Information processing device, system, information processing method and program

Abstract

To assist users in a wide range regarding the use of electronic settlement services.SOLUTION: An information processing means includes: an adjustment unit for, when a natural sentence is input, finely tuning an AI chatbot that has been trained to output an answer corresponding to a natural sentence, based on information relating to an electronic settlement service; an acquisition part for receiving an input sentence input via a user terminal device of a user and relating to the electronic settlement service, and inputting at least the input sentence into the finely-tuned AI chatbot to acquire an answer corresponding to the input sentence; and a display control unit for causing the user terminal device to display the answer according to the input sentence.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Conventionally, there is known a technology that utilizes a chatbot to assist users in purchasing products. For example, Patent Document 1 discloses a technology that searches for consultation products corresponding to a user request, executes a payment process for the consultation product selected from the search results, and causes the chatbot to display related information related to the consultation product for which payment has been completed on the user's terminal device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2023-502609 Summary of the Invention [Problem to be solved by the invention]

[0004] However, chatbots in the prior art often only provide simple functions such as simply notifying users of information or presenting answers according to options entered by the user, i.e., chatbots in the prior art do not provide extensive assistance to users in using electronic payment services.

[0005] The present invention has been made in consideration of the above circumstances, and one of its objects is to provide an information processing device, system, information processing method, and program that can provide a wide range of assistance to users in using electronic payment services. [Means for solving the problem]

[0006] One aspect of the present invention is an information processing device comprising: an adjustment unit that fine-tunes an AI chatbot that has been trained to output an answer corresponding to a natural sentence when the natural sentence is input, based on information related to an electronic payment service; an acquisition unit that accepts an input sentence related to the electronic payment service input via a user's user terminal device and acquires an answer corresponding to the input sentence by inputting at least the input sentence to the fine-tuned AI chatbot; and a display control unit that displays the answer corresponding to the input sentence on the user terminal device. Effect of the Invention

[0007] According to one aspect of the present invention, it is possible to provide an information processing device, a system, an information processing method, and a program that can provide a wide range of assistance to users regarding the use of electronic payment services. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing an example of a configuration for realizing an electronic payment service. [Diagram 2] This is a sequence diagram (part 1) illustrating the general flow of electronic payment. [Diagram 3] This is a sequence diagram (part 2) illustrating the general flow of electronic payment. [Figure 4] 1 is a configuration diagram of a payment server 100 according to a first embodiment. [Diagram 5] FIG. 13 is a diagram showing an example of the contents of user information 172. [Figure 6] FIG. 13 is a diagram showing an example of the contents of affiliated store / store information 176. [Figure 7] FIG. 13 is a diagram showing an example of a top screen IM of a payment application 20. [Figure 8] A sequence diagram showing an example of the flow of a chat function realized by cooperation between a payment application 20, a payment server 100, and an AI chatbot server 200. [Figure 9]FIG. 11 is a diagram for explaining updates to a chat function according to the present embodiment and the effects thereof. [Figure 10] FIG. 11 is a diagram showing an example of the flow of processing executed by an adjustment section 140A. [Figure 11] FIG. 13 is a diagram showing an example of a response generated by the AI ​​chatbot server 200 in response to an input sentence entered by a user. [Figure 12] FIG. 13 is a diagram showing an example of a response generated by the AI ​​chatbot server 200 in response to an input sentence entered by a user. [Figure 13] FIG. 13 is a diagram showing an example of a response generated by the AI ​​chatbot server 200 in response to an input sentence entered by a user. [Figure 14] FIG. 13 is a diagram showing an example of an input sentence to be processed by an acquisition unit 140B. [Figure 15] FIG. 11 is a sequence diagram showing an example of the flow of a chat function realized by cooperation between a payment application 20, a payment server 100, and an AI chatbot server 200 in a modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, with reference to the drawings, an embodiment of an information processing device, a system, an information processing method, and a program of the present invention will be described. Various devices for providing services to users and performing internal analysis, such as a "server", "management device", "information processing device", and "information providing device" that will appear below, may be realized by a group of distributed devices, and each device may be operated by a different business operator. Furthermore, the owner of the hardware of the device (the provider of the cloud server) and the business that actually operates the device may also be different. An application program and a payment server work together to provide an electronic payment service. In the following description, the application program is referred to as a payment application. An electronic payment service is a service that supports payments related to the purchase of goods and services at a store. A store is, for example, a physical store (real store) that exists in the real world, but may also include a virtual store for electronic commerce. A virtual store may include a store provided by an entity different from the operator of the electronic payment service. In that case, when making a payment for shopping at a virtual store, the screen is controlled to transition to an interface screen of the electronic payment service. In an electronic payment service, a store is treated as belonging to, for example, an affiliated store (brand), and processing such as payment when a purchase is made at a store is mainly performed between the user and the affiliated store. Alternatively, processing such as payment may be carried out between the user and the store.

[0010] [Electronic payment service] Fig. 1 is a diagram showing an example of a configuration for realizing an electronic payment service. The electronic payment service is realized mainly by a payment server 100. The payment server 100 communicates with, for example, one or more user terminal devices 10, one or more first store terminal devices 50, one or more second store terminal devices 70, and an AI chatbot server 200 via a network NW. The network NW includes, for example, the Internet, a LAN (Local Area Network), a wireless base station, a provider device, and the like.

[0011] The user terminal device 10 is, for example, a portable terminal device such as a smartphone or a tablet terminal. The user terminal device 10 is a computer device having at least an optical reading function, a communication function, a display function, an input reception function, and a program execution function. In the following description, components for realizing these functions are referred to as a camera, a communication device, a touch panel, a CPU (Central Processing Unit), etc. In the user terminal device 10, a processor such as a CPU executes a payment application 20, thereby operating to provide an electronic payment service to a user in cooperation with a payment server 100. The payment application 20 is installed in the user terminal device 10 from, for example, an application store, and controls the camera, communication device, touch panel, etc.

[0012] The first store terminal device 50 is installed, for example, in a store. The first store terminal device 50 is a computer device having at least a product price acquisition function, an optical reading function, a program execution function, and a communication function. The first store terminal device 50 includes a so-called POS (Point of Sale) device, and the product price acquisition function and the optical reading function may be realized by the POS device. The store code image 60 is placed in the store, and is a code image such as a QR code (registered trademark) printed on a paper or plastic medium. The store code image 60 may be displayed on a display placed in the store (which may be the display of a terminal device such as a smartphone).

[0013] The second store terminal device 70 is used by the operator of the affiliated store. The second store terminal device 70 is a smartphone, a tablet terminal, a personal computer, or the like. An interface 72 for affiliated stores runs on the second store terminal device 70. The interface 72 for affiliated stores may be an app for affiliated stores or a browser. The interface 72 for affiliated stores accepts coupon settings and the like made by the operator of the affiliated store and transmits them to the payment server 100. The second store terminal device 70, which is a smartphone, has the function of displaying a code image corresponding to a store code image and reading a code image displayed by the user terminal device 10 by executing the app for affiliated stores.

[0014] The payment server 100 realizes electronic payment based on payment information received from the user terminal device 10 or the first store terminal device 50. The first store terminal device 50 may include a POS device and an affiliated store server, in which case the payment information is sent from the POS device via the affiliated store server to the payment server 100. In the following explanation, no distinction is made between these two and it is assumed that the payment information is sent from the first store terminal device 50.

[0015] The AI ​​chatbot server 200 periodically obtains information from information sources 300 such as internet sites by crawling, and when natural language is input, it provides an AI chatbot that has been trained to create various responses based on common sense in response to the natural language. AI chatbots are known by names such as ChatGPT and Marvin.

[0016] 2 and 3 are sequence diagrams illustrating the general flow of electronic payment. There may be two patterns of electronic payment: pattern 1 and pattern 2.

[0017] In the case of pattern 1 (hereinafter referred to as user scan) shown in FIG. 2, the user terminal device 10 with the payment application 20 activated decodes the store code image 60 by the optical reading function (S1). The store code image 60 includes store URL (Uniform Resource Locator) information. This store URL is an electronic payment service domain to which store-identifying information is added, and is associated with an affiliated store ID, a store ID, etc. in the payment server 100 (described later). The payment application 20 transmits the first payment information including the store URL and the account ID to the payment server 100 (S2). The payment server 100 searches for store information (described later) from the affiliated store ID and the store ID corresponding to the store URL, acquires the affiliated store name and the store name information (S3), and transmits it to the payment application 20 (S4). The user inputs the payment amount into the user terminal device 10 on the screen on which the affiliated store name and the store name are displayed (S5). Then, the user terminal device 10 generates second payment information including at least the payment amount, and transmits it to the payment server 100 (S6). The payment server 100 performs electronic payment based on the received second payment information (S7). The payment server 100 then transmits a payment completion notice (information for displaying a payment completion screen) to the payment application 20 (S8), and the payment application 20 displays the payment completion screen (S9). Note that when the store code image 60 is displayed on a display installed in the store, the store code image 60 may include not only the store URL but also information on the payment amount. In this case, the step of the user inputting the payment amount is omitted, and the information on the payment amount is included in the first payment information and transmitted to the payment server 100. Information on the affiliated store name and the store name may be included in the payment completion screen and displayed.

[0018] In the case of pattern 2 (hereinafter referred to as store scan) shown in FIG. 3, when the payment application 20 is started, when a payment operation is performed in the payment application 20, when an automatic update timing (e.g., every minute) occurs, and at other timings, the payment application 20 transmits a request for issuing a one-time code to the payment server 100 (S11). The payment server 100 generates a one-time code (S12) and transmits it to the payment application 20 (S13). The payment application 20 displays a code image such as a QR code or a barcode generated based on the one-time code (S14). The user holds (presents) the display surface of the user terminal device 10 over the first store terminal device 50, and the first store terminal device 50 decodes the code image by an optical reading function and obtains the one-time code, etc. (S15). The first store terminal device 50 then generates payment information including the one-time code, payment amount, affiliated store ID, store ID, etc., and transmits it to the payment server 100 (S16). The payment amount information is acquired in advance by reading a barcode or manually entering it. The payment server 100 identifies the user corresponding to the one-time code based on the received information and performs electronic payment (S17). The payment server 100 then transmits a payment completion notice to the payment application 20 (S18), and the payment application 20 displays a payment completion screen (S19).

[0019] Note that electronic payment may be performed using only one of the above patterns. Furthermore, the "account ID" described in FIG. 2 may be other information (e.g., a phone number) that can be used as user identification information. Furthermore, issuance of a one-time code may be omitted in the store scan, and the payment application 20 may display a code image generated based on the user's account ID. In this case, the payment server 100 identifies the user corresponding to the account ID instead of identifying the user corresponding to the one-time code.

[0020] [Payment server] FIG. 4 is a configuration diagram of the payment server 100 according to the first embodiment. The payment server 100 includes, for example, a communication unit 110, a payment content providing unit 120, a payment processing unit 130, an information management unit 140, and a storage unit 170. The components other than the communication unit 110 and the storage unit 170 are realized by, for example, a hardware processor such as a CPU executing a program (software). Some or all of these components may be realized by hardware (including circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a GPU (Graphics Processing Unit), or may be realized by cooperation between software and hardware. The program may be stored in advance in a storage device (storage device having a non-transient storage medium) such as an HDD (Hard Disk Drive) or a flash memory, or may be stored in a removable storage medium (non-transient storage medium) such as a DVD or a CD-ROM, and may be installed in the storage device by mounting the storage medium in a drive device. The information management unit 140 further includes an adjustment unit 140A, an acquisition unit 140B, and a display control unit 140C, the functions of which will be described in detail later. The function of the information management unit 140 in the payment server 100 is an example of an "information processing device."

[0021] The storage unit 170 is a HDD, a flash memory, a RAM (Random Access Memory), etc. The storage unit 170 may be a NAS (Network Attached Storage) device that the payment server 100 can access via a network. The storage unit 170 stores information such as user information 172, payment content information 174, affiliated store / shop information 176, and specification disclosure information 178.

[0022] The communication unit 110 is a communication interface for connecting to the network NW. The communication unit 110 is, for example, a network interface card.

[0023] The payment content providing unit 120 has, for example, a function of a Web server, and provides information (content) for displaying various screens of the electronic payment service to the user terminal device 10. The payment content providing unit 120 appropriately reads necessary content from the payment content information 174 and provides it to the user terminal device 10. The user terminal device 10 accepts various inputs by the user while the content is being played by the payment application 20, and transmits the above-mentioned payment information and the like to the payment server 100.

[0024] The payment processing unit 130 performs payment processing based on the payment information transmitted by the user terminal device 10 or the first store terminal device 50. The payment processing unit 130 performs payment processing while referring to the user information 172.

[0025] FIG. 5 is a diagram showing an example of the contents of the user information 172. The user information 172 is an example of the registration information of a user. The user information 172 is, for example, a user URL, an account ID, a telephone number, a password, as well as an email address, a user ID, a name, an address, a date of birth, a registration date, a charge balance, a deferred payment setting, a deferred payment limit, a deferred payment usage amount, a deferred payment available amount, a payment method setting, a bank account, a credit card number, charge history information, and payment history information (including, for example, a payment date and time, a payment amount, and an affiliated store ID and a store ID where a payment was made) that are associated with the information. The user URL is used for a remittance process between users. When registering for the electronic payment service, it is necessary to register a telephone number and a password. The account ID is issued to the user by the payment server 100, and the user ID is an ID that can be set by the user at will (does not have to be set). Similarly, the email address, the name, the address, and the date of birth are information that can be set by the user at will (does not have to be set). The registration date is the date on which the user registered for the electronic payment service (the date on which the account was created). Hereinafter, the user's instance (electronic payment account) to which this information is associated will be referred to as an account.

[0026] The charge balance is information indicating the balance of electronic money that is set by a user by transferring money to an account in advance. The means of transfer include transfer from an ATM (Automatic Teller Machine) of a designated company (bank) and transfer from a registered bank account. The deferred payment setting is information indicating whether or not the setting for enabling electronic payment by deferred payment has been completed, and is set to either "completed" or "not completed." The deferred payment limit is the limit of deferred payment that can be used each month, the deferred payment usage amount is the amount of deferred payment that has already been used in the current month, and the deferred payment available amount is the amount of deferred payment that can be used in the current month, which is calculated by subtracting the deferred payment usage amount from the deferred payment limit. Although only one deferred payment limit is shown in the figure, in reality, there is also a daily upper limit, and the lower of these may be set as the deferred payment limit. Further details of deferred payment will be described later. The payment method setting is setting information indicating whether the user will perform electronic payment using the charge balance or payment by deferred payment at that time. The bank account and credit card number are information on the bank account or credit card number (account number, card number) that can be used to deposit funds into the electronic payment service. The charge history information is a history of the user increasing the charge balance by transferring funds to the electronic payment service in advance. The payment history information is information that shows the details of payments made by the user for each payment (date and time, store ID of the store where the purchase was made, payment amount, payment method, etc.). Details of followed affiliated stores, acquired coupons, and held points will be described later.

[0027] 6 is a diagram showing an example of the contents of affiliated store / store information 176. The affiliated store / store information 176 includes, for example, a first table 176A in which an affiliated store ID, a store ID, and a category are associated with a store URL, a second table 176B in which an affiliated store ID is associated with an affiliated store name and sales amount (described above), and a third table 176C in which a store ID is associated with a store name and a store address.

[0028] The specification disclosure information 178 is public information regarding the specifications of the functions of the electronic payment service. More specifically, the specification disclosure information 178 is document information such as a web page that is published on the website of the electronic payment service and that explains the specifications of the functions of the electronic payment service (account registration, identity authentication, information registration, electronic payment, mini-application, etc.). The document information in this case is not limited to a format such as HTML (HyperText Markup Language), and may be information in any format that can be published on a website, such as PDF (Portable Document Format). In addition to the web page, the specification disclosure information 178 may include information explained on the payment application 20 of the electronic payment service. Furthermore, the specification disclosure information 178 is not limited to technical information of the electronic payment service, and may include non-technical information such as press releases, news releases, IR information, and commentary articles. In this case, the specification disclosure information 178 is not limited to information published on the website of the electronic payment service, and may include information published on other companies' platforms.

[0029] The information management unit 140 manages user information 172, affiliated store / store information 176, and specification disclosure information 178 based on information acquired from the user terminal device 10 and the second store terminal device 70. The information management unit 140 adds new records to, edits, deletes, and so on for the user information 172, affiliated store / store information 176, and specification disclosure information 178.

[0030] [Electronic payment] When payment information is acquired from the user terminal device 10 or the first store terminal device 50, the payment processing unit 130 refers to the user information 172 to acquire the "payment method setting" of the user. For a user whose "payment method setting" is set to "charge balance", the payment processing unit 130 performs electronic payment as follows. For example, the payment processing unit 130 performs electronic payment by decreasing the charge balance managed in association with the user ID and increasing the item value of the affiliated store's sales. The item value of the affiliated store's sales is not used as electronic money itself, for example, and an amount corresponding to the item value of the sales is transferred to a bank account in a cycle according to an agreement between the affiliated store and the electronic payment service.

[0031] The payment processing unit 130 performs electronic payment for users whose "setting information" is set to "deferred payment" as follows. Deferred payment is set separately from "credit payment" in cooperation with a credit card company, which is a separate entity from the operator of the electronic payment service, and the operator of the electronic payment service acts as a creditor and allows electronic payment that is not dependent on the charge balance within the deferred payment limit. In order to receive the deferred payment service, a credit card provided by the operator of the electronic payment service may be required. The amount used for deferred payment is settled on the payment date of the following month, for example, by debiting from a bank account, for one month. In this case, the payment processing unit 130 performs provisional payment by adding the payment amount to the deferred payment amount and subtracting the same amount from the available deferred payment amount, and when the closing date comes, it performs processing to debit the payment for the current month on the payment date of the following month as described above, or requests the operator of the credit card company to perform such processing. In addition, if the payment amount exceeds the available deferred payment amount at the time of provisional payment, an error notification is returned to the payment application 20.

[0032] [Top page] FIG. 7 is a diagram showing an example of the top screen IM of the payment application 20. The top screen IM displays a code image CD. The code image CD includes, for example, a barcode and a QR code. In addition, together with the code image CD, text (in the figure, "Pay with balance") is displayed indicating whether electronic payment is to be made using the charge balance or electronic payment by deferred payment. This text is drawn by the payment application 20 based on information updated by the payment application 20 each time the changeover switch SW is operated. The top screen IM also includes an operation area CA including the changeover switch SW, and a transition button TB. This will be described later. Note that the "switch" and "button" are GUIs (Graphical User Interfaces) realized in cooperation with a touch panel. The changeover switch SW accepts an operation to switch between electronic payment using the charge balance and electronic payment by deferred payment. The changeover switch SW is set to make electronic payment using the charge balance by default, and each time the changeover switch SW is operated by a user, the setting is switched between making electronic payment using the charge balance and making electronic payment by deferred payment. In the figure, the explanation "Postpaid" is displayed, which means that the setting is for postpaid electronic payment. The operation area CA has buttons for instructing the main operations in electronic payment, such as a button for scanning (starting a user scan) and a button for charging. When the transition button TB is operated, the screen transitions to a payment screen that displays the code image used for electronic payment and the available balance. Furthermore, when the wallet button WA is operated, the screen transitions to a payment history display screen that displays the user's charge balance and available amount for postpaid payment, as well as a list of electronic payment history information in chronological order.

[0033] Below the operation area CA, for example, a group of buttons (switches) M1 to M2 for activating a mini app are further displayed. A mini app is an app that operates using the payment app 20 as a platform and provides some kind of service. A service provider develops a mini app by referring to a Software Development Kit (SDK), which is a program and technical documentation for app development provided by an administrator of the payment app 20. A mini app is an app that operates, for example, while the payment app 20 is activated. For example, a part or all of the mini app may be installed when the payment app 20 is installed, or a part or all of the mini app may be installed from a service server corresponding to the mini app. For example, when the mini app is activated, a service server (not shown) that provides a service corresponding to the mini app is accessed, and the mini app and the service server work together to provide the service to the user. At this time, the service server may be the payment server 100 itself, or may be an external server different from the payment server 100. In Figure 7, as an example, button M1 for a mini-app that provides a chat function described below, and button M2 for a mini-app that provides a function for asset management of the charge balance are displayed, but buttons for launching various types of mini-apps may be displayed, such as a coupon app for obtaining a coupon that can be used to receive a specified percentage of the payment amount back when making an electronic payment, or a payment app for paying for public transportation fares.

[0034] [AI Chatbot Server] In this way, the user can not only make electronic payments using payment application 20, but also operate the wallet button WA to check the charge balance and payment history, and use mini-apps to access various functions provided by the electronic payment service. However, in the prior art, users are not necessarily familiar with how to use such a wide range of electronic payment services, and may spend a lot of time, for example, accessing a website provided by the electronic payment service to find out how to use it.

[0035] In light of this situation, the information management unit 140 (adjustment unit 140A, acquisition unit 140B, display control unit 140C) of the payment server 100 according to this embodiment cooperates with the AI ​​chatbot server 200 to provide the payment application 20 with a chat function with the AI ​​chatbot server 200, and enables the provision of information useful to the user through chat with the user. In particular, the AI ​​chatbot server 200 in this case is not only trained based on information obtained from an information source 300 such as an Internet site, but also has the adjustment unit 140A input the latest specification disclosure information 178 into the AI ​​chatbot server 200 in advance to perform fine tuning. Fine tuning means re-training a part or the whole of a pre-trained neural network model using an additional data set (i.e., the specification disclosure information 178 in this embodiment). Below, the fine tuning by the AI ​​chatbot server 200 and the chat function obtained thereby will be described in detail.

[0036] FIG. 8 is a sequence diagram showing an example of the flow of the chat function realized by the cooperation of the payment application 20, the payment server 100, and the AI ​​chatbot server 200. First, the payment server 100 transmits the latest specification disclosure information 178 to the AI ​​chatbot server 200 (S31). Next, the AI ​​chatbot server 200 performs fine tuning based on the received latest specification disclosure information 178 (S32). Next, when the fine tuning is completed, the AI ​​chatbot server 200 transmits a fine tuning completion notification to the payment server 100 (S33). Next, when the payment server 100 receives the fine tuning completion notification, it transmits a chat function update completion notification to the payment application 20 (S34).

[0037] Next, the payment application 20 accepts, for example, an operation of the chat button M1 for activating the chat function on the top screen IM shown in FIG. 8 from the user, and in response, the payment application 20 activates the chat function (S35). Next, when the payment application 20 accepts an input text from the user, it transmits the accepted input text to the payment server 100 (S36). When the acquisition unit 140B accepts an input text, it includes a part or all of the user information 172 in the input text and transmits it to the AI ​​chatbot server 200 (S37). The part or all of the user information 172 included at this time is an example of "non-public information" in the claims.

[0038] When the AI ​​chatbot server 200 accepts the input sentence, it generates a response according to the accepted input sentence (S38) and transmits the generated response to the payment server 100 (S39). The display control unit 140C transmits an instruction to the payment application 20 to display the response received from the AI ​​chatbot server 200 (S40). The payment application 20 displays the received response on the chat screen (S41). This ends the processing of this sequence diagram.

[0039] [Chat feature updates] FIG. 9 is a diagram for explaining the update of the chat function according to this embodiment and its effect. FIG. 9 shows a time series flow from learning by the AI ​​chatbot server 200 to the use of the chat function by a user. For example, at a certain point in time t1, the AI ​​chatbot server 200 learns to create various answers according to natural sentences based on common sense when natural sentences are input based on information obtained by crawling from an information source 300 such as an Internet site. At this point in time, the AI ​​chatbot server 200 is also expected to crawl the specification disclosure information 178, so it can also answer questions from users about the functions of the electronic payment service.

[0040] However, as shown in FIG. 9, when the user uses the chat function at time t3, which is later than time t1, the AI ​​chatbot server 200 has not learned part or all of the specification disclosure information 178 updated during this period (i.e., the period t3-t1). As a result, the answer to the question input by the user at time t3 may be inaccurate. Therefore, the adjustment unit 140A inputs the latest specification disclosure information 178 at time t2, which is later than time t1, to the AI ​​chatbot server 200, and causes the AI ​​chatbot server 200 to perform fine tuning. This makes it possible to prevent the content of the answer from becoming inaccurate due to a discrepancy between the time when the specification disclosure information 178 was learned and the time when the user uses the chat function.

[0041] In order to keep the specification disclosure information 178 that the AI ​​chatbot server 200 uses for fine tuning up to date, the adjustment unit 140A may access the specification disclosure information 178 stored in the storage unit 170 at a predetermined control cycle (e.g., once a day), and when it is determined that the specification disclosure information 178 has been updated, input the specification disclosure information 178 at the time it was determined that it has been updated to the AI ​​chatbot server 200 to execute fine tuning. This allows the accuracy of answers provided by the AI ​​chatbot server 200 to be maintained at a high level.

[0042] FIG. 10 is a diagram showing an example of the flow of the process executed by the adjustment unit 140A. First, the adjustment unit 140A accesses the specification disclosure information 178 stored in the storage unit 170 (step S101). Next, the adjustment unit 140A judges whether the specification disclosure information 178 has been updated since the previous time (whether there is a difference) (step S102). If it is judged that the specification disclosure information 178 has been updated since the previous time, the adjustment unit 140A inputs the latest specification disclosure information 178 to the AI ​​chatbot server 200 and executes fine tuning (step S103). On the other hand, if it is judged that the specification disclosure information 178 has not been updated since the previous time, the adjustment unit 140A ends the process. This ends the process related to this flowchart.

[0043] [Examples of input sentences and answer generation] Below, with reference to FIG. 11 to FIG. 13, a specific example of an input sentence input by a user and an answer generated by the AI ​​chatbot server 200 in response to the input sentence will be described.

[0044] FIG. 11 is a diagram showing an example of a response generated by the AI ​​chatbot server 200 in response to an input sentence by a user. FIG. 11 shows a response obtained by the acquisition unit 140B receiving an input sentence ("Can I use a passport for personal authentication?") from a user regarding the personal authentication function of an electronic payment service and inputting the received input sentence to the AI ​​chatbot server 200. Since the AI ​​chatbot server 200 is fine-tuned based on the latest specification disclosure information 178 including an explanation of the personal authentication function, as shown in FIG. 11, the display control unit 140C can display an answer that is assumed to be highly accurate in response to a question from a user on the user terminal device 10. Furthermore, the display control unit 140C can display access destination information (such as a URL) based on the latest specification disclosure information 178 on the user terminal device 10.

[0045] FIG. 12 is a diagram showing another example of an answer generated by the AI ​​chatbot server 200 in response to an input sentence by a user. FIG. 12 shows an answer obtained by the acquisition unit 140B accepting an input sentence ("My monthly income is 300,000 yen, and I save 100,000 yen every month. How can I make more money?") from a user regarding a mini-application for an electronic payment service and inputting the accepted input sentence into the AI ​​chatbot server 200. Since the AI ​​chatbot server 200 is fine-tuned based on the latest specification disclosure information 178 including an explanation regarding the mini-application, as shown in FIG. 12, the display control unit 140C can display an answer that is assumed to be highly accurate in response to a question from a user on the user terminal device 10. Furthermore, similar to the case of FIG. 11, the display control unit 140C can display access destination information (such as a URL) based on the latest specification disclosure information 178 on the user terminal device 10.

[0046] FIG. 13 is a diagram showing another example of an answer generated by the AI ​​chatbot server 200 in response to an input sentence by a user. FIG. 13 shows an answer obtained by the acquisition unit 140B accepting an input sentence ("How much is my charge balance?") related to user information of an electronic payment service from a user and inputting the accepted input sentence to the AI ​​chatbot server 200. As described above, the AI ​​chatbot server 200 is fine-tuned based on the latest specification disclosure information 178, and also receives part or all of the user information 172 from the acquisition unit 140B together with the input sentence. Therefore, for example, when the received user information includes the charge balance of the user, the display control unit 140C can display an answer that is assumed to be highly accurate in response to a question from the user on the user terminal device 10.

[0047] In this way, the chat function according to this embodiment not only fine-tunes the AI ​​chatbot server 200 to the latest published specification information 178, but also transmits a part or all of the user information 172 to the AI ​​chatbot server 200 when an input sentence is entered, and obtains a response. This allows the chat function according to this embodiment to provide a wide range of assistance to users regarding the use of electronic payment services, such as support regarding the functions of the electronic payment service and support regarding personal problems of the user.

[0048] FIG. 14 is a diagram showing an example of an input sentence processed by the acquisition unit 140B. FIG. 14 shows a case where the acquisition unit 140B processes an input sentence received from a user by including a part or all of the user information 172 of the user. As shown in FIG. 14, when the acquisition unit 140B receives a first input sentence ("Can I use a passport for identity authentication?") from a user, the acquisition unit 140B processes the input sentence based on the received first input sentence so as to include an instruction information area AR_I for instructing the AI ​​chatbot server 200 on a role to improve the accuracy of the answer, a user information area AR_C showing a part or all of the user information 172, and a question area AR_Q showing details of the input sentence received from the user. FIG. 14 shows a case where the user information area AR_C includes information such as the user's account ID, address, date of birth, charge balance, available amount for post-payment, and payment history. Furthermore, as shown in Fig. 14, since the AI ​​chatbot server 200 is fine-tuned based on the latest specification public information 178, when the AI ​​chatbot server 200 refers to the latest specification public information 178, an instruction may be given to include a URL to the public information in the question area AR_Q. This makes it possible to improve user convenience by presenting the user with an access destination for detailed information, as shown in Figs. 11 and 12.

[0049] [Variations] In the above embodiment, the adjustment unit 140A inputs the latest specification disclosure information 178 to the AI ​​chatbot server 200 to perform fine tuning, and then the acquisition unit 140B inputs the input sentence received from the user using the chat function, including part or all of the user information 172 of the user acquired from the storage unit 170, to the AI ​​chatbot server 200 to acquire a response. On the other hand, in this modified example, the adjustment unit 140A inputs the latest specification disclosure information 178 and part or all of the user information 172 to the AI ​​chatbot server 200 to perform fine tuning, and then the acquisition unit 140B inputs the input sentence received from the user using the chat function to the AI ​​chatbot server 200 to acquire a response. This allows the payment server 100 to operate the chat function efficiently when it receives an input sentence from a user without generating additional processing with a high load, such as acquiring the user information 172 from the storage unit 170 (i.e., DB access).

[0050] FIG. 15 is a sequence diagram showing an example of the flow of the chat function realized by the cooperation of the payment application 20, the payment server 100, and the AI ​​chatbot server 200 in the modified example. First, the payment server 100 transmits the latest specification disclosure information 178 together with a part or all of the user information 172 to the AI ​​chatbot server 200 (S41). Next, the AI ​​chatbot server 200 performs fine tuning based on the received latest specification disclosure information 178 and a part or all of the user information 172 (S42). Next, when the fine tuning is completed, the AI ​​chatbot server 200 transmits a fine tuning completion notification to the payment server 100 (S43). Next, when the payment server 100 receives the fine tuning completion notification, it transmits a chat function update completion notification to the payment application 20 (S44).

[0051] Next, the payment application 20 accepts, for example, an operation of the chat button M1 for activating the chat function on the top screen IM shown in Fig. 8 from the user, and in response, the payment application 20 activates the chat function (S45). Next, when the payment application 20 accepts an input text from the user, it transmits the accepted input text to the payment server 100 (S46). The payment server 100 transmits the accepted input text including the user's identification information to the AI ​​chatbot server 200 (S47).

[0052] When the AI ​​chatbot server 200 accepts the input sentence, it generates a response according to the accepted input sentence (S48) and transmits the generated response to the payment server 100 (S49). The display control unit 140C transmits an instruction to the payment application 20 to display the response received from the AI ​​chatbot server 200 (S50). The payment application 20 displays the received response on the chat screen (S51). This ends the processing of this sequence diagram.

[0053] In the above embodiment and modified example, the adjustment unit 140A inputs at least the latest specification disclosure information 178 to the AI ​​chatbot server 200 and executes fine tuning. Furthermore, the adjustment unit 140A may also input non-disclosed information regarding the specifications of the electronic payment service to the AI ​​chatbot server 200 and execute fine tuning. This can further improve the accuracy of the answers provided by the AI ​​chatbot server 200.

[0054] According to the embodiment described above, an AI chatbot that has been trained to output a response corresponding to a natural sentence when the natural sentence is input is fine-tuned based on information related to electronic payment services, and an input sentence related to the electronic payment service input via a user's user terminal device is received, and at least the input sentence is input to the fine-tuned AI chatbot to obtain a response corresponding to the input sentence, and the response corresponding to the input sentence is displayed on the user terminal device. This makes it possible to provide a wide range of assistance to users regarding the use of electronic payment services.

[0055] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0056] 10 User terminal device 20. Payment App 100 Payment Server 110 Communications Department 120 Payment Contents Provider 130 Payment processing unit 140 Information Management Department 140A adjustment section 140B Acquisition Department 140C Display control unit 170 Storage section

Claims

1. An adjustment unit that fine-tunes an AI chatbot that has been trained to output a response corresponding to a natural sentence input based on information related to electronic payment services; an acquisition unit that receives an input sentence related to the electronic payment service inputted via a user's user terminal device, and inputs at least the input sentence into the fine-tuned AI chatbot to acquire an answer corresponding to the input sentence; A display control unit that causes the user terminal device to display an answer corresponding to the input sentence. Information processing device.

2. The information about the electronic payment service includes public information about the specifications of the electronic payment service; The adjustment unit fine-tunes the AI ​​chatbot based on publicly available information regarding the specifications of the electronic payment service. The information processing device according to claim 1 .

3. The acquisition unit inputs the input sentence and non-public information about the user to the fine-tuned AI chatbot, thereby acquiring an answer corresponding to the input sentence. The information processing device according to claim 2 .

4. The information relating to the electronic payment service further includes non-public information relating to the user; The adjustment unit fine-tunes the AI ​​chatbot based on public information regarding the specifications of the electronic payment service and private information regarding the user. The information processing device according to claim 2 .

5. A system including a user terminal device of a user and an information processing device, The information processing device includes: An adjustment unit that fine-tunes an AI chatbot that has been trained to output a response corresponding to a natural sentence input based on information related to electronic payment services; an acquisition unit that receives an input sentence related to the electronic payment service input via the user terminal device, and acquires an answer corresponding to the input sentence by inputting at least the input sentence to the fine-tuned AI chatbot; a display control unit that causes the user terminal device to display an answer corresponding to the input sentence, the user terminal device includes an input / output unit for allowing the user to input the natural sentence and for outputting a response corresponding to the input sentence; system.

6. The computer Fine-tuning an AI chatbot that has been trained to output a response corresponding to a natural sentence input based on information related to electronic payment services; Accepting an input sentence related to the electronic payment service inputted via a user's user terminal device, and inputting at least the input sentence into the fine-tuned AI chatbot to obtain an answer corresponding to the input sentence; causing the user terminal device to display an answer corresponding to the input sentence; Information processing methods.

7. On the computer, When a natural sentence is input, an AI chatbot that has been trained to output a response corresponding to the natural sentence is fine-tuned based on information related to electronic payment services; Accepting an input sentence related to the electronic payment service inputted via a user terminal device of a user, and inputting at least the input sentence into the fine-tuned AI chatbot to obtain an answer corresponding to the input sentence; causing the user terminal device to display an answer corresponding to the input sentence; program.

Images