Transaction information security storage method based on user industry label

Abstract

The invention relates to the field of data processing, in particular to a user industry label-based transaction information security storage method, which comprises the following steps of: acquiring an information point of transaction information of each user; clustering all information point coordinates by using different class cluster values; calculating the optimization degree of each class cluster value to obtain an optimal class cluster value; obtaining each class cluster corresponding to the optimal class cluster value; obtaining first ciphertext data and a first key of the transaction information according to the clustering center of each class cluster and a set reference vector and a conversion coefficient; obtaining a label value of each class cluster; obtaining a translation vector of each class cluster according to the reference clustering center; and obtaining vector coordinates of each information point according to the vector representation of each information point and the label value of the class cluster to which the information point belongs, further obtaining second ciphertext data and a second key of the transaction information, and storing the second ciphertext data. According to the method, an infinite key can be obtained, and the utilization rate of the storage space is increased while the data storage security is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method for securely storing transaction information based on user industry labels. Background Art

[0002] With the rapid development of digital technology, the digital and secure storage of transaction information from all walks of life has gradually become a hot technology in the industry. For example, for the financial transaction information of financial institutions, the original transaction information has high complexity of time series and user information. At the same time, for the transaction information of financial institutions, it is often necessary to conduct financial analysis of different industries based on the user's industry. Therefore, the transaction information of financial institutions needs to be classified and stored according to the user's industry label. At the same time, financial transaction information involves personal privacy. The loss or malicious tampering of financial transaction data will cause economic losses to users and reduce the credibility of financial institutions, affecting the development of financial institutions. Therefore, when storing transaction information, financial institutions need to encrypt the transaction information to ensure the security of user transaction information.

[0003] Since the transaction data of financial institutions has high complexity in terms of time and users, directly storing the original transaction information will result in a large amount of transaction information complexity accumulation. Therefore, the present invention represents the transaction information of a single user as the change of financial numerical values ​​on the time axis, and projects different transaction information of the same industry to points in three-dimensional space, thereby increasing the relationship between the original information and encrypting the original information using the positional relationship of the spatial points. In the encryption of information, the existing encryption algorithms mainly have the disadvantages of limited key space, large number of keys, etc., which limit the encryption effect and make it difficult to store the keys. Therefore, the present invention utilizes the diversity of vector operation combinations to transform the positions of spatial points, and simultaneously translates different spatial position points to the same relative space to reduce the storage space of ciphertext data, thereby facilitating the storage of encrypted data and achieving secure storage of user transaction information. Summary of the invention

[0004] The present invention provides a transaction information security storage method based on user industry tags to solve the existing problems.

[0005] The transaction information security storage method based on user industry tags of the present invention adopts the following technical solutions:

[0006] An embodiment of the present invention provides a method for securely storing transaction information based on user industry tags, the method comprising the following steps:

[0007] Get information points about transaction information of each user in the same industry;

[0008] Different cluster values ​​are set, and all information point coordinates are clustered according to each cluster value, and each cluster value obtains multiple clusters and cluster centers of each cluster in the multiple clusters; multiple spherical shell regions of each cluster are obtained according to the distribution range of information points in each cluster corresponding to each cluster value; the mean value between the information point density of each spherical shell region in each cluster is calculated to obtain the information point density of each cluster; the preference degree of each cluster value is obtained according to the difference in the information point density of each cluster corresponding to each cluster value; the cluster value corresponding to the maximum preference degree is taken as the optimal cluster value;

[0009] According to the cluster centers of each cluster corresponding to the optimal cluster value and the reference vectors and conversion coefficients set for each cluster, a vector representation of each information point in each cluster is obtained; the vector representation of each information point in each cluster is used as the first ciphertext data of the transaction information, and the cluster centers, reference vectors and conversion coefficients of each cluster are used as the first key of the transaction information;

[0010] The label value of each cluster is obtained according to the coordinates of the cluster center of each cluster; the translation vector of each cluster is obtained by taking the cluster center of each cluster as the starting point of the vector and the set reference cluster center of each cluster as the end point of the vector; the vector coordinates of each information point are obtained by adding the vector representation of each information point and the translation vector of the cluster to which each information point belongs; the vector coordinates of each information point and the label value of the cluster to which each information point belongs are used as the second ciphertext data of the transaction information, and the reference cluster center and the translation vector of each cluster are used as the second key of the transaction information; the second ciphertext data of the transaction information is stored.

[0011] Preferably, the method for obtaining the information points of the transaction information of each user in the same industry is:

[0012] First, the user industry tag is obtained through the user's registration information, and the user's transaction information is obtained through the transaction port of the financial institution. The transaction information includes the transaction time and financial value of each transaction of each user;

[0013] Users from different industries are divided according to their industry labels, and then a three-dimensional coordinate system is established with the user's transaction time as the horizontal axis, the user's financial value at the time of transaction as the vertical axis, and different users in the same industry as the vertical axis; each transaction information of each user in the same industry is projected into the three-dimensional coordinate system to obtain the information points corresponding to the transaction information of each user in the same industry.

[0014] Preferably, the method for obtaining the multiple spherical shell regions of each cluster according to the distribution range of the information points in each cluster corresponding to each cluster value is:

[0015] Set the sphere radius increment; obtain the maximum Euclidean distance from all information points in each cluster to the cluster center of each cluster, the maximum Euclidean distance is the distribution range of the information points in each cluster; take the cluster center of each cluster as the sphere center, and divide each cluster once for each increase in the sphere radius increment, and obtain a sphere area each time, thereby obtaining multiple sphere areas, and the number of the sphere areas is the result obtained by rounding up the ratio of the maximum Euclidean distance to the sphere radius increment;

[0016] The multiple spherical regions are sorted from small to large according to the spherical radius, and the area obtained by subtracting each spherical region from its adjacent spherical region is recorded as each spherical shell region, so as to obtain multiple spherical shell regions of each cluster; the adjacent spherical region refers to the spherical region with the largest radius among all spherical regions whose radii are smaller than those of the respective spherical regions.

[0017] Preferably, the calculation method of the information point density of each spherical shell region in each cluster is:

[0018] The number of information points contained in each spherical shell region and the volume of each spherical shell region are obtained; and the ratio between the number of information points contained in each spherical shell region and the volume of each spherical shell region is used as the information point density of each spherical shell region.

[0019] Preferably, the expression for the preference degree of each cluster value is:

[0020]

[0021] Among them, Q K is the preferred degree when the cluster value is K, S K is the variance of the density of information points of each cluster when the cluster value is K, and e is a natural constant.

[0022] Preferably, the method for obtaining the vector representation of each information point in each cluster is:

[0023] The vector formed by taking the cluster center of each cluster as the starting point and each information point in the cluster as the end point is used as the direction vector of each information point, and the ratio of the difference between the reference vector and the direction vector of each information point to the conversion coefficient is used as the vector representation of each information point.

[0024] Preferably, the method for obtaining the label value of each cluster according to the coordinates of the cluster center of each cluster is:

[0025] First, the cluster centers of each cluster are sorted from small to large according to the horizontal axis, then sorted from small to large according to the vertical axis, and finally sorted from small to large according to the vertical axis, and the serial number of each cluster is recorded as the label value of each cluster.

[0026] The beneficial effects of the present invention are as follows: the present invention first converts the transaction information of all users in the same industry into information points in a three-dimensional space, reduces the label information of the user transaction information, and reduces the storage volume of the transaction information; then clusters the coordinates of the information points, and obtains the best cluster value by constructing the degree of preference of different cluster values; finally, through the countless combinations of vector operations, the overall translation of each cluster is performed to achieve the position conversion of all information points in the space, obtain an infinite key, greatly increase the encryption effect, perform chaotic operations on each cluster, reduce the position correlation relationship of the information points distributed in the space, increase data confidentiality, and also increase the utilization rate of the storage space, which is beneficial to data storage. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 The present invention is a flowchart of the steps of the method for securely storing transaction information based on user industry tags. DETAILED DESCRIPTION

[0029] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of the transaction information security storage method based on user industry tags proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0030] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0031] The specific scheme of the transaction information secure storage method based on user industry tags provided by the present invention is described in detail below with reference to the accompanying drawings.

[0032] See also Figure 1, which shows a flowchart of a method for securely storing transaction information based on user industry tags provided by an embodiment of the present invention, the method comprising the following steps:

[0033] Step S001: Obtain information points of transaction information of each user in the same industry.

[0034] When storing transaction information of financial institutions, since the user industries involved are relatively wide and data analysis is required for users in different industries, the transaction information of users in different industries needs to be stored separately. In addition, the security of transaction information needs to be guaranteed when the data is stored. Therefore, the present invention converts transaction information into points in space and uses the positional relationship of spatial points to encrypt the original transaction information to ensure the security of transaction information.

[0035] Transactions of financial institutions basically adopt real-name registration. Therefore, the industry labels registered by different users during the registration process are first obtained, and the transaction information of each user's transaction is obtained according to the transaction port of the financial institution, including the user's transaction time and transaction amount. That is, the user's industry label information and each transaction information are obtained for different users in the financial transaction information.

[0036] First, users from different industries are divided according to their industry labels, and then the transaction information of users in each industry is processed separately: a three-dimensional coordinate system is established with the user's transaction time as the horizontal axis, the user's financial value at the time of transaction as the vertical axis, and different users in the same industry as the vertical axis; each transaction information of each user is projected into the three-dimensional coordinate system. At this time, each industry corresponds to a three-dimensional coordinate system, and each transaction information of each user in the same industry corresponds to an information point in the three-dimensional coordinate system.

[0037] By using the above method, the transaction information of different users in the same industry is projected into the three-dimensional space. All the transaction information of the same user is on the same plane. Therefore, by utilizing the relationship between different planes in the three-dimensional space, while reflecting the transaction information of a single user, it can also reflect the transaction information of all users at different times, which is convenient for statistical analysis of transaction information; the transaction information of all users in the same industry is represented as points in space, which reduces redundant data and facilitates data transmission and storage; at the same time, the original and more complex information is represented as points in space, which unifies the format of the original information, and uses the positional relationship of spatial points to represent the correlation between the original information, which is convenient for encryption operations of the original information.

[0038] Step S002: different cluster values ​​are set, and the coordinates of all information points are clustered according to each cluster value; the preference degree of each cluster value is calculated to obtain the best cluster value.

[0039] In order to ensure the security of financial transaction information of financial institutions, it is necessary to encrypt user transaction information, that is, to encrypt all information points obtained in the above steps.

[0040] The encryption process of the present invention is completed by converting the spatial position of points. First, clustering operations are performed on the points in the current space to obtain the cluster centers of each cluster, and then the vector representation of the information points in each cluster relative to the cluster center point is obtained. Then, each cluster center is used as the reference point for the position conversion of the information points in each cluster, and the cluster center of each cluster is translated to the same position, and all the information points in each cluster move with the cluster center, that is, the overall translation of each cluster is achieved, and then the chaotic operation of multiple clusters is achieved, thereby improving the encryption effect.

[0041] The present invention first uses the K-means clustering algorithm to cluster all information points. Since the K-means algorithm needs to preset the number of clusters to be obtained after clustering is completed, the cluster value of the K-means algorithm must first be obtained.

[0042] However, for a fixed number of information points, the smaller the cluster value, the fewer clusters are obtained by clustering, and the more information points are contained in each cluster. At this time, there are more combinations of vector representations of all information points, the greater the confusion of encryption scrambling, and the better the encryption effect. The larger the cluster value, the more clusters are obtained by clustering, and the fewer translation relationships are obtained when each cluster is translated as a whole. In addition, the position difference of the same cluster before and after the translation of the cluster center may be small, and the effect of translation encryption is worse. In addition, even in the same industry, different users may have different identities. At different times, transactions with different financial values ​​will occur, making the transaction information massive. If the cluster value is smaller, the information points in a single cluster are more likely to be sparsely distributed. After each cluster is translated, a larger space is needed to store these sparsely distributed information points, resulting in unnecessary waste of space. On the contrary, if there are more clusters, the number of information points in a single cluster is smaller, and the range of change of the information point coordinates is also smaller. After each cluster is translated, the distribution of information points is relatively more concentrated, which is more conducive to the storage of information. That is, for the encryption process of transaction information, the smaller the cluster value, the better, and for the storage of transaction information, the larger the cluster value, the better. Therefore, the present invention needs to first obtain the optimal cluster value:

[0043] Set the initial cluster value K = 2, use the K-means clustering algorithm, cluster all information points in the three-dimensional coordinate system according to the set cluster value, and obtain K clusters;

[0044] The mean of the horizontal coordinates, the mean of the vertical coordinates and the mean of the vertical coordinates of all information points in the ith cluster are respectively used as the horizontal coordinate, vertical coordinate and vertical coordinate of the cluster center of the ith cluster, and the cluster center of the ith cluster is recorded as C i , i∈[1,K]; then calculate the maximum Euclidean distance from the information point contained in the i-th cluster to the cluster center, set the sphere radius increment ΔR=5, take the cluster center of the i-th cluster as the sphere center, and divide the cluster once for each increase of ΔR in the sphere radius. Each division results in a sphere area, that is, the first division of the i-th cluster results in a sphere area with C i The spherical area with ΔR as the sphere center and the radius of the sphere is obtained by the second division. i The sphere area is the center of the sphere, 2ΔR is the radius of the sphere, and so on, until the radius of the sphere is greater than or equal to the maximum Euclidean distance, the division is completed. In this way, multiple sphere areas that can be divided in the cluster are obtained. The number of sphere areas is the result of dividing the above maximum Euclidean distance by ΔR and rounded up. The number of spheres that can be divided in the i-th cluster is n i .

[0045] The radius of all spherical regions is sorted from small to large, and the spherical shell region composed of each sphere and its adjacent spherical region is analyzed, where the region obtained by subtracting the i-1 spherical region from the i spherical region is the i spherical shell region, and the first spherical shell region is recorded as the first spherical region. The ratio of the number of information points contained in the i spherical shell region to the volume of the spherical shell region is recorded as the information point density of the spherical shell region, and the number of spherical shell regions is equal to the number of spherical regions.

[0046] Since the smaller the number of clusters, the better the encryption effect, but the smaller the cluster value, the unnecessary space waste will be caused. Therefore, the present invention needs to improve the utilization rate of storage space under the premise of the best encryption effect. Therefore, the present invention uses the variance between the average information point density between each cluster to characterize the clustering effect. That is, the larger the variance, the more sparse the distribution of information points in the cluster exists in different clusters. In this case, the clustering effect is poor, and unnecessary waste of storage space will occur. On the contrary, the denser the distribution of information points in each cluster, the smaller the probability of sparse distribution of information points in a single cluster, and the better the clustering effect. Since the fewer the number of clusters, the better the encryption effect, that is, the preferred degree of the cluster value is negatively correlated with the size of the cluster value, the present invention uses e -xThe negative correlation between the degree of preference and the size of the cluster value is established. In terms of the utilization rate of storage space, the higher the utilization rate, the better, and the smaller the corresponding variance, the better. Therefore, the present invention uses the inverse of the obtained variance to establish a negative correlation between the degree of preference and the variance. That is, when the cluster value of the K-means clustering algorithm is K, the degree of preference Q of the cluster value is K It can be expressed as:

[0047]

[0048] Among them, K represents the cluster value currently set; S K is the variance of the density of information points of each cluster when the cluster value is K; ρ j is the information point density of the jth spherical shell region in the ith cluster when the cluster value is K; e is a natural constant; n i is the number of spherical shell regions of the i-th cluster; It represents the average value of the information point density of all spherical shell areas in the i-th cluster, which is used to represent the information point density of the i-th cluster; VAR(.) is the variance function, which is used to calculate the variance between the information point densities of all clusters when the cluster value is K.

[0049] The size of each cluster value is continuously adjusted, and the cluster value corresponding to the maximum value among the preferred degrees of different cluster values ​​is taken as the optimal cluster value.

[0050] Step S003: Obtain the cluster center of each cluster corresponding to the optimal cluster value; obtain the vector representation of each information point in each cluster according to the cluster center of each cluster and the set reference vector and conversion coefficient, and then obtain the first ciphertext data and the first key of the transaction information.

[0051] Get the clusters corresponding to the best cluster value. For the t-th information point in the u-th cluster, the vector consisting of the cluster center of the u-th cluster as the starting point and the information point as the end point is denoted as f ut , select any vector from the vectors as the reference vector f u0 , set the conversion coefficient W of the u-th cluster u , when the conversion coefficient W u The larger the value, the smaller the representation range of each pixel after the conversion, and the distribution of information points will be more concentrated, thereby further improving the utilization of storage space. The vector representation of the t-th information point in the u-th cluster is recorded as F ut ,but:

[0052]

[0053] The vector representation of each information point is recorded as the first ciphertext data of the transaction information; the reference vector of the cluster to which each information point belongs, the conversion coefficient and the cluster center of the cluster constitute the first key of the transaction information.

[0054] In the above steps, firstly, the position of the original information point is changed by using vector operations. Since the vector has both direction and size, there are countless combinations of a vector difference, that is, the current encryption key space is infinite, and all encryptions have a better effect of hiding the position of the original space point, that is, the encryption effect is better; then, through the conversion coefficient, the information points after the position conversion are made denser in space, which is more conducive to the storage of ciphertext data.

[0055] Step S004: Obtain the label value and translation vector of each cluster; obtain the vector coordinates of each information point according to the vector representation of each information point in each cluster and the translation vector of the cluster to which it belongs, and then obtain the final stored ciphertext data and its key.

[0056] First, we randomly select a cluster center from all cluster centers as the reference cluster center C0, and then translate the cluster centers of all remaining clusters to the reference cluster center C0. In this process, each information point in each cluster moves simultaneously with the cluster center. For the uth cluster, the translation vector Y of the cluster is u It is a vector consisting of the u-th cluster center as the starting point and the reference cluster center as the end point.

[0057] At this time, in order to distinguish different clusters, each cluster is sorted according to the coordinates of the cluster center of each cluster, that is, firstly, the clusters are sorted from small to large according to the horizontal coordinates of the cluster centers, then the clusters are sorted from small to large according to the vertical coordinates of the cluster centers, and finally, the clusters are sorted from small to large according to the vertical coordinates of the cluster centers. The serial number corresponding to each cluster is the label value of the cluster;

[0058] The vector representation of each information point in each cluster before translation is added to the translation vector of the cluster to which the information point belongs to obtain the vector coordinates of the information point after translation. For the t-th information point in the u-th cluster, the vector coordinates of the point after translation are s ut It can be expressed as:

[0059] s ut =F ut +Y u

[0060] The vector coordinates of each information point after translation and the label value of the cluster to which the information point belongs are taken as the final ciphertext data of the information point. Therefore, the second ciphertext data of the t-th information point in the u-th cluster is (s ut,u), the second ciphertext data of all information points constitutes the second ciphertext data of all transaction information of all users in the same industry, and the reference cluster center and the translation vector of each cluster constitute the second key of all transaction information;

[0061] At this point, the ciphertext data finally stored on the data platform in the present invention is obtained, that is, the second ciphertext data, and the key corresponding to the ciphertext data is the second key.

[0062] The second ciphertext data is compressed using existing compression technology, such as Huffman coding, and then the compressed data is transmitted to a unified data platform for data storage. Thus, the present invention completes the secure storage of transaction information of users in various industries.

[0063] Through the above steps, different clusters are placed in the same relative space, avoiding the relative position relationship between different clusters, thereby increasing the confusion of the ciphertext and facilitating the hiding of the original information; at the same time, the relative position space of all spatial points is consistent, that is, the space required to store all points is reduced, reducing the storage space of the ciphertext, and facilitating the transmission and storage of the ciphertext.

[0064] When extracting transaction information from the data platform, you first need to obtain relevant extraction permissions, that is, obtain the key for the ciphertext data, and then decrypt the stored transaction information. The specific process of decryption is as follows:

[0065] Obtain the second ciphertext data of the transaction information and the second key of the transaction information. Obtaining the second ciphertext data of the transaction information means obtaining the vector coordinates of the information points corresponding to each transaction information in the transaction information and the cluster label value. Obtaining the second key of the transaction information means obtaining the benchmark clustering center and translation vector of each cluster.

[0066] First, all points are divided according to the cluster label value to obtain different clusters. Then, each cluster is translated based on the reference cluster center, that is, the vector coordinates of the information points in each cluster are subtracted from the translation vector of the cluster, so as to preliminarily restore the spatial position of each information point and obtain the first ciphertext data of the transaction information.

[0067] Then, the first key of the transaction information is obtained, that is, the reference vector, conversion coefficient and cluster center of each cluster in the transaction information are obtained. Since the position transformation result of each information point in each cluster is obtained according to the reference vector and conversion coefficient, the original position of each information point can be obtained by reverse deduction, thereby obtaining the original transaction information.

[0068] This completes the decryption process of the transaction information stored in the data platform.

[0069] Through the above steps, the transaction information of users in different industries can be securely stored.

[0070] The present invention first obtains the information point of each user's transaction information; then clusters all the information point coordinates using different cluster values; calculates the preferred degree of each cluster value to obtain the best cluster value; obtains each cluster and cluster center corresponding to the best cluster value; obtains the first ciphertext data and the first key of the transaction information according to the cluster center of each cluster and the set reference vector and conversion coefficient; obtains the label value of each cluster; obtains the translation vector of each cluster according to the reference cluster center; obtains the vector coordinates of each information point according to the vector representation of each information point and the label value of the cluster to which it belongs, and then obtains the second ciphertext data and the second key of the transaction information, and then stores the second ciphertext data, thereby realizing the safe storage of the user's transaction information. The present invention can obtain an infinitely large key, improve the security of data storage, and increase the utilization rate of storage space.

[0071] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for securely storing transaction information based on user industry labels, characterized in that: The method comprises the following steps: Get information points about transaction information of each user in the same industry; Different cluster values ​​are set, and all information point coordinates are clustered according to each cluster value, and each cluster value obtains multiple clusters and cluster centers of each cluster in the multiple clusters; multiple spherical shell regions of each cluster are obtained according to the distribution range of information points in each cluster corresponding to each cluster value; the mean value between the information point density of each spherical shell region in each cluster is calculated to obtain the information point density of each cluster; the preference degree of each cluster value is obtained according to the difference in the information point density of each cluster corresponding to each cluster value; the cluster value corresponding to the maximum preference degree is taken as the optimal cluster value; According to the cluster centers of each cluster corresponding to the optimal cluster value and the reference vectors and conversion coefficients set for each cluster, a vector representation of each information point in each cluster is obtained; the vector representation of each information point in each cluster is used as the first ciphertext data of the transaction information, and the cluster centers, reference vectors and conversion coefficients of each cluster are used as the first key of the transaction information; The label value of each cluster is obtained according to the coordinates of the cluster center of each cluster; the translation vector of each cluster is obtained by taking the cluster center of each cluster as the starting point of the vector and the set reference cluster center of each cluster as the end point of the vector; the vector coordinates of each information point are obtained by adding the vector representation of each information point and the translation vector of the cluster to which each information point belongs; the vector coordinates of each information point and the label value of the cluster to which each information point belongs are used as the second ciphertext data of the transaction information, and the reference cluster center and the translation vector of each cluster are used as the second key of the transaction information; the second ciphertext data of the transaction information is stored.

2. The method for securely storing transaction information based on user industry tags according to claim 1 is characterized in that: The method for obtaining the information points of transaction information of each user in the same industry is: First, the user industry tag is obtained through the user's registration information, and the user's transaction information is obtained through the transaction port of the financial institution. The transaction information includes the transaction time and financial value of each transaction of each user; Users from different industries are divided according to their industry labels, and then a three-dimensional coordinate system is established with the user's transaction time as the horizontal axis, the user's financial value at the time of transaction as the vertical axis, and different users in the same industry as the vertical axis; Project each transaction information of each user in the same industry into a three-dimensional coordinate system to obtain the information points corresponding to the transaction information of each user in the same industry.

3. The method for securely storing transaction information based on user industry labels according to claim 1 is characterized in that: The method for obtaining the multiple spherical shell regions of each cluster according to the distribution range of the information points in each cluster corresponding to each cluster value is: Set the sphere radius increment; obtain the maximum Euclidean distance from all information points in each cluster to the cluster center of each cluster, the maximum Euclidean distance is the distribution range of the information points in each cluster; take the cluster center of each cluster as the sphere center, and divide each cluster once for each increase in the sphere radius increment, and obtain a sphere area each time, thereby obtaining multiple sphere areas, and the number of the sphere areas is the result obtained by rounding up the ratio of the maximum Euclidean distance to the sphere radius increment; The multiple spherical regions are sorted from small to large according to the spherical radius, and the area obtained by subtracting each spherical region from its adjacent spherical region is recorded as each spherical shell region, so as to obtain multiple spherical shell regions of each cluster; the adjacent spherical region refers to the spherical region with the largest radius among all spherical regions whose radii are smaller than those of the respective spherical regions.

4. The method for securely storing transaction information based on user industry labels according to claim 1 is characterized in that: The calculation method of the information point density of each spherical shell region in each cluster is: The number of information points contained in each spherical shell region and the volume of each spherical shell region are obtained; and the ratio between the number of information points contained in each spherical shell region and the volume of each spherical shell region is used as the information point density of each spherical shell region.

5. The method for securely storing transaction information based on user industry labels according to claim 1 is characterized in that: The expression of the preference degree of each cluster value is: Among them, Q K is the preferred degree when the cluster value is K, S K is the variance of the density of information points of each cluster when the cluster value is K, and e is a natural constant.

6. The method for securely storing transaction information based on user industry labels according to claim 1 is characterized in that: The method for obtaining the vector representation of each information point in each cluster is: The vector formed by taking the cluster center of each cluster as the starting point and each information point in the cluster as the end point is used as the direction vector of each information point, and the ratio of the difference between the reference vector and the direction vector of each information point to the conversion coefficient is used as the vector representation of each information point.

7. The method for securely storing transaction information based on user industry labels according to claim 1 is characterized in that: The method for obtaining the label value of each cluster according to the coordinates of the cluster center of each cluster is: First, the cluster centers of each cluster are sorted from small to large according to the horizontal axis, then sorted from small to large according to the vertical axis, and finally sorted from small to large according to the vertical axis, and the serial number of each cluster is recorded as the label value of each cluster.

Images