Information providing method, control program, and information providing system

Abstract

To provide an information providing method, a control program, and an information providing system that can provide a user with appropriate information based on user's purchase results through an external service.SOLUTION: An information providing method includes the steps executed by a computer: acquiring user's purchase history data through an external service; transmitting, to a generative AI model, a prompt instructing the generative AI model to generate complementary data not included in the purchase history data based on the purchase history data, and the purchase history data; and providing the user with information based on the complementary data generated by the generative AI model.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information providing method, a control program, and an information providing system. [Background technology]

[0002] Japanese Patent Laid-Open Publication No. 2012-242940 (Patent Document 1) discloses a product recommendation device that recommends products to users in an e-commerce service. In this product recommendation device, new products are given priority in being recommended. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2012-242940 Summary of the Invention [Problem to be solved by the invention]

[0004] In the technology disclosed in Patent Document 1, products are recommended to users in an e-commerce service operated by the company based on the user's purchase history, etc. In the e-commerce service operated by the company, for example, information such as release date, category, and price trend can be associated with each product. In the e-commerce service operated by the company, for example, such information can be used to recommend products to users.

[0005] However, when providing information about products and the like to users based on their purchase history through external services, it is not easy to use information about the release date, category, price trend, etc. of each product, making it difficult to provide users with appropriate product information and the like.

[0006] The present invention has been made to solve such problems, and its purpose is to provide an information provision method, control program, and information provision system that can provide appropriate information to users based on the users' purchase history through external services. [Means for solving the problem]

[0007] An information providing method according to one aspect of the present invention includes, by a computer, steps of acquiring a user's purchase history data through an external service, sending to the generative AI model a prompt instructing the generative AI model to generate complementary data not included in the purchase history data based on the purchase history data, and the purchase history data, and providing information to the user based on the complementary data generated by the generative AI model.

[0008] According to this information provision method, information is provided to the user based on complementary data, and the complementary data is generated by a generation AI model based on purchase history data, so appropriate information can be provided to the user even if the purchase history data indicates purchase history through an external service.

[0009] In the above information provision method, the purchase history data may be data including the name of the first product, the complementary data may be data including information about the manufacturer of the first product or an affiliated company of the manufacturer of the first product, and the prompt may include an instruction to cause the generative AI model to output the complementary data based on the name of the first product.

[0010] According to this information provision method, data including information on the manufacturer of the first product or an affiliated company of the manufacturer of the first product is generated by a generation AI model based on purchase history data, so that appropriate information can be provided to the user even if the purchase history data indicates a purchase history through an external service.

[0011] In the information providing method, in the step of providing information, information on stocks of a manufacturer of the first product or an affiliated company of the manufacturer of the first product may be provided to the user.

[0012] According to this information provision method, even if the purchase history data indicates a purchase history through an external service, information regarding the stocks of the manufacturer of the first product or a company related to the manufacturer of the first product can be provided to the user.

[0013] In the above information provision method, in the step of providing information, information regarding a second product may be provided to the user, and the manufacturer of the second product may be the manufacturer of the first product or an affiliated company of the manufacturer of the first product.

[0014] According to this information provision method, even if the purchase history data indicates a purchase history through an external service, information about a second product manufactured by the manufacturer of the first product or an affiliated company of the manufacturer of the first product can be provided to the user.

[0015] In the above information providing method, the prompt may include an instruction to cause the generative AI model to extract the name of the first product from the purchase history data.

[0016] According to this information provision method, even if the purchase history data contains information other than the name of the first product, the name of the first product is extracted by the generative AI model, so the generative AI model can output complementary data based on the name of the first product with higher accuracy.

[0017] In the above information provision method, the computer may further execute a step of saving the complementary data generated by the generative AI model, and in the step of saving the complementary data, the purchase history data and the complementary data may be saved in a distinguishable manner, and the computer may further execute a step of displaying the purchase history data and the complementary data in a distinguishable manner.

[0018] According to this information providing method, the purchase history data and the complementary data are displayed in a distinguishable manner, which can prevent the user from confusing the purchase history data with the complementary data.

[0019] In the above information provision method, the purchase history data may be data including the name of the payee or the name of the product, the complementary data may be data including information regarding taxes, and the prompt may include an instruction to the generative AI model to output the complementary data based on the name of the payee or the name of the product.

[0020] According to this information provision method, data including tax information is generated by a generative AI model based on purchase history data, so appropriate information can be provided to the user even if the purchase history data indicates purchase history through an external service.

[0021] A control program according to another aspect of the present invention causes a computer to execute the steps of acquiring a user's purchase history data through an external service, sending the purchase history data and a prompt to the generative AI model instructing the generative AI model to generate complementary data not included in the purchase history data based on the purchase history data, and providing information to the user based on the complementary data generated by the generative AI model.

[0022] According to this control program, information is provided to the user based on complementary data, and the complementary data is generated by a generation AI model based on purchase history data, so that appropriate information can be provided to the user even if the purchase history data indicates purchase history through an external service.

[0023] According to another aspect of the present invention, an information provision system includes an acquisition unit, a transmission unit, and an information provision unit. The acquisition unit acquires purchase history data of a user through an external service. The transmission unit transmits the purchase history data and a prompt to the generative AI model, instructing the generative AI model to generate complementary data not included in the purchase history data based on the purchase history data. The information provision unit provides information to the user based on the complementary data generated by the generative AI model.

[0024] According to this information provision system, information is provided to users based on complementary data, which is generated by a generation AI model based on purchase history data. Therefore, even if the purchase history data indicates purchase history through an external service, appropriate information can be provided to users. [Effects of the Invention]

[0025] According to the present invention, it is possible to provide an information providing method, a control program, and an information providing system that can provide appropriate information to a user based on the user's purchase history through external services. [Brief explanation of the drawings]

[0026] [Figure 1] FIG. 1 is a diagram schematically illustrating a configuration of a system according to a first embodiment. [Figure 2] FIG. 10 is a diagram schematically illustrating a portion of an example of purchase history data. [Figure 3] 2 is a block diagram schematically illustrating a hardware configuration of an information providing server according to the first embodiment. FIG. [Figure 4] 3 is a diagram schematically illustrating an example of data for one user managed in a purchase history data DB in the first embodiment. FIG. [Figure 5] FIG. 2 is a block diagram schematically illustrating a hardware configuration of a user terminal according to the first embodiment. [Figure 6] 10 is a flowchart showing a procedure for providing information on products and the like that are likely to interest the user to the user. [Figure 7] FIG. 3 is a diagram schematically illustrating an example of a prompt indicated by prompt data in the first embodiment. [Figure 8] FIG. 10 is a diagram schematically illustrating an example of a screen including information on stocks that are likely to interest a user. [Figure 9] FIG. 10 is a diagram schematically illustrating a configuration of a system according to a second embodiment. [Figure 10] FIG. 10 is a block diagram schematically illustrating a hardware configuration of an information providing server according to a second embodiment. [Figure 11] FIG. 2 is a diagram schematically illustrating a personal data DB. [Figure 12] FIG. 11 is a diagram schematically illustrating an example of data for one user managed in a purchase history data DB in the second embodiment. [Figure 13] FIG. 10 is a block diagram schematically illustrating a hardware configuration of a user terminal according to a second embodiment. [Figure 14] 10 is a flowchart showing a procedure for providing tax-related information to a user. [Figure 15] FIG. 11 is a diagram schematically illustrating an example of a prompt indicated by prompt data in the second embodiment. [Figure 16] FIG. 10 is a diagram schematically illustrating an example of a screen that notifies a user whether or not the user is eligible for medical expense deductions. DETAILED DESCRIPTION OF THE INVENTION

[0027] An embodiment according to one aspect of the present invention (hereinafter also referred to as "the present embodiment") will be described in detail below with reference to the drawings. Note that the same or corresponding parts in the drawings are designated by the same reference numerals, and their description will not be repeated. Furthermore, for ease of understanding, each drawing is drawn schematically with objects appropriately omitted or exaggerated.

[0028] 1. First Embodiment <1-1. Overview> FIG. 1 is a diagram schematically illustrating the configuration of a system 10 according to the first embodiment. As shown in FIG. 1, the system 10 includes an information providing server 100, a user terminal 200, an EC (Electronic Commerce) server 300, and an AI chatbot server 400. Each of the information providing server 100, the EC server 300, and the AI ​​chatbot server 400 is implemented, for example, by a general-purpose computer. The user terminal 200 is implemented, for example, by a PC (Personal Computer), a tablet, or a smartphone. In the system 10, the information providing server 100, the user terminal 200, the EC server 300, and the AI ​​chatbot server 400 communicate with each other via the Internet N1.

[0029] The information providing server 100 provides asset management services to the user, for example, by cooperating with an asset management application (hereinafter also referred to as "asset management app") installed in the user terminal 200. The asset management app manages, for example, the user's deposit and withdrawal information, household ledger information, account information, and asset information. The information providing server 100 included in the system 10 according to the first embodiment further cooperates with the asset management app to provide the user with information on products, stocks, etc. (hereinafter also referred to as "products, etc.") that are likely to interest the user.

[0030] The EC server 300 provides users with electronic commerce services through an EC site. Users can purchase products through the EC site. The EC server 300 stores purchase history data 305 that indicates the purchase history of users.

[0031] FIG. 2 is a diagram schematically illustrating a portion of an example of purchase history data 305. As shown in FIG. 2, purchase history data 305 includes date information, product name information, unit price information, and quantity information. Date information indicates the date on which a product was purchased. Product name information indicates the name of the purchased product. Unit price information indicates the unit price of the purchased product. Quantity information indicates the number of products purchased. In purchase history data 305, date information, product name information, unit price information, quantity information, etc. are managed for each purchase history (each purchased product).

[0032] On many e-commerce sites, the product name information included in the purchase history data 305 contains additional information other than the actual product name. For example, in the example on the first line of Figure 2, only the entry "XXX" is the actual product name. On the other hand, the entries "[Free Shipping]", "(Gift Boxed)", "(Hand Cream)", and "(Gift)" are not the actual product name but are additional information.

[0033] Referring again to FIG. 1 , the information providing server 100 periodically acquires user purchase history data 305 from the EC server 300, for example, by crawling or scraping. The information providing server 100 uses the acquired purchase history data 305, for example, to update information managed in the asset management app. The information providing server 100 also uses the acquired purchase history data 305 to acquire data on products and the like that are likely to interest the user (hereinafter also referred to as "first supplementary data"). The first supplementary data is data that is not included in the purchase history data 305.

[0034] The AI ​​chatbot server 400 provides a generative AI model 410. The generative AI model 410 is generated, for example, through learning using information periodically acquired from various sites via the Internet N1. The generative AI model 410 receives input of natural language, for example, and generates various answers corresponding to the natural language based on common sense. Examples of the generative AI model 410 include ChatGPT and Marvin.

[0035] As will be described in detail later, the information providing server 100 transmits a prompt to the AI ​​chatbot server 400 (generative AI model 410) together with the purchase history data 305, instructing the generative AI model 410 to generate first complementary data based on the purchase history data 305. The information providing server 100 receives the output of the generative AI model 410 from the AI ​​chatbot server 400. The information providing server 100 generates screen data to be displayed on the user terminal 200 based on the received output (first complementary data) of the generative AI model 410, and transmits the screen data to the user terminal 200. The user terminal 200 displays a screen indicated by the screen data received from the information providing server 100. This provides the user with information on products and the like that are likely to interest the user. Details of the system 10 are described below.

[0036] <1-2.Configuration> (1-2-1. Information Server Configuration) Fig. 3 is a block diagram showing a schematic hardware configuration of the information providing server 100. As shown in Fig. 3, the information providing server 100 includes a control unit 110, a communication I / F (interface) 130, and a storage unit 120. Each component is electrically connected via a bus.

[0037] The control unit 110 includes a central processing unit (CPU) 112, a random access memory (RAM) 114, a read only memory (ROM) 116, and the like, and is configured to control each component in accordance with information processing.

[0038] The communication I / F 130 is configured to communicate with the user terminal 200, the EC server 300, and the AI ​​chatbot server 400 (FIG. 1), for example, via the Internet N1. The communication I / F 130 is configured, for example, as a wired LAN (Local Area Network) module or a wireless LAN module.

[0039] The storage unit 120 is configured, for example, with an auxiliary storage device such as a hard disk drive or a solid state drive. The storage unit 120 stores, for example, a control program 122, a purchase history data DB (database) 124, and prompt data 126. The control program 122 is executed by the CPU 112 to realize various functions of the information providing server 100. In the purchase history data DB 124, the purchase history data of each user is managed in a distinguishable manner.

[0040] FIG. 4 is a diagram schematically illustrating an example of data for one user managed in the purchase history data DB 124. As shown in FIG. 4, the purchase history data DB 124 manages purchase history data and first complementary data in association with each other. Flags F1 and F2 are assigned to the purchase history data and the first complementary data, respectively. That is, the purchase history data DB 124 manages the purchase history data and the first complementary data in a distinguishable manner. The purchase history data managed in the purchase history data DB 124 is raw data of the purchase history data 305 acquired from the EC server 300. On the other hand, the first complementary data managed in the purchase history data DB 124 is data (AI output data) generated by the generation AI model 410 based on the purchase history data 305.

[0041] Examples of the first supplementary data include product name, manufacturer company name, associated company name, manufacturer company stock, associated company stock, manufacturer company related products, and associated company related products. The product name indicates the name of the product purchased by the user. The manufacturer company name indicates the name of the manufacturer of the product purchased by the user. The associated company name indicates the name of the associated company of the manufacturer of the product purchased by the user. The manufacturer company stock indicates information about the stock of the manufacturer of the product purchased by the user. The associated company stock indicates information about the stock of the associated company of the manufacturer of the product purchased by the user. The manufacturer company related products indicate information about products related to the product purchased by the user that are manufactured by the manufacturer company. The associated company related products indicate information about products manufactured by the associated company that are related to the product purchased by the user. Data is added to the purchase history data DB124 every time purchase history data 305 is acquired from the EC server 300.

[0042] 3, the prompt data 126 is made up of instructions to the generative AI model 410. The prompt data 126 will be described in more detail later.

[0043] (1-2-2. User terminal configuration) Fig. 5 is a block diagram showing a schematic hardware configuration of user terminal 200. As shown in Fig. 5, user terminal 200 includes a control unit 210, a communication I / F 230, an operation unit 240, a display 250, and a storage unit 220. In user terminal 200, each component is electrically connected via a bus.

[0044] The control unit 210 includes a CPU, RAM, ROM, etc., and is configured to control each component in accordance with information processing. The communication I / F 230 is configured to communicate with the information providing server 100, the EC server 300, and the AI ​​chatbot server 400, for example, via the Internet N1. The communication I / F 230 is configured, for example, with a wired LAN module or a wireless LAN module.

[0045] The operation unit 240 is configured to receive input from a user and is configured, for example, with some or all of a touch panel, a keyboard, a mouse, and a microphone.

[0046] The display 250 is configured to display an image. The display 250 is configured, for example, by a monitor such as a liquid crystal monitor or an organic EL (Electro Luminescence) monitor. The display 250 displays, for example, a screen indicated by screen data received from the information providing server 100.

[0047] The storage unit 220 is, for example, an auxiliary storage device such as a hard disk drive or a solid state drive. The storage unit 220 stores, for example, a control program 222. When the control program 222 is executed by the CPU of the control unit 210, various functions of the user terminal 200 are realized.

[0048] <1-3. Information provision operation> 6 is a flowchart showing a procedure for providing a user with information on products and the like that the user is likely to be interested in. The process shown in this flowchart is executed by the control unit 110 of the information providing server 100 at predetermined intervals.

[0049] 6, control unit 110 determines whether new purchase history data has been added to purchase history data DB 124 for the user compared to the time when the process shown in this flowchart was last executed (step S100). If it is determined that new purchase history data has not been added to purchase history data DB 124 (NO in step S100), the process shown in this flowchart ends.

[0050] On the other hand, if it is determined that new purchase history data has been added to the purchase history data DB 124 (YES in step S100), the control unit 110 controls the communication I / F 130 to send the prompt data 126 and the added purchase history data to the AI ​​chatbot server 400 (step S110).

[0051] 7 is a diagram schematically illustrating an example of a prompt indicated by the prompt data 126. Referring to FIG. 7, the prompt indicated by the prompt data 126 includes, for example, the following instructions (1)-(4) for the generative AI model 410.

[0052] (1) Instructions to extract actual product names by performing data cleansing on product names included in purchase history data and output the actual product names (2) Instructions to output the names of the manufacturers of the products corresponding to the extracted product names and the names of the manufacturers' affiliated companies (3) Instructions to output information about the stock of the manufacturer of the product corresponding to the extracted product name and information about the stock of the manufacturer's affiliated companies (4) Instructions to output information about related products manufactured by the manufacturer and information about related products manufactured by related companies

[0053] 6, the control unit 110 determines whether or not an output has been received from the AI ​​chatbot server 400 (step S120). If it is determined that an output has not been received from the AI ​​chatbot server 400 (NO in step S120), the control unit 110 waits until an output is received from the AI ​​chatbot server 400.

[0054] On the other hand, if it is determined that output has been received from the AI ​​chatbot server 400 (YES in step S120), the control unit 110 controls the memory unit 120 to update the purchase history data DB 124 (step S130). For example, the control unit 110 adds the information received from the AI ​​chatbot server 400 (at least some of the product name, manufacturer company name, related company name, manufacturer company stock, related company stock, manufacturer company related products, and related company related products) to each added purchase history data in the purchase history data DB 124.

[0055] The control unit 110 generates screen data to be displayed on the display 250 of the user terminal 200 based on the updated purchase history data DB 124 (step S140). The screen data is data for displaying a screen on the display 250 of the user terminal 200 and is configured, for example, by an HTML (Hyper Text Markup Language) file. For example, the control unit 110 references the first complementary data in the updated purchase history data DB 124 to generate screen data including information on stocks that the user is likely to be interested in and screen data including information on products that the user is likely to be interested in. Furthermore, for example, when a display instruction from a user is received, a screen showing a list of the purchase history data and first complementary data related to the user that are included in the updated purchase history data DB 124 (for example, the table shown in FIG. 4) may be displayed on the display 250 of the user terminal 200. For example, flags F1 and F2 may be displayed on this screen to distinguish the purchase history data from the first complementary data.

[0056] The screen including information on stocks that are likely to interest the user includes, for example, at least one of information on stocks of the manufacturer of the product purchased by the user and information on stocks of companies related to the manufacturer of the product purchased by the user. The screen including information on products that are likely to interest the user includes, for example, information on other products manufactured by the manufacturer of the product purchased by the user and information on products of companies related to the manufacturer of the product purchased by the user. The control unit 110 controls the communication I / F 130 to transmit the generated screen data to the user terminal 200 (step S150). This provides the user with information on stocks that are likely to interest the user and information on products that are likely to interest the user.

[0057] FIG. 8 is a diagram schematically illustrating an example of a screen including information on stocks that are likely to interest the user. Referring to FIG. 8, stock information RC1 is displayed on the display 250 of the user terminal 200. On this screen, for example, initially, the stock information RC1, items OP2, OP3, and frame CS1 are not displayed. For example, when the user touches item OP1, items OP2 and OP3 are displayed. When the user touches item OP2, frame CS1 is displayed around item OP2, and stock information RC1 is also displayed. On the other hand, when the user touches item OP3, information on products that are likely to interest the user is displayed instead of the stock information RC1. The configuration of the screen including information on products that are likely to interest the user is similar to the configuration of a screen including information on stocks that are likely to interest the user.

[0058] The stock information RC1 includes, for example, information on stocks of companies that manufacture products purchased by the user and information on stocks of companies that manufacture the products purchased by the user. In the stock information RC1, an icon IC1 is attached to indicate that each piece of information was generated by the generation AI model 410. For example, when purchase history data is displayed, the icon IC1 is not attached. That is, the purchase history data and the first complementary data are displayed in a distinguishable manner on the user terminal 200. According to the system 10, the purchase history data and the first complementary data are displayed in a distinguishable manner on the user terminal 200, thereby preventing the user from confusing the purchase history data and the first complementary data.

[0059] <1-4. Features> As described above, in system 10 according to the first embodiment, information is provided to the user based on the first complementary data generated by generative AI model 410. Therefore, according to system 10, information is provided to the user based on the first complementary data, and the first complementary data is generated by generative AI model 410 based on the purchase history data. Therefore, even if the purchase history data indicates a purchase history through an external service, appropriate information can be provided to the user.

[0060] Furthermore, according to the system 10 according to the present embodiment 1, data including information on the manufacturer of the product purchased by the user or the related companies of the manufacturer of the product purchased by the user is generated by the generation AI model 410 based on the purchase history data, so that appropriate information can be provided to the user even if the purchase history data indicates a purchase history through an external service.

[0061] Furthermore, according to the system 10 according to this embodiment 1, even if the purchase history data contains information other than the product name, the actual product name is output by the generative AI model 410 through data cleansing, so that the generative AI model 410 can output first complementary data based on the actual product name with higher accuracy.

[0062] The configuration consisting of the communication I / F 130 and the control unit 110 is an example of the "acquisition unit" in the present invention. The configuration consisting of the communication I / F 130 and the control unit 110 is an example of the "transmission unit" in the present invention. The configuration consisting of the control unit 210 and the display 250 is an example of the "information provision unit" in the present invention.

[0063] 2. Second Embodiment In system 10 according to the first embodiment, information on stocks that are likely to interest the user and information on products that are likely to interest the user are provided to the user. In system 10A according to the second embodiment, information on taxes (e.g., information on whether or not medical expenses can be deducted) is provided to the user based on the user's purchase history data (including data on hospital payment history, etc.). The following will mainly describe the differences from the first embodiment, and will not repeat the description of the same parts as in the first embodiment.

[0064] <2-1. Overview> FIG. 9 is a diagram schematically illustrating the configuration of a system 10A according to the second embodiment. As shown in FIG. 9, the system 10A includes an information providing server 100A, a user terminal 200A, an EC server 300, a financial server 350, and an AI chatbot server 400. Each of the information providing server 100A and the financial server 350 is implemented, for example, by a general-purpose computer. The user terminal 200A is implemented, for example, by a PC, tablet, or smartphone. In the system 10A, the information providing server 100A, the user terminal 200A, the EC server 300, the financial server 350, and the AI ​​chatbot server 400 communicate with each other via the Internet N1.

[0065] The information providing server 100A provides an asset management service to a user, for example, by cooperating with an asset management application installed in the user terminal 200A. The asset management application manages, for example, the user's deposit and withdrawal information, household ledger information, account information, and asset information. The information providing server 100A included in the system 10A according to the second embodiment further provides the user with information related to taxes (for example, information related to medical expense deductions).

[0066] The financial server 350 provides users with financial services such as online banking. The financial server 350 is composed of, for example, multiple servers each operated by a different financial institution. The financial server 350 stores, for example, card statement data showing details of credit card transactions by the user, electronic money statement data showing details of electronic money transactions by the user, and bank account statement data showing details of bank account transactions by the user.

[0067] The information providing server 100A periodically acquires EC usage statement data (e.g., purchase history data 305 (see FIG. 2)) indicating the user's usage details from the EC server 300, for example, by crawling or scraping. The information providing server 100A also periodically acquires the user's card usage statement data, electronic money usage statement data, bank account usage statement data, etc. from the financial server 350, for example, by crawling or scraping. The information providing server 100A also acquires receipt data (hereinafter also referred to as "receipt data") read by an OCR (Optical Character Recognition / Reader) from the user terminal 200A.

[0068] The information providing server 100A uses, for example, EC transaction statement data, card transaction statement data, electronic money transaction statement data, bank account transaction statement data, and receipt data to update information managed in the asset management app. The information providing server 100A also uses the EC transaction statement data, card transaction statement data, electronic money transaction statement data, bank account transaction statement data, and receipt data to obtain data (hereinafter also referred to as "second supplementary data") used to determine whether or not an income deduction is possible. The second supplementary data is data indicating the item of expense to be paid (for example, "medical expenses," "education expenses," or "other"), and is data that is not included in the EC transaction statement data, card transaction statement data, electronic money transaction statement data, bank account transaction statement data, and receipt data.

[0069] In the information providing server 100A, for example, EC transaction detail data, card transaction detail data, electronic money transaction detail data, bank account transaction detail data, and receipt data are managed as purchase history data. As will be described in detail later, the information providing server 100A transmits a prompt to the AI ​​chatbot server 400 (generative AI model 410) along with the purchase history data, instructing the generation AI model 410 to generate second complementary data based on the purchase history data. The information providing server 100A receives the output of the generation AI model 410 from the AI ​​chatbot server 400. Based on the received output of the generation AI model 410 (second complementary data), the information providing server 100A generates screen data to be displayed on the user terminal 200A and transmits the screen data to the user terminal 200A. The user terminal 200A displays a screen indicated by the screen data received from the information providing server 100A. This provides information on taxes, such as income deductions, to the user. The system 10A is described in detail below.

[0070] <2-2.Configuration> (2-2-1. Information Server Configuration) Fig. 10 is a block diagram showing a schematic hardware configuration of the information providing server 100A. As shown in Fig. 10, the information providing server 100A includes a control unit 110, a communication I / F (interface) 130, and a storage unit 120A. Each component is electrically connected via a bus.

[0071] The storage unit 120A is configured with, for example, an auxiliary storage device such as a hard disk drive or a solid state drive. The storage unit 120A stores, for example, a control program 122A, a personal data DB 128, a purchase history data DB 124A, and prompt data 126A. Execution of the control program 122A by the CPU 112 realizes various functions of the information providing server 100A. In the personal data DB 128, personal data of each user is managed in a distinguishable manner. Furthermore, in the purchase history data DB 124A, purchase history data of each user is managed in a distinguishable manner.

[0072] FIG. 11 is a diagram schematically illustrating the personal data DB 128. Referring to FIG. 11, the personal data DB 128 manages personal data of each user of the asset management app. The personal data DB 128 manages an ID (identification), name information, family structure information, and occupation information in association with each other. The ID is information that can uniquely identify each user and indicates an identifier assigned to each user. The name information indicates the user's name. The family structure information indicates the user's family structure and includes, for example, information indicating whether the user is married or not, and information indicating the number of children and grandchildren. The occupation information indicates information related to the user's occupation and includes, for example, information regarding the type of industry, job title, and whether or not year-end tax adjustment is required.

[0073] 12 is a diagram schematically illustrating an example of data for one user managed in the purchase history data DB 124A. As shown in FIG. 12, the purchase history data DB 124A manages the purchase history data and the second complementary data in association with each other. The purchase history data and the second complementary data are assigned flags F1A and F2A, respectively. That is, the purchase history data DB 124A manages the purchase history data and the second complementary data in a manner that allows them to be distinguished from each other.

[0074] The purchase history data managed in the purchase history data DB124A is raw data extracted from, for example, e-commerce transaction detail data, card transaction detail data, electronic money transaction detail data, bank account transaction detail data, and receipt data. Meanwhile, the second supplementary data managed in the purchase history data DB124A is data (AI output data) generated by the generation AI model 410 based on the purchase history data. As described above, the second supplementary data is data indicating the expense item to be paid (e.g., "medical expenses (deductible)," "medical expenses (non-deductible)," "education expenses," "education expenses (tax-exempt 1)," "education expenses (tax-exempt 2)," or "other"). "Education expenses (tax-exempt 1)" and "education expenses (tax-exempt 2)" are expense items allocated to payments that fall within the scope of the lump-sum educational fund donation system. For example, "education expenses (tax-exempt 1)" is allocated to "expenses paid directly to schools, etc.", and "education expenses (tax-exempt 2)" is allocated to "expenses paid directly to entities other than schools, etc." For example, with regard to medical expenses, it may not be easy to determine whether the payment is eligible for medical expense deductions based on the name of the payee alone. In system 10A, the expense items to be paid are output by generative AI model 410, allowing for relatively accurate estimation of the expense items to be paid. For example, information regarding whether a payment to a certain medical institution is eligible for medical expense deductions is output by generative AI model 410, allowing for relatively accurate estimation of whether a payment to a certain medical institution is eligible for medical expense deductions. Data is added to purchase history data DB 124A each time new data is acquired from EC server 300 or financial server 350, or each time new receipt data is received from user terminal 200.

[0075] 10, prompt data 126A is made up of instructions to generative AI model 410. Prompt data 126A will be described in detail later.

[0076] (2-2-2. User terminal configuration) Fig. 13 is a block diagram showing a schematic hardware configuration of user terminal 200A. As shown in Fig. 13, user terminal 200A includes control unit 210, communication I / F 230, operation unit 240, display 250, camera 260, and storage unit 220A. In user terminal 200A, each component is electrically connected via a bus.

[0077] The camera 260 is configured to capture an image of a subject and generate image data. The storage unit 220A is, for example, an auxiliary storage device such as a hard disk drive or a solid state drive. The storage unit 220A stores, for example, a control program 222A. The control program 222A is executed by the CPU of the control unit 210, thereby realizing various functions of the user terminal 200A.

[0078] <2-3. Information provision operation> 14 is a flowchart showing the procedure for providing information on taxes to a user. The process shown in this flowchart is executed by the control unit 110 of the information providing server 100A at predetermined intervals.

[0079] 14, control unit 110 determines whether new purchase history data has been added to purchase history data DB 124A for the user compared to the time when the process shown in this flowchart was last executed (step S200). If it is determined that new purchase history data has not been added to purchase history data DB 124A (NO in step S200), the process shown in this flowchart ends.

[0080] On the other hand, if it is determined that new purchase history data has been added to the purchase history data DB 124A (YES in step S200), the control unit 110 controls the communication I / F 130 to send the prompt data 126A and the added purchase history data to the AI ​​chatbot server 400 (step S210).

[0081] 15 is a diagram schematically illustrating an example of a prompt indicated by prompt data 126A. Referring to FIG. 15, the prompt indicated by prompt data 126A includes, for example, the following instructions (1)-(3) for generative AI model 410.

[0082] (1) For purchase history on an e-commerce site among multiple purchase histories included in the purchase history data, instructions to extract the actual product name by performing data cleansing on the payment recipient name or product name. (2) Instructions to assign one of the following expense categories to each purchase history based on the name of the payee or product name included in the purchase history data: "Medical Expenses (deductible)," "Medical Expenses (non-deductible)," "Education Expenses (tax-exempt 1)," "Education Expenses (tax-exempt 2)," or "Other," and to output the assigned expense category. (3) With regard to purchase history on the e-commerce site, instructions to assign one of the following expense categories to each purchase history based on the actual product names extracted: "Medical Expenses (Deductible)," "Medical Expenses (Non-Deductible)," "Education Expenses," "Education Expenses (Exempt 1)," "Education Expenses (Exempt 2)," or "Other," and to output the assigned expense category.

[0083] 14, the control unit 110 determines whether or not an output has been received from the AI ​​chatbot server 400 (step S220). If it is determined that an output has not been received from the AI ​​chatbot server 400 (NO in step S220), the control unit 110 waits until an output is received from the AI ​​chatbot server 400.

[0084] On the other hand, if it is determined that output has been received from the AI ​​chatbot server 400 (YES in step S220), the control unit 110 controls the storage unit 120A to update the purchase history data DB 124A (step S230). For example, the control unit 110 adds the information received from the AI ​​chatbot server 400 (information related to expense items (second supplementary data)) to each added purchase history data in the purchase history data DB 124A.

[0085] The control unit 110 generates screen data to be displayed on the display 250 of the user terminal 200A based on the updated purchase history data DB 124A (step S240). The screen data is data for displaying a screen on the display 250 of the user terminal 200A, and is configured by, for example, an HTML file.

[0086] The control unit 110 determines whether the user is eligible for medical expense deductions by, for example, referring to the second supplementary data in the updated purchase history data DB 124A and the personal data DB 128, and generates screen data showing the determination result. Also, the control unit 110 determines whether the user is eligible for a lump-sum educational fund donation system by, for example, referring to the second supplementary data in the purchase history data DB 124A and the personal data DB 128, and generates screen data showing the determination result.

[0087] The control unit 110 controls the communication I / F 130 to transmit the generated screen data to the user terminal 200A (step S250), thereby providing the user with information about taxes.

[0088] FIG. 16 is a diagram illustrating an example of a screen notifying a user whether or not they are eligible for a medical expense deduction. Referring to FIG. 16, a table CT1 and a message MS1 are displayed on the display 250 of the user terminal 200A. The table CT1 lists the user's purchase (payment) history. The message MS1 indicates that the user is likely to be unable to receive a medical expense deduction. To generate the message MS1, the user's current total annual medical expenses are calculated, and a determination is made as to whether the total medical expenses exceed 100,000 yen. For example, "items" are automatically assigned within the information providing server 100A. Even if appropriate content is not assigned as an "item," the information on the expense item (second supplementary data) is used to determine whether or not the user is likely to be eligible for a medical expense deduction. For example, initially, the table CT1, the message MS1, items OP5 and OP6, and the frame CS2 are not displayed on this screen. For example, when the user touches item OP4, items OP5 and OP6 are displayed. When the user touches item OP5, a frame CS2 is displayed around item OP5, along with table CT1 and message MS1. On the other hand, when the user touches item OP6, instead of table CT1 and message MS1, a screen is displayed notifying the user whether or not they are eligible for the lump-sum educational fund donation system. The configuration of the screen notifying the user whether or not they are eligible for the lump-sum educational fund donation system is similar to the configuration of the screen notifying the user whether or not they are eligible for medical expense deductions, for example.

[0089] In table CT1, among the payment objects, those whose expense item is medical expenses (deductible) are highlighted. That is, payment objects whose expense item is medical expenses (deductible) stand out more than payment objects whose expense item is not medical expenses (deductible). Furthermore, in table CT1, the expense items are marked with icon IC2. This indicates that the expense item information has been generated by the generation AI model 410. For example, the icon IC2 is not marked on purchase history data (raw data). That is, the purchase history data and the second complementary data are displayed in a distinguishable manner on the user terminal 200A. According to the system 10A, since the purchase history data and the second complementary data are displayed in a distinguishable manner on the user terminal 200A, it is possible to prevent the user from confusing the purchase history data and the second complementary data.

[0090] <2-4. Features> As described above, in system 10A according to the second embodiment, information is provided to the user based on the second complementary data generated by generative AI model 410. Therefore, according to system 10A, information is provided to the user based on the second complementary data, and the second complementary data is generated by generative AI model 410 based on the purchase history data. Therefore, even if the purchase history data indicates a purchase history through an external service, appropriate information can be provided to the user.

[0091] Furthermore, according to the system 10A according to the second embodiment, data including information regarding taxes (data indicating expense items) is generated by the generation AI model 410 based on the purchase history data, so that appropriate information can be provided to the user even if the purchase history data indicates a purchase history through an external service.

[0092] The configuration consisting of the communication I / F 130 and the control unit 110 is an example of the "acquisition unit" in the present invention. The configuration consisting of the communication I / F 130 and the control unit 110 is an example of the "transmission unit" in the present invention. The configuration consisting of the control unit 210 and the display 250 is an example of the "information provision unit" in the present invention.

[0093] 3. Other Embodiments The concept of the above embodiment is not limited to the embodiment described above. Below, examples of other embodiments to which the concept of the above embodiment can be applied will be described.

[0094] <3-1> In the above-described first and second embodiments, data cleansing was performed on the product names indicated in the purchase history on the e-commerce site. However, data cleansing does not necessarily have to be performed on the product names indicated in the purchase history on the e-commerce site. For example, in the first embodiment, based on the product names indicated in the purchase history on the e-commerce site, the name of the manufacturer of the product, the name of an affiliated company of the manufacturer, information on the stock of the manufacturer of the product, information on the stock of an affiliated company of the manufacturer, information on related products manufactured by the manufacturer, and information on related products manufactured by the affiliated companies may be generated. Furthermore, for example, in the second embodiment, based on the product names indicated in the purchase history on the e-commerce site, one of the following expense items may be assigned to each purchase history: "Medical Expenses (Deductible)," "Medical Expenses (Non-Deductible)," "Education Expenses," "Education Expenses (Exempt 1)," "Education Expenses (Exempt 2)," and "Other."

[0095] <3-2> In the first embodiment, the first complementary data is generated by the generative AI model 410, and in the second embodiment, the second complementary data is generated by the generative AI model 410. However, the complementary data is not limited to the first complementary data and the second complementary data. The complementary data may be any data that is not included in the purchase history data.

[0096] <3-3> In the above-described first and second embodiments, the information providing server 100, 100A acquires purchase history data (EC usage detail data) from one EC site. However, the number of EC sites is not limited to this. The information providing server 100, 100A may acquire purchase history data (EC usage detail data) from multiple EC sites.

[0097] <3-4> In the first embodiment, the first complementary data is acquired based on the purchase history data. However, the first complementary data does not necessarily have to be acquired based on the purchase history data. For example, the user's card statement data, electronic money statement data, bank account statement data, etc. may be acquired separately, and the first complementary data may be acquired based on the user's card statement data, electronic money statement data, bank account statement data, etc. For example, the card statement data, electronic money statement data, bank account statement data, etc. may omit the name of a purchased product. Therefore, the prompt data 126 sent to the generative AI model 410 may include an instruction such as "If the product name is omitted, please output the full product name." In other words, the generative AI model 410 may be instructed to perform a data supplementation process instead of data cleansing.

[0098] The above describes exemplary embodiments of the present invention. That is, the detailed description and the accompanying drawings are disclosed for the purpose of illustrative explanation. Therefore, some of the components described in the detailed description and the accompanying drawings may be non-essential components for solving the problems. Therefore, just because these non-essential components are described in the detailed description and the accompanying drawings, it should not be immediately recognized that these non-essential components are essential.

[0099] Furthermore, the above-described embodiments are merely illustrative of the present invention in all respects. Various improvements and modifications to the above-described embodiments are possible within the scope of the present invention. For example, at least a portion of the configuration of any of the embodiments may be combined with at least a portion of the configuration of any of the other embodiments. In other words, when implementing the present invention, specific configurations can be appropriately adopted depending on the embodiment. [Explanation of symbols]

[0100] 10,10A System, 100,100A Information providing server, 110,210 Control unit, 112 CPU, 114 RAM, 116 ROM, 120,120A,220,220A Memory unit, 122,122A,222,222A Control program, 124,124A Purchase history data DB, 126,126A Prompt data, 128 Personal data DB, 130,230 Communication I / F, 200,200A User terminal, 240 Operation unit, 250 Display, 260 Camera, 300 EC server, 305 Purchase history data, 350 Financial server, 400 AI chatbot server, 410 Generative AI model, CS1,CS2 Frame, CT1 Table, F1,F1A,F2,F2A Flag, IC1,IC2 Icon, MS1 Message, N1 Internet, OP1,OP2,OP3,OP4,OP5,OP6 items, RC1 Stock information.

Claims

1. Acquiring purchase history data of a user through an external service; sending a prompt to the generating AI model to instruct the generating AI model to generate complementary data not included in the purchase history data based on the purchase history data, and the purchase history data; and providing information to the user based on the complementary data generated by the generative AI model,

2. the purchase history data is data including a name of a first product, the complementary data is data including information on a manufacturer of the first product or an associated company of the manufacturer of the first product, The information providing method of claim 1 , wherein the prompt includes an instruction to cause the generative AI model to output the complementary data based on a name of the first product.

3. 3. The information providing method according to claim 2, wherein in the step of providing information, information regarding stocks of a manufacturer of the first product or an affiliated company of the manufacturer of the first product is provided to the user.

4. In the step of providing information, information about a second product is provided to the user; The information providing method according to claim 2 , wherein the manufacturer of the second product is the manufacturer of the first product or an associated company of the manufacturer of the first product.

5. The information providing method according to claim 2 , wherein the prompt includes an instruction to cause the generative AI model to extract the name of the first product from the purchase history data.

6. the computer further performs a step of storing the complementary data generated by the generative AI model; In the step of storing the complementary data, the purchase history data and the complementary data are stored in a distinguishable manner; The information providing method according to claim 1 , further comprising the step of displaying the purchase history data and the complementary data in a distinguishable manner.

7. The purchase history data is data including a name of a payee or a product name, the supplementary data is data including information on taxes, The information providing method of claim 1 , wherein the prompt includes an instruction to cause the generative AI model to output the complementary data based on the name of the payee or the name of the product.

8. Acquiring purchase history data of a user through an external service; sending a prompt to the generating AI model to instruct the generating AI model to generate complementary data not included in the purchase history data based on the purchase history data, and the purchase history data; and providing information to the user based on the complementary data generated by the generative AI model.

9. an acquisition unit that acquires purchase history data of a user through an external service; a transmitting unit that transmits to the generating AI model a prompt that instructs the generating AI model to generate complementary data not included in the purchase history data based on the purchase history data, and the purchase history data; An information provision system comprising an information provision unit that provides information to the user based on the complementary data generated by the generative AI model.

Images