Information Processing System, Information Processing Method, and Program

Abstract

To allow for purchase and sale of feature quantities extracted from data electronically between third parties.SOLUTION: An information processing system includes a receiving unit, an extraction unit, and a purchase information management unit. The receiving unit receives a commodity registration request including data from which feature quantity is to be extracted, from a first client terminal. The extraction unit extracts feature quantity indicating characteristics of a person from the above data. The purchase information management unit executes settlement processing for the feature quantity in accordance with a purchase request for the feature quantity from a second client terminal, and stores purchase information based on the settlement processing in a storage unit.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] Embodiments of the present invention relate to an information processing system, an information processing method, and a program.

Background Art

[0002] In recent years, companies such as broadcasting stations that handle a large amount of content have been increasingly introducing face recognition systems using AI (artificial intelligence). By having the AI automatically perform person matching, the added value of the company's own content is improved, and the workload is reduced.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional technology, the feature amounts extracted from data could not be electronically traded between third parties.

Means for Solving the Problems

[0005] The information processing system according to the embodiment includes a reception unit, an extraction unit, and a purchase information management unit. The reception unit receives a product registration request including feature amount extraction target data from a first client terminal. The extraction unit extracts a feature amount indicating a person's feature from the feature amount extraction target data. The purchase information management unit executes a settlement process for the feature amount in response to a purchase request for the feature amount from a second client terminal, and stores purchase information based on the settlement process in a storage unit.

Brief Description of the Drawings

[0006]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Modes for Carrying Out the Invention

[0007] Hereinafter, embodiments of an information processing system, an information processing method, and a program will be described in detail with reference to the accompanying drawings.

[0008] First, an example of the configuration of the information processing system according to the embodiment will be described.

[0009] [Example of the Configuration of the Information Processing System] FIG. 1 is a diagram showing an example of the configuration of the information processing system 1 according to the embodiment. The information processing system 1 according to the embodiment is a system that realizes an e-commerce transaction of feature amounts extracted from data such as images. The information processing system 1 according to the embodiment extracts, for example, the feature amounts of face images included in an image, and sells the feature amounts. Thereby, it is possible to reduce the labor of complicated right processing, reduce the communication capacity, and reduce the labor of extracting the feature amounts, and it becomes possible to perform an e-commerce transaction more easily between third parties.

[0010] The information processing system 1 according to the embodiment includes a feature amount extraction service 11, a product management system 12, a user management system 13, a purchase management system 14, a Web server device 15, a client terminal 16, and a network 17.

[0011] The feature amount extraction service 11, the product management system 12, the user management system 13, the purchase management system 14, and the Web server device 15 are realized by one or more information processing devices. For example, the feature amount extraction service 11, the product management system 12, the user management system 13, and the purchase management system 14 may be realized by one information processing device, and the Web server device 15 may be realized by another information processing device, resulting in a configuration of two information processing devices.

[0012] The feature amount extraction service 11 extracts feature amounts used for prediction and judgment by machine learning such as deep learning from data of feature amount extraction targets (for example, images and videos). The feature amount is data that quantitatively represents the features and characteristics of the analysis target included in the data of the feature amount extraction target. The feature amount includes, for example, data indicating the features of a person's face included in the data of the feature amount extraction target. Specifically, the feature amount is represented by, for example, numerical values. In the embodiment, the case where the feature amount extraction target is an image will be described as an example.

[0013] The product management system 12 stores product information (see FIG. 4 described later) including the feature amounts extracted by the feature amount extraction service 11.

[0014] The user management system 13 stores information about users who use the client terminal 16 (see FIG. 6 described later).

[0015] When a user purchases a product (feature amount), the purchase management system 14 stores purchase information including purchase records and the like (see FIG. 8 described later).

[0016] The Web server device 15 receives requests from the feature amount extraction service 11, the product management system 12, the user management system 13, the purchase management system 14, and the client terminal 16. For example, the Web server device 15 receives a product registration request for requesting the registration of a product to the product management system 12 from the client terminal 16 via the network 17.

[0017] The client terminal 16 transmits, for example, a product registration request, a product search request, a product purchase request, etc. to the Web server device 15 via the network 17. The number of client terminals 16 may be arbitrary.

[0018] The network 17 communicably connects the Web server device 15 and the client terminal 16. The communication method of the network 17 may be a wired method or a wireless method. Also, the network 17 may be configured by combining a wired method and a wireless method. Specifically, the network 17 is an Internet line or the like.

[0019] [Example of the functional configuration of the feature amount extraction service] FIG. 2 is a diagram showing an example of the functional configuration of the feature amount extraction service 11 of the embodiment. The feature amount extraction service 11 of the embodiment includes a reception unit 111, an extraction unit 112, and a transmission unit 113. The reception unit 111 receives data such as an image from the Web server device 15. The extraction unit 112 extracts a feature amount from data such as an image. The transmission unit 113 transmits the feature amount to the product management system 12.

[0020] [Example of the functional configuration of the product management system] FIG. 3 is a diagram showing an example of the functional configuration of the product management system 12 according to the embodiment. The product management system 12 according to the embodiment includes a product information DB 121, a reception unit 122, a product information management unit 123, a search unit 124, and a transmission unit 125. The product information DB 121 stores a product information table 1211.

[0021] FIG. 4 is a diagram showing an example of the product information table 1211 according to the embodiment. The product information table 1211 according to the embodiment includes a product ID, name, category, meta information, feature amount, usage license rank, publication flag, registration date and time, and registration user ID.

[0022] The product ID is information for identifying a product (feature amount). The name is the name of the person specified by the feature amount. The category indicates, for example, the occupation of the person specified by the feature amount. The meta information (additional information) is information indicating matters related to the product (feature amount). The feature amount is information extracted from an image or the like by the feature amount extraction service 11.

[0023] The usage license rank is information indicating the scope of usage license of the product. In the embodiment, for example, rank 1 is permitted only within the scope of personal use. Rank 2 is permitted within the scope of personal use and use in research and development. Rank 3 is permitted within the scope of personal use, use in research and development, and commercial use.

[0024] The publication flag indicates whether the product has already been published (sold) (1: published, 0: not published). The registration date and time indicates the date and time when the product was registered in the product information DB 121. The registration user ID is information for identifying the user who registered the product.

[0025] Returning to FIG. 3, the receiving unit 122 receives feature quantities from the feature quantity extraction service 11. The product information management unit 123 stores product information including the feature quantities as products in a storage unit (in the embodiment, the product information DB 121). Specifically, the product information management unit 123 adds (registers), changes, and deletes product information with respect to the product information DB 121. The search unit 124 searches the product information in the product information DB 121 according to search conditions. The search conditions are specified, for example, by a product search request from the client terminal 16. The transmission unit 125 transmits data included in the product information DB 121 in response to a request from the Web server device 15 or the like.

[0026] Note that the product information table 1211 may store a plurality of types of feature quantities. In this case, the extraction unit 112 of the feature quantity extraction service 11 extracts a plurality of types of feature quantities using a plurality of recognition engines. Then, the product information management unit 123 associates the feature quantities with information for identifying the recognition engines used for the recognition of the feature quantities, and stores the plurality of types of feature quantities in the product information table 1211.

[0027] [Example of Functional Configuration of User Management System] FIG. 5 is a diagram showing an example of the functional configuration of the user management system 13 according to the embodiment. The user management system 13 according to the embodiment includes a user information DB 131, a receiving unit 132, a user information management unit 133, and a transmission unit 134. The user information DB 131 stores a user information table 1311.

[0028] FIG. 6 is a diagram showing an example of the user information table 1311 according to the embodiment. The user information table 1311 according to the embodiment includes a user ID, a user name, and an attribute. The user ID is information for identifying a user. The user name is the name of the user. The attribute indicates the company and organization to which the user belongs.

[0029] Returning to FIG. 5, the receiving unit 132 receives a product purchase completion notification request including product information of the purchased product from the product management system 12. The user information management unit 133 adds (registers), changes, and deletes user information in the user information DB 131. When the transmitting unit 134 receives a product purchase completion notification request from the product management system 12, it transmits a product purchase completion notification request further including the user information of the user who purchased the product to the purchase management system 14.

[0030] [Example of Functional Configuration of Purchase Management System] FIG. 7 is a diagram showing an example of the functional configuration of the purchase management system 14 according to the embodiment. The purchase management system 14 according to the embodiment includes a purchase information DB 141, a receiving unit 142, a purchase information management unit 143, and a transmitting unit 144. The purchase information DB 141 stores a purchase information table 1411.

[0031] FIG. 8 is a diagram showing an example of the purchase information table according to the embodiment. The purchase information table 1411 according to the embodiment includes a purchase user ID, a purchase date and time, a product ID, and a price. The purchase user ID is information for identifying the user who purchased the product. The purchase date and time indicates the date and time when the product was purchased. The product ID is information for identifying the purchased product. The price indicates the price of the purchased product.

[0032] Returning to FIG. 7, the receiving unit 142 receives a product purchase completion notification request from the user management system 13. The purchase information management unit 143 executes the settlement process of the product and adds (registers), changes, and deletes the purchase information in the purchase information DB 141. When the transmitting unit 144 receives a product purchase completion notification request from the user management system 13, it transmits a product purchase completion notification request further including the purchase information of the purchased product to the client terminal 16 via the Web server device 15.

[0033] [Example of Information Processing Method] FIG. 6 is a diagram showing an example of the information processing method according to the embodiment.

[0034] [Flow of Product Registration Process] First, the client terminal 16 sends a product registration request to the Web server device 15 (step S1). Next, when the Web server device 15 receives the product registration request from the client terminal 16, it sends the product registration request to the product management system 12 (step S2).

[0035] Next, the product information management unit 123 of the product management system 12 registers product information other than feature amounts (product ID, name, category, meta information, usage license rank, public flag, registration date and time, and registration user ID) in the product information table 1211 in response to the product registration request from the Web server device 15 (step S3). Next, the transmission unit 125 of the product management system 12 sends data such as images (data to be subjected to feature amount extraction) included in the product registration request to the feature amount extraction service 11 (step S4).

[0036] Next, the reception unit 111 of the feature amount extraction service 11 receives data such as images from the product management system 12 (step S5). Next, the extraction unit 112 of the feature amount extraction service 11 extracts feature amounts from the data such as images (step S6). Next, the transmission unit 113 of the feature amount extraction service 11 sends the feature amounts to the product management system 12 (step S7).

[0037] Next, when the reception unit 122 of the product management system 12 receives the feature amounts from the feature amount extraction service 11 (step S8), the product information management unit 123 registers the feature amounts in the product information table 1211 and sends a product registration completion notification request to the Web server device 15.

[0038] Next, when the Web server device 15 receives the product registration completion notification request from the product management system 12, it sends the product registration completion notification request to the client terminal 16 (step S9). Next, when the client terminal 16 receives the product registration completion notification request from the Web server device 15, it completes the product registration process (step S10).

[0039] <Flow of product search process> First, the client terminal 16 sends a product search request to the Web server device 15 (step S11). Next, when the Web server device 15 receives the product search request from the client terminal 16, it sends the product search request to the product management system 12 (step S12).

[0040] Next, the search unit 124 of the product management system 12 searches for product information from the product information table 1211 in response to the product search request from the Web server device 15 (step S13). For example, the search unit 124 uses the name, category, meta information, etc. to search for product information with high similarity to the content of the product search request (appropriate product information based on the product search request) as candidates. Next, the transmission unit 125 of the product management system 12 sends a search result notification request including the search result of the product to the Web server device 15 (step S14).

[0041] Next, when the Web server device 15 receives the search result notification request from the product management system 12, it sends the search result notification request to the client terminal 16 (step S15). Next, when the client terminal 16 receives the search result notification request from the Web server device 15, it displays the search result included in the search result notification request on the display unit etc. of the client terminal 16 (step S16).

[0042] <Flow of product purchase process> First, the client terminal 16 sends a product purchase request to the Web server device 15 (step S17). Next, when the Web server device 15 receives the product purchase request from the client terminal 16, it sends the product purchase request to the product management system 12 (step S18).

[0043] Next, the product information management unit 123 of the product management system 12 acquires product information from the product information table 1211 in response to the product purchase request from the Web server device 15 (step S19).

[0044] Next, the transmission unit 125 of the product management system 12 transmits a product purchase completion notification request including the product information of the purchased product to the user management system 13 (step S13).

[0045] Next, when the reception unit 132 of the user management system 13 receives the product purchase completion notification request from the product management system 12, it acquires the user information of the user who purchased the product from the user information table 1311 (step S21). Then, the transmission unit 134 of the user management system 13 transmits a product purchase completion notification request further including the user information acquired in step S21 to the purchase management system 14.

[0046] Next, when the reception unit 142 of the purchase management system 14 receives the product purchase completion notification request from the user management system 13, the purchase information management unit 143 records the purchase information in the purchase information table 1411 (step S22). Then, the transmission unit 144 of the purchase management system 14 transmits a product purchase completion notification request further including the purchase information recorded in step S22 to the Web server device 15.

[0047] Next, when the Web server device 15 receives the product purchase completion notification request from the purchase management system 14, it transmits the product purchase completion notification request to the client terminal 16 (step S23). Next, when the client terminal 16 receives the product purchase completion notification request from the Web server device 15, it displays the purchase information and the like included in the product purchase completion notification request on the display unit of the client terminal 16 as needed, and completes the product purchase process (step S24).

[0048] As described above, in the information processing system 1 of the embodiment, the receiving unit 122 receives a product registration request including data to be feature-extracted from the client terminal 16 (first client terminal). The extraction unit 112 extracts a feature amount indicating a person's feature from the data to be feature-extracted. The purchase information management unit 143 executes a settlement process for the feature amount in response to a purchase request for the feature amount from the client terminal 16 (second client terminal), and stores purchase information based on the settlement process in a storage unit (in the embodiment, the purchase information DB 141).

[0049] Accordingly, according to the information processing system 1 of the embodiment, the feature amount extracted from the data to be feature-extracted can be electronically traded among third parties. Specifically, according to the information processing system 1 of the embodiment, a business operator who wants to sell a feature amount as a product can register product information in the above-described product information DB 121. Further, according to the information processing system 1 of the embodiment, based on the category and meta information of the product, etc., appropriate product candidates can be presented to a business operator who wants to purchase the feature amount. Thereby, a purchaser can more easily find a product, and an electronic transaction can be easily performed among third parties.

[0050] Conventionally, for example, in order to recognize a person from an image, it has been very difficult to perform the work of registering a person's image for face verification in advance. Also, if such a registration work has already been performed by another business operator, there has been a need to solve it even at a cost. Further, for a business operator who creates a dictionary (feature amount) for recognizing a person from data to be feature-extracted such as an image and a video, since the work of creating the dictionary (feature amount) takes time, there has been a need to find added value in the dictionary (feature amount).

[0051] According to the information processing system 1 of the above-described embodiment, an electronic commerce platform that meets such needs can be provided.

[0052] In recent years, in order to analyze the trends of famous people, the need for machine learning using the face images of famous people has been increasing. However, for information users who need feature quantities for machine learning, the communication capacity when receiving a large amount of data, the labor required to extract feature quantities after reception, and the labor required to prepare appropriate data have been issues. Also, for information transmitters, in addition to the above issues, there were many issues such as the right of portrait and publicity rights of the people reflected in the image that had to be resolved in order to transmit the information of the images and videos they possessed.

[0053] According to the information processing system 1 of the embodiment, it is possible to match a person who needs the feature quantities necessary for machine learning with a person who wants to sell, and provide a platform capable of conducting an e-commerce transaction between third parties using the feature quantities extracted from images and the like. Furthermore, in the information processing system 1 of the embodiment, without directly handling data such as images and videos, by realizing an e-commerce transaction only for the feature quantities of the face images included in the images or videos, (1) Minimize the communication capacity required at the time of buying and selling, (2) Reduce the labor required to extract feature quantities after purchase, (3) Reduce the labor of right processing when conducting an e-commerce transaction on an image or video, (4) Reduce the labor required to prepare appropriate data (data necessary for machine learning), can also be realized.

[0054] Finally, an example of the hardware configuration of the information processing system 1 of the embodiment will be described.

[0055] [Example of Hardware Configuration] FIG. 10 is a diagram showing an example of the hardware configuration of the information processing system 1 of the embodiment. The information processing system 1 of the embodiment is realized by a combination of one or more computers having the hardware configuration shown in FIG. 10.

[0056] The information processing system 1 of the embodiment includes a control device 201, a main storage device 202, an auxiliary storage device 203, a display device 204, an input device 205, and a communication device 206. The control device 201, the main storage device 202, the auxiliary storage device 203, the display device 204, the input device 205, and the communication device 206 are connected via a bus 210.

[0057] The control device 201 executes a program read from the auxiliary storage device 203 into the main storage device 202. The main storage device 202 is a memory such as a ROM and a RAM. The auxiliary storage device 203 is an HDD (Hard Disk Drive), a memory card, or the like.

[0058] The display device 204 displays display information. The display device 204 is, for example, a liquid crystal display or the like. The input device 205 is, for example, a keyboard, a mouse, or the like. The communication device 206 is an interface for communicating with other devices.

[0059] The program executed in the information processing system 1 of the embodiment is recorded in a computer-readable storage medium such as a CD-ROM, a memory card, a CD-R, and a DVD in an installable format or an executable format file, and is provided as a computer program product.

[0060] Alternatively, the program executed in the information processing system 1 of the embodiment may be stored on a computer connected to a network such as the Internet, and provided by being downloaded via the network. Also, the program executed in the information processing system 1 of the embodiment may be provided via a network such as the Internet without being downloaded.

[0061] Alternatively, the program of the information processing system 1 of the embodiment may be provided by being pre-embedded in a ROM or the like.

[0062] The program executed in the information processing system 1 of the embodiment has a module configuration including functional blocks that can also be realized by the program among the above-described functional blocks (Figs. 2, 3, 5, and 7). Each of these functional blocks, as actual hardware, is loaded onto the main storage device 202 when the control device 201 reads and executes the program from the storage medium. That is, each of the above functional blocks is generated on the main storage device 202.

[0063] Note that part or all of each of the above-described functional blocks may be realized by hardware such as an IC (Integrated Circuit) instead of by software.

[0064] Also, when realizing each function using a plurality of processors, each processor may realize one of each function or may realize two or more of each function.

[0065] Also, the operation mode of the information processing system 1 of the embodiment may be arbitrary. For example, the feature amount extraction service 11, the product management system 12, the user management system 13, and the purchase management system 14 of the information processing system 1 of the embodiment may be operated as a cloud system on the network 17, for example.

[0066] Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention and are included in the invention described in the claims and the equivalent scope thereof.

Description of Reference Numerals

[0067] 1 Information processing system 11 Feature amount extraction service 12 Product management system 13 User management system 14 Purchase Management System 15 Web Server Device 16 Client Terminal 17 Network 111 Receiver 112 Extractor 113 Transmitter 121 Product Information DB 122 Receiver 123 Product Information Management Section 124 Search Section 125 Transmitter 131 User Information DB 132 Receiver 133 User Information Management Section 134 Transmitter 141 Purchase Information DB 142 Receiver 143 Purchase Information Management Section 144 Transmitter 201 Control Device 202 Main Memory Device 203 Auxiliary Memory Device 204 Display Device 205 Input Device 206 Communication Device 210 Bus 1211 Product Information Table 1311 User Information Table 1411 Purchase Information Table

Claims

1. A receiving unit that receives a product registration request including data to be feature-extracted from a first client terminal; An extraction unit that extracts a feature amount indicating a person's feature from the data to be feature-extracted; A purchase information management unit that executes a settlement process for the feature amount in response to a purchase request for the feature amount from a second client terminal and stores purchase information based on the settlement process in a storage unit; An information processing system comprising the above.

2. A product information management unit that stores product information including the feature amount as a product in the storage unit; A search unit that searches for the product information from the storage unit in response to a search request for the product information from the second client terminal; A transmission unit that transmits a search result by the search unit to the second client terminal; The information processing system according to claim 1, further comprising the above.

3. The product information includes at least one of information for identifying the feature amount as a product, the name of a person specified by the feature amount, the category of a person specified by the feature amount, information indicating a matter related to the product, information indicating the scope of permission to use the feature amount, information indicating whether the feature amount has already been made public, the date and time when the feature amount was registered as the product, and information for identifying a user who registered the product. The information processing system according to claim 2.

4. The extraction unit extracts a plurality of types of the feature amounts using a plurality of recognition engines; The product information management unit stores the plurality of types of feature amounts in the storage unit in association with the feature amounts and information for identifying the recognition engine used for recognition of the feature amounts. The information processing system according to claim 2 or 3.

5. The purchase information includes at least one of information for identifying a user who purchased the product, the date and time when the product was purchased, information for identifying the purchased product, and the price of the purchased product. The information processing system according to any one of claims 2 to 4.

6. The data to be feature-extracted is at least one of an image and a video. The information processing system according to any one of claims 1 to 5.

7. The feature amount includes data indicating features of the person's face. The information processing system according to any one of claims 1 to 6.

8. A step in which a receiving unit receives a product registration request including data to be feature-extracted from a first client terminal; a step in which an extraction unit extracts a feature amount indicating a person's feature from the data to be subjected to feature amount extraction; a step in which a purchase information management unit executes a settlement process for the feature amount in response to a purchase request for the feature amount from a second client terminal, and stores purchase information based on the settlement process in a storage unit; An information processing method including the above.

9. A computer, a receiving unit that receives a product registration request including data to be subjected to feature amount extraction from a first client terminal; an extraction unit that extracts a feature amount indicating a person's feature from the data to be subjected to feature amount extraction; a purchase information management unit that executes a settlement process for the feature amount in response to a purchase request for the feature amount from a second client terminal, and stores purchase information based on the settlement process in a storage unit; A program for causing the computer to function as described above.

Images