Analytical device, analytical system, store server, analytical method, encryption method, and program

Abstract

An analysis device according to the present disclosure comprises: an acquisition means that acquires, from store servers of a plurality of sub-dealers, sales data relating to the situation of vehicle sales in a format encrypted by a homomorphic encryption scheme; an analysis means that, on the basis of the encrypted sales data, executes marketing analysis for vehicle sales in the encrypted format; and a transmission means that transmits an analysis result to each of the store servers in the encrypted format.

Description

Analysis device, analysis system, store server, analysis method, encryption method, and recording medium

[0001] The present disclosure relates to an analysis device, an analysis system, a store server, an analysis method, an encryption method, and a recording medium.

[0002] In marketing analysis, in order to improve the accuracy of analysis, it is required to utilize not only data held by a company but also data held by other companies. Patent Document 1 discloses a technology for safely utilizing data held by each company without disclosing the contents of the data to other companies.

[0003] Japanese Patent Application Laid-Open No. 2022-29386

[0004] Incidentally, in order to conduct accurate marketing analysis of vehicle sales, sales data held by a large number of vehicle dealerships is required. Vehicle dealerships include authorized dealers that have signed exclusive dealership agreements with vehicle manufacturers, and sub-dealers that handle vehicles from multiple manufacturers. However, it is difficult to obtain the sales data held by each sub-dealer as is for marketing analysis.

[0005] An example of an objective of the present disclosure is to provide an analysis device or the like that can improve the accuracy of marketing analysis while keeping sensitive sales data confidential.

[0006] An analysis device in one aspect of the present disclosure includes an acquisition means for acquiring sales data regarding vehicle sales status from store servers of multiple sub-dealers in a format encrypted using a homomorphic encryption method, an analysis means for performing marketing analysis for vehicle sales in an encrypted format based on the encrypted sales data, and a transmission means for transmitting the analysis results to each store server in an encrypted format.

[0007] An analysis system in one aspect of the present disclosure is an analysis system having the above-mentioned analysis device and multiple store servers, each of which includes a data storage means for storing sales data regarding the sales status of vehicles at its own store, an encryption means for encrypting the sales data using a homomorphic encryption method, and an input / output means for transmitting the sales data in encrypted form to the analysis device.

[0008] In one aspect of the present disclosure, the store server includes a data storage means for storing sales data regarding the sales status of vehicles at the store, an encryption means for encrypting the sales data using a homomorphic encryption method, and an input / output means for transmitting the sales data in encrypted form to an analysis device.

[0009] In one aspect of the present disclosure, an analysis method involves a computer obtaining sales data regarding vehicle sales status from store servers of multiple sub-dealers in a format encrypted using homomorphic encryption, performing marketing analysis for vehicle sales in an encrypted format based on the encrypted sales data, and transmitting the analysis results to each store server in an encrypted format.

[0010] In one aspect of the encryption method of the present disclosure, a computer stores sales data regarding the sales status of vehicles at its own store, encrypts the sales data using homomorphic encryption, and transmits the sales data in encrypted form to an analysis device.

[0011] In one aspect of the present disclosure, a recording medium stores a program that causes a computer to obtain sales data regarding vehicle sales status from store servers of multiple sub-dealers in a format encrypted using homomorphic encryption, perform marketing analysis for vehicle sales in an encrypted format based on the encrypted sales data, and transmit the analysis results to each store server in an encrypted format.

[0012] One example of the effect of the present disclosure is that it can improve the accuracy of marketing analysis while keeping sensitive sales data confidential.

[0013] FIG. 1 is a block diagram showing the configuration of an analysis system according to the present disclosure. FIG. 2 is a diagram showing a hardware configuration in which the analysis system according to the present disclosure is realized by a computer device and its peripheral devices. FIG. 3 is an example of an analysis result output according to the present disclosure. FIG. 4 is an example of an analysis result output according to the present disclosure. FIG. 5 is a flowchart showing the analysis operation according to the present disclosure. FIG. 6 is a block diagram showing the configuration of the analysis system according to the present disclosure. FIG. 7 is a flowchart showing the analysis operation according to the present disclosure.

[0014] Hereinafter, with reference to the drawings, embodiments of an analysis device, an analysis system, a store server, an analysis method, an encryption method, a program, and a non-transitory recording medium for recording a program according to the present disclosure will be described in detail. The present embodiments do not limit the disclosed technology.

[0015] 1 is a block diagram showing the configuration of an analysis system 10 according to the present disclosure. The analysis system 10 is a system that performs marketing analysis for promoting vehicle sales by using sales data held by multiple sub-dealers in encrypted form.

[0016] In the present disclosure, marketing analysis refers to, for example, analysis for understanding vehicle sales trends at a vehicle dealership, and the analysis results are used to propose vehicle models to be purchased by a specific customer segment or for product planning for new cars. A specific example of marketing analysis is an analysis of sales trends for a specific vehicle model at multiple sub-dealers. Other examples of marketing analysis include analysis for understanding vehicle sales trends for each customer attribute, such as customer age, gender, occupation, annual income, and family structure, and comparison of sales trends of vehicle models aimed at the same target segment from multiple manufacturers.

[0017] In this disclosure, an authorized dealer is an authorized retailer that sells new and used cars, and is a dealer that has signed a dealership agreement with an automobile manufacturer or a sales subsidiary of an automobile manufacturer, etc. A sub-dealer is a dealership that does not have a dealership agreement with a specific manufacturer and is able to handle cars from various manufacturers.

[0018] 1, an analysis system 10 includes an analysis device 100 and multiple store servers 200 (200a, ..., 200n). The store servers 200 are owned by each sub-dealer or by a person who manages the sales data of each sub-dealer.

[0019] The analysis device 100 is owned, for example, by a person who performs marketing analysis or a marketing analysis service provider. The analysis device 100 performs marketing analysis for vehicle sales in an encrypted format based on sales data encrypted using homomorphic encryption and provided by each of multiple sub-dealers. The analysis device 100 includes an acquisition unit 101, an analysis unit 102, and a transmission unit 103.

[0020] Each of the store servers 200 includes a data storage unit 201i (i = 1, ..., k) that stores sales data related to the sales status of vehicles at its own store, an encryption unit 202i (i = 1, ..., k) that encrypts the sales data stored in the data storage unit 201i using homomorphic encryption, and an input / output unit 203i (i = 1, ..., k) that transmits the sales data in encrypted form to the analysis device 100. The number of store servers 200 provided is equal to the number (k) of sub-dealers that provide sales data. The analysis device 100, which is an essential component of the present disclosure, will be described in detail below.

[0021] 2 is a diagram illustrating an example of a hardware configuration in which the analysis device 100 according to the present disclosure is realized by a computer device 500 including a processor. As shown in FIG. 2, the analysis device 100 includes a central processing unit (CPU) 501, memories such as a read-only memory (ROM) 502 and a random access memory (RAM) 503, a storage device 505 such as a hard disk for storing a program 504, a communication interface (I / F) 508 for network connection, and an input / output interface 511 for inputting and outputting data. In the present disclosure, sales data received from each store server 200 is input to the analysis device 100 via the communication I / F 508.

[0022] The CPU 501 runs an operating system to control the entire analysis device 100 according to the present disclosure. The CPU 501 also reads programs and data into memory from a recording medium 506 attached to, for example, a drive device 507. The CPU 501 also functions as the acquisition unit 101, analysis unit 102, and transmission unit 103 according to the present disclosure, or as part of these units, and executes processing or commands in the flowchart shown in FIG. 5, which will be described later, based on the program.

[0023] 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 part of the recording medium in 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) connected to a communication network.

[0024] 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 output.

[0025] As described above, the analytical device 100 shown in FIG. 1 is realized by the computer hardware shown in FIG. 2. However, the means for realizing each unit of the analytical device 100 in FIG. 1 is not limited to the configuration described above. The analytical device 100 may be realized by a single physically coupled device, or by two or more physically separate 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 analytical device 100 shown in FIG. 1 can also be configured using cloud computing or the like.

[0026] The acquisition unit 101 is a means for acquiring sales data related to the sales status of vehicles from the store servers 200 of multiple sub-dealers in a format encrypted using homomorphic encryption. The sales status may be, for example, sales information for each vehicle model or type. It may also be sales information aggregated by vehicle body color, even for the same vehicle model or type. The sales information may also include sales information for accessories sold together with the vehicle. Accessories include car navigation systems, on-board ETC (Electronic Toll Collection System) units, on-board cameras, backup monitors, automatic braking systems, brake assist functions, automatic parking functions, and materials used in the vehicle body, such as genuine leather seats.

[0027] Homomorphic encryption is a public key encryption method that is homomorphic, and operations performed on ciphertext are maintained even after decryption. In the present disclosure, by encrypting sales data using homomorphic encryption, sales data acquired from multiple sub-dealers is encrypted by each store server 200, and analytical operations can be performed in the encrypted format by the analysis device 100. This allows marketing analysis of sales data provided by sub-dealers while keeping it confidential from other sub-dealers and those conducting the marketing analysis.

[0028] The acquisition unit 101 receives sales data held by each of the multiple store servers 200 via the network in a format encrypted using homomorphic encryption, for example, triggered by an operation to perform marketing analysis.

[0029] The analysis unit 102 is a means for performing marketing analysis for vehicle sales in an encrypted format based on the encrypted sales data. The analysis unit 102, for example, aggregates sales information acquired from each sub-dealer according to an analysis method. The analysis unit 102 may, for example, aggregate the number of units sold of a specific vehicle model for each customer attribute, or may aggregate the number of customers who purchase a specific vehicle model. The analysis unit 102 may, for example, aggregate the analysis results in an encrypted format by inputting the encrypted sales data into an analytical model that has been machine-learned in advance. The analytical model is, for example, stored in the storage device 505. The analytical model may also be used in a format encrypted using homomorphic encryption.

[0030] The analysis unit 102 may also perform marketing analysis using multiple analytical models. In this case, the analysis unit 102 may integrate (ensemble) the results calculated by each analytical model. The method for integrating the results calculated by each analytical model is not particularly limited, and may be, for example, averaging or majority voting. The analysis unit 102 may also integrate parameters of multiple analytical models using homomorphic encryption. Known methods can be used as the parameter integration method. For example, when integrating, the weight of the parameters corresponding to each model may be changed depending on the characteristics of each model.

[0031] The transmission unit 103 is a means for transmitting the analysis results in encrypted form to each store server 200. In this embodiment, each store server 200 possesses a decryption key for decrypting the analysis results that it encrypted. When each store server 200 receives the encrypted analysis results, it decrypts the encrypted analysis results using its own decryption key and transmits the decrypted analysis results to the analysis device 100 or the server device that requested the analysis. With this method, the analysis device 100 or the server device that requested the analysis can obtain the analysis results, but the content of the sales data of each sub-dealer is not known.

[0032] 3 and 4 are examples of analysis results output in the present disclosure. The example of the analysis result in Fig. 3 shows the percentage of customers who purchased a specific vehicle model. In the example of Fig. 3, the customer segments are classified by annual income, but the customer segments may also be classified by customer attributes such as age, gender, residential area, occupation, family structure, hobbies, and preferences.

[0033] The example of the analysis result in Figure 4 shows the percentage of car models purchased by a specific customer segment. While the example in Figure 4 shows the purchase percentage for each car model, the analysis result may also show the purchase percentage for each body color for a specific car model or the purchase percentage for options for a specific car model.

[0034] From the example of the analysis results in Fig. 3, it is possible to understand, for example, which customer segments a particular car model is popular with. Also, from the example of the analysis results in Fig. 4, it is possible to understand which car models, body colors, or options are popular with a particular customer segment.

[0035] The operation of the analysis device 100 configured as above will be described with reference to the flowchart of FIG.

[0036] 5 is a flowchart showing an outline of the operation of the analysis device 100 according to the present disclosure. Note that the processing according to this flowchart may be executed based on program control by the processor described above.

[0037] 5 , first, the acquisition unit 101 acquires sales data on vehicle sales status from the store servers 200 of multiple sub-dealers in a format encrypted using homomorphic encryption (step S101). Next, the analysis unit 102 performs marketing analysis for vehicle sales in an encrypted format based on the encrypted sales data (step S102). Finally, the transmission unit 103 transmits the analysis results in an encrypted format to each store server 200 (step S103). This completes the analysis operation of the analysis device 100.

[0038] In the analysis device 100, the acquisition unit 101 acquires sales data on vehicle sales status from the store servers 200 of multiple sub-dealers in a format encrypted using homomorphic encryption. The analysis unit 102 then performs marketing analysis for vehicle sales in encrypted format based on the encrypted sales data. By performing marketing analysis on the sales data held by the multiple store servers 200 in encrypted format, the accuracy of the marketing analysis can be improved while keeping sensitive sales data confidential.

[0039] [Variation 1 of the First Embodiment] Next, a variation of the first embodiment will be described. In this variation, the acquisition unit 101 acquires sales data in a format encrypted by homomorphic encryption from some of the multiple store servers 200. That is, among the multiple store servers 200 in FIG. 1 , there is a store server that does not include an encryption unit 202i (i = 1, ..., k). In this case, the input / output unit 203i (i = 1, ..., k) transmits the sales data in plain text to the analysis device 100 without encrypting it. Therefore, the acquisition unit 101 receives both encrypted sales data and plain text sales data.

[0040] In this modification, the analysis unit 102 performs marketing analysis based on the encrypted sales data and the unencrypted sales data. That is, the analysis unit 102 performs marketing analysis for vehicle sales using the partially encrypted sales data. The transmission unit 103 then transmits the analysis results in the partially encrypted format to the store server 200, which holds each decryption key.

[0041] In this modification, the acquisition unit 101 acquires sales data in encrypted format from one of the multiple store servers, and the analysis unit 102 performs marketing analysis for vehicle sales in encrypted format based on the encrypted sales data and unencrypted sales data. As in this modification, by performing calculations on sales data that does not need to be kept secret from the person performing the marketing analysis in plain text, the load used for encryption and calculations can be reduced.

[0042] [Second Modification of First Embodiment] In the above-described present modification, any one of the multiple store servers 200 may be a store server of an authorized dealer. In this case, the acquisition unit 101 acquires sales data from the store servers 200 of the multiple sub-dealers, and further acquires sales data related to the vehicle sales status from the store server 200 of the authorized dealer. Then, the analysis unit 102 performs marketing analysis based on the sales data of the sub-dealers and the sales data of the authorized dealer.

[0043] In this modification, the acquisition unit 101 further acquires sales data on the vehicle sales status from the authorized dealer's store server, and the analysis unit 102 performs marketing analysis based on the sales data of the sub-dealer and the sales data of the authorized dealer. In this way, by using more sales data, the accuracy of the marketing analysis is improved.

[0044] [Variation 3 of the First Embodiment] Furthermore, the above-described Variation 1 and Variation 2 may be combined. That is, the acquisition unit 101 may acquire sales data from the store servers 200 of multiple authorized dealers, and may acquire sales data in a format encrypted using homomorphic encryption from some of the authorized dealer's store servers 200 among the multiple authorized dealer's store servers 200. In other words, the acquisition unit 101 acquires sales data encrypted using homomorphic encryption from some of the authorized dealer's store servers 200, and acquires unencrypted sales data from other authorized dealer's store servers 200. Then, the analysis unit 102 performs marketing analysis for vehicle sales based on the sub-dealer's sales data, the authorized dealer's sales data encrypted using homomorphic encryption, and the unencrypted authorized dealer's sales data, with some of the sales data in an encrypted format.

[0045] [Second Embodiment] Next, a second embodiment of the present disclosure will be described in detail with reference to the drawings. Below, descriptions of content that overlaps with the above description will be omitted to the extent that the description of this embodiment is not unclear. As with the computer device shown in FIG. 2, the functions of each component in each embodiment of the present disclosure can be realized not only by hardware but also by a computer device or software based on program control.

[0046] 6 is a block diagram showing the configuration of an analysis system 11 including an analysis device 110 according to the present disclosure. The analysis device 110 and the store servers 210i (i = 1, ..., k) will be described with reference to Fig. 6, focusing on differences from the analysis system 10. In this embodiment, it is assumed that the store server 210 generates an encryption key for encrypting sales data and a decryption key for decrypting analysis results.

[0047] <Analysis Device 110> The analysis device 110 includes an acquisition unit 111, an analysis unit 112, a transmission unit 113, a reception unit 114, and an output unit 115. The reception unit 114 combines the results of distributed decoding performed by each store server 210 to decode the analysis result. Specific operations of the reception unit 114 will be described later. The output unit 115 displays the decoded analysis result on a display device such as a display. Examples of display of the analysis result are as shown in Figures 3 and 4. Other configurations are basically the same as those in the first embodiment.

[0048] <Store Server 210> Each store server 210 includes a data storage unit 211i (i = 1, ..., k) that stores sales data related to the sales status of vehicles at its own store, an encryption unit 212i (i = 1, ..., k) that encrypts the sales data stored in the data storage unit using a homomorphic encryption method, and an input / output unit 213i (i = 1, ..., k) that transmits the sales data to the analysis device 110 in encrypted form. In addition, each store server 210 includes a key generation unit 214i (i = 1, ..., k) that generates an encryption key and a decryption key, an encryption key storage unit 215i (i = 1, ..., k) that stores the encryption key generated by the key generation unit 214, a decryption key storage unit 216i (i = 1, ..., k) that stores the decryption key generated by the key generation unit 214, and a decryption unit 217i (i = 1, ..., k) that decrypts the encrypted analysis results received from the analysis device 110 using the decryption key.

[0049] The key generation unit 214 generates a key pair of an encryption key and a decryption key in a homomorphic public key cryptosystem. The key generation unit 214 generates the key pair of an encryption key and a decryption key using various known techniques. For example, the key generation unit 214 of each store server 210 generates an individual key pair of an encryption key and a decryption key and stores them in the encryption key storage unit 215 and the decryption key storage unit 216, respectively (multi-key homomorphic encryption).

[0050] Alternatively, each store server 210 may use a single key pair of encryption and decryption keys (single-key homomorphic encryption). In this case, the key generation unit 214 of any one store server 210 among the multiple store servers 210 generates a key pair of encryption and decryption keys and transmits the encryption key and decryption key to the encryption key storage unit 215 and decryption key storage unit 216 of each store server 210, respectively. The store server 210 that generates the key pair of encryption and decryption keys may be predetermined or selected randomly.

[0051] Alternatively, a composite key may be generated by combining the encryption keys generated by the key generation unit 214 of each store server 210 (threshold homomorphic encryption). In this case, each key generation unit 214 transmits the generated encryption key to the key generation unit 214 of one of the store servers 210. The key generation unit 214 that receives the encryption key from another store server 210 generates a composite key of the encryption keys using a known method. The store server 210 that generates the composite key may be predetermined or selected randomly.

[0052] The decryption unit 217 decrypts the encrypted analysis results received from the analysis device 110 using a decryption key. When the sales data is encrypted using multi-key homomorphic encryption or threshold homomorphic encryption, among the encryption methods described above, the decryption unit 217 communicates with the decryption units 217 of other store servers 210 to distribute and decrypt the analysis results using a decryption key corresponding to the encryption key used to encrypt the sales data. In the present disclosure, distributed decryption refers to each store server 210 calculating a distributed decryption result, in the sense of an "incomplete decryption result," rather than dividing a ciphertext corresponding to a single piece of data into multiple parts. The input / output unit 213 then transmits the distributed decryption result to a device that wishes to obtain the decrypted analysis result. In this embodiment, the case where the device that wishes to obtain the decrypted analysis result is the analysis device 110 is described. However, the device may be a server device owned by the analysis requester other than the analysis device 110. The analysis device 110 or the analysis requester's server combines the distributed decryption results, which are incomplete decryption results, to obtain a completely decrypted analysis result.

[0053] On the other hand, if the driving data is encrypted using single-key homomorphic encryption, the decryption unit 217 of the store server 210, which has generated a key pair consisting of an encryption key and a decryption key, decrypts the analysis results. The decryption unit 217 transmits the decrypted analysis results to the analysis device 110 or a server device other than the analysis device 110 via the input / output unit 213.

[0054] Here, an example of a shared decryption method in multi-key homomorphic encryption or threshold homomorphic encryption will be described. The shared decryption method described below employs the method described in Chen et al., "Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference," CCS'19. However, this shared decryption method is only an example, and a different method may also be used. The store server 210i (i = 1, ..., k) receives a decryption key s ｉ In addition, the ciphertext ct has integer coefficients as shown in the following formula (1), and (X ｎ +1) is the polynomial ring.

[0055] In addition, in formula (1), when q is an integer, it is expressed as Rq = R / (q·R), and the coefficient has a value on mod q, and (X ｎ +1). For simplicity, in this disclosure, it is assumed that k people (devices each having k decryption keys) are involved in the calculation, and ct is the ciphertext of the calculation result.

[0056] The acquisition unit 111 acquires the ciphertext from each store server 210i (i=1, . . . , k), and the analysis unit 112 analyzes the ciphertext while it is still encrypted, and outputs the ciphertext as the analysis result as ct=(c ０ , c １ , ..., c ｋ ) and the sending unit 113 sends the following to the store server 210i (i=1, . . . , k): ｉ (i=1, . . . , k) are transmitted to the decryption unit 217 of each store server 210. ｉ Specifically, each i-th store server 210 performs shared decryption using the shared decryption result μ ｉ is calculated by the formula (2). In the formula (2), e ｉ is noise sampled from the noise distribution φ. Each decoding unit 217 transmits the results of these distributed decoding operations to the analysis device 110.

[0057]

[0058] Next, the receiving unit 114 of the analysis device 110 combines and decodes the results of the distributed decoding received by each store server from 210. Specifically, the receiving unit 114 receives μ ｉ is obtained from the i-th store server 210, and the plaintext m is calculated using equation (3).

[0059] however,

[0060] Note that equation (4) indicates the value of x rounded off to the nearest whole number, and when t is an integer in equation (3), the plaintext m∈R ｔ is.

[0061] The operation of the analysis system 11 configured as above will be described with reference to the flowchart of FIG.

[0062] FIG. 7 is a flowchart showing an outline of the operation of the analysis system 11 according to the present disclosure. The processing according to this flowchart may be executed based on program control by the aforementioned processor. The flow in FIG. 7 illustrates a case in which sales data is encrypted using multi-key homomorphic encryption, in which individual key pairs are generated in multiple store servers 210. Furthermore, the flow (S201) in which the key pair is generated by the key generation unit 214 and the flow (S202) in which the encryption unit 212 encrypts the sales data do not need to be executed consecutively.

[0063] 7 , first, in each of the store servers 210, the key generation unit 214 generates a key pair consisting of an encryption key and a decryption key, and stores the key pair in the encryption key storage unit 215 and the decryption key storage unit 216 (step S201). Next, the encryption unit 212 encrypts the sales data stored in the data storage unit 211 using the encryption key by homomorphic encryption (step S202). Next, the input / output unit 213 transmits the sales data in encrypted form to the analysis device 110 (step S203).

[0064] In the analysis device 110, the acquisition unit 111 acquires sales data in encrypted format from multiple store servers 210 (step S204). Next, the analysis unit 112 performs marketing analysis for vehicle sales in encrypted format based on the encrypted sales data (step S205). Next, the transmission unit 113 transmits the analysis results in encrypted format to the store servers 210 (step S206).

[0065] Again, in each of the multiple store servers 210, the input / output unit 213 receives the encrypted analysis result (step S207). Next, the decryption unit 217 performs shared decryption of the encrypted analysis result using the decryption key stored in the decryption key storage unit 216 (step S208). Next, the input / output unit 213 transmits the shared decrypted analysis result to the analysis device 110 (step S209).

[0066] Furthermore, in the analysis device 110, the receiving unit 114 combines the results of the distributed decoding of the analysis results at each store server 220 and decodes the analysis results (step S210). Finally, the output unit 115 outputs the analysis results (step S211). This completes the analysis operation of the analysis system 11.

[0067] In the multiple store servers 210 in this embodiment, each key generation unit 214 generates a key pair of an encryption key and a decryption key, and the encryption unit 212 encrypts the sales data using the individual encryption key generated by each store server 210. In this case, the sales data cannot be decrypted unless the decryption key paired with the encryption key is used, thereby further improving confidentiality.

[0068] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above-described 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.

[0069] For example, although multiple operations are described in a sequential order in the form of a flowchart, the order of description does not limit the order in which the multiple operations are performed. Therefore, when implementing each embodiment, the order of the multiple operations can be changed within the scope that does not affect the content.

[0070] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0071] (Supplementary Note 1) An analysis device comprising: an acquisition means for acquiring sales data relating to vehicle sales status from store servers of a plurality of sub-dealers in a format encrypted using a homomorphic encryption method; an analysis means for performing marketing analysis for vehicle sales in an encrypted format based on the encrypted sales data; and a transmission means for transmitting analysis results in an encrypted format to each store server.

[0072] (Supplementary Note 2) The analysis device described in Supplementary Note 1, wherein the acquisition means acquires sales data from some of the multiple store servers in a format encrypted using a homomorphic encryption method, and the analysis means performs marketing analysis based on the encrypted sales data and unencrypted sales data.

[0073] (Supplementary Note 3) The analysis device described in Supplementary Note 1 or Supplementary Note 2, wherein the acquisition means further acquires sales data regarding vehicle sales status from a store server of an authorized dealer, and the analysis means performs marketing analysis based on the sales data of the sub-dealer and the sales data of the authorized dealer.

[0074] (Supplementary Note 4) The analysis device described in Supplementary Note 1 or Supplementary Note 2, wherein the acquisition means further acquires sales data regarding vehicle sales status from store servers of a plurality of authorized dealers, the acquisition means acquires some of the sales data from the store servers of the plurality of authorized dealers in a format encrypted using a homomorphic encryption method, and the analysis means performs marketing analysis based on the sub-dealer's sales data, the encrypted authorized dealer's sales data, and the unencrypted authorized dealer's sales data.

[0075] (Supplementary Note 5) The analysis device according to any one of Supplementary Notes 1 to 4, wherein the acquisition means acquires the sales data from store servers of a plurality of sub-dealers in a format encrypted by homomorphic encryption using a key that differs for each store server.

[0076] (Supplementary Note 6) The analysis device according to any one of Supplementary Notes 1 to 4, wherein the analysis means performs marketing analysis for selling vehicles to a specific customer segment.

[0077] (Supplementary Note 7) The analysis device according to any one of Supplementary Notes 1 to 6, wherein the sales data includes sales information of accessories sold together with the vehicle.

[0078] (Supplementary Note 8) The analysis device according to any one of Supplementary Notes 1 to 7, further comprising: a receiving means for combining the results of the distributed decryption performed by each store server to decrypt the analysis result; and an output means for outputting the decrypted analysis result.

[0079] (Supplementary Note 9) The analysis device according to any one of Supplementary Notes 1 to 8, wherein the analysis means performs the marketing analysis using an analytical model used for the marketing analysis.

[0080] (Supplementary Note 10) The analysis device according to Supplementary Note 9, wherein the analysis means performs marketing analysis using an analytical model in encrypted form.

[0081] (Supplementary Note 11) The analysis device according to Supplementary Note 9 or Supplementary Note 10, wherein the analysis means integrates analysis results obtained by performing marketing analysis using each of a plurality of analysis models.

[0082] (Supplementary Note 12) An analysis system having the analysis device according to any one of Supplements 1 to 11 and a plurality of store servers, wherein each of the store servers comprises: a data storage means for storing sales data relating to the sales status of vehicles at its own store; an encryption means for encrypting the sales data using a homomorphic encryption method; and an input / output means for transmitting the sales data in encrypted form to the analysis device.

[0083] (Supplementary Note 13) The analysis system described in Supplementary Note 12 comprises: a key generation means for generating a key pair of an encryption key and a decryption key of a homomorphic public key cryptosystem; and a decryption means for decrypting the encrypted analysis results received from the analysis device using the decryption key, wherein the encryption means encrypts the sales data using the encryption key; and the input / output means outputs the decrypted analysis results.

[0084] (Appendix 14) The analysis system described in Appendix 13, wherein the encryption means encrypts the sales data using a homomorphic encryption method using an encryption key generated by each of the plurality of store servers, and the decryption means decrypts the calculated analysis results using a decryption key generated by each of the plurality of store servers.

[0085] (Supplementary Note 15) The analysis system described in Supplementary Note 13, wherein the encryption means encrypts the sales data using a homomorphic encryption method using a composite key of encryption keys generated by each of the plurality of store servers, and the decryption means decrypts the calculated analysis results using a decryption key generated by each of the plurality of store servers.

[0086] (Supplementary Note 16) A store server comprising: a data storage means for storing sales data relating to the sales status of vehicles at the store; an encryption means for encrypting the sales data using a homomorphic encryption method; and an input / output means for transmitting the sales data in encrypted form to an analysis device.

[0087] (Supplementary Note 17) An analysis method in which a computer acquires sales data on vehicle sales status from store servers of multiple sub-dealers in a format encrypted using homomorphic encryption, performs marketing analysis for vehicle sales in an encrypted format based on the encrypted sales data, and transmits the analysis results to each store server in an encrypted format.

[0088] (Supplementary Note 18) An encryption method in which a computer stores sales data relating to the sales status of vehicles at its own store, encrypts the sales data using a homomorphic encryption method, and transmits the sales data in encrypted form to an analysis device.

[0089] (Supplementary Note 19) A recording medium storing a program that causes a computer to execute the following: acquire sales data regarding vehicle sales status from store servers of multiple sub-dealers in a format encrypted using homomorphic encryption; perform marketing analysis for vehicle sales in an encrypted format based on the encrypted sales data; and transmit the analysis results to each store server in an encrypted format.

[0090] (Supplementary Note 20) A recording medium storing a program that causes a computer to store sales data regarding the sales status of vehicles at its own store, encrypt the sales data using homomorphic encryption, and transmit the sales data in encrypted form to an analysis device.

[0091] Some or all of the configurations described in Supplements 2 to 11 that are dependent on Supplement 1 above may also be dependent on Supplement 17 and Supplement 19 in the same dependent relationship as Supplements 2 to 11. Not limited to Supplements 1, 17, and 19, some or all of the configurations described as Supplements may be made dependent on various hardware, software, various recording devices for recording software, or systems, within the scope of each of the above-mentioned embodiments.

[0092] 10, 11 Analysis system 100, 110 Analysis device 101, 111 Acquisition unit 102, 112 Analysis unit 103, 113 Transmission unit 114 Reception unit 115 Output unit 200, 210 Store server 201, 211 Data storage unit 202, 212 Encryption unit 203, 213 Input / output unit 214 Key generation unit 215 Encryption key storage unit 216 Decryption key storage unit 217 Decryption unit 500 Computer device 501 CPU 502 ROM 503 RAM 504 Program 505 Storage device 506 Recording medium 507 Drive device 508 Communication interface 511 Input / output interface 512 Bus

Claims

1. A means for acquiring sales data regarding vehicle sales status from the store servers of multiple sub-dealers in an encrypted format using homomorphic encryption, Based on the aforementioned encrypted sales data, an analytical means performs marketing analysis for vehicle sales in an encrypted format. A transmission method that sends the analysis results in an encrypted format to each store's server, An analytical device equipped with the following features.

2. The acquisition means acquires sales data from some of the store servers among multiple store servers in a format encrypted using homomorphic encryption. The analysis apparatus according to claim 1, wherein the analysis means performs marketing analysis based on encrypted sales data and unencrypted sales data.

3. A receiving means combines the results of distributed decryption from each store server to decrypt the analysis results, The analytical apparatus according to claim 1 or claim 2, further comprising an output means for outputting decoded analysis results.

4. An analysis system comprising an analysis device according to claim 1 or claim 2 and a plurality of store servers, Each of the aforementioned store servers includes a data storage means for storing sales data related to the sales status of vehicles at its own store, An encryption means for encrypting the aforementioned sales data using a homomorphic encryption scheme, An input / output means for transmitting the sales data in an encrypted format to the analysis device, An analytical system equipped with the following features.

5. A key generation means for generating encryption and decryption key pairs for a homomorphic public-key cryptosystem, The system includes a decryption means that decrypts the encrypted analysis results received from the analysis device using the decryption key, The encryption means encrypts the sales data using the encryption key, The analysis system according to claim 4, wherein the input / output means outputs the decoded analysis results.

6. A data storage means for storing sales data related to the sales status of vehicles at the store, An encryption means for encrypting the aforementioned sales data using a homomorphic encryption scheme, A store server comprising input / output means for transmitting the aforementioned sales data to an analysis device in an encrypted format.

7. Computers Sales data regarding vehicle sales status is obtained from the store servers of multiple sub-dealers in an encrypted format using homomorphic encryption. Based on the aforementioned encrypted sales data, marketing analysis for vehicle sales is performed in an encrypted format. An analysis method in which the analysis results are sent to each store's server in an encrypted format.

8. Computers Store sales data regarding the sales status of vehicles at your store. The aforementioned sales data is encrypted using a homomorphic encryption method. An encryption method for transmitting the aforementioned sales data to an analysis device in an encrypted format.

9. Sales data regarding vehicle sales status is obtained from multiple sub-dealer store servers in an encrypted format using homomorphic encryption with a different key for each store server. Based on the aforementioned encrypted sales data, marketing analysis for vehicle sales is performed in an encrypted format. A program that stores a program that instructs a computer to send the analysis results in an encrypted format to each store's server.

10. Store sales data regarding the sales status of vehicles at your store. The aforementioned sales data is encrypted using a homomorphic encryption method. A program that causes a computer to transmit the aforementioned sales data to an analysis device in an encrypted format.