Analysis device, analysis method, and analysis program
The analysis device facilitates secure testing of Cox proportional hazard regression analysis by using secret calculation methods, addressing the challenge of testing encrypted data while maintaining data confidentiality.
Patent Information
- Application Number
- JP2023075875
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-01
- Publication Date
- 2024-11-14
AI Technical Summary
Conventional methods face difficulties in testing Cox proportional hazard regression analysis performed by secret calculation.
An analysis device and method that utilize a partial regression coefficient, Hessian matrix, and score vector obtained by Cox proportional hazard regression analysis through secret calculation, incorporating a test section and an output control section to perform tests on encrypted data.
Enables secure testing of Cox proportional hazard regression analysis, ensuring data confidentiality by performing calculations without revealing the original data.
Smart Images

Figure 2024160648000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an analysis device, an analysis method, and an analysis program. [Background technology]
[0002] Conventionally, there is known a secure computation system that performs statistical computations while keeping data secret and provides the statistical values obtained as a result of the computations to a user. For example, the secure computation system may be used to analyze data in the medical field, etc., which handles important personal information.
[0003] There is also known a secure computation system that performs statistical processing on encrypted data. For example, a technique is known that uses encrypted data to find parameters for logistic regression analysis (see, for example, Patent Document 2).
[0004] In addition, Cox proportional hazards regression analysis, which is a method similar to logistic regression analysis and is used for survival time analysis, is known (see, for example, Patent Document 3). [Prior art documents] [Patent documents]
[0005] [Patent Document 1] International Publication No. 2019 / 124260 [Patent Document 2] JP 2020-042128 A [Patent Document 3] JP 2008-299370 A [Non-patent literature]
[0006] [Non-Patent Document 1] Nippon Telegraph and Telephone Corporation, Secure Computation System and Its Principles, [online], [Retrieved January 6, 2023], Internet<URL:https: / / www.rd.ntt / sil / project / sc / secure_computation.html> Summary of the Invention [Problem to be solved by the invention]
[0007] However, the conventional technology has a problem in that it may be difficult to test Cox proportional hazards regression analysis performed using secure computation. [Means for solving the problem]
[0008] In order to solve the above-mentioned problems and achieve the object, the analysis device of the present invention is characterized in having a testing unit that performs testing of the Cox proportional hazards regression analysis by secret calculation using at least one of a partial regression coefficient, a Hessian matrix, and a score vector obtained by the Cox proportional hazards regression analysis by secret calculation, and an output control unit that outputs the result of the testing by the testing unit. Effect of the Invention
[0009] According to the present invention, it is possible to perform testing of Cox proportional hazards regression analysis performed by secure computation. [Brief description of the drawings]
[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of an analysis system according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of the analysis device according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of learning data. [Figure 4] FIG. 4 is a diagram showing the definitions of symbols. [Diagram 5] FIG. 5 is a flowchart showing the flow of the Wald test. [Figure 6]FIG. 6 is a flow chart showing the flow of the Score test. [Figure 7] FIG. 7 is a flowchart showing the flow of the likelihood ratio test. [Figure 8] FIG. 8 is a flowchart showing the flow of the process of calculating the log partial likelihood. [Figure 9] FIG. 9 is a diagram illustrating an example of a computer that executes an analysis program. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an embodiment of an analysis device, an analysis method, and an analysis program according to the present application will be described in detail with reference to the drawings. Note that the present invention is not limited to the embodiment described below.
[0012] First, the configuration of the analysis system will be described with reference to Figure 1. The analysis system is a system for analyzing data using secure computation.
[0013] 1, the analysis system 1 includes a secure computation system 10. The secure computation system 10 is connected to a providing device 20 and a providing device 30 via a network N. For example, the network N is the Internet. The secure computation system 10 is also connected to a terminal device 40.
[0014] The providing device 20 and the providing device 30 are devices on the data provider side. The providing device 20 and the providing device 30 provide (register) data to the secure computing system 10.
[0015] The data provided by the providing device 20 and the providing device 30 includes information that is desirably kept anonymous (e.g., personal information such as an individual's name and address). For example, the providing device 20 and the providing device 30 provide medical treatment data or health checkup data used in medical institutions. However, the data provided by the providing device 20 and the providing device 30 is not limited to data used in medical institutions.
[0016] The secure computation system 10 includes a data storage unit 11 and a data processing unit 12. The data storage unit 11 includes a plurality of storage devices (storage device 111, storage device 112, storage device 113) that store data by secret sharing. The data processing unit 12 includes a plurality of computation devices (computation device 121, computation device 122, computation device 123) that process data by secure computation. Note that the number of storage devices and the number of computation devices are not limited to the example shown in FIG. 1.
[0017] The secure computation system 10 can perform secret sharing and secure computation according to the method described in Non-Patent Document 1 (URL: https: / / www.rd.ntt / sil / project / sc / secure_computation.html).
[0018] First, data provided to the secure computing system 10 is divided (fragmented) into a plurality of shares. Then, each of the plurality of shares is distributed and stored in a plurality of storage devices included in the data storage unit 11. In the example of Fig. 1, the provided data is divided into three shares. Then, storage device 111, storage device 112, and storage device 113 each store one share.
[0019] Data processing unit 12 performs secure computation on the shares accumulated in data accumulation unit 11. Data processing unit 12 performs secure computation by multi-party computation using multiple computing devices. In the example of FIG. 1, data processing unit 12 performs secure computation by computing device 121, computing device 122, and computing device 123.
[0020] The data processing unit 12 can perform various statistical calculations without restoring the shares. For example, the data processing unit 12 can perform table operations such as sorting and joining, tallying the number of records, calculating statistics such as sums, averages, maximum values, minimum values, and sample variances, and performing statistical tests such as t-tests. Furthermore, the data processing unit 12 can perform statistical analyses such as regression analysis and principal component analysis.
[0021] The analysis device 13 analyzes the data by using the data processing unit 12. The analysis device 13 provides the analysis result to the terminal device 40 on the data user side based on the result of the secure computation executed by the data processing unit 12. The user can obtain the data analysis result via the terminal device 40.
[0022] For example, the secure computing system 10 may be provided with data on the attributes and physical state of each individual. The data on the attributes and physical state is personal information that is preferably kept confidential. The data on the attributes and physical state includes, for example, age, sex, height, weight, etc. The data storage unit 11 stores the provided data into fragmented shares in each storage device.
[0023] Each share is meaningless on its own. Therefore, it is not possible to restore the original data from a single share. However, by collecting multiple shares, it is possible to restore the original data.
[0024] Although users of the data cannot view the registered data itself, they can view the results of data analysis via the analysis device 13 and the terminal device 40. For example, if the data includes the gender and weight of individuals, the users cannot view the gender and weight of each individual, but can view the "average weight of men," which is the result of the data analysis.
[0025] As an example, the data storage unit 11 can perform secret sharing using a technique known as Shamir's threshold secret sharing scheme. In this case, the data storage unit 11 stores, as shares, three coordinates passing through a polynomial with the original data as an intercept in each server. In addition, since the slope of the polynomial is determined randomly, the shares are not necessarily the same each time even if the original data is the same. The original data may be a numerical value, or may be data that has already been converted into a numerical value.
[0026] The secure computation system 10 can restore the original data from multiple shares. If the polynomial is a linear expression, the secure computation system 10 can find an intercept (corresponding to the original data) from the intersection of a line connecting two coordinates (corresponding to shares) and the axis. On the other hand, since a line cannot be determined from a single coordinate, the original data cannot be restored.
[0027] As described above, the data processing unit 12 can perform secure computation on the original data without recovering the shares. For example, the result of adding the shares represented by coordinates corresponds to the share resulting from adding the original data of each share.
[0028] The analysis device 13 causes the data processing unit 12 to execute processing using secure computation in response to a request from the terminal device 40. Note that the data processing unit 12 or the terminal device 40 may realize functions equivalent to those of the analysis device 13. For example, the analysis system 1 may be configured not to include the analysis device 13. In that case, the terminal device 40 is connected to the data processing unit 12 and executes processing equivalent to that of the analysis device 13. Furthermore, statistical computation based on shares may be executed by the terminal device 40 instead of the data processing unit 12.
[0029] In the first embodiment, an example will be described in which the analysis device 13 performs Cox proportional hazards regression analysis and testing of the Cox proportional hazards regression analysis by secure computation.
[0030] The configuration of the analysis device 13 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the analysis device according to the embodiment.
[0031] The following describes each part of the analysis device 13. As shown in FIG.
[0032] The communication unit 131 communicates data with other devices. For example, the communication unit 131 is a network interface card (NIC). The communication unit 131 can transmit and receive data with other devices.
[0033] The input unit 132 is an interface for receiving input of data, and is connected to input devices such as a mouse and a keyboard.
[0034] The output unit 133 is an interface for outputting data, and is connected to input devices such as a display and a speaker.
[0035] The storage unit 134 is a storage device such as a hard disk drive (HDD), a solid state drive (SSD), an optical disk, etc. The storage unit 134 may be a semiconductor memory in which data can be rewritten, such as a random access memory (RAM), a flash memory, or a non-volatile static random access memory (NVSRAM). The storage unit 134 stores an operating system (OS) and various programs executed by the analysis device 13.
[0036] The control unit 135 controls the entire analysis device 13. The control unit 135 is, for example, an electronic circuit such as a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or a GPU (Graphics Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 135 also has an internal memory for storing programs that define various processing procedures and control data, and executes each process using the internal memory.
[0037] The control unit 135 functions as various processing units by the operation of various programs. For example, the control unit 135 includes a calculation unit 1351, an update unit 1352, a test unit 1353, and an output control unit 1354.
[0038] The calculation unit 1351 performs calculation of Cox proportional hazards regression by secure calculation. The calculation unit 1351 inputs explanatory variables to the Cox proportional hazards regression model and outputs a response variable.
[0039] The definitions of symbols used in the following description are shown in Fig. 4. Fig. 4 is a diagram showing the definitions of symbols.
[0040] As shown in Figure 4, N is the number of records. k is the number of attributes (explanatory variables). The dataset X contains attribute information for each record in an N × k matrix. For example, the i-th record is (x1, ..., x k ).
[0041] The result is information indicating whether a record is alive or dead. t is the observation time. y is a binary value of 0 (alive) or 1 (dead).
[0042] The partial regression coefficients and the score vector are expressed as column vectors. The score vector is the first derivative of the log partial likelihood. The Hessian matrix is the second derivative of the log partial likelihood.
[0043] In addition, the partial regression coefficients, score vectors, Hessian matrices, and log partial likelihoods are subscripted with 0. The method of calculating the log partial likelihoods will be described later.
[0044] The update unit 1352 updates the parameters of the Cox proportional hazards regression model by secure computation so that the objective variable calculated by the calculation unit 1351 approaches the correct value.
[0045] The processing of the calculation unit 1351 and the update unit 1352 is performed once or a plurality of times, whereby the Cox proportional hazards regression model is learned.
[0046] Fig. 3 is a diagram showing an example of learning data. The values in the "Age" column, "Gender" column, "Calorie Intake" column, and "Weight Loss" column in Fig. 3 are explanatory variables of the Cox proportional hazards regression model. In addition, the predicted survival rate based on the value in the "Survival Time" column is the objective variable of the Cox proportional hazards regression model, and corresponds to the hazard function h(t|x).
[0047] A calculation unit 1351 inputs values of the "age", "gender", "calorie intake", and "weight loss" columns into a Cox proportional hazards regression model to obtain an output. An update unit 1352 updates parameters of the Cox proportional hazards regression model so that the output obtained by the calculation unit 1351 approaches a predicted survival rate based on values of the "survival time" column.
[0048] The testing unit 1353 tests the Cox proportional hazards regression model. In secure computation, it is difficult to obtain the learning data itself from outside. Therefore, the testing unit 1353 calculates statistics for testing based on limited information that can be obtained.
[0049] Here, the testing unit 1353 performs testing of the Cox proportional hazards regression analysis by secure computation using at least one of the partial regression coefficient, the Hessian matrix, and the score vector obtained by the Cox proportional hazards regression analysis by secure computation. The testing unit 1353 obtains information on the Cox proportional hazards regression analysis, such as the partial regression coefficient, the Hessian matrix, and the score vector, from the secure computation system 10.
[0050] The process performed by the test unit 1353 in carrying out the Wald test, the Score test, and the likelihood ratio test will be described.
[0051] (Wald test) 5 is a flowchart showing the flow of the Wald test. As shown in Fig. 5, the test unit 1353 acquires the partial regression coefficients and the Hessian matrix of the trained Cox proportional hazards regression model from the secure computation system 10 (step S101).
[0052] Next, the testing unit 1353 calculates the statistics of the Wald test as shown in equation (1) (step S102). Then, the testing unit 1353 executes the test and outputs the test result via the output control unit 1354 (step S103). However, when the initial partial regression coefficient is set to 0, the testing unit 1353 calculates the statistics by equation (2).
[0053]
number
[0054]
number
[0055] In this way, the testing unit 1353 calculates the statistics of the Wald test based on the partial regression coefficients and the Hessian matrix, and performs the chi-square test based on the statistics.
[0056] (Score test) Fig. 6 is a flowchart showing the flow of the score test. As shown in Fig. 6, the test unit 1353 acquires the Hessian matrix (initial Hessian matrix in Fig. 4) and the score vector (initial score vector in Fig. 4) at the start of learning of the trained Cox proportional hazards regression model from the secure computation system 10 (step S201).
[0057] Next, the testing unit 1353 calculates the statistics of the Score test as shown in equation (3) (step S202). Then, the testing unit 1353 executes the test and outputs the test result via the output control unit 1354 (step S203).
[0058]
number
[0059] In this way, the testing unit 1353 calculates statistics for the Score test based on the Hessian matrix and score vector at the start of learning of the regression model of the Cox proportional hazards regression analysis, and performs a chi-square test based on the statistics.
[0060] (Likelihood ratio test) 7 is a flowchart showing the flow of the likelihood ratio test. The test unit 1353 acquires the partial regression coefficients and Hessian matrix of the trained Cox proportional hazards regression model from the secure computation system 10.
[0061] In addition, each record of the training data in Figure 3 corresponds to each patient, and the hazard function of the Cox proportional hazards regression model represents the survival probability of a patient at a certain time. Whether or not a patient has died at a certain time is derived from the survival time of the training data.
[0062] Among the records in the training data, records corresponding to patients who are deceased at the specified time are called death records, and among the records in the training data, records corresponding to patients who are not deceased at the specified time are called remaining records.
[0063] 7, first, the testing unit 1353 calculates initial log partial likelihoods from partial regression coefficients at the start of learning (step S301). Also, the testing unit 1353 calculates log partial likelihoods from learned partial regression coefficients (step S302).
[0064] The test unit 1353 calculates the log partial likelihood by equation (4). The test unit 1353 also calculates the initial log partial likelihood by an equation in which β in equation (4) is replaced with β0. The calculation of the log partial likelihood will be described in detail later.
[0065]
number
[0066] Next, the testing unit 1353 calculates statistics of the likelihood ratio test from the initial log partial likelihood and the log partial likelihood as shown in equation (5) (step S303). Then, the testing unit 1353 performs a chi-square test and outputs the test result (step S304).
[0067]
number
[0068] Fig. 8 is a flowchart showing the flow of a process for calculating a log partial likelihood. As shown in Fig. 8, first, the testing unit 1353 uses secure computation sorting to sort the records of the data set in ascending order of time (step S311).
[0069] Next, the testing unit 1353 calculates the product-sum value of the partial regression coefficient and the record by secure computation (step S312). Also, the testing unit 1353 calculates the death risk (exp on the right side of equation (4)), which is the exponential value of the product-sum value, by a secure computation mapping (step S313).
[0070] Here, the testing unit 1353 calculates the sum of death risks of j where the record number is i<=j (Σ on the right side of the right side of the formula (4)) using the secure computation sum for i=1, . . . , N (step S314).
[0071] Next, the testing unit 1353 calculates the logarithm of the sum of the death risks (log of the right-hand side of equation (4)) using the secure computation mapping (step S315).
[0072] Then, the test unit 1353 calculates the difference between the sum-of-products value and the logarithm value by secure subtraction (subtraction of the right side of equation (4)) (step S316). Furthermore, the test unit 1353 uses the sum-of-products-by-secure calculation to obtain information on whether the person is alive or dead (y i ) and calculate the log partial likelihood from the result of the subtraction (step S317).
[0073] In this way, the testing unit 1353 calculates, by secret calculation, the sum of the products of the death records and partial regression coefficients used in training the regression model of Cox proportional hazards regression analysis as a first death risk, calculates, by secret calculation, the sum of the products of the remaining records and partial regression coefficients used in training the regression model as a second death risk, calculates a log-likelihood based on the first death risk and the second death risk, and performs testing based on the log-likelihood.
[0074] [Effects of the embodiment] As described above, the analysis device 13 includes the testing unit 1353 and the output control unit 1354. The testing unit 1353 performs testing of the Cox proportional hazards regression analysis by secure computation using at least one of the partial regression coefficient, the Hessian matrix, and the score vector obtained by the Cox proportional hazards regression analysis by secure computation. The output control unit 1354 outputs the result of the testing by the testing unit 1353.
[0075] This enables the analysis device 13 to test the Cox proportional hazards regression analysis performed by secure computation.
[0076] For example, the testing unit 1353 calculates statistics of the Wald test based on the partial regression coefficients and the Hessian matrix, and performs the test based on the statistics.
[0077] For example, the testing unit 1353 calculates statistics for the Score test based on the Hessian matrix and score vector at the start of learning of the regression model of the Cox proportional hazards regression analysis, and performs the test based on the statistics.
[0078] For example, the testing unit 1353 uses secret calculation to calculate the sum of the products of the death records and partial regression coefficients used in training the regression model of Cox proportional hazards regression analysis as a first death risk, and uses secret calculation to calculate the sum of the products of the remaining records and partial regression coefficients used in training the regression model as a second death risk, calculates a log-likelihood based on the first death risk and the second death risk, and performs testing based on the log-likelihood.
[0079] In this way, the analysis device 13 can perform the Wald test, the Score test, and the likelihood ratio test.
[0080] [System configuration, etc.] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or a part of it can be functionally or physically distributed or integrated in any unit according to various loads, usage conditions, etc. Furthermore, each processing function performed by each device can be realized in whole or in any part by a CPU (Central Processing Unit) and a program analyzed and executed by the CPU, or can be realized as hardware by wired logic. Note that the program may be executed not only by the CPU but also by other processors such as a GPU.
[0081] Furthermore, among the processes described in this embodiment, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified.
[0082] [program] In one embodiment, the analysis device 13 can be implemented by installing an analysis program that executes the above-mentioned analysis processing as package software or online software on a desired computer. For example, the above-mentioned analysis program can be executed by an information processing device, thereby making the information processing device function as the analysis device 13. The information processing device here includes desktop and notebook personal computers. In addition, the information processing device also includes mobile communication terminals such as smartphones, mobile phones, and PHS (Personal Handyphone System), and further slate terminals such as PDA (Personal Digital Assistant), etc.
[0083] The analysis device 13 can also be implemented as an analysis server device that provides services related to the above-mentioned analysis processing to a client, the client being a terminal device used by a user. For example, the analysis server device is implemented as a server device that provides an analysis service that receives as input the partial regression coefficients, Hessian matrix, and score vector obtained by Cox proportional hazards regression analysis using secure computation, and outputs the test results of the Cox proportional hazards regression analysis.
[0084] 9 is a diagram showing an example of a computer that executes an analysis program. The computer 1000 includes, for example, a memory 1010 and a CPU 1020. The computer 1000 also includes a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.
[0085] The memory 1010 includes a read only memory (ROM) 1011 and a random access memory (RAM) 1012. The ROM 1011 stores a boot program such as a basic input output system (BIOS). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1100. A removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to a mouse 1110 and a keyboard 1120, for example. The video adapter 1060 is connected to a display 1130, for example.
[0086] The hard disk drive 1090 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. That is, a program that defines each process of the analysis device 13 is implemented as a program module 1093 in which computer-executable code is written. The program module 1093 is stored, for example, in the hard disk drive 1090. For example, a program module 1093 for executing the same process as the functional configuration of the analysis device 13 is stored in the hard disk drive 1090. The hard disk drive 1090 may be replaced by an SSD (Solid State Drive).
[0087] Furthermore, setting data used in the processing of the above-described embodiment is stored as program data 1094, for example, in the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads out the program module 1093 or the program data 1094 stored in the memory 1010 or the hard disk drive 1090 into the RAM 1012 as necessary, and executes the processing of the above-described embodiment.
[0088] Note that the program module 1093 and the program data 1094 are not limited to being stored in the hard disk drive 1090, but may be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and the program data 1094 may be stored in another computer connected via a network (such as a local area network (LAN) or wide area network (WAN)). The program module 1093 and the program data 1094 may then be read by the CPU 1020 from the other computer via the network interface 1070. [Explanation of symbols]
[0089] 1. Analysis system 10. Secure Computing System 11 Data Storage Section 12 Data Processing Section 13 Analyzer 131 Communications Department 132 Input section 133 Output section 134 Storage section 135 Control Unit 1351 Calculation Department 1352 Update Department 1353 Examination Department 1354 Output control section
Claims
1. a verification unit that performs verification of the Cox proportional hazards regression analysis by secure computation using at least one of a partial regression coefficient, a Hessian matrix, and a score vector obtained by the Cox proportional hazards regression analysis by secure computation; an output control unit that outputs a result of the test by the test unit; An analytical device comprising:
2. 2. The analysis device according to claim 1, wherein the test unit calculates statistics of a Wald test based on the partial regression coefficients and the Hessian matrix, and performs the test based on the statistics.
3. The analysis device according to claim 1 , wherein the test unit calculates statistics for a score test based on the Hessian matrix and the score vector at a start of learning of the regression model of the Cox proportional hazards regression analysis, and performs the test based on the statistics.
4. The analysis device described in claim 1, characterized in that the testing unit calculates, using secret calculation, a product sum of the death records used in training the regression model of the Cox proportional hazards regression analysis and the partial regression coefficient as a first mortality risk, calculates, using secret calculation, a product sum of the remaining records used in training the regression model and the partial regression coefficient as a second mortality risk, calculates a log-likelihood based on the first mortality risk and the second mortality risk, and performs testing based on the log-likelihood.
5. An analytical method performed by an analytical device, comprising: a verification step of verifying the Cox proportional hazards regression analysis by secure computation using at least one of a partial regression coefficient, a Hessian matrix, and a score vector obtained by the Cox proportional hazards regression analysis by secure computation; an output control step of outputting a result of the inspection performed by the inspection step; An analytical method comprising the steps of:
6. a verification step of verifying the Cox proportional hazards regression analysis by secure computation using at least one of a partial regression coefficient, a Hessian matrix, and a score vector obtained by the Cox proportional hazards regression analysis by secure computation; an output control step of outputting a result of the test performed in the test step; An analysis program characterized by causing a computer to execute the above.
Citation Information
Patent Citations
Recommendation device, recommendation method, recommendation program and recording medium with same program recorded
JP2008299370A
Secret statistic processing system, method, statistical processing apparatus, and program
JP2020042128A
Secure computation system and method
WO2019124260A1
