Enterprise portrait method and system based on homomorphic encryption technology and multi-party joint calculation

Abstract

The invention discloses an enterprise portraying method and system based on a homomorphic encryption technology and multi-party joint calculation, and relates to the technical field of enterprise development analysis, and the method comprises the following steps: calculating an independent characteristic index value, carrying out homomorphic encryption calculation, and uploading an encryption calculation result to a privacy calculation platform; factors of the joint feature indexes are calculated, homomorphic encryption calculation is carried out, then the factors are transmitted to the privacy calculation platform, and the privacy calculation platform calculates the joint feature indexes according to the joint feature index factors; the privacy computing platform computes the independent feature indexes and the combined feature indexes according to portrait dimensions, and decrypts the independent feature indexes and the combined feature indexes to obtain portrait evaluation values of all dimensions of the enterprise; and transmitting the portrait evaluation value of each dimension of the enterprise to an enterprise portrait function module, and outputting an enterprise portrait result by the enterprise portrait function module. According to the method, enterprise development potential comprehensive portraying is carried out by fusing the data of the data sources, and support is provided for dynamically mastering the development direction of enterprises and social and economic development.

Description

Technical Field

[0001] The present invention relates to the field of enterprise development analysis technology, and in particular to an enterprise profiling method and system based on homomorphic encryption technology and multi-party joint computing. Background Art

[0002] For all large and medium-sized enterprises, banks, tax bureaus, and power grid companies have a large amount of important data on the operation of the enterprise, which can reflect the development potential of the enterprise. Therefore, in the past, enterprise portraits mainly used single data sources to evaluate portrait indicators. For example, power grid companies used the electricity consumption data of enterprise users to carry out user portraits to support the analysis of users' electricity consumption trends and electricity consumption energy efficiency, and banks used the loan repayment and transaction information of enterprises to analyze the credit issues of enterprises. However, due to the problems of data islands and data barriers in the above data sources, it is difficult for enterprises to obtain comprehensive utilization and analysis of their data, and it is difficult to comprehensively and accurately reflect the development potential of enterprises.

[0003] Based on this, the present invention proposes an enterprise portrait method based on homomorphic encryption technology and multi-party joint computing, which integrates data from various data sources to comprehensively portrait the development potential of the enterprise, providing support for dynamically grasping the development direction of the enterprise and social and economic development. Summary of the invention

[0004] The present invention is proposed in view of the problems existing in the existing enterprise portraits and systems based on homomorphic encryption technology and multi-party joint computing.

[0005] Therefore, the problem to be solved by the present invention is that it is difficult to comprehensively utilize and analyze enterprise data.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides an enterprise profiling method based on homomorphic encryption technology and multi-party joint computing, which includes the following steps:

[0008] Calculate the independent characteristic index value, perform homomorphic encryption calculation, and upload the encrypted calculation results to the privacy computing platform;

[0009] Calculate the factors of the joint feature index, perform homomorphic encryption calculations, and transmit them to the privacy computing platform. The privacy computing platform calculates the joint feature index based on the factors of the joint feature index.

[0010] The privacy computing platform calculates independent feature indicators and joint feature indicators according to the portrait dimensions, and obtains the portrait evaluation values ​​of each dimension of the enterprise after decryption;

[0011] The evaluation values ​​of the enterprise portraits in various dimensions are transmitted to the enterprise portrait function module, and the enterprise portrait function module outputs the enterprise portrait results.

[0012] As a preferred solution of the enterprise profiling method based on homomorphic encryption technology and multi-party joint computing described in the present invention, the subject of calculating the independent characteristic index value includes a power grid company, a tax bureau and a banking institution;

[0013] When the power grid company calculates the independent characteristic index value, the information calculated includes: the regular payment rate of electricity bills, the year-on-year change in electricity consumption, and the positive evaluation of electricity theft;

[0014] When the tax bureau calculates the independent characteristic index value, the information calculated includes: year-on-year revenue, positive evaluation of tax evasion, asset-liability ratio, and negative evaluation of debt warning;

[0015] When the banking institution calculates the independent characteristic indicator value, the calculated information includes: normal loan repayment rate and abnormal loan repayment rate.

[0016] As a preferred solution of the enterprise profiling method based on homomorphic encryption technology and multi-party joint computing described in the present invention, the step of calculating the joint feature index includes:

[0017] The enterprise's kilowatt-hour output value is the ratio of the enterprise's output value in the past N months to the total electricity consumption of the enterprise in the past N months. The calculation formula is:

[0018]

[0019] In the formula, λ dd W is the electricity output value of the enterprise; be Q is the total electricity consumption of the enterprise in the past N months; cz is the output value of the enterprise in the past N months;

[0020] The enterprise kilowatt-hour output value ratio is the ratio of the enterprise kilowatt-hour output value to the national kilowatt-hour output value, and the calculation formula is:

[0021]

[0022] In the formula, λ ddb is the enterprise's electricity output value ratio; dd0 The national electricity output value.

[0023] As a preferred solution of the enterprise profiling method based on homomorphic encryption technology and multi-party joint computing described in the present invention, the step of calculating the joint feature index also includes:

[0024] The power grid company uses its own public key and the public keys of the tax bureau and the banking institution to Perform homomorphic encryption calculations to obtain encrypted calculation results Encrypt the calculation results Send to the privacy computing platform;

[0025] The tax bureau counts the output value Q of the enterprise in the past N months cz , using its own public key and the public keys of the power grid company and the bank to establish a secure connection with Q cz Perform homomorphic encryption calculation and obtain the encrypted calculation result E(Q cz ), and E(Q cz ) is sent to the privacy computing platform;

[0026] Privacy computing platform acquisition and E(Q cz ), and then perform homomorphic encryption multiplication to obtain the kilowatt-hour output value ratio λ ddb The encrypted calculation result E(λ ddb ).

[0027] As a preferred solution of the enterprise portrait method based on homomorphic encryption technology and multi-party joint computing described in the present invention, the dimensional portrait includes credit dimension, revenue dimension, liability dimension, and social value dimension.

[0028] Credit dimension portrait evaluation includes the regular payment rate of electricity bills, positive evaluation of electricity theft, positive evaluation of tax evasion, and regular loan repayment rate;

[0029] The revenue dimension portrait evaluation indicators include year-on-year revenue and year-on-year electricity consumption;

[0030] Liability dimension portrait evaluation indicators include asset-liability ratio and liability warning negative evaluation;

[0031] The only evaluation indicator for social value dimension portrait is the kilowatt-hour output value ratio.

[0032] As a preferred solution of the enterprise profiling method based on homomorphic encryption technology and multi-party joint computing described in the present invention, it also includes:

[0033] The encrypted calculation result sent by the normal payment rate of electricity charges E(λ df ), electricity consumption year-on-year E(λ yd ), positive evaluation of the enterprise's electricity theft behavior E(λ qd ), year-on-year revenue E(λ ys ), positive evaluation of tax evasion behavior E(λ ts ), debt-to-asset ratio E(λ fzl ), negative evaluation of debt warning E(λ jj ), normal loan repayment rate E(λ dk ), abnormal loan repayment rate E(λ yc );

[0034] The privacy computing platform performs homomorphic encryption addition operations to obtain the ciphertext of the enterprise's portrait evaluation values ​​in each dimension: credit dimension portrait evaluation value E(μ xy ), revenue dimension portrait evaluation value E(μys ), liability dimension portrait evaluation value E(μ fz ), social value dimension portrait evaluation value E(μ sh ),

[0035] After joint decryption by the homomorphic encryption module, the decrypted plaintext of the portrait evaluation value of each dimension is obtained: Credit dimension portrait evaluation value μ xy , Revenue dimension portrait evaluation value μ ys , Liability dimension portrait evaluation value μ fz , social value dimension portrait evaluation value μ sh .

[0036] As a preferred solution of the enterprise portrait method based on homomorphic encryption technology and multi-party joint computing described in the present invention, wherein: the enterprise portrait function module outputs portrait rules according to the enterprise portrait dimension.

[0037] In a second aspect, an embodiment of the present invention provides an enterprise portrait system based on homomorphic encryption technology and multi-party joint computing, which includes a privacy computing platform, a homomorphic encryption module, a homomorphic decryption module, and an enterprise portrait function module;

[0038] The privacy computing platform is a third-party platform, or a platform with privacy computing capabilities jointly built by power grid companies, tax bureaus, and banking institutions. The privacy computing platform is mainly responsible for calculating joint feature indicators and portrait indicators;

[0039] The homomorphic encryption module is a functional module with homomorphic encryption capabilities independently built by the power grid company, the tax bureau, and the banking institution. It uses its own public key and the public key shared by other parties to encrypt its own data and transmit it to the privacy computing platform;

[0040] The homomorphic decryption module is a functional module with decryption capability independently built by the power grid company, the tax bureau, and the banking institution. The portrait evaluation index is decrypted by the private key. The plain text of the portrait index can only be obtained after the joint decryption of the three parties;

[0041] The enterprise portrait function module is a function module with enterprise portrait capabilities jointly built by power grid companies, tax bureaus, and banking institutions, and outputs enterprise portrait results based on the evaluation values ​​of enterprise portrait indicators in each dimension.

[0042] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned enterprise profiling method based on homomorphic encryption technology and multi-party joint computing.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the above-mentioned enterprise profiling method based on homomorphic encryption technology and multi-party joint computing.

[0044] The beneficial effects of the present invention are: by integrating data from various data sources, a comprehensive portrait of the enterprise's development potential is created, providing support for dynamically grasping the development direction of the enterprise and social and economic development; through multi-source data fusion technology, data from different sources and in different formats are integrated to improve data integrity and accuracy, supporting more in-depth analysis and decision-making; using homomorphic encryption technology, data is calculated and analyzed without leaking the original data, which is particularly important for application scenarios that need to protect user privacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative work. Among them:

[0046] Figure 1 This is a flowchart of the enterprise profiling method based on homomorphic encryption technology and multi-party joint computing.

[0047] Figure 2 This is a structural diagram of the enterprise profiling method based on homomorphic encryption technology and multi-party joint computing. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0051] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0052] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0053] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0054] Example 1

[0055] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides an enterprise profiling method based on homomorphic encryption technology and multi-party joint computing, including the following steps:

[0056] S1. Calculate the independent characteristic index value, perform homomorphic encryption calculation, and upload the encrypted calculation results to the privacy computing platform.

[0057] The entities that calculate the independent characteristic index values ​​include power grid companies, tax bureaus, and banking institutions;

[0058] When the power grid company calculates the independent characteristic index value, the information calculated includes: the regular payment rate of electricity bills, the year-on-year change in electricity consumption, and the positive evaluation of electricity theft;

[0059] When the tax bureau calculates the independent characteristic index value, the information calculated includes: year-on-year revenue, positive evaluation of tax evasion, asset-liability ratio, and negative evaluation of debt warning;

[0060] When the banking institution calculates the independent characteristic indicator value, the calculated information includes: normal loan repayment rate and abnormal loan repayment rate.

[0061] Normal electricity bill payment rate:

[0062] Collect statistics on the electricity bill payment of enterprises in the past 12 months, and record the proportion of months in which enterprises pay electricity bills normally as the normal payment rate λ df , the calculation formula is:

[0063]

[0064] Among them, N df The number of months that the enterprise has paid electricity bills normally in the past 12 months.

[0065] Electricity consumption year-on-year:

[0066] The total electricity consumption of the enterprise in the past 12 months and the total electricity consumption in the previous 12 months are counted, and the ratio of the total electricity consumption of the enterprise in the past 12 months to the total electricity consumption in the previous 12 months is the year-on-year growth rate of the enterprise's electricity consumption yd , the calculation formula is:

[0067]

[0068] Among them, W be W is the total electricity consumption of the enterprise in the past 12 months; sh It is the total electricity consumption of the enterprise in the previous 12 months.

[0069] Positive comments on electricity theft:

[0070] If the enterprise has engaged in electricity theft in the past 12 months, the positive evaluation of electricity theft is 0, otherwise it is 1. The calculation formula is:

[0071]

[0072] Among them, λ qd Give a positive evaluation to the enterprise's electricity theft.

[0073] Completion of normal electricity bill payment rate λ df , electricity consumption year-on-year yd , positive evaluation of corporate electricity theft qd Afterwards, the power grid company uses its own public key and the public keys of the tax bureau and the banking institution to perform homomorphic encryption calculations on the above indicators, and obtains the encrypted normal payment rate of electricity charges E(λ df ), electricity consumption year-on-year E(λ yd), positive evaluation of the enterprise's electricity theft behavior E(λ qd ), and upload the above encryption results to the privacy computing platform.

[0074] Revenue YoY:

[0075] The total revenue of the enterprise in the past 12 months and the total revenue in the previous 12 months are counted, and the ratio of the total revenue of the enterprise in the past 12 months to the total revenue in the previous 12 months is recorded as the year-on-year revenue of the enterprise ys , the calculation formula is:

[0076]

[0077] Among them, Q be Q is the total revenue of the enterprise in the past 12 months; sh It is the total revenue of the enterprise in the previous 12 months.

[0078] Positive comments on tax evasion:

[0079] If the enterprise has engaged in tax evasion in the past 12 months, the positive evaluation of tax evasion is 0, otherwise it is 1. The calculation formula is:

[0080]

[0081] Among them, λ ts Give positive comments on corporate tax evasion.

[0082] Debt-to-asset ratio:

[0083] The ratio of a company's total liabilities to its total assets is the company's asset load ratio, which can be directly obtained by the tax bureau through the company's financial statements. The company's asset-liability ratio is denoted by λ fz .

[0084] Negative evaluation of liability warning:

[0085] If the company's asset-to-asset ratio exceeds the warning line in the past 12 months, the negative evaluation of the debt warning is 1, otherwise it is 0. The calculation formula is:

[0086]

[0087] Among them, λjj is the negative evaluation of enterprise debt warning.

[0088] Get the company's year-on-year revenue λ ys , positive evaluation of tax evasion ts , debt-to-asset ratio λ fzl After the negative evaluation of debt warning λjj, the tax bureau uses its own public key and the public keys of the power grid company and the banking institution to perform homomorphic encryption calculations on the above indicators, and obtains the encrypted calculation results of revenue year-on-year E(λys ), positive evaluation of tax evasion behavior E(λ ts ), debt-to-asset ratio E(λ fzl ), debt warning negative evaluation E(λjj), and upload the above encrypted results to the privacy computing platform.

[0089] Normal loan repayment rate:

[0090] Statistics on the normal repayment of enterprises in the past 12 months, the ratio of the number of normal repayments to the number of required repayments in 12 months is recorded as the normal repayment rate of enterprise loans. If the enterprise does not need to repay in the past 12 months, the normal repayment rate of loans is recorded as 100%. The calculation formula is:

[0091]

[0092] Among them, λ dk is the normal repayment rate of enterprise loans; M zc The number of normal repayments made by the enterprise within 12 months; M m0 The number of repayments that the enterprise needs to make within 12 months.

[0093] Abnormal loan repayment rate:

[0094] Statistics are collected on the normal repayments of enterprises in the past 12 months. The ratio of the number of abnormal repayments to the number of required repayments in the past 12 months is recorded as the abnormal repayment rate of enterprise loans. If the enterprise does not need to repay in the past 12 months, the abnormal repayment rate of loans is recorded as 0. The calculation formula is:

[0095]

[0096] Among them, λ yc M is the abnormal repayment rate of corporate loans; yc The number of abnormal repayments made by the enterprise within 12 months.

[0097] Get the normal loan repayment rate λ of the enterprise dk , abnormal loan repayment rate λ yc Afterwards, the bank uses its own public key and the public keys of the tax bureau and the power grid company to perform homomorphic encryption calculations on the above indicators, and obtains the encrypted calculation results of the normal loan repayment rate E(λ dk ), abnormal loan repayment rate E(λ yc ), and upload the above encryption results to the privacy computing platform.

[0098] S2. Calculate the factors of the joint feature indicator, perform homomorphic encryption calculations, and transmit them to the privacy computing platform. The privacy computing platform calculates the joint feature indicator based on the factors of the joint feature indicator.

[0099] The steps to calculate the joint feature index include:

[0100] The enterprise's kilowatt-hour output value is the ratio of the enterprise's output value in the past N months to the total electricity consumption of the enterprise in the past N months. The calculation formula is:

[0101]

[0102] In the formula, λ dd W is the electricity output value of the enterprise; be Q is the total electricity consumption of the enterprise in the past N months; cz The output value of the enterprise in the past N months;

[0103] The enterprise kilowatt-hour output value ratio is the ratio of the enterprise kilowatt-hour output value to the national kilowatt-hour output value, and the calculation formula is:

[0104]

[0105] In the formula, λ ddb is the enterprise's electricity output value ratio; dd0 The national electricity output value.

[0106] The step of calculating the joint feature index also includes,

[0107] The power grid company uses its own public key and the public keys of the tax bureau and the banking institution to Perform homomorphic encryption calculations to obtain encrypted calculation results Encrypt the calculation results Send to the privacy computing platform;

[0108] The tax bureau counts the output value Q of the enterprise in the past N months cz , using its own public key and the public keys of the power grid company and the bank to establish a secure connection with Q cz Perform homomorphic encryption calculation and obtain the encrypted calculation result E(Q cz ), and E(Q cz ) is sent to the privacy computing platform;

[0109] Privacy computing platform acquisition and E(Q cz ), and then perform homomorphic encryption multiplication to obtain the kilowatt-hour output value ratio λ ddb The encrypted calculation result E(λ ddb ).

[0110] S3. The privacy computing platform calculates independent feature indicators and joint feature indicators according to the portrait dimensions, and obtains the portrait evaluation values ​​of each dimension of the enterprise after decryption.

[0111] The dimension portraits include credit dimension, revenue dimension, liability dimension, and social value dimension.

[0112] Credit dimension portrait evaluation includes the regular payment rate of electricity bills, positive evaluation of electricity theft, positive evaluation of tax evasion, and regular loan repayment rate;

[0113] The revenue dimension portrait evaluation indicators include year-on-year revenue and year-on-year electricity consumption;

[0114] Liability dimension portrait evaluation indicators include asset-liability ratio and liability warning negative evaluation;

[0115] The only evaluation indicator for social value dimension portrait is the kilowatt-hour output value ratio.

[0116] Table 1: Enterprise portrait dimensions and characteristic indicators

[0117]

[0118]

[0119] Credit dimension portrait evaluation:

[0120] The credit dimension portrait evaluation indicators include the normal payment rate of electricity bills, positive evaluation of electricity theft, positive evaluation of tax evasion, and normal loan repayment rate. The credit dimension portrait evaluation value μ xy Even if the formula is:

[0121]

[0122] Revenue dimension portrait evaluation:

[0123] The revenue dimension portrait evaluation indicators include year-on-year revenue and year-on-year electricity consumption. The revenue dimension portrait evaluation value μ ys The calculation formula is:

[0124]

[0125] Liability dimension portrait evaluation:

[0126] The liability dimension portrait evaluation indicators include asset-liability ratio and liability warning negative evaluation, and the liability dimension portrait evaluation value μ fz The calculation formula is:

[0127]

[0128] Social value dimension portrait evaluation:

[0129] The social value dimension portrait evaluation index only has the kilowatt-hour output value ratio and the social value dimension portrait evaluation value μ sh Equal to the kilowatt-hour output value ratio.

[0130] The encrypted calculation result sent by the normal payment rate of electricity charges E(λ df ), electricity consumption year-on-year E(λ yd ), positive evaluation of the enterprise's electricity theft behavior E(λ qd ), year-on-year revenue E(λ ys), positive evaluation of tax evasion behavior E(λ ts ), debt-to-asset ratio E(λ fzl ), negative evaluation of debt warning E(λ jj ), normal loan repayment rate E(λ dk ), abnormal loan repayment rate E(λ yc );

[0131] The privacy computing platform performs homomorphic encryption addition operations to obtain the ciphertext of the enterprise's portrait evaluation values ​​in each dimension: credit dimension portrait evaluation value E(μ xy ), revenue dimension portrait evaluation value E(μ ys ), liability dimension portrait evaluation value E(μ fz ), social value dimension portrait evaluation value E(μ sh ),

[0132] After joint decryption by the homomorphic encryption module, the decrypted plaintext of the portrait evaluation value of each dimension is obtained: Credit dimension portrait evaluation value μ xy , Revenue dimension portrait evaluation value μ ys , Liability dimension portrait evaluation value μ fz , social value dimension portrait evaluation value μ sh .

[0133] S4. The evaluation values ​​of the enterprise portraits in each dimension are transmitted to the enterprise portrait function module, and the enterprise portrait function module outputs the enterprise portrait results.

[0134] The enterprise portrait function module outputs portrait rules according to the enterprise portrait dimensions.

[0135] Table 2: Enterprise portrait dimension rules

[0136]

[0137] In summary, by integrating data from various data sources to create a comprehensive portrait of the company's development potential, we can provide support for dynamically grasping the company's development direction and social and economic development; through multi-source data fusion technology, we can integrate data from different sources and in different formats to improve data integrity and accuracy, and support deeper analysis and decision-making; using homomorphic encryption technology, we can calculate and analyze data without leaking the original data, which is especially important for application scenarios that need to protect user privacy.

[0138] Example 2

[0139] On the basis of the first embodiment, this embodiment further provides an enterprise portrait system based on homomorphic encryption technology and multi-party joint computing, including a privacy computing platform, a homomorphic encryption module, a homomorphic decryption module, and an enterprise portrait function module;

[0140] The privacy computing platform is a third-party platform, or a platform with privacy computing capabilities jointly built by power grid companies, tax bureaus, and banking institutions. The privacy computing platform is mainly responsible for calculating joint feature indicators and portrait indicators;

[0141] The homomorphic encryption module is a functional module with homomorphic encryption capabilities independently built by the power grid company, the tax bureau, and the banking institution. It uses its own public key and the public key shared by other parties to encrypt its own data and transmit it to the privacy computing platform;

[0142] The homomorphic decryption module is a functional module with decryption capability independently built by the power grid company, the tax bureau, and the banking institution. The portrait evaluation index is decrypted by the private key. The plain text of the portrait index can only be obtained after the joint decryption of the three parties;

[0143] The enterprise portrait function module is a function module with enterprise portrait capabilities jointly built by power grid companies, tax bureaus, and banking institutions, and outputs enterprise portrait results based on the evaluation values ​​of enterprise portrait indicators in each dimension.

[0144] This embodiment also provides a computer device, which is suitable for the enterprise profiling method based on homomorphic encryption technology and multi-party joint computing, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the enterprise profiling method based on homomorphic encryption technology and multi-party joint computing as proposed in the above embodiment.

[0145] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0146] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the enterprise profiling method based on homomorphic encryption technology and multi-party joint computing as proposed in the above embodiment is implemented.

[0147] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0148] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for enterprise profiling based on homomorphic encryption technology and multi-party joint computing, characterized by: The following steps are included: Calculate the independent characteristic index value, perform homomorphic encryption calculation, and upload the encrypted calculation results to the privacy computing platform; Calculate the factors of the joint feature index, perform homomorphic encryption calculations, and transmit them to the privacy computing platform. The privacy computing platform calculates the joint feature index based on the factors of the joint feature index. The privacy computing platform calculates independent feature indicators and joint feature indicators according to the portrait dimensions, and obtains the portrait evaluation values ​​of each dimension of the enterprise after decryption; The evaluation values ​​of the enterprise portraits in various dimensions are transmitted to the enterprise portrait function module, and the enterprise portrait function module outputs the enterprise portrait results.

2. The enterprise profiling method based on homomorphic encryption technology and multi-party joint computing according to claim 1 is characterized by: The entities that calculate the independent characteristic index values ​​include power grid companies, tax bureaus, and banking institutions; When the power grid company calculates the independent characteristic index value, the information calculated includes: the regular payment rate of electricity bills, the year-on-year change in electricity consumption, and the positive evaluation of electricity theft; When the tax bureau calculates the independent characteristic index value, the information calculated includes: year-on-year revenue, positive evaluation of tax evasion, asset-liability ratio, and negative evaluation of debt warning; When the banking institution calculates the independent characteristic indicator value, the calculated information includes: normal loan repayment rate and abnormal loan repayment rate.

3. The enterprise profiling method based on homomorphic encryption technology and multi-party joint computing as claimed in claim 2 is characterized by: The steps to calculate the joint feature index include: The enterprise's kilowatt-hour output value is the ratio of the enterprise's output value in the past N months to the total electricity consumption of the enterprise in the past N months. The calculation formula is: In the formula, λ dd W is the electricity output value of the enterprise; be Q is the total electricity consumption of the enterprise in the past N months; cz The output value of the enterprise in the past N months; The enterprise kilowatt-hour output value ratio is the ratio of the enterprise kilowatt-hour output value to the national kilowatt-hour output value, and the calculation formula is: In the formula, λ ddb is the enterprise's electricity output value ratio; dd0 The national electricity output value.

4. The enterprise profiling method based on homomorphic encryption technology and multi-party joint computing as claimed in claim 3 is characterized by: The step of calculating the joint feature index also includes, The power grid company uses its own public key and the public keys of the tax bureau and the banking institution to Perform homomorphic encryption calculations to obtain encrypted calculation results Encrypt the calculation results Send to the privacy computing platform; The tax bureau counts the output value Q of the enterprise in the past N months cz , using the tax bureau's own public key and the public keys of the power grid company and the banking institution to verify Q cz Perform homomorphic encryption calculation and obtain the encrypted calculation result E(Q cz ), and E(Q cz ) is sent to the privacy computing platform; Privacy computing platform acquisition and E(Q cz ), and then perform homomorphic encryption multiplication to obtain the kilowatt-hour output value ratio λ ddb The encrypted calculation result E(λ ddb ).

5. The enterprise profiling method based on homomorphic encryption technology and multi-party joint computing as claimed in claim 4 is characterized by: The dimension portraits include credit dimension, revenue dimension, liability dimension, and social value dimension. Credit dimension portrait evaluation includes the regular payment rate of electricity bills, positive evaluation of electricity theft, positive evaluation of tax evasion, and regular loan repayment rate; The revenue dimension portrait evaluation indicators include year-on-year revenue and year-on-year electricity consumption; Liability dimension portrait evaluation indicators include asset-liability ratio and liability warning negative evaluation; The only evaluation indicator for social value dimension portrait is the kilowatt-hour output value ratio.

6. The enterprise profiling method based on homomorphic encryption technology and multi-party joint computing as claimed in claim 5, characterized in that: Also includes, The encrypted calculation result sent by the normal payment rate of electricity charges E(λ df ), electricity consumption year-on-year E(λ yd ), positive evaluation of the enterprise's electricity theft behavior E(λ qd ), revenue year-on-year E(λ ys ), positive evaluation of tax evasion behavior E(λ ts ), debt-to-asset ratio E(λ fzl ), negative evaluation of debt warning E(λ jj ), normal loan repayment rate E(λ dk ), abnormal loan repayment rate E(λ yc ); The privacy computing platform performs homomorphic encryption addition operations to obtain the ciphertext of the enterprise's portrait evaluation values ​​in each dimension: credit dimension portrait evaluation value E(μ xy ), revenue dimension portrait evaluation value E(μ ys ), liability dimension portrait evaluation value E(μ fz ), social value dimension portrait evaluation value E(μ sh ), After joint decryption by the homomorphic encryption module, the decrypted plaintext of the portrait evaluation value of each dimension is obtained: Credit dimension portrait evaluation value μ xy , Revenue dimension portrait evaluation value μ ys , Liability dimension portrait evaluation value μ fz , social value dimension portrait evaluation value μ sh .

7. The enterprise profiling method based on homomorphic encryption technology and multi-party joint computing according to claim 6 is characterized in that: The enterprise portrait function module outputs portrait rules according to the enterprise portrait dimensions.

8. An enterprise portrait system based on homomorphic encryption technology and multi-party joint computing, based on the enterprise portrait method based on homomorphic encryption technology and multi-party joint computing according to any one of claims 1 to 7, characterized in that: Includes privacy computing platform, homomorphic encryption module, homomorphic decryption module, and enterprise profiling function module; The privacy computing platform is a third-party platform, or a platform with privacy computing capabilities jointly built by power grid companies, tax bureaus, and banking institutions. The privacy computing platform is mainly responsible for calculating joint feature indicators and portrait indicators; The homomorphic encryption module is a functional module with homomorphic encryption capabilities independently built by the power grid company, the tax bureau, and the banking institution. It uses its own public key and the public key shared by other parties to encrypt its own data and transmit it to the privacy computing platform; The homomorphic decryption module is a functional module with decryption capability independently built by the power grid company, the tax bureau, and the banking institution. The portrait evaluation index is decrypted by the private key. The plain text of the portrait index can only be obtained after the joint decryption of the three parties; The enterprise portrait function module is a function module with enterprise portrait capabilities jointly built by power grid companies, tax bureaus, and banking institutions, and outputs enterprise portrait results based on the evaluation values ​​of enterprise portrait indicators in each dimension.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the enterprise profiling method based on homomorphic encryption technology and multi-party joint computing described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the enterprise profiling method based on homomorphic encryption technology and multi-party joint computing as described in any one of claims 1 to 7 are implemented.

Images