Information providing device, information providing system, and information providing method

The information providing device uses a secure computation system to anonymize and process user data for accurate recommendations, addressing privacy concerns and improving suggestion accuracy in unfamiliar areas.

WO2026239486A1PCT designated stage Publication Date: 2026-11-19NT T INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2025/017374
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2025-05-13
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

Existing information provision systems, such as those provided by Google, often recommend stores based on the user's past visits, leading to inaccurate suggestions in unfamiliar areas, and require sharing detailed personal information to improve accuracy, which users are hesitant to do due to privacy concerns.

Method used

An information providing device that utilizes a secure computation system to anonymize and process user information of multiple users, allowing for accurate recommendations without revealing personal details, by using technologies like secret sharing and homomorphic encryption to maintain user anonymity.

Benefits of technology

Enables highly accurate information suggestions in unfamiliar areas by leveraging anonymized user data, enhancing user privacy and consent for personal information use.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2025017374_19112026_PF_FP_ABST
    Figure JP2025017374_19112026_PF_FP_ABST
Patent Text Reader

Abstract

This information providing device comprises an input / output unit, a recording unit, a statistical designation unit, a secret calculation unit, and a selection unit. The recording unit records user information, usage permission information indicating usage permission for the user information, and candidate information to be provided to the user. The statistical designation unit designates statistical processing for obtaining an evaluation value for each piece of candidate information. The secret calculation unit executes: processing for communicating with a secret calculation system and instructing the secret calculation system to perform statistical processing; processing for concealing the user information permitted to be used and transmitting the concealed user information to the secret calculation system; and processing for restoring a concealment evaluation value to an evaluation value that is not concealed. The secret calculation system executes processing using information that has been concealed in accordance with statistical processing, and obtains the concealment evaluation value that is a concealed evaluation value. The selection unit selects provision information to be provided to the user from the candidate information on the basis of the evaluation value.
Need to check novelty before this filing date? Find Prior Art

Description

Information Providing Device, Information Providing System, and Information Providing Method

[0001] The present invention relates to an information providing device, an information providing system, and an information providing method that use a secure computation system.

[0002] As technologies for proposing restaurants and the like, the technology disclosed in Non-Patent Document 1, maps provided by Google (registered trademark), and the like are known. In the technology of Non-Patent Document 1, user preferences are recognized from the user's terminal operation history and the like, and technologies such as automatic determination of accompanying persons using GPS (Global Positioning System) and destination prediction from action history are combined to propose restaurants. In addition, even with maps and the like provided by Google, surrounding store information can be obtained by providing current location information. In recent years, as secure computation technologies that perform calculations while maintaining information in a concealed state, secure computation using secret sharing (Multi Party Computation), Homomorphic Encryption, TEE (Trusted Execution Environment) and the like are known.

[0003] Hirohisa Tezuka, Koji Ito, Takuya Murayama, Shun-ichi Seko, Masaaki Nishino, Nobuhiro Muto, Masanobu Abe, "Restaurant Recommendation Using Life Logs", NTT Technical Journal, July 2010, [searched on April 16, Reiwa 7], Internet <https: / / journal.ntt.co.jp / backnumber2 / 1007 / files / jn201007029.pdf>.

[0004] However, in Non-Patent Document 1, since stores are proposed based on the activity information of the user themselves or accompanying persons, stores of the type that have been frequently visited in the past tend to be recommended. When there are many stores of types that the user does not usually visit, such as at a travel destination visited for the first time, the accuracy of the proposal may deteriorate. The maps provided by Google allow store information to be viewed, but do not have a store proposal function. Therefore, it is time-consuming to find a store that suits the user in an unfamiliar area.

[0005] To obtain highly accurate suggestions, even in places you've never visited before, one possible approach is to refer to the behavior of people similar to the user. However, this requires providing detailed personal information (such as age, gender, place of origin, favorite foods, hobbies, etc.) to the suggestion system and granting permission for that information to be shared with many other people. In other words, when making suggestions to yourself, the system uses the personal information of other users, and when making suggestions to other users, it uses your own personal information. However, since this is personal information, many people feel uncomfortable with the idea of ​​sharing it with the personal information of many others.

[0006] This invention has been made in view of these circumstances, and aims to provide information provision technology that facilitates obtaining consent for the use of personal information.

[0007] The information providing device of the present invention comprises an input / output unit, a recording unit, a statistical designation unit, a secure computation unit, and a selection unit. The input / output unit communicates with a terminal operated by the user. The recording unit records user information, license information indicating permission to use the user information, and candidate information to be provided to the user. The statistical designation unit specifies statistical processing to obtain an evaluation value for each piece of candidate information. The secure computation unit communicates with a secure computation system and performs the following: processing to instruct the secure computation system to perform statistical processing, processing to encrypt the licensed user information and send it to the secure computation system, and processing to restore the encrypted evaluation value to an unencrypted evaluation value. The secure computation system performs processing using the encrypted information according to the statistical processing and obtains an encrypted evaluation value, which is the encrypted evaluation value. The selection unit selects the information to be provided to the user from among the candidate information based on the evaluation value.

[0008] According to the information provision device of the present invention, when selecting information to provide to a user, it utilizes not only the user's own user information but also the user information of other users. The user information of other users is anonymized and recorded in a secure computing system, and processed while maintaining its anonymity. Therefore, the user information of other users remains unknown. Consequently, this invention provides an information provision technology that makes it easier to obtain consent for the use of personal information.

[0009] A diagram showing an example of the overall functional configuration of the system including the information providing device of the present invention. A diagram showing an example of the processing flow for recording user information and license information. A diagram showing an example of the processing flow for recording user information. A diagram showing another example of the processing flow for recording user information and license information. A diagram showing an example of a user management DB. A diagram showing an example of a user attribute management DB. A diagram showing an example of a user location information management DB. A diagram showing an example of a candidate information DB. A diagram showing an example of an activity history information DB. A diagram showing an example of the processing flow for information provision triggered by a request from a user. A diagram showing an example of the processing flow for processing performed by a secure computing system. A diagram showing an example of the processing flow for information provision triggered by the information providing device. A diagram showing an example of the functional configuration of a computer.

[0010] The embodiments of the present invention will be described in detail below. Components having the same function will be numbered identically, and redundant explanations will be omitted.

[0011] Figure 1 shows an example of the functional configuration of an information provision system including the information provision device of the present invention. Figure 2 is an example of a processing flow for recording user information and license information, Figure 3 is an example of a processing flow for recording user information, and Figure 4 is another example of a processing flow for recording user information and license information.

[0012] The information providing device 100 includes an input / output unit 110, a recording unit 190, a statistical designation unit 120, a secure computation unit 130, and a selection unit 140. The information providing device 100 may also include an operation control unit 150. The information providing device 100 is connected to a plurality of user-operated terminals 800 via a network 820. Terminals 800 include communication terminals with a user interface, devices without a user interface such as Wi-Fi® repeaters, and combinations of terminals with a user interface and Wi-Fi repeaters. The information providing device 100 is also connected to a secure computation system 200 via a network 220. The secure computation system 200 may use technologies such as secure computation using secret sharing (multi-party computation), homomorphic encryption, and TEE (Trusted Execution Environment). Figure 1 shows an example using multi-party computation, which consists of three secure computation devices 210-1 to 210-3. However, although Figure 1 shows a configuration with three secure computing devices 210-1 to 210-3, it may also consist of four or more devices. Furthermore, the information provision system 300 is composed of the information provision device 100, the secure computing system 200, and the terminal 800.

[0013] The input / output unit 110 communicates with the terminal 800 operated by the user. The recording unit 190 only needs to record candidate information to be provided to the user in advance. Candidate information is information that may be provided to the user, such as the characteristics and location of restaurants, shops, museums, etc. The statistical specification unit 120 specifies statistical processing to obtain an evaluation value for each piece of candidate information.

[0014] The secure computation unit 130 communicates with the secure computation system 200 and performs the following processes: instructing the secure computation system 200 to perform statistical processing, sending the licensed user information to the secure computation system 200 after concealing it, and restoring the concealed evaluation value to the unconcealed evaluation value. The secure computation system 200 performs processing using the concealed information according to the statistical processing and obtains a concealed evaluation value, which is the concealed evaluation value. The secure computation unit 130 can also have candidate information recorded in the secure computation system 200 in advance. The candidate information may be concealed or may be recorded in plain text. The selection unit 140 selects the information to be provided to the user from the candidate information based on the evaluation value.

[0015] In the processing flow for recording user information and license information shown in Figure 2, the user inputs user information and license information using terminal 800 (S801). The input / output unit 110 acquires the user information and license information (S111). The user information acquired here includes name, contact information, etc., and user attribute information such as gender, age, nationality or place of origin, hobbies, and preferences may also be included in the user information. The recording unit 190 records the user information and license information indicating permission to use the user information (S191). The secure calculation unit 130 encrypts the licensed user information and transmits it to the secure calculation system 200 (S131). Each secure calculation system 200 records the encrypted user information (S201).

[0016] For example, consider a case where location information is included in the user license information. In this case, in the processing flow for recording user information shown in Figure 3, terminal 800 transmits the user's location information to information providing device 100 (S802). Input / output unit 110 acquires the user's location information as user information (S112). The location information may include not only latitude and longitude information, but also candidate information (such as store names) that exists at that latitude and longitude location. Furthermore, combining date and time information with location information including candidate information results in activity information. User information such as location information and activity information can be managed as tabular data. Secure computation unit 130 anonymizes the location information, which is the licensed user information, and transmits it to secure computation system 200 (S132). Secure computation system 200 records the anonymized location information in association with the user information of the same user (S202). For example, the technology described in references 1 and 2 can be used.

[0017] [Reference 1] Hiroyuki Hojo, Takuya Yamaguchi, Konami Nishiyama, Hajime Takahashi, Asami Miyajima, Keiichi Hirota, Shoko Nishida, Junko Hashimoto, "Trial Provision of the Secure Computation System Sanshi (Registered Trademark)", NTT Technical Journal, February 2019, [Retrieved May 2, 2025], Internet<https: / / journal.ntt.co.jp / wp-content / uploads / 2020 / 06 / JN20190219.pdf> [Reference 2] Nippon Telegraph and Telephone Corporation, “Secret Computing Platform (Trust-SC) V3.0 “Sanshi””, August 2, 2018, [Retrieved May 2, 2020], Internet<https: / / www.rd.ntt / research / SI0005.html> .

[0018] By repeating the process shown in Figure 3, user information can be made to include movement history information. Furthermore, for example, if the license information includes information about the stores used, the user information may also include the store information and its rating.

[0019] Figure 4 shows another processing flow for recording user information and license information, an example of concealing user information such as attribute information and travel history information together. For example, if the user of terminal 800 is a traveler from abroad, it may be possible to conceal travel history information from the trip together after returning home. The user inputs user information and license information using terminal 800 at the beginning of the trip (S801). The input / output unit 110 acquires the user information and license information (S111). The user information acquired here includes name, contact information, and user attribute information such as gender, age, nationality or place of origin, hobbies, and preferences. The recording unit 190 records the user information such as attribute information and the license information indicating permission to use the user information as initial information (S191). Subsequently, terminal 800 transmits the user's location information as user information (S802), which is acquired by the input / output unit 110 (S112), and recorded by the recording unit 190 (S192). User information may also include evaluation values ​​of visited stores. When it is determined that the trip has ended (S101), user information, which combines attribute information and travel history information, is recorded in the recording unit 190. The secure calculation unit 130 may then conceal the authorized user information (the user's attribute information and associated travel history information) (S131), and the secure calculation system 200 may record the concealed user information (S201). By concealing the travel history information together with the attribute information in this way, it becomes easier to record user information for the same user in association.

[0020] The processing flow shown in Figures 2-4 completes a database in which user information of other users, used to select the information to be provided, is concealed. Examples of databases are shown in Figures 5-9. Figure 5 shows an example of a user management DB (database), Figure 6 shows an example of a user attribute management DB, and Figure 7 shows an example of a user location information management DB. The DB for managing users, the DB for managing attributes, and the DB for managing location information are associated using the user ID. Figure 8 shows an example of a candidate information DB, and Figure 9 shows an example of an activity history information DB. The candidate information DB shows candidates such as stores and their location information. The activity history information DB associates date and time information with candidate information. All are examples of data managed in tabular format. Figures 10-12 show the process of providing information to a user using a database in which user information of other users who have used terminal 800 in the past is concealed.

[0021] Figure 10 shows the processing flow for information provision triggered by a user request. Terminal 800 requests information (S803). For example, terminal 800 attaches its current location information and requests information about restaurants near its current location. Alternatively, if the recording unit 190 has already recorded the action plan information as user information and the location can be determined by specifying the date and time, terminal 800 may request information about restaurants for lunch tomorrow.

[0022] In the information providing device 100, which has been requested to provide information, the statistical designation unit 120 specifies the statistical processing to be performed by the secure computing system 200 (S120). The secure computing unit 130 instructs the secure computing system 200 to perform statistical processing by attaching attribute information and location information of the user using the terminal 800 (S133). The secure computing system 200 performs processing using the concealed information according to the specified statistical processing (S203). For example, the statistical designation unit 120 could specify a process to introduce stores that have been visited by many past users whose attribute information is similar to that of the current terminal 800 user, and the secure computing unit 130 could instruct the secure computing system 200 to do so. Alternatively, the statistical designation unit 120 could specify a process to introduce stores that have been highly rated by past users whose attribute information is similar to that of the current terminal 800 user, and the secure computing unit 130 could instruct the secure computing system 200 to do so. Any other statistical processing that allows for the selection of candidate information may also be used.

[0023] Figure 11 shows an example of the processing performed by the secure computation system 200 in step S203. The secure computation system 200 selects candidate store information and creates a candidate list (S211). For example, if current location information is attached, it is sufficient to select candidate information around the current location. Also, if location information for tomorrow at noon is attached, it is sufficient to select candidate information around that location or near the route around tomorrow at noon. The secure computation system 200 removes candidate information that should be excluded from the candidate list (S212). For example, it is sufficient to remove stores that the same user has already visited from the candidate list. The secure computation system 200 creates a list of other users (comparison user list) to be used when evaluating stores using secure computation (S213). For example, a list of users (comparison user list) may be created by referring to movement history information. Alternatively, a list of users (comparison user list) who have visited stores included in the candidate list and given evaluation values ​​may be created from among other users in the past.

[0024] The secure computation system 200 uses secure computation to compare the attribute information of the user requesting information with the attribute information of the comparison user list and calculates the similarity of each user in the comparison user list (S214). The similarity can be calculated using prior art. For example, it can be calculated by vectorizing the attributes and measuring the distance, or it can be calculated using the Pearson correlation coefficient or cosine similarity.

[0025] The secure computation system 200 calculates an evaluation value for each candidate information included in the candidate list using secure computation based on similarity and evaluation values ​​previously assigned by other users (S215). For example, it may identify visited stores from travel history information and perform calculations such that stores frequently visited by other users with high similarity receive higher evaluation values.

[0026] Alternatively, for example, K is the number of past users in the user comparison list, k is an integer between 1 and K, and S is an integer between 1 and K. k The similarity to the kth past user, E k Let be the rating value assigned by the k-th past user. Then, the rating value E' for each candidate information can be calculated as follows: As a result of the processing up to step S215, the secure computation system 200 records the confidentiality evaluation value for the candidate information in the candidate list.

[0027] The secure calculation unit 130 restores the confidential evaluation value to an unconfidential evaluation value (S134). The selection unit 140 selects the information to be provided based on the evaluation value (S140). One or more pieces of information may be selected. The selected information to be provided is output from the terminal 800 used by the user (S804).

[0028] Figure 12 shows an example of an information provision processing flow triggered by an information provision device. In the processing shown in Figure 12, the information provision device 100 also includes an operation control unit 150. The timing is specified in advance for the operation control unit 150. For example, information provision for a specified time the following day may be requested at a specified time in the evening. Alternatively, information may be provided in a push-type manner when a trigger is received from the store. The operation control unit 150 then starts processing in the statistical specification unit 120, the secure calculation unit 130, the selection unit 140, etc., at the specified timing (S150). Figure 12 differs from Figure 10 only in step S150; everything else is the same.

[0029] According to the information provision device 100, when selecting information to provide to a user, it utilizes not only the user's user information but also the user information of other users. The user information of other users is recorded in the secure computing system 200 in an anonymized state and processed while maintaining that anonymity. Therefore, even the operator of the secure computing system 200 that uses the user information cannot know the user information of other users. Thus, it is possible to provide information provision technology that makes it easier to obtain consent for the use of personal information.

[0030] [Processors, Programs, Recording Media] The functions realized by the components described herein may be implemented in a circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), CPUs (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to realize the functions described herein. A processor includes transistors and other circuits and is considered a circuitry or processing circuitry. A processor may be a programmed processor that executes a program stored in memory.

[0031] In this specification, circuitry, unit, and means are hardware programmed to perform or execute the functions described herein. Such hardware may be any hardware disclosed herein, or any hardware known to be programmed to perform or execute the functions described herein.

[0032] If the hardware is a processor that is considered to be a type of circuitry, then the circuitry, means, or unit is a combination of hardware and software used to constitute the hardware and / or processor.

[0033] The various processes described above can be carried out by loading a program that executes each step of the above method into the recording unit 2020 of the computer 2000 shown in Figure 13, and then causing the control unit 2010, input unit 2030, output unit 2040, display unit 2050, etc. to operate.

[0034] The program describing this process can be recorded on a computer-readable recording medium. Any computer-readable recording medium can be used, such as a magnetic recording device, optical disc, magneto-optical recording medium, or semiconductor memory.

[0035] Furthermore, this program may be distributed, for example, by selling, transferring, or lending portable recording media such as DVDs or CD-ROMs on which the program is recorded. Alternatively, the program may be stored on the recording device of a server computer and distributed by transferring the program from the server computer to other computers via a network.

[0036] A computer executing such a program may, for example, first store the program, either recorded on a portable storage medium or transferred from a server computer, in its own storage device. Then, when processing is to be executed, the computer reads the program stored in its own storage device and executes the processing according to the read program. Alternatively, the computer may directly read the program from the portable storage medium and execute the processing according to that program, or it may sequentially execute the processing according to the received program each time a program is transferred to it from the server computer. Furthermore, the processing may be executed using a so-called ASP (Application Service Provider) type service, where the processing function is realized only by issuing execution instructions and obtaining results, without transferring the program from the server computer to this computer.In addition, the processing may be executed using a so-called SaaS (Software as a Service) type service, where a part of the server computer is made available to the user along with the program. Furthermore, the term "program" in this form includes information used for processing by an electronic computer that is equivalent to a program (data, etc., that is not a direct instruction to the computer but has the property of defining the processing of the computer).

[0037] Furthermore, in this configuration, the device is configured by executing a predetermined program on a computer, but at least a part of these processes may be implemented in hardware.

[0038] 100 Information provision device 110 Input / output unit 120 Statistics designation unit 130 Secure calculation unit 140 Selection unit 150 Operation control unit 190 Recording unit 200 Secure calculation system 210 Secure calculation device 220, 820 Network 300 Information provision system 800 Terminal

Claims

1. An information providing device comprising: an input / output unit that communicates with a terminal operated by a user; a recording unit that records user information, license information indicating permission to use the user information, and candidate information to be provided to the user; a statistical designation unit that specifies statistical processing for determining an evaluation value for each of the candidate pieces of information; a secure calculation unit that communicates with a secure calculation system that performs processing using the information concealed according to the statistical processing and determines a concealed evaluation value, which is a concealed evaluation value; and a selection unit that selects information to be provided to the user from among the candidate pieces of information, wherein the secure calculation unit performs processing to instruct the secure calculation system to perform the statistical processing, processing to conceal the licensed user information and transmit it to the secure calculation system, and processing to restore the concealed evaluation value to an unconcealed evaluation value; and the selection unit selects information to be provided based on the evaluation value.

2. An information providing device according to claim 1, wherein the user information includes user attribute information, and the statistical processing is a process based on the similarity of attribute information with other users.

3. An information providing device according to claim 2, characterized in that the statistical processing is also based on the user's current location.

4. An information providing device according to claim 2, wherein the user information also includes the user's action plan, and the statistical processing is also based on the location at the date and time specified by the user.

5. An information provision system comprising the information provision device according to claim 3 or 4, the secure computing system, and the terminal, wherein the other user information includes the movement history information of other users, and the secure computing system performs the following processes: selecting candidate information based on the location; selecting a comparison target user from among the other users using the movement history information of other users; determining the similarity of attribute information with the comparison target user; and determining the confidentiality evaluation value based on the similarity.

6. An information provision method comprising: an input / output step for communicating with a terminal operated by a user; a recording step for recording user information, license information indicating a license to use the user information, and candidate information to be provided to the user in a recording unit; a statistical specification step for specifying a statistical process for determining an evaluation value for each of the candidate pieces of information; a secret computation step for communicating with a secret computation system to perform processing using the information that has been concealed according to the statistical processing and to determine a concealed evaluation value, which is a concealed evaluation value; and a selection step for selecting information to be provided to the user from the candidate pieces of information, wherein the secret computation step performs processing to instruct the secret computation system to perform the statistical processing, processing to conceal the licensed user information and transmit it to the secret computation system, and processing to restore the concealed evaluation value to an unconcealed evaluation value; and the selection step selects information to be provided based on the evaluation value.