Information processing device, information processing system, information processing method, and program

Abstract

To improve convenience for users or service providers. [Solution] An information processing device comprising: an acquisition unit that acquires multiple pieces of target information which are combinations of first information relating to a service inquiry entered by a user to an unmanned chat and second information relating to a service inquiry entered to a manned service in which a person answers the inquiry after the unmanned chat; and a processing unit that references the content of at least the second information of the target information, classifies the second information according to the type of content, and displays classification information on the display unit of the service provider's terminal device, which associates the result of the classification corresponding to the first information with an index indicating the number of the types, as information for improving the information provided by the unmanned chat.

Description

Technical Field

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

Background Art

[0002] Conventionally, a customer support system is known that includes a public solution database publicly available to users by a customer support entity and an internal solution database normally used within the customer support entity (see Patent Document 1). When the user inquires the customer support entity, the search result of the public solution database by the user is transmitted to the customer support entity together with the inquiry content, and an answer obtained by searching the internal solution database and processing by an agent is displayed on the customer terminal of the user.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventionally, when a computer could not give an answer, an operator answered on behalf of the computer. In this case, it was sometimes impossible to handle congestion or it was costly, resulting in low convenience for users or service providers.

[0005] This invention has been made in consideration of these circumstances, and one of its objectives is to provide an information processing device, an information processing system, an information processing method, and a program that can help improve the convenience of users or service providers. For example, it can provide information to improve the mechanism by which a computer provides answers. [Means for solving the problem]

[0006] One aspect of the present invention is an information processing device comprising: an acquisition unit that acquires a plurality of target information sets which are combinations of first information sets which are inquiries about a service entered by a user to an unmanned chat and second information sets which are inquiries about a service entered to a manned service after the unmanned chat, in which a person responds to the inquiries; and a processing unit that references the content of at least the second information sets which of the target information sets, classifies the second information sets which of the types of content sets, and displays classification information on the display unit of the service provider's terminal device, which associates the result of the classification corresponding to the first information with an index indicating the number of the types, as information for improving the information provided by the unmanned chat. [Effects of the Invention]

[0007] According to one aspect of the present invention, it is possible to provide an information processing device, an information processing system, an information processing method, and a program that can help improve the convenience of users or service providers (or administrators). [Brief explanation of the drawing]

[0008] [Figure 1] This diagram shows an example of a configuration for implementing an electronic payment service. [Figure 2] This is a sequence diagram (part 1) illustrating the general flow of electronic payments. [Figure 3] This is a sequence diagram (part 2) illustrating the general flow of electronic payments. [Figure 4] This is a configuration diagram of the payment server 100 according to the embodiment. [Figure 5] This figure shows an example of the contents of user information 172. [Figure 6] This figure shows an example of the contents of merchant / store information 176. [Figure 7] This figure shows an example of the functional configuration of the card server 200. [Figure 8] This figure shows an example of the functional configuration of the information processing device 400. [Figure 9] This figure shows an example of the interface screen IM1 provided by the card server 200 and the mini-application 30. [Figure 10] This figure shows an example of the contents of log information 276. [Figure 11] This diagram illustrates an example of the processing flow performed by the information processing device 400. [Figure 12] This figure shows an example of the analysis results. [Figure 13] This figure shows another example of the analysis results. [Figure 14] This figure shows another example of the analysis results. [Figure 15] This is a diagram illustrating the comparative example and this embodiment. [Figure 16] This figure shows the chat information 274 before the update and the chat information 274 after the update. [Figure 17] This is a diagram illustrating an example of updating the display mode. [Figure 18] This figure shows the trend in the number of live chat messages over a specified period. [Modes for carrying out the invention]

[0009] The following describes embodiments of the information processing device, information processing system, information processing method, and program of the present invention with reference to the drawings. Various devices such as "servers" that appear below, which provide services to users or perform internal analysis, may be implemented by a distributed group of devices, and the operators of each device may be different. Furthermore, the owner of the hardware of the devices (the provider of the cloud server) and the operator that actually operates them may also be different. The application program and the payment server work together to provide an electronic payment service. In the following description, the application program will be referred to as a payment app. The electronic payment service is a service that supports payment for 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 e-commerce. A virtual store may include one provided by an entity different from the operator of the electronic payment service. In that case, when settling a purchase at a virtual store, the user may be directed to the interface screen of the electronic payment service. In the electronic payment service, stores are treated as belonging to, for example, affiliated merchants (brands), and processing such as payment when a purchase is made at a store is mainly carried out between the user and the affiliated merchant. Alternatively, payment and other processing may be conducted between the user and the store.

[0010] [Electronic payment service] FIG. 1 is a diagram showing an example of the configuration of an electronic payment system that realizes an electronic payment service. The electronic payment service is realized centering around a payment server 100. An electronic payment system that realizes an electronic payment service includes, 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, a payment server 100, a card server 200, a manned chat terminal device 300, an information processing device 400, and a management device 500. These devices communicate with each other via, for example, 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. Some or all of the functional configurations included in the electronic payment system may be distributed among a plurality of devices in any form or integrated into any device.

[0011] [User Terminal Device] 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, the configurations for realizing these functions are referred to as a camera, a communication device, a touch panel, a CPU (Central Processing Unit), etc., respectively. In the user terminal device 10, the payment application 20 is executed by a processor such as a CPU, and it operates to provide an electronic payment service to the user in cooperation with the payment server 100. The payment application 20 is installed in the user terminal device 10 from, for example, an application store, and controls a camera, a communication device, a touch panel, etc. A mini-application 30 that operates within the payment application 20 is installed in the user terminal device 10. The mini-application 30 provides, for example, services related to credit cards to the user in cooperation with the card server 200.

[0012] [First Store Terminal Device] The first store terminal device 50 is installed in a store, for example. 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. Note that the store code image 60 may be displayed by a display placed in the store (which may be a display of a terminal device such as a smartphone).

[0013] [Second Store Terminal Device] The second store terminal device 70 is used by the operator of the franchise store. The second store terminal device 70 is a smartphone, a tablet terminal, a personal computer, or the like. In the second store terminal device 70, the interface 72 for franchise stores operates. The interface 72 for franchise stores may be an application for franchise stores or a browser. The interface 72 for franchise stores accepts settings of coupons, etc. by the operator of the franchise store and transmits them to the settlement server 100. The second store terminal device 70 which is a smartphone has a function of displaying a code image corresponding to the store code image or reading the code image displayed by the user terminal device 10 by executing an application for franchise stores.

[0014] [Settlement Server] The settlement server 100 realizes electronic settlement based on the settlement 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 a franchise store server. In that case, the settlement information is transmitted from the POS device to the settlement server 100 via the franchise store server. In the following description, without particularly distinguishing this, it is assumed that the settlement information is transmitted from the first store terminal device 50.

[0015] FIG. 2 and FIG. 3 are sequence diagrams illustrating a rough flow of electronic settlement. There may be two patterns, pattern 1 and pattern 2, in electronic settlement.

[0016] In the case of Pattern 1 shown in Figure 2 (hereinafter referred to as User Scan), the user terminal device 10, with the payment application 20 running, decodes the store code image 60 using its optical reading function (S1). The store code image 60 contains information about the store URL (Uniform Resource Locator). This store URL is an electronic payment service domain to which information that can identify the store has been added, and is associated with the merchant ID and store ID, etc., at the payment server 100 (described later). The payment application 20 sends the first payment information, including the store URL and account ID, to the payment server 100 (S2). The payment server 100 searches for store information (described later) from the merchant ID and store ID corresponding to the store URL, obtains the merchant name and store name information (S3), and sends it to the payment application 20 (S4). The user enters the payment amount into the user terminal device 10 on the screen where the merchant name and store name are displayed (S5). The user terminal device 10 then generates second payment information, including at least the payment amount, and sends 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 sends a payment completion notification (information for displaying the payment completion screen) to the payment application 20 (S8), and the payment application 20 displays the payment completion screen (S9). If the store code image 60 is displayed on a display placed in the store, the store code image 60 may include payment amount information as well as the store URL. In this case, the procedure for the user to enter the payment amount is omitted, and the payment amount information is included in the first payment information and sent to the payment server 100. Merchant name and store name information may be included and displayed on the payment completion screen.

[0017] In the case of Pattern 2 shown in Figure 3 (hereinafter referred to as Store Scan), when the payment app 20 is launched, when a payment operation is performed in the payment app 20, when it is time for an automatic update (for example, every minute), and at other times, the payment app 20 sends a request to the payment server 100 to issue a one-time code (S11). The payment server 100 generates a one-time code (S12) and sends it to the payment app 20 (S13). The payment app 20 displays a code image such as a QR code or barcode that was generated based on the one-time code (S14). The user holds the display surface of the user terminal device 10 over the first store terminal device 50 (presents it), and the first store terminal device 50 decodes the code image using its optical reading function and obtains the one-time code, etc. (S15). Then, the first store terminal device 50 generates payment information including the one-time code, payment amount, merchant ID, store ID, etc., and sends it to the payment server 100 (S16). The payment amount information is obtained in advance by barcode scanning or manual input. Based on the received information, the payment server 100 identifies the user corresponding to the one-time code and performs the electronic payment (S17). The payment server 100 then sends a payment completion notification to the payment app 20 (S18), and the payment app 20 displays a payment completion screen (S19).

[0018] Furthermore, electronic payment may be performed using only one of the above patterns. Also, the "account ID" explained in Figure 2 may be other information that can be used as user identification information (for example, a phone number). In addition, the issuance of a one-time code may be omitted during store scanning, and the payment app 20 may display a code image generated based on the user's account ID. In that case, the payment server 100 will identify the user corresponding to the account ID instead of identifying the user corresponding to the one-time code.

[0019] [Payment Server Functional Configuration] Figure 4 is a diagram of the configuration of the payment server 100. The payment server 100 includes, for example, a communication unit 110, a content provision unit 120, a payment processing unit 130, an information management unit 140, and a storage unit 170. Components other than the communication unit 110 and the storage unit 170 are realized, for example, by 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 LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), GPU (Graphics Processing Unit), and SOC (System On Chip), or by the cooperation of software and hardware. The program may be stored in advance on a storage device such as an HDD (Hard Disk Drive) or flash memory (a storage device equipped with a non-transient storage medium), or it may be stored on a removable storage medium such as a DVD or CD-ROM (a non-transient storage medium) and installed on the storage device when the storage medium is inserted into the drive device.

[0020] The storage unit 170 can be an HDD, flash memory, RAM (Random Access Memory), etc. The storage unit 170 may also be a NAS (Network Attached Storage) device that the payment server 100 can access via the network. The storage unit 170 stores information such as user information 172, content information 174, and merchant / store information 176. Some of this information may also be stored in the storage unit of the user terminal device 10. Details of each piece of information will be described later.

[0021] The communication unit 110 is a communication interface for connecting to a network NW. The communication unit 110 is, for example, a network interface card.

[0022] The content provider unit 120, for example, has the functionality of a web server and provides information (content) for displaying various screens of the electronic payment service to the user terminal device 10. The content provider unit 120 reads the necessary content from the content information 174 as appropriate and provides it to the user terminal device 10. The user terminal device 10 accepts various inputs from the user while the content is being played by the payment application 20 and transmits the aforementioned payment information to the payment server 100. The above content may also be generated by the payment application 20. In this case, the content provider unit 120 provides the payment application 20 with the information necessary for generating the content.

[0023] The payment processing unit 130 performs payment processing based on 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.

[0024] [User information] Figure 5 shows an example of the contents of User Information 172. User Information 172 is an example of user registration information. User Information 172 includes, for example, user URL, account ID, telephone number, password, as well as information such as email address, user ID, name, address, date of birth, registration date, charge balance, credit payment settings, credit payment limit, credit payment amount, available credit payment amount, payment method settings, bank account, credit card number, charge history information, and payment history information. The user URL is used for money transfer processing between users. When registering for a new electronic payment service, registration of a telephone number and password is mandatory. The account ID is issued to the user by the payment server 100, and the user ID is an ID that the user can set at will (or does not have to set). Similarly, the email address and name, address, and date of birth are also information that the user can set at will (or does not have to set). The registration date is the date the user registered for the electronic payment service (the date the account was created). Hereafter, the user instance (electronic payment account) to which this information is associated will be referred to as an account.

[0025] The charge balance is information indicating the balance of electronic money set by the user by sending money to their account in advance. Methods of sending money include sending from an ATM (Automatic Teller Machine) of a designated provider (bank) and sending from a registered bank account. The credit payment setting indicates whether or not the user has completed the settings to enable electronic payments via credit card using the payment app 20, and is set to either "Completed" or "Not Completed". The credit payment limit is the monthly limit for available credit payments, the credit payment amount is the amount already used for credit payments in the current month, and the available credit payment amount is the amount available for credit payments in the current month, calculated by subtracting the credit payment amount from the credit payment limit. While the diagram shows only one credit payment limit, in reality there are also daily limits, and the lower of these may be set as the credit payment limit. Further details on credit payments will be described later. The payment method setting indicates whether the user will use electronic payment with the charge balance or payment by credit card at that time. The bank account and credit card number information, respectively, refers to the bank account or credit card number (account number, card number) to which funds can be deposited into the electronic payment service. The charge history information is a record of when the user has previously sent money to the electronic payment service to increase the charge balance. The payment history information shows the details of each payment made by the user (date and time, store ID of the store where the purchase was made, payment amount, payment method, etc.).

[0026] [Franchise / Store Information] Figure 6 shows an example of the contents of the merchant / store information 176. The merchant / store information 176 includes, for example, a first table 176A in which the merchant ID and store ID are associated with the store URL, a second table 176B in which the merchant name and sales amount (as described above) are associated with the merchant ID, and a third table 176C in which the store name is associated with the store ID. In addition to this information, the merchant / store information 176 may also include information such as the merchant or store category, the store's location, and payment patterns.

[0027] The information management unit 140 acquires information provided by other server devices and the card server 200. Based on the information acquired from the user terminal device 10 and the second store terminal device 70, the information management unit 140 manages user information 172 and merchant / store information 176. The information management unit 140 performs operations such as adding, editing, and deleting new records for user information 172 and merchant / store information 176.

[0028] [Electronic payment] When the payment processing unit 130 obtains payment information from the user terminal device 10 or the first store terminal device 50, it refers to the user information 172 to obtain the user's "payment method setting". For users 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, which is managed in association with the user ID, and increasing the value of the merchant's sales proceeds item. For example, the value of the merchant's sales proceeds item is not used as electronic money itself, but rather the amount corresponding to the value of the sales proceeds item is transferred to the bank account in a cycle according to the agreement between the merchant and the electronic payment service.

[0029] The payment processing unit 130 performs electronic payment as follows for users whose "settings information" is set to "credit payment (credit payment using code information)". Credit payment is a payment method that is carried out in cooperation with a credit card company, which is a separate entity from the operator of the electronic payment service. The operator of the electronic payment service acts as the donor and allows electronic payment that does not depend on the charge balance within the credit payment limit. In order to use the credit payment service, it may be required to obtain a credit card provided by the operator of the electronic payment service. The amount used by credit payment is settled in a lump sum for the month on the payment date of the following month, for example, by withdrawal from a bank account. In this case, the payment processing unit 130 performs a provisional settlement by adding the settlement amount to the amount used by credit payment and subtracting the same amount from the available credit payment limit. When the closing date arrives, it processes the payment for the current month to be withdrawn on the payment date of the following month as described above, or requests the operator of the credit card company to perform the said process. If the settlement amount exceeds the available credit payment limit at the time of provisional settlement, an error notification is sent back to the payment app 20.

[0030] [Card Server] The card server 200 works in conjunction with the payment application 20 or mini-application 30 to provide credit card-related services to the user terminal device 10. Hereinafter, the mini-application 30 will be the one providing the credit card-related services. For example, the card server 200 displays various information, such as credit card usage history and information regarding credit card usage charges, on the display unit of the user terminal device 10 in response to the user's operation of the mini-application 30.

[0031] Figure 7 shows an example of the functional configuration of the card server 200. The card server 200 includes, for example, a communication unit 210, a content provision unit 220, a chat processing unit 230, an information processing unit 240, and a storage unit 270. Some or all of the functional configurations included in the card server 200 may be included in the payment server 100.

[0032] The components other than the communication unit 210 and the storage unit 270 are realized, for example, by 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 LSIs, ASICs, FPGAs, GPUs, and SOCs, or by the cooperation of software and hardware. The program may be stored in advance in a storage device such as an HDD or flash memory (a storage device equipped with a non-transient storage medium), or it may be stored in a removable storage medium such as a DVD or CD-ROM (a non-transient storage medium) and installed in the storage device when the storage medium is mounted in a drive device.

[0033] The storage unit 270 can be an HDD, flash memory, RAM, etc. The storage unit 270 may also be a NAS device accessible by the card server 200 via a network. The storage unit 270 stores information such as content information 272, chat information 274, and log information 276. Details of each piece of information will be described later.

[0034] The communication unit 210 is a communication interface for connecting to a network NW. The communication unit 210 is, for example, a network interface card.

[0035] The content provider unit 220, for example, has the functionality of a web server and provides information (content) for displaying various service screens to the user terminal device 10. The content provider unit 220 reads the necessary content from the content information 272 as appropriate and provides it to the user terminal device 10. The user terminal device 10 accepts various inputs from the user while the content is being played by the payment application 20 and transmits the aforementioned payment information to the card server 200. The above content may also be generated by the payment application 20. In this case, the content provider unit 220 provides the payment application 20 with the information necessary for generating the content.

[0036] The chat processing unit 230 works in conjunction with the content provision unit 220 to conduct unattended chats with users. The chat processing unit 230 refers to the chat information 274 to provide users with options and answers to their inquiries.

[0037] The information processing unit 240 updates chat information 274 and manages log information 276.

[0038] [Manned chat terminal device] The manned chat terminal device 300 is a terminal device operated by an operator of the administrator (service provider). If the chat processing unit 230 is unable to answer a user's inquiry via unmanned chat, the operator uses the manned chat terminal device 300 to chat with the user via the user terminal device 10 and provide an answer to the inquiry. For example, if the chat processing unit 230 determines that it cannot answer a user's inquiry via unmanned chat, the chat processing unit 230 notifies the manned chat terminal device 300 and provides the manned chat terminal device 300 with the history of unmanned chats to date. In response to the notification, the operator refers to the history of unmanned chats and provides an answer that matches the user's intent.

[0039] [Information Processing Device] Figure 8 shows an example of the functional configuration of the information processing device 400. The information processing device 400 includes, for example, an acquisition unit 410, a processing unit 420, and a storage unit 470. The components of the acquisition unit 410 and the processing unit 420 are realized, for example, by 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, ASIC, FPGA, GPU, or SOC, or by the cooperation of software and hardware. The program may be stored in advance in a storage device such as an HDD or flash memory (a storage device equipped with a non-transient storage medium), or it may be stored in a removable storage medium such as a DVD or CD-ROM (a non-transient storage medium) and installed in the storage device when the storage medium is mounted on a drive device.

[0040] The storage unit 470 can be an HDD, flash memory, RAM, etc. The storage unit 470 may also be a NAS device accessible by the information processing device 400 via a network. The storage unit 470 stores information such as log information 472 and analysis information 474. The log information 472 is log information 276 provided by the card server 200. The analysis information 474 is information of the processing results of the processing unit 420.

[0041] The acquisition unit 410 acquires log information 472 (target information) from the card server 200. The processing unit 420 analyzes the log information 472 and displays the analysis results on the display unit of the administrator's management device 500.

[0042] [Management device] The management device 500 is, for example, a terminal device used by the administrator. The management device 500 is a device that provides the processing results of the card server 200. The administrator updates the contents of the chat information 274 of the card server 200 by referring to the processing results of the information processing device 400.

[0043] [overview] The information processing device 400 acquires multiple pieces of target information, which are combinations of first information regarding service inquiries entered by the user to an unmanned chat and second information regarding service inquiries entered to a manned service where a person answers the inquiry after the unmanned chat. The processing unit 420 refers to the content of at least the second piece of target information and classifies the second piece of information according to the type of content. The processing unit 420 displays classification information corresponding to the first piece of information, which associates the classification result with an index indicating the number of types, on the display unit of the administrator's management device 500. The index indicating the number may be the number itself, or it may be an index indicating a degree, such as "many" or "few".

[0044] The above-mentioned manned service is either a manned chat or a manned telephone service. Alternatively, a service different from the unmanned chat may be used instead of the manned service. This different service might be, for example, one that places a greater load or cost on the card server 200 or the administrator than the unmanned chat. In the following explanation, the manned service will be described as a manned chat.

[0045] [Regarding inquiries from users] Users can make inquiries about credit cards by operating the mini-application 30. Figure 9 shows an example of the interface screen IM1 provided by the card server 200 and the mini-application 30. For example, the chat processing unit 230 refers to the chat information 274 and presents options corresponding to the inquiry entered by the user. The chat processing unit 230 uses a language processing algorithm to recognize the meaning of the entered inquiry and presents options corresponding to the recognized meaning of the inquiry. For example, the chat processing unit 230 presents the next option corresponding to the selected option from the options.

[0046] Chat information 274 includes scenarios for unattended chat. Chat information 274 is information that associates options or answers with an inquiry or the meaning of an inquiry. Chat information 274 is also information that associates one or more options or answers with an option.

[0047] Users can input their inquiries into the interface screen IM1, which is a chat screen, and receive answers to their inquiries by chatting with an automated chat system. For example, if a user inputs that they want to apply for the XX service, the automated chat system will display instructions on how to apply for the XX service on the display unit of the user terminal device 10.

[0048] As described above, answers can sometimes be obtained, but in other cases, answers may not be available. For example, this may occur if the user selects the wrong option or if the available options do not match the user's intent. In such cases, a live chat service is used. However, using live chat services is undesirable for administrators because it increases costs and causes congestion. Furthermore, it can be inconvenient for users, as they prefer to easily obtain answers to their inquiries through automated chat.

[0049] For example, if the reason is that the user does not have a choice that matches their intention, the use of human-operated chat can be reduced by providing the user with more appropriate choices, inquiries, or answers. In this embodiment, the information processing device 400 helps improve the convenience of the user or administrator by providing the administrator with classification information to identify more appropriate choices, inquiries, or answers. The information processing device 400 can provide information to improve the mechanism by which the computer provides answers (for example, information to improve the chat information 274).

[0050] [Log Information] Figure 10 shows an example of the contents of log information 276. Log information 276 is information that associates an inquiry made by a user in the automated chat (an example of "first information") with the answer to that inquiry (an example of "second information"). The inquiry includes, for example, the option selected by the user that initiated the transition to the human service (clicked FAQ) or the last option selected by the user (clicked FAQ) from among the options provided by the automated chat. In the following explanation, it will be assumed that this is the last option the user operated on. For example, if a user operates on the option "I have a bill I don't recognize" from among several options and transitions to a human chat, the inquiry will be "I have a bill I don't recognize".

[0051] In unattended chats, the options "Resolved" and "Not Resolved" are displayed immediately before connecting to a live chat, and if "Not Resolved" is selected, a connection to a live chat may be established. The "last option selected by the user" mentioned above refers to, for example, the last option selected immediately before or before the "Resolved" and "Not Resolved" options. The "initial user-selected option" refers to a different option from "Resolved" and "Not Resolved" that triggered the connection to the live chat.

[0052] The inquiry may be information entered by a human chat operator, or it may be information automatically registered in log information 276 based on the user's actions. For example, when an operator enters the information, the information processing device 400 may allow the operator to easily select the type of inquiry in advance using a pull-down button or similar. Inquiries may also be identified by numbers or symbols.

[0053] The responses to inquiries include, for example, responses provided via live chat. The above responses are, for example, information entered by a live chat operator via the live chat terminal device 300. In addition to (or instead of) the responses, the content of the inquiry in the live chat (another example of "secondary information") may be used.

[0054] The information processing device 400 analyzes the log information 276 to help improve the convenience of users or administrators. This process is described below.

[0055] [Process Flow] Figure 11 is a diagram illustrating an example of the processing flow performed by the information processing device 400. (1) The acquisition unit 410 of the information processing device 400 acquires log information 472. (2) Next, the processing unit 420 of the information processing device 400 deletes personal information from the log information 472. The processing unit 420 deletes information that is presumed to be personal information from the log information 472, for example, by using a natural language algorithm. (3) Next, the processing unit 420 analyzes the log information 472, and (4) provides the analyzed classification results to the management device 500.

[0056] [About the analysis] The processing unit 420 analyzes the target information in the log information 472 and classifies the target information into classes (types). The processing unit 420 classifies the target information (or second information) by content type based on the words contained in the content of the target information. The target information is a combination of an inquiry and the answer to the inquiry. In addition to the above information, the target information (second information) may also include the content of the response from the operator of the human service. The target information may include the content of the chat between the user and the automated chat in the automated chat, or it may include information on the choices selected by the user in the automated chat (e.g., operation and chat history).

[0057] The processing unit 420, for example, extracts a predetermined number of characteristic words from the content of the target information and identifies the frequency of occurrence of these characteristic words. The processing unit 420 extracts characteristic words using language processing algorithms such as TF-IDF.

[0058] The processing unit 420 uses the processing results described above to classify the target information into which class it belongs. For example, the processing unit 420 identifies a class based on one or both of the characteristic word (or word type) and the frequency of occurrence of the word (word type). Figure 12 shows an example of the analysis results. For example, the target information is classified into classes (C1-C5) according to the pattern of the characteristic word, and furthermore, the number for each classification result is displayed in association with the characteristic word and the query (operation), as shown in Figure 12. This information and the information in Figure 13, which will be described later, are displayed on the display unit of the management device 500. The number of classes to be classified may be a number specified by the administrator.

[0059] The processing unit 420 may display the analysis results in a graph. Figure 13 shows another example of the analysis results. As shown in Figure 13, the types of target information may be represented by different symbols. Each symbol corresponds to one piece of target information. When an administrator operates the management device 500 to select one piece of target information, the inquiry contained in the target information and the answer to the inquiry may be displayed on the display unit.

[0060] The classes in the analysis results may be associated with the content of the user's inquiry. The content of the user's inquiry is, for example, the true content of the inquiry inferred from the target information. For example, as shown in Figure 13, the content of an inquiry in one class is "remaining items in bulk," the content of an inquiry in another class is "address unknown," and the content of an inquiry in yet another class is "lost and reissued."

[0061] The information shown in Figure 13 is an example of classification information that associates the results of the classification corresponding to the first information (information expressed in terms of symbol types) with an index indicating the number of the types (number of symbols), as information for improving the information provided by the unmanned chat. The information shown in Figure 13 is an example of classification information that associates the results of the classification corresponding to the first information with an index indicating the number of the types and the inquiry content recognized from the second information. The inquiry in the first information (the option selected by the user) is "None of the above," the classification result is represented by the type of symbol, and the index is represented by the number of symbols. The inquiries recognized from the second information are "Remaining balance," "Address unknown," and "Lost and reissued."

[0062] The process of identifying the true query may be performed manually by the administrator and associated with the classification result, or the information processing device 400 may automatically identify or estimate it and associate it with the classification result. The content of the true query is the information associated by the administrator by referring to the second information of the classification result, or the information estimated by the processing unit 420 from the second information of the classification result.

[0063] The content of the inquiry is, for example, something that the administrator has identified by referring to the content of the target information. For example, the administrator operates the management device 500 and selects an appropriate inquiry from among the pre-prepared inquiry contents displayed on the interface screen provided by the processing unit 420, thereby associating the inquiry content with a class, as shown in Figure 13.

[0064] For example, the processing unit 420 may identify the true query using a learning model (not shown). The learning model is a model that has been trained to output the true query content corresponding to the target information (e.g., the answer to the query in log information 472) when the target information is input. The learning model may be a generative AI that has learned the above information. The learning model may also be a model that has been trained to output the true query content corresponding to the target information by taking characteristic words contained in the target information (second information) used to classify the target information as input instead of the target information. If multiple true queries are obtained for a certain type of target information, the processing unit 420 performs statistical processing or the like to identify the true query to adopt. In this way, the processing unit 420 can identify the true query content (e.g., "address unknown") from the target information.

[0065] The processing unit 420 may display information on the display unit of the management device 500 that associates the query (operation), the content of the query (the true content of the query), and the number of items, as shown in Figure 14. Figure 14 shows another example of the analysis results. The administrator can check the details of the record log information 472 by performing a predetermined operation.

[0066] The information shown in Figure 14 is an example of classification information that associates the results of the classification corresponding to the first information (information expressed in each record) with an index indicating the number of items of the type (count), as information for improving the information provided by the unmanned chat. The information shown in Figure 14 is an example of classification information that associates the results of the classification corresponding to the first information with an index indicating the number of items of the type and the inquiry content recognized from the second information. The inquiry in the first information (the option selected by the user) is "None of the above," the classification result is represented by a record, and the index is represented by the count. The inquiries recognized from the second information are "Remaining items all at once," "Address unknown," and "Lost and reissued."

[0067] The administrator can refer to the content and number of true inquiries, such as those shown in Figures 13 and 14 above, to consider whether the automated chat can handle true inquiries exceeding a certain number. For example, if the automated chat can handle true inquiries, the administrator can consider what options or inquiries should be offered to the user and update the chat information 274 scenario to include appropriate options or inquiries.

[0068] In the classification information shown in Figure 13 or Figure 14 above, information indicating whether the inquiry required human service or could be handled by automated chat may be added to the classification result. The information processing device 400 displays on the display unit of the management device 500 information that it associates with the inquiry whether the inquiry recognized from the second information can be handled by automated chat. The information that it associates with the inquiry is information that the administrator has associated with the inquiry by referring to the inquiry content, or it is information that the processing unit 420 has estimated from the inquiry content.

[0069] For example, log information 472 may include information indicating whether the inquiry entered by the operator required human service or whether it was an inquiry that could be handled by automated chat, associated with each piece of information. In this case, the information processing device 400 may refer to the operator's input in log information 472 and associate the information indicating whether the inquiry required human service or whether it could be handled by automated chat with the classification result and display it on the display unit. For example, if both information indicating an inquiry requiring human service and information indicating an inquiry that could be handled by automated chat are associated with the same type of information, the information processing device 400 will use statistical processing or the like to prioritize the one that meets the criteria. This makes it easy for administrators to identify inquiries that can be handled by automated chat and are targets for improvement.

[0070] The information processing device 400 may use a learning model (not shown) to acquire (estimate) information indicating whether an inquiry required human service or could be handled by automated chat. The learning model is a model that has learned information that associates label information indicating whether an inquiry required human service or could be handled by automated chat with target information (secondary information). The learning model is a model that has been learned to output label information corresponding to target information (secondary information) when target information (secondary information) is input. The information processing device 400 inputs each of the target information included in the results of each classification into the learning model and statistically processes the label information output by the learning model to determine whether the classification result was an inquiry requiring human service or an inquiry that could be handled by automated chat. The learning model may be a generative AI that has learned the above information. In this process as well, if different results are obtained for a certain classification, statistical processing is used to determine whether human service was required or could be handled by automated chat.

[0071] [Comparison between the comparative example and this embodiment] Figure 15 is a diagram illustrating a comparative example and this embodiment. Figure 15(A) is a diagram illustrating a comparative example. In (A), when the user clicks "Other inquiries" and then clicks "Other," there are no applicable options, so the card server 200 connects the user terminal device 10 to a live chat. The user can obtain an answer using the live chat.

[0072] Figure 15(B) is a diagram illustrating this embodiment. As shown in Figure 15(B), clicking "Other" displays the option "Card replacement due to magnetic failure or damage, etc." When the user clicks this option, the card server 200 displays an interface screen that accepts card replacement requests. The user can then request card replacement via automated chat.

[0073] In this embodiment, the administrator confirms that the true content of the inquiry from the user who clicked "Other" is "Card replacement due to magnetic failure or damage," and that the number of such inquiries exceeds a predetermined number in the live chat. The administrator updated chat information 274 so that the option "Card replacement due to magnetic failure or damage" is displayed after "Other" is clicked in chat information 274. As a result, the issue was resolved in the unattended chat as shown in Figure 15(B) above.

[0074] Figure 16 shows the chat information 274 before and after the update. For example, the card server 200, in cooperation with the management device 500, accepts updates to the scenario used by the automated chat so that the automated chat can answer inquiries that it was unable to answer. Based on instructions from the administrator via the management device 500, who have referenced the classification information, the card server 200 updates the scenario of the chat information 274 to include answers to inquiries that the automated chat could not answer. The card server 200 then refers to the updated scenario and provides answers to inquiries that it could not answer before the update to the user via the automated chat.

[0075] The processing unit 420 may use a learning model (not shown) to identify the answer to the true inquiry (or an additional inquiry). The information processing unit 400 may include a learning model that outputs an answer to an inquiry (or an additional inquiry) when an inquiry is input. The learning model is a model that has been trained to output an answer to an inquiry when an inquiry is input. The information processing unit 400 inputs the inquiries that could not be answered by the unmanned chat into the learning model and obtains the answers output by the learning model. The information processing unit 400 registers the answers output by the learning model as answers to inquiries that could not be answered by the unmanned chat into the scenario of the chat information 274 and updates the scenario. The learning model may be a generative AI that has learned the above information.

[0076] In Figure 16 (A), the pre-update chat information 274 had a scenario where clicking "Other" would connect the user to a live chat. In contrast, in Figure 16 (B), the post-update chat information 274 has a scenario where clicking "Other" displays the option "Card replacement due to magnetic failure or damage."

[0077] As described above, the card server 200 can help resolve inquiries via unattended chat by allowing the administrator to refer to the analysis results and update the chat information 274.

[0078] [Example of updating the display format of the information provided] Figure 17 illustrates an example of updating the display format. Assume that the processing unit 420 has classified the target information and recognized that the true content of the inquiry is "Instructions for Sending Account Request Forms". The user has reached the information indicating the instructions for sending account request forms, but the administrator can deduce that the response is difficult for the user to understand because they are using a live chat. In this case, the administrator updates the chat information 274 to correct the response. For example, by making key characters in the response provided by the unmanned chat stand out, or by displaying the above characters as links, the user can obtain an answer via the unmanned chat.

[0079] [Connection level to live chat after update] Figure 18 shows the trend in the number of human-operated chat inflows over a predetermined period. The vertical axis of Figure 18 represents the number of human-operated chat inflows, and the horizontal axis represents the period (months). Chat information 274 was updated so that a response could be obtained via unattended chat after M1. The number of human-operated chat inflows in M2 after the update was lower than the number of human-operated chat inflows in M1.

[0080] As described above, by updating the chat information 274 using the analysis results of the processing unit 420, the number of incoming chat messages from human users can be suppressed. This improves convenience for users or administrators.

[0081] [Consider attributes] In this embodiment, the above analysis may be performed for each user's attributes. For example, users may be classified based on gender, age, occupation, address, etc., and analysis may be performed for each user. Chat information 274 may be prepared for each attribute, and the prepared chat information 274 may be updated. In this case, the card server 200 obtains the user's identification information from the user terminal device 10, refers to information that associates the user's identification information with attributes, and recognizes the attribute corresponding to the user's identification information. The card server 200 uses the chat information 274 corresponding to the attribute to chat with the user. For example, even for the same inquiry, depending on the user's attributes, it may be more appropriate to connect to a human service rather than an automated chat. For example, for a certain inquiry, it may be appropriate for users of a certain age group to connect to a human service and receive an answer.

[0082] As described above, the true content of the inquiry can be recognized for each attribute. Administrators can refer to this information to update chat information 274.

[0083] According to the embodiments described above, the card server 200 acquires multiple pieces of target information, which are combinations of first information relating to a service inquiry entered by a user to an unmanned chat and second information relating to a service inquiry entered to a manned service where a person responds to the inquiry after the unmanned chat. The card server 200 then refers to the content of at least the second piece of information of the target information, classifies the second piece of information according to the type of content, and displays classification information on the display unit of the administrator's (service provider's) terminal device, which associates the result of the classification corresponding to the first piece of information with an index indicating the number of the types, as information for improving the information provided by the unmanned chat. This improves the convenience of the user or administrator.

[0084] Although embodiments for carrying out the present invention have been described above using examples, the present invention is not limited in any way to these embodiments, and various modifications and substitutions can be made without departing from the spirit of the present invention. [Explanation of Symbols]

[0085] 10. User terminal device 20 Payment Apps 100 Payment Servers 120 Content Provision Department 130 Payment Processing Unit 140 Information Management Department 230 Chat Processing Unit 400 Information Processing Devices 410 Acquisition Department 420 Processing Unit

Claims

1. An acquisition unit that acquires multiple pieces of target information which are combinations of first information regarding a service inquiry entered by a user in an unmanned chat and second information regarding a service inquiry entered in a manned service after the unmanned chat, in which a person responds to the inquiry. Referencing at least the content of the second information of the target information, classifying the second information according to the type of content, A processing unit that displays classification information, which associates the results of the classification corresponding to the first information with an index indicating the number of the types, on the display unit of the service provider's terminal device, as information for improving the information provided by the unmanned chat, An information processing device equipped with the following features.

2. The aforementioned manned service is a manned chat or manned telephone service. The information processing apparatus according to claim 1.

3. The first information includes, among the options provided by the unmanned chat for the inquiry, at least the option selected by the user that initiated the transition to the manned service, or at least the last option selected by the user. The information processing apparatus according to claim 1.

4. The processing unit classifies the second information according to the type of content based on the words contained in the content. The information processing apparatus according to any one of claims 1 to 3.

5. The processing unit causes the service provider's terminal device to display classification information on the display unit, which associates the classification result corresponding to the first information, an index indicating the number of types, and the inquiry content recognized from the second information. The information processing apparatus according to any one of claims 1 to 3.

6. The above inquiry concerns: Information associated by the administrator with the results of the classification, or The processing unit estimates the information from the second information of the classification result. The information processing apparatus according to claim 5.

7. When the second information is input, the processing unit performs the estimation using a learning model that has been trained to output information indicating the content of the query recognized from the second information. The information processing apparatus according to claim 6.

8. The processing unit causes the service provider's terminal device to display information on the display unit of the service provider's terminal device that indicates whether the inquiry recognized from the second information is an inquiry that can be handled by the unmanned chat, and associates this information with the inquiry. The information processing apparatus according to claim 5.

9. The information indicating whether the inquiry recognized from the second information above is an inquiry that can be handled by the automated chat is: Information that the administrator has matched based on the aforementioned inquiry, or The processing unit estimates the information from the content of the inquiry. The information processing apparatus according to claim 8.

10. The processing unit, upon receiving the inquiry content, performs the estimation using a learning model trained to output information indicating whether or not the inquiry content can be handled by the automated chat system. The information processing apparatus according to claim 9.

11. The information processing apparatus according to claim 6, The system includes a chat device that accepts updates to the scenario used by the automated chat so that the automated chat can answer inquiries that the automated chat could not answer, The chat device updates the scenario to include answers to inquiries that the unattended chat could not answer, based on instructions given by the administrator via the administrator's terminal device, after the administrator has referred to the classification information. Information processing system.

12. The chat device, referring to the updated scenario, provides the user with answers to the inquiries that could not be answered before the update via the unattended chat. The information processing system according to claim 11.

13. The system includes a learning model that outputs a response to the aforementioned inquiry when the aforementioned inquiry content is input. The learning model is trained to output an answer to the query when the query is input. The aforementioned information processing device is The inquiry that could not be answered by the automated chat is input to the learning model, and the answer output by the learning model is obtained. The response output by the learning model is registered in the scenario as the response to the inquiry that the unmanned chat could not answer, and the scenario is updated. The information processing system according to claim 12.

14. Computers Multiple pieces of target information are obtained, which are combinations of first information regarding service inquiries entered by the user in an unmanned chat, and second information regarding service inquiries entered in a manned service where a person answers the inquiry after the unmanned chat. Referencing at least the content of the second information of the target information, classifying the second information according to the type of content, As information for improving the information provided by the unmanned chat, classification information that associates the results of the classification corresponding to the first information with an index indicating the number of the types is displayed on the display unit of the service provider's terminal device. Information processing methods.

15. On the computer, A process to acquire multiple pieces of target information, which are combinations of first information regarding a service inquiry entered by the user in an unmanned chat, and second information regarding a service inquiry entered in a manned service after the unmanned chat, where a person responds to the inquiry. A process of referring to at least the content of the second information of the target information and classifying the second information according to the type of content, As information for improving the information provided by the unmanned chat, a process is performed to display classification information on the display unit of the service provider's terminal device, which associates the results of the classification corresponding to the first information with an index indicating the number of the types. A program that executes the command.

Images