shared charging station user privacy protection method and system

Abstract

The invention relates to the field of shared charging piles, in particular to a shared charging station user privacy protection method and system, and the method specifically comprises the steps: obtaining a charging record of a shared charging station user, obtaining a preset privacy budget of each field, calculating the correlation of different fields in the charging record, and obtaining a preset privacy budget of each field; obtaining the privacy budget of each field according to the correlation of the fields and the preset privacy budget; encoding data items in the charging record, determining the probability distribution of each encoded data item of a field based on the privacy budget of the field, determining a plurality of random numbers according to the probability distribution of the data items, and constructing a random number pool corresponding to the data items by using the plurality of random numbers; and extracting a random number from the random number pool corresponding to the data item, and generating a report value of the data item according to the probability distribution and the extracted random number. According to the invention, data leakage possibly caused by field correlation can be eliminated.

Description

Technical Field

[0001] The present invention relates to the field of shared charging piles, and in particular to a method and system for protecting user privacy at a shared charging station. Background Art

[0002] With the popularity of electric vehicles and the increase in charging demand, the number and layout of charging piles, as an important infrastructure for electric vehicle charging, are also expanding. With the popularity of shared charging piles and the increase in data collection, the issue of user privacy protection has received increasing attention. When using shared charging piles, users often need to provide personal information and location information, and charging behavior will also be recorded. While these data provide service optimization and user behavior analysis for the platform, they also bring potential privacy risks. If not effectively protected, the user's identity, behavior pattern and location information may be maliciously exploited, resulting in privacy leakage and security threats.

[0003] In data analysis and charging prediction of shared charging stations, analysis is usually performed based on the data of shared charging piles. However, when it comes to third parties that are not fully trusted, data privacy and security become a key issue. In this case, exposing the original data directly to third parties may lead to the leakage of user privacy or data abuse. Through Local Differential Privacy (LDP), the user's data has been randomized before uploading. Even if a third party obtains this data, it is difficult to restore the user's real information, thereby effectively protecting user privacy. The privacy protection strength in LDP is usually controlled by a privacy budget. However, some fields of charging data have a strong correlation. The fixed privacy budget method ignores the correlation of the fields. If two fields are highly correlated, the privacy leakage information of one field can be used to infer the information of the other field, which brings potential privacy leakage risks. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a method for protecting user privacy of a shared charging station, the method comprising the following steps: Obtain charging records of users of the shared charging station, obtain a preset privacy budget for each field, calculate the correlation between different fields in the charging records, and obtain a privacy budget for each field based on the correlation of the fields and the preset privacy budget; Encode the data items in the charging record, determine the probability distribution of each encoded data item of the field based on the privacy budget of the field, determine multiple random numbers according to the probability distribution of the data items, and use the multiple random numbers to construct a random number pool corresponding to the data items; Take a random number from the random number pool corresponding to the data item, and generate the report value of the data item based on the probability distribution and the taken random number.

[0005] Preferably, the calculation of the correlation of different fields in the charging record and obtaining the privacy budget of each field according to the correlation of the fields and the preset privacy budget are specifically as follows: Calculate the correlation matrix between each field and other fields, calculate the sum of the correlations between the field and other fields through the correlation matrix, calculate the inverse of the sum of the correlations of each field, and normalize the inverse of the field to obtain the correlation weight of each field; The average value of the relevance weights of all fields is calculated, the ratio of the relevance weight of the field to the average value is calculated, and the product of the ratio and the preset privacy budget of the field is used as the privacy budget of the field.

[0006] Preferably, the determining of multiple random numbers according to the probability distribution of the data item and the use of the multiple random numbers to construct a random number pool corresponding to the data item are specifically: Determine the number of intervals according to the number of bits after the data item is encoded, and the number of intervals is the same as the number of bits after the encoding; Calculate the cumulative probability range in each interval, generate at least one random number in each cumulative probability range, the size of the random number is within the cumulative probability range, so that the number of random numbers finally generated is positively correlated with the range size of each cumulative probability range, and put the generated random number into the random number pool corresponding to the data item.

[0007] Preferably, the data item is encoded using one-hot encoding, the number of encoded bits is the encoding length after one-hot encoding, and each encoding bit corresponds to an interval.

[0008] Preferably, the calculation is performed on the cumulative probability range in each interval, specifically: Calculate the probability distribution of the encoded data item. Each encoding bit has a probability. The lower limit of the cumulative probability range of the i-th interval is the sum of the probabilities of the previous i-1 encoding bits, and the upper limit is the sum of the probabilities of the previous i encoding bits. i is a positive integer, and 1≤i≤N, N is the number of encoded bits.

[0009] In another aspect, the present invention provides a shared charging station user privacy protection system, the system comprising the following modules: A privacy budget determination module is used to obtain the charging records of the shared charging station users, obtain the preset privacy budget of each field, calculate the correlation of different fields in the charging records, and obtain the privacy budget of each field according to the correlation of the fields and the preset privacy budget; A random number determination module, used to encode data items in the charging record, determine the probability distribution of each encoded data item of the field based on the privacy budget of the field, and determine multiple random numbers according to the probability distribution of the data items, and use the multiple random numbers to construct a random number pool corresponding to the data items; The privacy processing module is used to take out a random number from the random number pool corresponding to the data item, and generate a report value of the data item according to the probability distribution and the taken random number.

[0010] Preferably, the calculation of the correlation of different fields in the charging record and obtaining the privacy budget of each field according to the correlation of the fields and the preset privacy budget are specifically as follows: Calculate the correlation matrix between each field and other fields, calculate the sum of the correlations between the field and other fields through the correlation matrix, calculate the inverse of the sum of the correlations of each field, and normalize the inverse of the field to obtain the correlation weight of each field; The average value of the relevance weights of all fields is calculated, the ratio of the relevance weight of the field to the average value is calculated, and the product of the ratio and the preset privacy budget of the field is used as the privacy budget of the field.

[0011] Preferably, the determining of multiple random numbers according to the probability distribution of the data item and the use of the multiple random numbers to construct a random number pool corresponding to the data item are specifically: Determine the number of intervals according to the number of bits after the data item is encoded, and the number of intervals is the same as the number of bits after the encoding; Calculate the cumulative probability range in each interval, generate at least one random number in each cumulative probability range, the size of the random number is within the cumulative probability range, so that the number of random numbers finally generated is positively correlated with the range size of each cumulative probability range, and put the generated random number into the random number pool corresponding to the data item.

[0012] Preferably, the data item is encoded using one-hot encoding, the number of encoded bits is the encoding length after one-hot encoding, and each encoding bit corresponds to an interval.

[0013] Preferably, the calculation is performed on the cumulative probability range in each interval, specifically: Calculate the probability distribution of the encoded data item. Each encoding bit has a probability. The lower limit of the cumulative probability range of the i-th interval is the sum of the probabilities of the previous i-1 encoding bits, and the upper limit is the sum of the probabilities of the previous i encoding bits. i is a positive integer, and 1≤i≤N, N is the number of encoded bits.

[0014] In addition, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0015] Furthermore, the present invention also provides a computer device, which includes at least a readable storage medium and a processor, wherein a computer program is stored on the readable storage medium, and the computer program implements the above method when executed by the processor.

[0016] In order to reduce the possibility of inferring the information of another field through the privacy leakage information of one field for highly correlated fields, the present invention obtains the privacy budget of each field according to the correlation of the fields and the preset privacy budget, thereby reducing the information leakage of highly correlated fields; in addition, in the differential privacy mechanism, the selection of random numbers is completely random, but the cumulative probability intervals of each data item are not of equal size, which leads to a high probability that some cumulative probability intervals will be selected. Based on this, the present invention also adjusts the random number according to the upper and lower limits of each cumulative probability interval, so that the probability of each cumulative probability interval being selected is as equal as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of Embodiment 1; Figure 2 This is a structural diagram of the second embodiment. DETAILED DESCRIPTION

[0018] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0019] The first embodiment, as Figure 1 As shown, the present invention provides a method for protecting user privacy of a shared charging station, the method comprising the following steps: Step 1: obtain the charging records of the shared charging station users, obtain the preset privacy budget of each field, calculate the correlation of different fields in the charging records, and obtain the privacy budget of each field according to the correlation of the fields and the preset privacy budget; The user's charging record will be recorded in the server of the shared charging station. The charging record includes at least the charging date, charging start time, charging end time, charging power, charging fee, user information, charging pile information, etc. Each record includes multiple fields, and the field is the content recorded in the record. For example, the charging start time is a field, and the data item is the actual data of the field. For example, 16:56:55 is a data item of the field "charging start time".

[0020] In differential privacy, a privacy budget is used to determine the degree of data protection. The larger the privacy budget, the weaker the data protection and the higher the data accuracy. The smaller the privacy budget, the stronger the data protection and the lower the data accuracy. For example, for the same data one-hot encoded as [0,1,0], the results obtained after using privacy budgets of 1 and 10 are: [0.2119,0.5762,0.2119] and [4.54×10 −5 ,0.99991,4.54×10 −5 ] where the probability of each coded bit is , where ϵ is the privacy budget, xi is the i-th element after encoding, and then the probability of each encoded bit is divided by the sum of the probabilities of all encoded bits to get the value of each encoded bit. Since it is only normalized, this value is also called probability. For example, 0.2119 in [0.2119, 0.5762, 0.2119] is a probability distribution.

[0021] If a field involves more privacy content or is more sensitive, a smaller privacy budget is set. However, if another field is positively correlated with the entire field, for example, the two satisfy a linear equation, and if the privacy budget set for the other field is relatively large, it is easy to infer the relevant content of the first field through the other field. Based on this, the present invention calculates the correlation of different fields, and then obtains the privacy budget of each field according to the correlation of the fields and the preset privacy budget of each field.

[0022] In one embodiment, the correlation between a field and other fields is calculated, the field most correlated with the field is found, and it is determined whether the correlation is greater than a threshold. If so, the maximum value of the privacy budget of the field and the most correlated field is adjusted to the average value of the privacy budgets of the two fields. For example, there are 5 fields, namely A, B, C, D, and E, and the field most correlated with field A is C. If the correlation between the two is greater than the threshold, the maximum value of the pre-set privacy budgets of field A and field C is found, and the maximum value is adjusted to the average value of the pre-set privacy budgets of field A and field C. In more detail, if the privacy budget of field A is 1 and the privacy budget of field C is 2, then the maximum value is 2, and the average value of the two is 1.5, then the privacy budget of field C is adjusted to 1.5.

[0023] The above embodiment only considers the correlation between two separate fields. In another embodiment, the correlation between the field and all other fields is considered at the same time, specifically: Calculate the correlation matrix between each field and other fields, calculate the sum of the correlations between the field and other fields through the correlation matrix, calculate the inverse of the sum of the correlations of each field, and normalize the inverse of the field to obtain the correlation weight of each field; The average value of the relevance weights of all fields is calculated, the ratio of the relevance weight of the field to the average value is calculated, and the product of the ratio and the preset privacy budget of the field is used as the privacy budget of the field.

[0024] The correlation matrix is ​​an M×M matrix, where c ij is the correlation between the i-th field and the j-th field. If i=j, then c ij =1, where i, j, and M are all positive integers, and 1≤i, j≤M, where M is the number of fields in the record. For each field, the sum of the correlations between this field and other fields is summed up, and all c values ​​in the same row where i is not equal to j are summed up in the correlation matrix. ij The sum of the relevance of field i can be obtained by adding them up, and then the inverse of the sum of the relevance of the field is standardized or normalized so that the sum of the relevance weights of all fields is 1.

[0025] For example, there are three fields A, B, and C, and the sum of the correlations of the three fields is 1.3, 1.4, and 1.1 respectively. After calculating the inverse and standardizing, the correlation weights of each field are 0.32, 0.30, and 0.38, and the average value is 0.33. Further assuming that the preset privacy budgets of A, B, and C are 2, 3, and 1, the privacy budgets of the three fields are recalculated as: 1.94, 2.73, and 1.15. Since the correlation weights are standardized, in the above embodiment, the average value can also be directly obtained by using the inverse of the number of fields. Through the above process, the privacy budget of the field with high correlation becomes smaller, and the privacy budget of the field with low correlation increases, achieving a balance between data protection and data accuracy.

[0026] Step 2: Encode the data items in the charging record, determine the probability distribution of each encoded data item of the field based on the privacy budget of the field, determine multiple random numbers according to the probability distribution of the data items, and use the multiple random numbers to construct a random number pool corresponding to the data items; After obtaining the privacy budget of a field, the probability distribution of each data item under this field can be calculated, and the cumulative probability distribution can be further calculated. After encoding a data item, for example, after one-hot encoding, each encoding bit has a probability, and the cumulative probability distribution is obtained by accumulating the probabilities. Taking the above [0.2119, 0.5762, 0.2119] as an example, the cumulative probability distribution is [P1=0.2119, P2=0.7881, P3=1]. If the random number ?≤?1, the first interval is reported, that is, [1, 0, 0, 0]; if ?1<?≤?2, the second interval is reported, that is, [0, 1, 0, 0]. If ?2<?≤?3, the third interval is reported, that is, [0, 0, 1, 0]; if ?3<?≤?4, the fourth interval is reported, that is, [0, 0, 0, 1].

[0027] Although random numbers are completely random, when the amount of data is small, the average distribution of random numbers cannot be guaranteed, and random numbers cannot be truly completely random. Based on this, multiple random numbers are determined according to the cumulative probability distribution of the data item, and the random number pool corresponding to the data item is constructed using the multiple random numbers. Specifically: Determine the number of intervals according to the number of bits after the data item is encoded, and the number of intervals is the same as the number of bits after the encoding; Calculate the cumulative probability range in each interval, generate at least one random number in each cumulative probability range, the size of the random number is within the cumulative probability range, so that the number of random numbers finally generated is positively correlated with the range size of each cumulative probability range, and put the generated random number into the random number pool corresponding to the data item.

[0028] For example, after one-hot encoding a data item, the binary encoding result is [0, 1, 0], the number of bits is 3, and the number of intervals is also 3. The probability value of each bit is calculated according to the privacy budget: [0.2119, 0.5762, 0.2119]. The range sizes of the three intervals are: 0.2119, 0.5762, and 0.2119 respectively.

[0029] Then the total cumulative probability distribution is [0.2119, 0.7881, 1], and the cumulative probability distribution in each interval is [0, 0.2119], [0.2119, 0.7881], [0.7881, 1], respectively. At least one random number is generated within the first cumulative probability range, at least one random number is generated within the second cumulative probability range, and at least one random number is generated within the third cumulative probability range. The number of random numbers generated within these three cumulative probability ranges is assumed to be n1, n2, and n3, which are positively correlated with 0.2119, 0.5762, and 0.2119. More specifically, n1=21, n2=58, and n3=21. Among them, generating at least one random number in each cumulative probability range means that the size of the generated random number is within the cumulative probability range. In a specific embodiment, the random number pools of the same data items are the same.

[0030] More specifically, the data item is encoded using one-hot encoding, the number of encoded bits is the encoding length after one-hot encoding, and each encoding bit corresponds to an interval.

[0031] Among them, the cumulative probability range in each interval is calculated as follows: Calculate the probability distribution of the encoded data item. Each encoding bit has a probability. The lower limit of the cumulative probability range of the i-th interval is the sum of the probabilities of the previous i-1 encoding bits, and the upper limit is the sum of the probabilities of the previous i encoding bits. i is a positive integer, and 1≤i≤N, N is the number of encoded bits.

[0032] For example, the lower limit of the third interval is the sum of the probabilities of the first two codes, and the upper limit is the sum of the probabilities of the first three codes. In a more specific embodiment, each random number does not take the boundary value of the cumulative probability range.

[0033] Step three, take a random number from the random number pool corresponding to the data item, and generate a report value of the data item based on the probability distribution and the taken random number.

[0034] After obtaining the probability distribution, a random number is randomly taken from the random number pool of the data item, and the report value of the data item can be generated according to the probability distribution and the taken random number, where the report value is also the result of differential privacy of the data item.

[0035] The following is a specific example to illustrate how the above process can protect user privacy. Assume that there are 1000 data items that are encoded as [0, 1, 0], with the same privacy budget, and thus the probability distribution is [0.2119, 0.5762, 0.2119], and the total cumulative probability distribution is [0.2119, 0.7881, 1]. If the ratio of the number of random numbers in the random number pool (0, 0.2119), (0.2119, 0.7881), and (0.7881, 1) is 21:58:21, then the number of these 100 data items with the final reported value of [1, 0, 0] is approximately 210, the number of reported values ​​of [0, 1, 0] is approximately 580, and the number of reported values ​​of [0, 0, 1] is approximately 210. It can be seen that the data items originally [0,1,0] are dispersed into multiple different coded values, but [0,1,0] still occupies the majority position. By adjusting the privacy budget, the proportion of true values ​​can be adjusted. The above calculation is based on a privacy budget of 1. If the privacy budget is adjusted to 0.5, the proportion of [0,1,0] in the reported value will be further increased.

[0036] When other users receive a data item with a reported value of [0,1,0], they cannot determine whether the actual encoding is [0,1,0], but they can still perform statistical analysis, thereby protecting user privacy.

[0037] In a second embodiment, the present invention provides a user privacy protection system for a shared charging station, such as Figure 2 As shown, the system includes the following modules: A privacy budget determination module is used to obtain the charging records of the shared charging station users, obtain the preset privacy budget of each field, calculate the correlation of different fields in the charging records, and obtain the privacy budget of each field according to the correlation of the fields and the preset privacy budget; A random number determination module, used to encode data items in the charging record, determine the probability distribution of each encoded data item of the field based on the privacy budget of the field, and determine multiple random numbers according to the probability distribution of the data items, and use the multiple random numbers to construct a random number pool corresponding to the data items; The privacy processing module is used to take out a random number from the random number pool corresponding to the data item, and generate a report value of the data item according to the probability distribution and the taken random number.

[0038] Preferably, the calculation of the correlation of different fields in the charging record and obtaining the privacy budget of each field according to the correlation of the fields and the preset privacy budget are specifically as follows: Calculate the correlation matrix between each field and other fields, calculate the sum of the correlations between the field and other fields through the correlation matrix, calculate the inverse of the sum of the correlations of each field, and normalize the inverse of the field to obtain the correlation weight of each field; The average value of the relevance weights of all fields is calculated, the ratio of the relevance weight of the field to the average value is calculated, and the product of the ratio and the preset privacy budget of the field is used as the privacy budget of the field.

[0039] Preferably, the determining of multiple random numbers according to the probability distribution of the data item and the use of the multiple random numbers to construct a random number pool corresponding to the data item are specifically: Determine the number of intervals according to the number of bits after the data item is encoded, and the number of intervals is the same as the number of bits after the encoding; Calculate the cumulative probability range in each interval, generate at least one random number in each cumulative probability range, the size of the random number is within the cumulative probability range, so that the number of random numbers finally generated is positively correlated with the range size of each cumulative probability range, and put the generated random number into the random number pool corresponding to the data item.

[0040] Preferably, the data item is encoded using one-hot encoding, the number of encoded bits is the encoding length after one-hot encoding, and each encoding bit corresponds to an interval.

[0041] Preferably, the calculation is performed on the cumulative probability range in each interval, specifically: Calculate the probability distribution of the encoded data item. Each encoding bit has a probability. The lower limit of the cumulative probability range of the i-th interval is the sum of the probabilities of the previous i-1 encoding bits, and the upper limit is the sum of the probabilities of the previous i encoding bits. i is a positive integer, and 1≤i≤N, N is the number of encoded bits.

[0042] In a third embodiment, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first embodiment.

[0043] In a fourth embodiment, the present invention provides a computer device, the computer device at least comprising a readable storage medium and a processor, the readable storage medium storing a computer program, the computer program implementing the method described in the first embodiment when executed by the processor. .

[0044] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0045] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0046] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0047] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0048] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. Among them, the server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

Claims

1. A method for protecting user privacy in a shared charging station, characterized in that: The method comprises the following steps: Obtain charging records of users of the shared charging station, obtain a preset privacy budget for each field, calculate the correlation between different fields in the charging records, and obtain a privacy budget for each field based on the correlation of the fields and the preset privacy budget; Encode the data items in the charging record, determine the probability distribution of each encoded data item of the field based on the privacy budget of the field, determine multiple random numbers according to the probability distribution of the data items, and use the multiple random numbers to construct a random number pool corresponding to the data items; Take a random number from the random number pool corresponding to the data item, and generate the report value of the data item based on the probability distribution and the taken random number.

2. The method according to claim 1, characterized in that The calculation of the correlation of different fields in the charging record and obtaining the privacy budget of each field according to the correlation of the fields and the preset privacy budget are specifically as follows: Calculate the correlation matrix between each field and other fields, calculate the sum of the correlations between the field and other fields through the correlation matrix, calculate the inverse of the sum of the correlations of each field, and normalize the inverse of the field to obtain the correlation weight of each field; The average value of the relevance weights of all fields is calculated, the ratio of the relevance weight of the field to the average value is calculated, and the product of the ratio and the preset privacy budget of the field is used as the privacy budget of the field.

3. The method according to claim 1, characterized in that The method of determining a plurality of random numbers according to the probability distribution of the data item and using the plurality of random numbers to construct a random number pool corresponding to the data item is specifically as follows: Determine the number of intervals according to the number of bits after the data item is encoded, and the number of intervals is the same as the number of bits after the encoding; Calculate the cumulative probability range in each interval, generate at least one random number in each cumulative probability range, the size of the random number is within the cumulative probability range, so that the number of random numbers finally generated is positively correlated with the range size of each cumulative probability range, and put the generated random number into the random number pool corresponding to the data item.

4. The method according to claim 3, characterized in that The data item is encoded using one-hot encoding, the number of encoded bits is the encoding length after one-hot encoding, and each encoding bit corresponds to an interval.

5. The method according to claim 3, characterized in that The calculation of the cumulative probability range in each interval is specifically: Calculate the probability distribution of the encoded data item. Each encoding bit has a probability. The lower limit of the cumulative probability range of the i-th interval is the sum of the probabilities of the previous i-1 encoding bits, and the upper limit is the sum of the probabilities of the previous i encoding bits. i is a positive integer, and 1≤i≤N, N is the number of encoded bits.

6. A shared charging station user privacy protection system, characterized in that: The system includes the following modules: A privacy budget determination module is used to obtain the charging records of the shared charging station users, obtain the preset privacy budget of each field, calculate the correlation of different fields in the charging records, and obtain the privacy budget of each field according to the correlation of the fields and the preset privacy budget; A random number determination module, used to encode data items in the charging record, determine the probability distribution of each encoded data item of the field based on the privacy budget of the field, and determine multiple random numbers according to the probability distribution of the data items, and use the multiple random numbers to construct a random number pool corresponding to the data items; The privacy processing module is used to take out a random number from the random number pool corresponding to the data item, and generate a report value of the data item according to the probability distribution and the taken random number.

7. The system according to claim 6, characterized in that The calculation of the correlation of different fields in the charging record and obtaining the privacy budget of each field according to the correlation of the fields and the preset privacy budget are specifically as follows: Calculate the correlation matrix between each field and other fields, calculate the sum of the correlations between the field and other fields through the correlation matrix, calculate the inverse of the sum of the correlations of each field, and normalize the inverse of the field to obtain the correlation weight of each field; The average value of the relevance weights of all fields is calculated, the ratio of the relevance weight of the field to the average value is calculated, and the product of the ratio and the preset privacy budget of the field is used as the privacy budget of the field.

8. The system according to claim 6, characterized in that The method of determining a plurality of random numbers according to the probability distribution of the data item and using the plurality of random numbers to construct a random number pool corresponding to the data item is specifically as follows: Determine the number of intervals according to the number of bits after the data item is encoded, and the number of intervals is the same as the number of bits after the encoding; Calculate the cumulative probability range in each interval, generate at least one random number in each cumulative probability range, the size of the random number is within the cumulative probability range, so that the number of random numbers finally generated is positively correlated with the range size of each cumulative probability range, and put the generated random number into the random number pool corresponding to the data item.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 5.

10. A computer device, comprising at least a readable storage medium and a processor, wherein a computer program is stored on the readable storage medium, wherein: When the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 5.

Images