Secure computation system, information processing system, secure computation method, and program

Abstract

A secure computing system according to the present disclosure is used to analyze financial transactions based on information regarding customer assets, and comprises: a parameter reception means that receives input of encrypted parameters of a plurality of models generated by each of a plurality of financial institutions; a secure computing means that integrates the plurality of encrypted parameters through secure computation; and an output means that outputs, in an encrypted format, the parameters integrated by the secure computing means.

Description

[Technical field]

[0001] The present disclosure relates to a secure computation system, a financial institution server, an information processing system, a secure computation method, and a recording medium. [Background technology]

[0002] Financial institutions use information on assets held by their customers (individuals and corporations), income, and asset management status to select customers to whom they can propose financial products such as investment trusts. Models using AI (Artificial Intelligence) are used as a means of selecting customers. When generating models using AI, customer information held by each financial institution is used. To improve the performance and accuracy of the models, technology is used that performs prediction processing on distributed customer data while protecting privacy.

[0003] For example, Patent Document 1 discloses a system that performs prediction processing while still encrypted, using an encrypted prediction model and user information encrypted in a similar manner to the distributed prediction model. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-215512 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the invention described in the above-mentioned Patent Document 1 outputs data predicted by a single prediction model, so there is a limit to how much accuracy can be improved in the prediction data. When analyzing customer information in the financial industry, a more accurate model can be generated by using information on models held by multiple financial institutions rather than using models held by individual financial institutions. However, the models held by each financial institution are confidential information and cannot be provided to third parties.

[0006] One example of the objective of the present disclosure is to provide more accurate models while keeping the parameters of each model secret. [Means for solving the problem]

[0007] A secure computing system in one aspect of the present disclosure is used for analyzing financial transactions based on information about customer assets, and comprises a parameter receiving means for receiving input of anonymized parameters of a plurality of models generated by each of a plurality of financial institutions, a secure computing means for integrating the plurality of anonymized parameters through secure computation, and an output means for outputting the parameters integrated by the secure computing means in anonymized form.

[0008] In one aspect of the present disclosure, the financial institution server is equipped with an analysis means for a customer's financial transactions using an updated model updated by federated learning using secure computation based on customer information or financial transaction information regarding the customer's assets.

[0009] An information processing system according to one aspect of the present disclosure is an information processing system having a plurality of financial institution servers and a secure computation system, each of the plurality of financial institution servers including a model storage unit that stores a model generated based on information on a customer's assets and that analyzes financial transactions of the customer, an anonymization unit that anonymizes parameters of the model, a model input / output means that transmits the model to the secure computation system in an anonymized format, and a restoration unit that restores the anonymized parameters, and the secure computation system is used for analyzing financial transactions based on the information on the customer's assets, and includes a parameter receiving means that receives input of anonymized parameters of a plurality of models generated in each of the plurality of financial institutions, a secure computation means that integrates the anonymized parameters by secure computation, and an output means that outputs the parameters integrated by the secure computation means in an anonymized format.

[0010] A secure computation method in one aspect of the present disclosure is used for analyzing financial transactions based on information about customer assets, and accepts input of anonymized parameters of a plurality of models generated by each of a plurality of financial institutions, integrates the anonymized parameters using secure computation, and outputs the integrated parameters in anonymized form.

[0011] A recording medium in one aspect of the present disclosure stores a program that causes a computer to execute the following steps: (1) receive input of anonymized parameters of a plurality of models used in analyzing financial transactions based on information regarding customer assets, for a plurality of models generated by each of a plurality of financial institutions, (2) integrate the anonymized parameters through secure computation, and (3) output the integrated parameters in anonymized form. Effect of the Invention

[0012] One example of the effect of the present disclosure is that it is possible to provide a more accurate financial analysis model while keeping the parameters of each model confidential. [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is a block diagram showing the configuration of an information processing system according to the first embodiment. [Diagram 2] FIG. 2 is a diagram showing a hardware configuration in which the secure computation system according to the first embodiment is realized by a computer device and its peripheral devices. [Diagram 3] FIG. 3 is a flowchart showing the operation of secure computation in the first embodiment. [Figure 4] FIG. 4 is a block diagram showing a configuration of an information processing system according to the second embodiment. [Diagram 5] FIG. 5 is a flowchart showing an information processing operation in the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Next, an embodiment will be described in detail with reference to the drawings.

[0015] [First embodiment] FIG. 1 is a block diagram showing a configuration of an information processing system 10 in the first embodiment. The information processing system 10 in the first embodiment is a system for integrating, by secure computation, a plurality of parameters of a model for analysis using customer information or financial transaction information held by each financial institution. Referring to FIG. 1, the information processing system 10 includes a secure computation system 100 and a plurality of financial institution servers 200 (200a, 200b). The secure computation system 100 is implemented by a service provider that provides financial analysis service tools and the like to each of the financial institutions. The service provider integrates parameters of trained models in each financial institution server 200, and provides the financial analysis service and the like using an updated model to which the integrated parameters are applied. The secure computation system 100 includes a parameter receiving unit 101, a secure computation unit 102, and an output unit 103. Each of the financial institution servers 200 includes a model storage unit 201 (201a, 201b) that stores a trained model for analyzing customer information or financial transaction information, a concealment unit 202 (202a, 202b) that conceals model parameters, a model input / output unit 203 (203a, 203b) that inputs and outputs parameters to and from the secure computation system 100, and a restoration unit 204 (204a, 204b) that restores the concealed parameters. In this embodiment, the multiple financial institution servers 200 are provided in two locations, but this is not limited to this. The multiple financial institution servers 200 are provided in the same number as the number of financial institutions that perform federated learning. Below, the secure computation system 100, which is an essential component of this embodiment, will be described in detail.

[0016] Fig. 2 is a diagram showing an example of a hardware configuration in which the secure computation system 100 in the first embodiment of the present disclosure is realized by a computer device 500 including a processor. As shown in Fig. 2, the secure computation system 100 includes a CPU (Central Processing Unit) 501, memories such as a ROM (Read Only Memory) 502 and a RAM (Random Access Memory) 503, a storage device 505 such as a hard disk for storing a program 504, a communication I / F (Interface) 508 for network connection, and an input / output interface 511 for inputting and outputting data. In the first embodiment, parameter information received from each financial institution server 200 is input to the secure computation system 100 via the communication I / F 508.

[0017] The CPU 501 operates an operating system to control the entire secure computation system 100 according to the first embodiment of the present invention. The CPU 501 also reads out programs and data from a recording medium 506 mounted in, for example, a drive device 507 into a memory. The CPU 501 also functions as the parameter receiving unit 101, the secure computation unit 102, and the output unit 103 in the first embodiment, or as a part of these, and executes processes or commands in the flowchart shown in Fig. 3, which will be described later, based on the program.

[0018] The recording medium 506 is, for example, an optical disk, a flexible disk, a magneto-optical disk, an external hard disk, or a semiconductor memory. A recording medium that is a part of the storage device is a non-volatile storage device, and the program is recorded therein. The program may also be downloaded from an external computer (not shown) that is connected to a communication network.

[0019] The input device 509 is realized by, for example, a mouse, a keyboard, built-in key buttons, etc., and is used for input operations. The input device 509 is not limited to a mouse, a keyboard, or built-in key buttons, and may be, for example, a touch panel. The output device 510 is realized by, for example, a display, and is used to check the output.

[0020] As described above, the first embodiment shown in FIG. 1 is realized by the computer hardware shown in FIG. 2. However, the means for realizing each part of the secure computation system 100 in FIG. 1 is not limited to the configuration described above. The secure computation system 100 may be realized by one physically combined device, or may be realized by two or more physically separated devices connected by wire or wirelessly. For example, the input device 509 and the output device 510 may be connected to the computer device 500 via a network. The secure computation system 100 in the first embodiment shown in FIG. 1 may also be configured by cloud computing or the like.

[0021] In FIG. 1, the parameter receiving unit 101 is a means for receiving input of anonymized parameters of a plurality of models used for financial analysis based on information on a client's assets and generated by each of a plurality of financial institutions. The financial analysis is, for example, analysis for a financial institution to advise a client on financial transactions. The financial institution includes a bank (including a city bank, Japan Post Bank, a regional bank, a credit union, and a credit association), a securities company, an insurance company, and other financial product dealers, as well as a credit card company and a payment service provider that handles cashless payments. The financial institution in the first embodiment also includes an item rental company that leases or rents automobiles and home appliances. The financial products include, for example, deposits, bonds, investment trusts, foreign currency, stocks, futures trading, FX, virtual currency, and the like.

[0022] The parameter receiving unit 101 receives and receives the parameters of the trained model in a concealed format through the network via the communication I / F 508 in each of the multiple financial institution servers 200, for example, triggered by an operation for integrating parameters by a service provider. The model is a model that is determined in advance by machine learning in each financial institution, for example, using customer information or past financial transaction data to output a specific analysis result. For example, when information on a customer's assets is input, a financial product or financial transaction recommended to the customer, or credit information (credit limit) of the customer is output. The machine learning model includes, but is not limited to, a decision tree model, a linear regression model, a logistic regression model, a neural network model, etc.

[0023] The secure computation unit 102 is a means for integrating, by secure computation, a plurality of anonymized parameters received by the parameter receiving unit 101. In this embodiment, integrating a plurality of anonymized parameters by secure computation means that the secure computation system 100 performs machine learning in a state where the secure computation system 100 is distributed to each financial institution server 200 (federated learning), and integrates the parameters of a model that has already been trained in each financial institution server 200, by using secure computation. In this embodiment, this also includes the secure computation system 100 integrating the parameters of a model that each financial institution server 200 has trained by machine learning.

[0024] The secure computing unit 102 integrates the concealed parameters according to a predetermined combination rule. A known method can be used as a parameter integration method. For example, when integrating the parameters, the weight of the parameters corresponding to each model can be changed according to the characteristics of each model.

[0025] As the secure computation method, a special encryption corresponding to a specific process such as homomorphic encryption, a trusted execution environment (Trusted Execution Environment) in which processing is performed in an isolated state on hardware, or multi-party computation in which computation is performed (secret sharing computation) while keeping secret sharing among multiple servers can be used. Specific examples of the secure computation method of multi-party computation include the following. For example, the concealed data a is secretly shared into shared values ​​x, y, ..., and x, y, ... are sent to different servers by administrators. Next, while keeping the concealed data a secretly shared, the computation proceeds while communicating with each other, and finally, the shared values ​​u, v, ... of the output, which are the computation results of each server, are collected and restored, thereby obtaining the computation result F(a). This computation result becomes a parameter that integrates the parameters of each model. For this reason, when multi-party computation is used as the secure computation method, the secure computation unit 102 includes multiple servers. According to multi-party computation, management of encryption keys and an isolated environment are not required, and computation processing is faster. The secure computation unit 102 outputs the model parameters thus obtained to the output unit 103 in a concealed format.

[0026] The output unit 103 is a means for transmitting the parameters integrated by the secure computation unit 102 to the financial institution server 200 in a confidential format. The output unit 103 transmits the integrated parameters in a format that allows the parameters of the model to be updated on the financial institution server 20 side. When transmitting to the financial institution server 200, the output unit 103 can transmit the differences between the updated parameters (only the improvements) instead of the updated parameters.

[0027] The operation of the secure computation system 100 configured as above will now be described with reference to the flow chart of FIG.

[0028] 3 is a flowchart showing an outline of the operation of the secure computing system 100 in the second embodiment. Note that the processing according to this flowchart may be executed based on program control by the above-mentioned processor.

[0029] As shown in Fig. 3, first, the parameter receiving unit 101 receives input of a plurality of concealed parameters for each of models that have been trained in a plurality of financial institutions (step S101). Next, the secure computation unit 102 integrates the plurality of concealed parameters by secure computation (step S102). Finally, the output unit 103 outputs the model parameters calculated by the secure computation unit 102 in a concealed format (step S103). With this, the secure computation system 100 ends the operation of the secure computation.

[0030] In the secure computation system 100, the secure computation unit 102 integrates a plurality of concealed parameters through secure computation, thereby making it possible to provide a more accurate model while keeping the parameters of each model secret.

[0031] [Second embodiment] Next, the second embodiment of the present disclosure will be described in detail with reference to the drawings. Hereinafter, the contents that overlap with the above description will be omitted to the extent that the description of this embodiment is not unclear. In the second embodiment, the information processing system 11 is used to provide a model updated using federated learning using secure computation. These updated models are incorporated into, for example, an analysis tool for providing advice on financial transactions to customers and setting a customer's credit limit (loan screening). Advice on financial transactions includes advice on financial management strategies and financial product transactions for corporations, such as M&A support or recommendations for financial products and services. In this embodiment, financial transactions refer to normal financial transactions and are a concept that excludes fraudulent transactions and fraud detection that are problematic in financial transactions. Each component in each embodiment of the present disclosure can be realized not only in hardware, but also in a computer device based on program control and firmware, as in the computer device shown in FIG. 2. These models are models generated based on customer information or financial transaction information related to the assets of the customers, and are stored in each model storage unit 211 (211a, 211b) of each financial institution server 210 (210a, 210b).

[0032] FIG. 4 is a block diagram showing a configuration of an information processing system 11 including a secure computation system 110 according to a second embodiment of the present disclosure. With reference to FIG. 4, the secure computation system 110 and financial institution server 210 (210a, 210b) according to the second embodiment will be described, focusing on the parts different from the information processing system 10 according to the first embodiment. The secure computation system 110 according to the second embodiment includes a parameter receiving unit 111, a secure computation unit 112, and an output unit 113. The multiple financial institution servers 210 (210a, 210b) include a model storage unit 211 (211a, 211b), a concealment unit 212 (212a, 212b), a model input / output unit 213 (213a, 213b), a restoration unit 214 (214a, 214b), and an analysis unit 215 (215a, 215b). The secure computation system 110 integrates multiple parameters of the trained models received from multiple financial institution servers 210a, 210b using secure computation.

[0033] Here, the details of each model used in the financial analysis tool for corporations will be described. There are models for M&A support used by the acquiring side and models used by the seller (acquired side). The acquiring side model is, for example, a model that is trained based on past successful cases using industry, sales, region, etc. as training data. This model inputs the name of the company that wishes to be acquired, and outputs whether the acquisition will be possible and the acquisition amount. The seller side model is, for example, a model that is trained based on past successful cases using industry, sales, region, etc. as training data. This model inputs the name of the company that wishes to be acquired, and outputs the possibility that the company wishes to be acquired and the expected desired acquisition amount. For these models, by integrating the parameters of models that have been trained at multiple financial institutions, the accuracy of matching buyers and sellers can be improved, and financing opportunities can be increased.

[0034] A loan screening model, for example, takes the repayment status of existing corporate clients as input and outputs the loan amount (increase, refinancing, extension of term). By integrating the parameters of models that have already been trained at multiple financial institutions, it becomes easier to make decisions on loans and screening work, and the efficiency of work can be improved. A product / service recommendation model inputs customer information and transaction details from a certain period of the past, and outputs financial products or groups of financial products to recommend to the customer. By integrating the parameters of models that have already been trained at multiple financial institutions, it is possible to output more accurate analysis results and increase lending opportunities.

[0035] <Secure computation system> The secure computation unit 112 receives the parameters of the trained model of each financial institution from the financial institution server 210 through the communication I / F 508. Next, the secure computation unit 112 integrates the received parameters of the concealed model by secure computation according to a predetermined combination rule, and outputs the parameters of the integrated concealed model to the output unit 113 in a concealed format. The output unit 113 transmits the integrated parameters to each financial institution server 210 through the model input / output unit 213. In addition, after transmitting the parameters to the financial institution server 210, if the financial institution server 210 again learns the model and updates the parameters, the secure computation system 110 may receive the updated parameters again. Note that the operations of the parameter reception unit 111, the secure computation unit 112, and the output unit 113 are similar to the operations of the parameter reception unit 101, the secure computation unit 102, and the output unit 103 in the first embodiment, and therefore will not be described here.

[0036] <Financial institution server> The financial institution server 210 updates the model stored in the model storage unit 211 to a model to which the parameters received from the secure computation system 110 are applied. Specifically, the model input / output unit 213 receives the parameters in a concealed format and outputs them to the restoration unit 214. Next, the restoration unit 214 restores the parameters and replaces them with the parameters of the model stored in the model storage unit 211. Next, the analysis unit 215 performs analysis using the updated model. The updated model is incorporated in a financial analysis tool for corporations used by financial institutions. The analysis unit 215 performs analysis on M&A using the updated model, triggered by a user's operation on the financial analysis tool, and outputs the analysis results in a state that can be viewed on a display device or the like. For example, in a tool using the acquirer's model, the analysis unit 215 accepts input of the name of the company to be acquired and outputs whether or not the acquisition will be possible and the acquisition amount. For example, in a tool using the seller's model, the analysis unit 215 accepts input of the company name of the desired acquiree and outputs the possibility that the desired acquiree will wish to be acquired and the expected desired acquisition amount. In order to improve the accuracy of the analysis results by the analysis unit 215, the financial institution server 210 may perform learning again based on additionally obtained customer data and financial transaction information, and may transmit the updated parameters to the secure computation system 110. The accuracy of the model can be further improved by repeating the updating of parameters through learning in each financial institution server 210 and the integration of parameters in the secure computation system 110 until, for example, a predetermined condition is satisfied. The predetermined condition is stored in, for example, the storage device 505.

[0037] The operation of the information processing system 11 configured as above will be described with reference to the flowchart of FIG.

[0038] 5 is a flowchart showing an outline of the operation of the information processing system 11 in the first embodiment. Note that the processing according to this flowchart may be executed based on program control by the above-mentioned processor.

[0039] As shown in FIG. 5, first, the financial institution server 210 locally learns using customer information held by the financial institution (step S201). Next, the anonymization unit 212 anonymizes the parameters of the model learned in each financial institution server 210 (step S202). Next, the model input / output unit 213 outputs the parameters in anonymized format to the secure computation system 110 (step S203). Next, the parameter reception unit 111 of the secure computation system 110 receives the anonymized parameters (step S204). Next, the secure computation unit 112 integrates the multiple anonymized parameters by secure computation (step S205). Next, the output unit 113 outputs the parameters of the model integrated by the secure computation unit 112 in anonymized format to each financial institution server 210 (step S206). Next, the financial institution server 210 acquires the integrated parameters in anonymized format through the model input / output unit 213 (step S207). Next, the restoration unit 214 restores the concealed parameters (step S208). Next, the financial institution server 210 updates the model stored in the model storage unit 211 to a model to which the restored parameters are applied (step S209). Next, the financial institution server 210 determines whether or not a predefined condition is satisfied (step S210). If the predefined condition is satisfied (step S210; YES), the analysis unit 215 performs analysis using the updated model and ends the flow (step S211). If the predefined condition is not satisfied, the financial institution server 210 returns to step S201 (step S210; NO) and executes the flow again. With the above, the information processing system 11 ends the operation of the secure computation.

[0040] In the second embodiment of the present disclosure, parameters of multiple models for providing support to corporations are integrated to output more accurate analysis results.

[0041] [Modification of the second embodiment] The information processing system 11 in the second embodiment can also be used as a system for integrating parameters of trained models for providing support to individuals in financial institutions. Examples of models for integrating parameters include loan screening, purchase prediction, and cancellation prediction. The loan screening model outputs the amount to be lent using customer attributes and repayment status as input values. The purchase prediction outputs a judgment on whether to recommend a financial product of the financial institution or a judgment on which financial product to recommend using the transaction status of a certain period of the past as input values. The cancellation prediction outputs a score for each customer of the financial institution on the possibility of early repayment of a loan or the possibility of canceling a fixed deposit or account using the transaction status of each financial institution over a certain period of the past as input values.

[0042] The information processing system 11 can also utilize a model related to personnel affairs (evaluation / aptitude / transfer) of financial institutions. The personnel model determines the probability of an employee leaving the company, the probability of promotion, the necessity of transfer and the transfer destination, etc., based on the personnel information of the employee for a certain period of time in the past. By integrating the parameters of this model, the time required for judgment can be reduced, and business efficiency can be improved.

[0043] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above-mentioned embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0044] For example, although a number of operations are described in a sequence in the form of a flowchart, the sequence does not limit the order in which the operations are performed. Therefore, when implementing each embodiment, the sequence of the operations can be changed as long as it does not affect the content.

[0045] In addition, in this embodiment, the multiple financial institutions are not limited to financial institutions in the same business sector, and may be composed of banks and non-bank financial institutions, such as banks, securities companies, or insurance companies. Even if the multiple financial institutions are composed of banks, they may be composed of banks of different sizes, such as city banks and regional banks.

[0046] A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes.

[0047] (Appendix 1) A parameter receiving means for receiving an input of anonymized parameters of a plurality of models used for analyzing financial transactions based on information on customer assets and generated by each of a plurality of financial institutions; a secure computation means for integrating the multiple concealed parameters through secure computation; an output means for outputting the parameters integrated by the secure computation means in a concealed format; A secure computing system.

[0048] (Appendix 2) The model is a secure computation system described in Appendix 1, which accepts input of desired M&A partner information and outputs whether the acquisition will be successful or the estimated acquisition price.

[0049] (Appendix 3) The secure computing system according to claim 1, wherein the model is a model that inputs information about the customer's assets and outputs credit information about the customer.

[0050] (Appendix 4) The secure computing system of claim 1, wherein the model is a model that inputs information about the customer's assets and outputs financial products and financial transactions to be recommended to the customer.

[0051] (Appendix 5) 5. The secure computation system according to any one of claims 1 to 4, wherein the secure computation is a secret sharing computation.

[0052] (Appendix 6) A financial institution server comprising an analysis means for analyzing a customer's financial transactions using an updated model updated by federated learning using secure computation based on customer information or financial transaction information relating to the customer's assets.

[0053] (Appendix 7) The financial institution server according to claim 6, wherein the analysis means performs analysis on M&A using an updated model updated by federated learning using secret computation based on financial transaction information on past M&A cases as the financial transaction information.

[0054] (Appendix 8) 7. The financial institution server according to claim 6, wherein the analysis of the financial transaction of the customer by the analysis means is an analysis of credit information of the customer.

[0055] (Appendix 9) 7. The financial institution server according to claim 6, wherein the analysis of the financial transactions of the customer by the analysis means is an analysis of financial products to be recommended to the customer.

[0056] (Appendix 10) An information processing system having a plurality of financial institution servers and a secure computation system, Each of the plurality of financial institution servers has a model storage unit that stores a model that is generated based on information on assets of the customer and analyzes financial transactions of the customer; a concealment unit that conceals parameters of the model stored in the model storage unit; a model input / output means for transmitting the model anonymized by the anonymization unit in an anonymized form to a secure computing system; a restoration unit that restores the concealed parameters; Equipped with The secure computing system comprises: A parameter receiving means for receiving an input of anonymized parameters of a plurality of models used for analyzing financial transactions based on information on customer assets and generated by each of a plurality of financial institutions; a secure computation means for integrating the received multiple concealed parameters through secure computation; an output means for outputting the parameters integrated by the secure computation means in a concealed format; Equipped with Information processing system.

[0057] (Appendix 11) receiving input of anonymized parameters of a plurality of models used in analyzing financial transactions based on information on customer assets and generated by each of a plurality of financial institutions; The concealed parameters are integrated by secure computation; The integrated parameter is output in a concealed format.

[0058] (Appendix 12) receiving input of anonymized parameters of a plurality of models used in analyzing financial transactions based on information on customer assets and generated by each of a plurality of financial institutions; The concealed parameters are integrated by secure computation; A recording medium storing a program for causing a computer to execute the steps of: outputting the integrated parameters in a concealed format. [Explanation of symbols]

[0059] 10, 11 Information Processing Systems 100, 110 Secure Calculation System 101, 111 Parameter reception section 102, 112 Secret Computation Department 103, 113 Output section 200, 210 Financial institution server 201, 211 Model memory section 202, 212 Concealment Department 203, 213 model input / output section 204, 214 Restoration Department 215 Analysis Department

Claims

1. A parameter receiving means for receiving an input of anonymized parameters of a plurality of models used for analyzing financial transactions based on information on customer assets and generated by each of a plurality of financial institutions; a secure computation means for integrating the multiple concealed parameters through secure computation; an output means for outputting, in a concealed format, improvements of the parameters integrated by the secure calculation means from each of the input parameters to a corresponding server of each of the plurality of financial institutions; Equipped with the secure computing means determines weights for each of the multiple anonymized parameters in accordance with features of the corresponding model, and integrates the multiple parameters based on the determined weights; Secret calculation system.

2. The secure computation system according to claim 1 , wherein the model receives input of desired M&A counterparty information and outputs whether the acquisition will be successful or an estimated acquisition price.

3. 2. The secure computing system according to claim 1, wherein the model is a model that inputs information about the customer's assets and outputs credit information about the customer.

4. 4. The secure computation system according to claim 1, wherein the secure computation is a secret sharing computation.

5. An information processing system having a plurality of financial institution servers and a secure computation system, Each of the plurality of financial institution servers includes a model storage unit that stores a model that is generated based on information on assets of the customer and analyzes financial transactions of the customer; a concealment unit that conceals parameters of the model stored in the model storage unit; a model input / output means for transmitting the model anonymized by the anonymization unit in an anonymized form to a secure computing system; A restoration unit that restores the concealed parameters, The secure computing system comprises: a parameter receiving means for receiving an input of anonymized parameters of a plurality of models used in the analysis of financial transactions based on the information on the assets of the customer and generated by each of a plurality of financial institutions; a secure computation means for integrating the concealed parameters by secure computation; an output means for outputting, in a concealed format, improvements of the parameters integrated by the secure calculation means from each of the input parameters to a corresponding server of each of the plurality of financial institutions; Equipped with the secure computation means determines a weight for each of the anonymized parameters in accordance with a feature of the corresponding model; Information processing system.

6. The financial institution server includes an analysis means for performing an analysis of the financial transactions of the customer by using an updated model updated by federated learning using secret computation based on customer information or financial transaction information related to assets of the customer, The information processing system according to claim 5 , wherein the updated model is updated based on improvements to parameters of the model obtained in a concealed form from the secure computing system.

7. The information processing system described in Claim 6, wherein the analysis means performs analysis regarding M&A using the updated model updated by federated learning using secret computation based on financial transaction information regarding past M&A cases as the financial transaction information.

8. An information processing system as described in claim 6, wherein the analysis of the financial transactions of the customer in the analysis means is an analysis of the credit information of the customer.

9. The computer receiving input of anonymized parameters of a plurality of models used in analyzing financial transactions based on information on customer assets and generated by each of a plurality of financial institutions; The multiple concealed parameters are integrated by secure computation; outputting improvements of the integrated parameters from each of the input parameters to a corresponding server of each of the plurality of financial institutions in a confidential format; In the step of integrating, weights of the multiple anonymized parameters are determined in accordance with features of the corresponding models, and the multiple parameters are integrated based on the determined weights. Secret calculation method.

10. receiving input of anonymized parameters of a plurality of models used in analyzing financial transactions based on information on customer assets and generated by each of a plurality of financial institutions; The multiple concealed parameters are integrated by secure computation; outputting improvements of the integrated parameters from each of the input parameters to a corresponding server of each of the plurality of financial institutions in a concealed format; In the integrating process, a weight for each of the plurality of concealed parameters is determined in accordance with a feature of the corresponding model, and the plurality of parameters are integrated based on the determined weight. program.

Images