System

Abstract

A system is provided.SOLUTION: A system for providing a chat-format service using a generated AI model for providing information related to local government support based on a request message received from a user device, the system comprising: means for acquiring address information from a user; means for searching for support information of a corresponding local government based on the address information; means for acquiring annual income information from the user; means for filtering support contents based on the address information and the annual income information; and means for transmitting the filtered support contents and document information necessary for an application to the user device.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] The conventional method of obtaining information on local government support required users to individually research each local government's website or make inquiries, which was extremely time-consuming and laborious. As a result, many users found the complex conditions of the support system cumbersome and gave up on applying. Furthermore, the support content differs for each local government, making it even more difficult to obtain information. There is an urgent need to solve these issues and enable users to easily and quickly obtain information on the local government support they are eligible for. [Means for solving the problem]

[0005] In order to solve the above problem, the present invention provides a system for providing a chat-style service using a generative AI model that provides information on local government support based on a request message received from a user terminal. The system includes the following means:

[0006] 1. How to get address information from users

[0007] 2. A way to search for support information from the relevant local government based on address information

[0008] 3. How to obtain annual income information from users

[0009] 4. A way to filter donations based on address and income information

[0010] 5. Means of sending filtered support details and document information required for application to the user terminal

[0011] This system allows users to easily obtain the support content that applies to them through simple input operations. This significantly improves user convenience without being bothered by the complexity and time required for the support system. It also allows users to quickly determine whether they meet the conditions of the support system, making it possible for them to receive appropriate support.

[0012] A "user terminal" is a device through which a user inputs information and communicates with a server via a communication network.

[0013] A "request message" is a message that a user sends to the system requesting information, and requests the provision of support content.

[0014] A "generative AI model" is a model generated using artificial intelligence technology that provides local government support information based on user input.

[0015] "Address information" refers to geographical information about the user's residence, and is used to identify the support content.

[0016] "Annual income information" refers to the user's annual income amount, and is used to determine whether or not the user satisfies the conditions for receiving support.

[0017] "Support details" refers to details of support programs such as subsidies and eco-points provided by local governments.

[0018] "Documents required for application" refers to the official documents that must be submitted to receive assistance, and these vary depending on the assistance program.

[0019] "Filtering" refers to the process of selecting relevant assistance content based on information provided by the user.

[0020] "Means of searching" refers to the means of searching the database based on address information and finding support information for the relevant local government.

[0021] The "transmitting means" refers to a means for transmitting the filtered support information and documents required for application to the user terminal. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0023] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0024] First, the terms used in the following description will be explained.

[0025] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0026] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0027] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0028] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0029] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0033] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0034] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0035] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0036] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0037] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0040] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0041] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0042] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0043] MODE FOR CARRYING OUT THE INVENTION

[0044] The present invention is a chat-based local government support service that utilizes a generative AI model and is a system that allows users to easily obtain local government support information. This system receives input from a user's terminal and provides relevant support information based on that input. Specific embodiments of the present invention are described in detail below.

[0045] Natural language explanation of program processing

[0046] Receiving the initial request

[0047] The user sends a request message via the user terminal requesting information about local government support, for example, by typing "Tell me about xx subsidies."

[0048] The server receives this request message and sends a message to the user terminal saying "Please tell us where you live."

[0049] Obtaining address information

[0050] The user terminal prompts the user to enter address information, and when the user enters the address, it sends it to the server. For example, the user enters "Chiyoda-ku, Tokyo."

[0051] The server receives the address information, generates a message based on it asking "What is your annual income?" and sends it to the user's terminal.

[0052] Obtaining annual income information

[0053] The user terminal prompts the user to input annual income information, and when the user inputs their annual income, for example, "5 million yen," the input annual income information is sent to the server.

[0054] The server receives the annual income information and searches the database together with the address information to extract applicable support information.

[0055] Support information filtering

[0056] The server filters the support content based on address and annual income information and lists relevant support programs.

[0057] For example, if your address is Chiyoda-ku, Tokyo and your annual income is 5 million yen, the following support activities will be filtered:

[0058] xx Benefit: Up to 100,000 yen

[0059] xx Eco Points: Up to 30,000 points

[0060] Providing support

[0061] The server generates a list of the filtered support items and the corresponding documents required for application. For example, it generates the following information:

[0062] xx Benefit: Up to 100,000 yen

[0063] xx Eco Points: Up to 30,000 points

[0064] Required documents for application: Proof of address, Proof of income, Proof of identity

[0065] The server sends this information to the user terminal.

[0066] The user terminal displays the support information and necessary documents that have been sent to the user so that the user can check them.

[0067] Specific examples

[0068] 1. The user types "Tell me about the xx benefit" in the chat window and sends it.

[0069] 2. The server responds, "Please tell us where you live."

[0070] 3. The user enters "Chiyoda-ku, Tokyo" and submits.

[0071] 4. The server sends a message asking, "What is your annual income?"

[0072] 5. The user enters "5 million yen" and submits.

[0073] 6. The server searches for the relevant assistance and generates the following information:

[0074] xx Benefit: Up to 100,000 yen

[0075] xx Eco Points: Up to 30,000 points

[0076] Required documents for application: Proof of address, Proof of income, Proof of identity

[0077] 7. The server sends the above information to the user terminal.

[0078] 8. The user terminal displays the sent information and asks the user to confirm it.

[0079] In this way, the present invention enables users to easily obtain support information provided by local governments and smoothly make the necessary applications.

[0080] The processing flow will be explained below.

[0081] Step 1:

[0082] The user's device starts up, and the user enters a message in the chat window requesting information about local government support. For example, the user types, "Tell me about the xx subsidy," and sends it.

[0083] Step 2:

[0084] The server analyzes the request message received from the user terminal and generates a message requesting the address, which is the next required information. It then sends the message "Please tell me where you live" to the user terminal.

[0085] Step 3:

[0086] The user terminal receives the message sent from the server and prompts the user to enter address information. The user enters "Chiyoda-ku, Tokyo" and sends the message.

[0087] Step 4:

[0088] The server receives the address information from the user terminal, records it, and simultaneously generates a message requesting the next required piece of information, annual income, and sends the message "Please tell me your annual income" to the user terminal.

[0089] Step 5:

[0090] The user terminal receives the message sent from the server and prompts the user to enter their annual income information. The user enters "5 million yen" and submits the message.

[0091] Step 6:

[0092] The server receives and records annual income information from the user's device. It then searches the database based on the address and annual income information to identify support information for the relevant local government.

[0093] Step 7:

[0094] The server uses a generative AI model to filter the information on local government support obtained from the database, resulting in a list of support options that match the address and annual income.

[0095] Step 8:

[0096] The server generates a message containing the filtered support details and the document information required for application. For example, it contains information such as "xx benefit: up to 100,000 yen," "xx eco points: up to 30,000 points," and "documents required for application: address certificate, income certificate, and ID card."

[0097] Step 9:

[0098] The server transmits the generated information to the user terminal.

[0099] Step 10:

[0100] The user terminal receives the support information sent from the server and displays it to the user, who then checks the support information and necessary documents.

[0101] Example 1

[0102] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0103] In modern society, there is a demand for a means to quickly and accurately obtain a variety of support information provided by public organizations. However, many users do not know the proper procedures for searching for support information and applying for the necessary support. This makes the process of obtaining support information and applying for it cumbersome and difficult to proceed efficiently.

[0104] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0105] In this invention, the server includes means for providing a chat-style service using a generative algorithm model that provides information on public organization support based on a request message received from a user terminal, means for acquiring address information from the user, means for searching for support information from relevant public organizations based on the address information, means for acquiring income information from the user, means for filtering support content based on the address information and income information, and means for transmitting the filtered support content and document information required for application to the user terminal. This enables users to easily and efficiently acquire support information that suits their requirements and make appropriate applications.

[0106] "User terminal" refers to an electronic device that is directly operated by a user to input and receive information.

[0107] "Request message" refers to a message containing instructions sent by a terminal by a user seeking particular information or service.

[0108] "Generative algorithmic model" refers to an artificial intelligence technique used to generate an appropriate response to a given input.

[0109] "Chat-style service" means a service in which users and the system interact through text messages.

[0110] "Address information" refers to information indicating where a user lives.

[0111] "Public body" refers to a public organization such as a local government or government agency.

[0112] "Support information" refers to information about support such as subsidies and welfare benefits provided by public organizations.

[0113] "Income Information" refers to information regarding a User's income amount.

[0114] "Filtering" refers to the process of sorting and organizing information based on specific criteria.

[0115] "Documentation required for application" refers to the list of official documents required to receive a particular assistance.

[0116] MODE FOR CARRYING OUT THE INVENTION

[0117] The present invention is a chat-based public organization support service that utilizes a generative AI model and is a system that allows users to easily obtain public organization support information. This system receives input from a user's terminal and provides relevant support information based on that input. Specific embodiments of the present invention are described in detail below.

[0118] Hardware and software used

[0119] server:

[0120] Hardware: A server with a powerful CPU and sufficient memory (e.g., Intel Xeon, AMD EPYC)

[0121] Software: Web servers (e.g., Apache®, Nginx), databases (e.g., MySQL®, PostgreSQL), generative AI models (e.g., OpenAI® GPT-3®)

[0122] User device:

[0123] Hardware: Smartphones, tablets, PCs, etc.

[0124] Software: Web browser (e.g., Chrome, Firefox), chat interface (e.g., custom web app)

[0125] Detailed Description of the Invention

[0126] This system allows users to obtain public organization support information using a chat interface. Specifically, users enter and send a request message in the chat window. The server then uses a generative AI model to generate an appropriate response and prompts the user to enter the required information sequentially. Based on the response, the server filters the support information and finally provides the required information to the user's device.

[0127] Specific examples

[0128] 1. The user types "Tell me about the xx benefit" in the chat window and sends it.

[0129] 2. The server responds, "Where do you live?"

[0130] 3. The user enters "Chiyoda-ku, Tokyo" and submits.

[0131] 4. The server sends a message asking, "What is your annual income?"

[0132] 5. The user enters "5 million yen" and submits.

[0133] 6. The server searches for the relevant assistance and generates the following information:

[0134] xx Benefit: Up to 100,000 yen

[0135] xx Eco Points: Up to 30,000 points

[0136] Required documents for application: Proof of address, Proof of income, Proof of identity

[0137] 7. The server sends the above information to the user terminal.

[0138] 8. The user terminal displays the sent information and asks the user to confirm it.

[0139] By utilizing a generative AI model, this system can quickly and efficiently provide specific support information that users need. In addition, because it is easy for users to operate, they can obtain the necessary information without any hassle.

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1:

[0142] The user enters a request message in the chat window, such as "Tell me about the xx benefit," and sends it.

[0143] Specific action: The user types a text message through the chat interface and presses the send button.

[0144] Input: User request message "Tell me about xx benefits"

[0145] Output: The message is sent to the server

[0146] Step 2:

[0147] The server parses the request message received from the user and generates the prompt "Where do you live?"

[0148] What happens: The server uses the generative AI model to parse the request message and then generates the appropriate prompt to retrieve the required information.

[0149] Input: User request message "Tell me about xx benefits"

[0150] Data processing / calculation: Generative AI models are used to generate optimal prompts

[0151] Output: Prompt message "Where do you live?"

[0152] Step 3:

[0153] The server generates a prompt message and sends it to the user terminal.

[0154] Specific operation: The server performs network communication to send the generated message to the user terminal.

[0155] Input: Prompt message "Where do you live?"

[0156] Output: The message is displayed on the user's terminal.

[0157] Step 4:

[0158] The user terminal displays the received prompt message to the user.

[0159] What it does: A message from the server will be displayed in the chat interface.

[0160] Input: Prompt message sent from the server

[0161] Output: The user is prompted with "Where do you live?"

[0162] Step 5:

[0163] The user enters the address information "Chiyoda-ku, Tokyo" and submits it.

[0164] Specific behavior: The user enters address information in the chat window and presses the send button again.

[0165] Input: Address information "Chiyoda-ku, Tokyo"

[0166] Output: The message is sent to the server

[0167] Step 6:

[0168] The server parses the received address information and generates a prompt asking, "What is your annual income?"

[0169] Specific operation: The server analyzes the address information and then generates a message to obtain the required information (annual income).

[0170] Input: Address information "Chiyoda-ku, Tokyo"

[0171] Data processing / computation: Generate prompt messages using generative AI models

[0172] Output: Prompt message "What is your annual salary?"

[0173] Step 7:

[0174] The server generates a prompt message and sends it to the user terminal.

[0175] Specific operation: The server performs network communication to send the generated message to the user terminal.

[0176] Input: Prompt message "What is your annual salary?"

[0177] Output: The message is displayed on the user's terminal.

[0178] Step 8:

[0179] The user terminal displays the received prompt message to the user.

[0180] What it does: A message from the server will be displayed in the chat interface.

[0181] Input: Prompt message sent from the server

[0182] Output: The user is prompted with the message "What is your annual income?"

[0183] Step 9:

[0184] The user enters the annual income information "5 million yen" and submits it.

[0185] Specific behavior: The user enters annual salary information in the chat window and presses the send button again.

[0186] Input: Annual income information "5 million yen"

[0187] Output: The message is sent to the server

[0188] Step 10:

[0189] The server searches the database based on the received annual income information and address information and extracts the relevant support information.

[0190] Specific operation: The server checks the address information and annual income information against the database to search for the appropriate support program.

[0191] Input: Address information "Chiyoda-ku, Tokyo", Annual income information "5 million yen"

[0192] Data processing / calculation: Execute database queries to extract relevant support information

[0193] Output: Filtered support information list (e.g., xx grant up to 100,000 yen, xx eco points up to 30,000 points)

[0194] Step 11:

[0195] The server generates the filtered support content and document information required for application and sends it to the user's terminal.

[0196] Specific operation: The server creates a list of appropriate support information and documents required for application and sends it to the user's terminal in the form of a message.

[0197] Input: Filtered support information (xx benefit up to 100,000 yen, xx eco points up to 30,000 points)

[0198] Output: Support information and a list of required documents (Proof of Address, Proof of Income, Proof of Identity) are sent to the user's device.

[0199] Step 12:

[0200] The user terminal displays the received support information and required document information to the user.

[0201] Specific behavior: Support information and required documents will be displayed on the chat interface.

[0202] Input: Support information and required document list sent from the server

[0203] Output: User is presented with support information and required documentation

[0204] In this way, there are clear inputs and outputs at each step, and appropriate support information is provided to the user using a generative AI model and database search.

[0205] (Application example 1)

[0206] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0207] There is a problem that there is a lack of means for users to easily obtain information about local government support. In particular, there is a need for a means for customers in physical stores to quickly and accurately grasp the local government support information that applies to them. In order to obtain such information, various conditions must be met, and the process is complicated, which places a heavy burden on users.

[0208] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0209] In this invention, the server includes means for acquiring address information from a user, means for searching for support information from applicable local governments based on the address information, means for acquiring annual income information from the user, means for filtering support content based on the address information and annual income information, means for transmitting the filtered support content and document information required for application to a user terminal, and means for customers at physical stores to acquire support information from local governments using their smartphones or smart glasses. This allows customers to efficiently and quickly acquire applicable local government support information when they visit physical stores, thereby reducing the effort required for application procedures.

[0210] A "user terminal" is a device that a user directly operates to input and display information, and includes smartphones, smart glasses, and the like.

[0211] A "generative AI model" is an artificial intelligence model that generates appropriate answers based on user input, and is specialized in providing information on supporting local governments.

[0212] A "chat-style service" is a service that provides an interface for users and systems to exchange information in a dialogue format.

[0213] "Address information" is geographical data that a user inputs to indicate their place of residence.

[0214] "Support information" refers to information about grants, points, and other support programs provided by local governments.

[0215] "Annual income information" is data indicating the user's annual income.

[0216] "Filtering" is the process of extracting and selecting relevant information based on the user's specific criteria.

[0217] "Document information required for application" is a list of documents that must be submitted in order to receive local government support.

[0218] "Brick and mortar store" refers to a commercial establishment that exists in a physical location and can be visited by customers.

[0219] "Smart glasses" are eyeglass-type electronic devices worn by a user that can display or input information.

[0220] "Support details" refers to details of benefits, points, and other support programs provided as a result of filtering.

[0221] The present invention provides a system that enables users to easily obtain local government support information using a chat format that utilizes a generative AI model. Specific embodiments of this system are described in detail below.

[0222] Hardware and Software Configuration

[0223] This system is implemented using the following hardware and software:

[0224] User device: smartphone, smart glasses, or computer

[0225] Server: A computer server for hosting the database and generative AI models.

[0226] software:

[0227] Flask (Web framework)

[0228] Requests (a library for processing HTTP requests)

[0229] System operation flow

[0230] 1. Receiving the initial request:

[0231] The user terminal transmits a request message from the user (for example, "Tell me about xx benefit amount") to the server.

[0232] The server receives this request and sends a message to the user terminal saying "Please tell me where you live."

[0233] 2. Obtaining address information:

[0234] The user terminal provides an interface for the user to input address information, and when the user inputs "Chiyoda-ku, Tokyo," this is sent to the server.

[0235] 3. Obtaining annual income information:

[0236] The user terminal prompts the user to input annual income information, and when the user inputs "5 million yen," it sends this to the server.

[0237] 4. Filtering support information:

[0238] The server searches the database based on the address and annual income information and extracts the relevant support information.

[0239] 5. Provision of support:

[0240] The server generates the filtered support content and document information required for application and transmits them to the user terminal.

[0241] The user terminal displays the received information to the user so that the user can check it.

[0242] Specific examples

[0243] Below is a concrete example of a user using smart glasses in a brick-and-mortar store to obtain local government support information:

[0244] 1. The customer uses the voice command on their smart glasses to say, "Tell me about support information from the local government."

[0245] 2. The smart glasses display the message "Please tell us your address," and the customer answers by voice, "Chiyoda-ku, Tokyo."

[0246] 3. The smart glasses display the message, "Please tell us your annual income," and the customer answers by voice, "5 million yen."

[0247] 4. The smart glasses send the information to the server and search for the relevant support information.

[0248] 5. The server generates assistance information and sends it to the smart glasses.

[0249] 6. The smart glasses will display support information to the customer, including "xx benefit: up to 100,000 yen," "xx eco points: up to 30,000 points," and "Documents required for application: address proof, income proof, identification card."

[0250] This will allow customers to efficiently and quickly obtain applicable local government support information when they visit a physical store, reducing the hassle of the application process.

[0251] Prompt Sentence Examples

[0252] "Please tell me your address."

[0253] "Please tell me your annual income."

[0254] "Display relevant support information."

[0255] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0256] Step 1:

[0257] The user terminal receives a request message from the user (e.g., "Tell me about the xx benefit amount") as input. The terminal sends this message to the server. The server receives this request message, generates a message saying "Please tell me where you live" and sends it to the user terminal. This prompt sentence is intended to prompt the user for the next input.

[0258] Step 2:

[0259] The user terminal provides an interface for the user to input address information. When the user inputs the address information (e.g., "Chiyoda-ku, Tokyo"), it sends it to the server. The server receives the address information, generates a message based on it saying, "Please tell us your annual income," and sends it to the user terminal. This prepares the server to obtain the next input data.

[0260] Step 3:

[0261] The user terminal provides an interface for the user to input annual income information. When the user inputs the annual income information (e.g., "5 million yen"), it is sent to the server. The server receives the annual income information and searches the database based on this information along with the address information. This allows data processing to extract the relevant support information from the database.

[0262] Step 4:

[0263] The server searches for and filters the corresponding support information in the database based on the received address information and annual income information. For example, if the address is "Chiyoda-ku, Tokyo" and the annual income is "5 million yen," the server extracts support information that applies (e.g., "xx benefit: up to 100,000 yen," "xx eco points: up to 30,000 points"). The filtered information is then prepared for provision to the user.

[0264] Step 5:

[0265] The server generates the filtered support information and the corresponding document information required for the application (e.g., address certificate, income certificate, identity certificate), and sends this information to the user's terminal. The user's terminal displays the received information to the user so that they can confirm it. This output helps the user obtain the necessary local government support information and complete the application procedure.

[0266] Step 6:

[0267] When a user visits a physical store, they use smart glasses to obtain local government support information. When the user issues a voice command (e.g., "Tell me about local government support information"), the smart glasses send a request message to the server. The server generates information based on this request and displays it on the smart glasses. This allows the user to quickly obtain support information at the physical store.

[0268] Through these processing steps, users can efficiently and quickly obtain local government support information that is applicable to them.

[0269] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0270] MODE FOR CARRYING OUT THE INVENTION

[0271] The present invention relates to a chat-based local government support service that utilizes a generative AI model and further combines it with an emotion engine that recognizes the user's emotions to improve the user experience. This system includes a user terminal, a server, a generative AI model, and an emotion engine, and is implemented by the following specific processing steps.

[0272] Natural language explanation of program processing

[0273] Receiving the initial request

[0274] The user inputs a request message via the user terminal requesting information on local government support. For example, the user inputs "Tell me about xx benefits" and sends it.

[0275] The server receives this request message and sends the message "Please tell me where you live" to the user terminal. At the same time, the emotion engine analyzes the emotional tone of the user's input message.

[0276] Obtaining address information

[0277] The user terminal prompts the user to enter address information, and when the user enters the address, it sends it to the server. For example, the user enters "Chiyoda-ku, Tokyo."

[0278] The server receives the address information, generates a message based on it, such as "Please tell me your annual income," and sends it to the user's device. The emotion engine also analyzes and adapts the emotional tone of the user's input message at this stage.

[0279] Obtaining annual income information

[0280] The user terminal prompts the user to input annual income information, and when the user inputs their annual income, for example, "5 million yen," the input annual income information is sent to the server.

[0281] The server receives and records the annual income information. It searches the database based on the address and annual income information to extract applicable support information. The emotion engine optimizes the response message based on the user's emotional state.

[0282] Support information filtering

[0283] The server uses a generative AI model to filter the support content based on address and annual income information, and lists relevant support programs.

[0284] For example, if your address is Chiyoda-ku, Tokyo and your annual income is 5 million yen, the following support activities will be filtered:

[0285] xx Benefit: Up to 100,000 yen

[0286] xx Eco Points: Up to 30,000 points

[0287] Generating support content and responding to emotions

[0288] The server generates a list of the filtered support items and the corresponding documents required for application. For example, it generates the following information:

[0289] xx Benefit: Up to 100,000 yen

[0290] xx Eco Points: Up to 30,000 points

[0291] Required documents for application: Proof of address, Proof of income, Proof of identity

[0292] The emotion engine adds customization to the generated response based on the user's emotional state, for example, if the user is feeling anxious, it generates an additional message such as "Don't worry, this information is official."

[0293] Providing and responding to support

[0294] The server sends this information to the user terminal.

[0295] The user terminal displays the support information and necessary documents sent to the user for the user to confirm, and also displays a response message customized by the emotion engine.

[0296] Specific examples

[0297] 1. The user types "Tell me about the xx benefit" in the chat window and sends it.

[0298] 2. The server responds with, "Please tell me where you live." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "interested."

[0299] 3. The user enters "Chiyoda-ku, Tokyo" and submits.

[0300] 4. The server sends the message "Please tell me your annual income." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "in a bit of a hurry."

[0301] 5. The user enters "5 million yen" and submits.

[0302] 6. The server searches for the relevant assistance and generates the following information:

[0303] xx Benefit: Up to 100,000 yen

[0304] xx Eco Points: Up to 30,000 points

[0305] Required documents for application: Proof of address, Proof of income, Proof of identity

[0306] The sentiment engine adds a message to reassure users: "Don't worry, this information is official."

[0307] 7. The server sends the above information to the user terminal.

[0308] 8. The user device displays the information sent, along with a customized message to reassure the user.

[0309] By combining a generative AI model and an emotion engine, the present invention provides a system that allows users to easily and safely obtain local government support information.

[0310] The processing flow will be explained below.

[0311] Step 1:

[0312] The user's device starts up, and the user enters a message in the chat window requesting information about local government support. For example, the user types, "Tell me about the xx subsidy," and sends it.

[0313] Step 2:

[0314] The server analyzes the request message received from the user device and generates a message requesting the address, which is the next required information. It sends the message "Please tell me where you live" to the user device. At the same time, the emotion engine analyzes the emotional tone of the user's input message.

[0315] Step 3:

[0316] The user terminal receives the message sent from the server and prompts the user to enter address information. The user enters "Chiyoda-ku, Tokyo" and sends the message.

[0317] Step 4:

[0318] The server receives address information from the user's device and records it. At the same time, it generates a message requesting the next required piece of information, annual income, and sends the message "Please tell me your annual income" to the user's device. At this stage, the emotion engine also analyzes the emotional tone of the user's input message and responds by conveying a sense of "friendliness" and "comfort."

[0319] Step 5:

[0320] The user terminal receives the message sent from the server and prompts the user to enter their annual income information. The user enters "5 million yen" and submits the message.

[0321] Step 6:

[0322] The server receives and records annual income information from the user's device. It searches a database based on the address and annual income information to extract applicable support information. The emotion engine optimizes the response message based on the user's emotional state.

[0323] Step 7:

[0324] The server uses a generative AI model to filter the information on local government support obtained from the database, resulting in a list of support options that match the address and annual income.

[0325] Step 8:

[0326] The server generates the filtered support content and document information required for application, and uses an emotion engine to reinforce messages based on the user's emotional state, for example, adding a message such as "Don't worry, this information is official."

[0327] Step 9:

[0328] The server transmits the generated information to the user terminal.

[0329] Step 10:

[0330] The user terminal displays the support information and necessary documents sent from the server to the user, along with the emotion-responsive message, and the user confirms the support information and necessary documents.

[0331] Example 2

[0332] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0333] Currently, many local government support services do not take the user's emotional state into consideration when providing information, resulting in a uniform user experience. Furthermore, there is a need to provide more personalized services by understanding the user's emotions during the support information provision process and providing appropriate feedback accordingly.

[0334] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring address information from the user, means for searching for support information for the relevant local government based on the address information, and means for acquiring annual income information from the user. This improves the user experience and makes it possible to provide appropriate local government support information. Furthermore, by including means including an emotion engine that analyzes the user's emotional state and means for generating a customized response according to the user's emotion using the emotion engine, it is possible to provide a personalized service that allows the user to acquire local government support information with peace of mind.

[0335] A "user terminal" is a device through which a user inputs information and communicates with a server or other system.

[0336] A "request message" is a text message sent by a user requesting particular information or services.

[0337] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to generate information based on specific prompts.

[0338] "Local government support information" refers to information on various types of support provided by local governments, such as grants and point programs.

[0339] An "emotion engine" is software or a system for analyzing a user's input message and inferring their emotional state.

[0340] "Address information" is information that indicates the geographical location where the user lives.

[0341] "Annual income information" is information indicating the user's annual income.

[0342] "Filtering" is the process of sorting or narrowing down information based on specific criteria.

[0343] "Document information required for application" is a list of documents that must be submitted to receive specific assistance.

[0344] A "customized response" is a personalized response message that is generated based on the user's emotional state or specific situation.

[0345] "Error Message" means a notification message that is displayed if the information entered is invalid or incorrect.

[0346] The present invention relates to a chat-based local government support service that utilizes a generative AI model and further combines it with an emotion engine that recognizes the user's emotions to improve the user experience. This system includes a user terminal, a server, a generative AI model, and an emotion engine, and is implemented by the following specific processing steps.

[0347] Hardware and software used

[0348] User devices: communication devices such as smartphones, tablets, and PCs

[0349] Server: Cloud server or on-premise server

[0350] Generative AI model: An AI model that enables natural language processing

[0351] Emotion Engine: Software that analyzes the emotional tone of users' messages

[0352] Specific processing method of the system

[0353] The user inputs a request message into the chat window via the user terminal, requesting information about local government support. For example, they input "Tell me about xx subsidies" and send it. This request message is sent to the server.

[0354] The server receives the user's request message, generates an initial response message saying "Please tell me where you live" and sends it to the user's device. At the same time, the emotion engine analyzes the emotional tone of the request message. For example, at this stage, the emotion engine determines the user's emotion as "interested."

[0355] The user enters address information in the chat window and sends it. For example, they enter "Chiyoda-ku, Tokyo." The terminal then sends the entered address information to the server.

[0356] The server receives the address information, generates a message saying, "Please tell me your annual income," and sends it to the user's device. The emotion engine also analyzes the user's emotional tone at this stage and determines that the user is "in a bit of a hurry."

[0357] The user then enters and submits their annual income information. For example, they enter "5 million yen." The terminal then sends the annual income information to the server.

[0358] The server searches the database based on annual income and address information to extract applicable support information. During this search process, the generative AI model is used to filter the support content. For example, the following support content will be filtered for a user who lives in Chiyoda Ward, Tokyo, and has an annual income of 5 million yen:

[0359] xx Benefit: Up to 100,000 yen

[0360] xx Eco Points: Up to 30,000 points

[0361] The server generates a list of the filtered support items and the corresponding documents required for the application. For example, it generates the following information:

[0362] xx Benefit: Up to 100,000 yen

[0363] xx Eco Points: Up to 30,000 points

[0364] Required documents for application: Proof of address, Proof of income, Proof of identity

[0365] Based on the generated response, the emotion engine adds a customized message depending on the user's emotional state: if the user is feeling anxious, it generates a message like "Don't worry, this information is official."

[0366] The server sends the generated support details, required document list, and customized message to the user's terminal, which displays this information for the user to check.

[0367] Examples of prompt statements

[0368] User: "Tell me about the xx benefit."

[0369] Server: "Where do you live?"

[0370] User: "Chiyoda-ku, Tokyo"

[0371] Server: "What is your annual salary?"

[0372] User: "5 million yen"

[0373] Server: "xx Benefit: Up to 100,000 yen, xx Eco Points: Up to 30,000 points, Documents required for application: Address proof, Income proof, ID card, Rest assured, this information is official."

[0374] By combining a generative AI model and an emotion engine, the present invention provides a system that allows users to easily and safely obtain local government support information.

[0375] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0376] Step 1:

[0377] The user uses the user terminal to input a request message into the chat window requesting information about local government support. The specific prompt text is "Tell me about the xx benefit." This is the input.

[0378] The terminal sends the user's request message to the server. The output is the request message.

[0379] Step 2:

[0380] The server receives the user's request message, which is the input.

[0381] As an initial response, the server generates a message saying "Please tell me where you live" and sends it to the user's device. At the same time, the emotion engine analyzes the emotional tone of the request message and determines that the user is "interested." This analysis result is also saved as data. The output is the response message and the emotional tone analysis result.

[0382] Step 3:

[0383] The terminal displays the response message received from the server to the user. The input is the response message from the server. The user is shown "Please tell me where you live."

[0384] The user enters address information into the chat window and submits it. For example, they enter "Chiyoda-ku, Tokyo." This becomes the input data.

[0385] The terminal sends the input address information to the server, and the output is the address information.

[0386] Step 4:

[0387] The server receives the address information. The input data is the address information.

[0388] Based on the received address information, the server generates a message asking "What is your annual income?" and sends it to the user's device. The emotion engine also analyzes the user's emotional tone and determines that the user is "in a bit of a hurry." This analysis result is also saved. The output is a message inquiring about annual income and the emotional tone analysis result.

[0389] Step 5:

[0390] The terminal displays messages received from the server to the user, and the input is the message sent by the server.

[0391] The user enters their annual income information into the chat window and submits it. For example, they enter "5 million yen." This is the input data.

[0392] The terminal sends annual income information to the server, and the output is annual income information.

[0393] Step 6:

[0394] The server receives the annual income information. The input data is the annual income information.

[0395] The server searches the local government support database based on the received annual income and address information. It processes the data and performs search operations to extract relevant support information from the database. The emotion engine also analyzes the user's emotional tone and prepares appropriate feedback. The output is the filtered support information and the results of the emotional tone analysis.

[0396] Step 7:

[0397] The server uses the generative AI model to generate filtered support content and a list of documents required for the corresponding application. The input data is the filtered support information.

[0398] For example, the following will be generated:

[0399] xx Benefit: Up to 100,000 yen

[0400] xx Eco Points: Up to 30,000 points

[0401] Required documents for application: Proof of address, Proof of income, Proof of identity

[0402] A customized response from the emotion engine is added to this information. For example, if it determines that the user is feeling anxious, the message "Don't worry, this information is official" is added. The output is the generated support information, a list of required documents, and a customized message.

[0403] Step 8:

[0404] The server transmits the generated support information, required document list, and customized message to the user terminal. The input data are the generated support information, required document list, and customized message.

[0405] The terminal receives this information and displays it to the user, and the output is support information and customized messages.

[0406] (Application example 2)

[0407] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0408] With the current local government support information system, users have to spend time searching for information and understanding the information required for applications, and they are prone to becoming frustrated when error messages appear when the information they enter is inappropriate. Furthermore, users often feel uneasy when making payments or other electronic transactions, which contributes to a poor user experience. In these circumstances, there is a need for a system that allows users to use the service without feeling burdened and with peace of mind.

[0409] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for providing a chat-style service using a generative AI model that provides information on local government support based on a request message received from a user terminal, means for acquiring address information from the user, means for searching for support information for the relevant local government based on the address information, means for acquiring annual income information from the user, means for filtering support content based on the address information and annual income information, means for transmitting the filtered support content and document information required for application to the user terminal, and means for analyzing the user's emotional state in real time and generating a response message according to the results. This makes it possible to provide a system that allows users to conduct transactions and obtain information with peace of mind.

[0410] A "user terminal" is a device that a user uses to input and receive information, and includes smartphones, tablets, personal computers, and the like.

[0411] A "generative AI model" is an artificial intelligence model trained using large datasets to generate appropriate responses to user requests.

[0412] "Emotional state" refers to the emotional state analyzed from the user's input, facial expression, voice, etc., and includes, for example, relief, anxiety, interest, etc.

[0413] A "chat-style service" is a service in which a user and a system communicate in a text-based, interactive format.

[0414] "Address information" is information for identifying the user's place of residence, and includes, for example, city, ward, town, village, area name, and the like.

[0415] "Local government support information" is information about various types of support and services provided by local governments, including grants, subsidies, eco-points, etc.

[0416] "Annual income information" is information indicating the user's annual income, and is used to determine the scope of application of the assistance program.

[0417] "Filtering" refers to the process of selecting and narrowing down information based on specific conditions, and is a means of providing appropriate information to users.

[0418] "Information about documents required for application" is information showing a list of documents that must be submitted when applying for a support program.

[0419] An "error message" is a message that is displayed when there is an error in the information entered by the user, and is displayed to prompt the user to make appropriate corrections.

[0420] "Means for analyzing the user's emotional state in real time" refers to technology that instantly analyzes the user's input content, facial expressions, etc., and grasps their emotional state.

[0421] This invention relates to a system that uses a generative AI model to provide information on local government support, and analyzes the user's emotional state in real time to improve the user experience. The system mainly includes a user terminal, a server, a generative AI model, and an emotion engine.

[0422] System configuration

[0423] 1. User Device:

[0424] A device that allows users to input and receive information, including smartphones, tablets, and PCs.

[0425] 2. Server:

[0426] We use generative AI models using multiple methods to provide local government support information.

[0427] 3. Generative AI Model:

[0428] It is an artificial intelligence model trained using large datasets to generate appropriate responses to user requests.

[0429] 4. Emotion Engine:

[0430] It is an engine that analyzes the emotional state from the user's input, facial expressions, voice, etc. For example, it uses Google® Cloud Natural Language API, Microsoft® Azure® Text Analytics service, OpenCV, AWS® Rekognition, etc.

[0431] Data Flow and Processing

[0432] 1. Receiving the initial request:

[0433] A user inputs a specific request message via the user terminal. When a user wants to know specific information, for example, they input and send "Tell me about xx benefits." The server receives this request message and then sends the required information (for example, address) to the user terminal, while the emotion engine analyzes the emotional tone of the user's input message.

[0434] 2. Obtaining address information:

[0435] The user device prompts the user to enter address information, and once the user has entered the address, it sends that information to the server. The server receives the address information and sends the next required information (e.g., annual income) to the user device based on that information. The emotion engine also analyzes the emotional tone of the user's input message at this stage.

[0436] 3. Obtaining annual income information:

[0437] The user device prompts the user to enter their annual income information, which is then sent to the server. The server receives the information and filters out local government support information based on the address and income information. The emotion engine optimizes the response message according to the user's emotional state.

[0438] 4. Providing support information:

[0439] The server generates a list of the filtered support content and the corresponding documents required for application, and then sends it to the user's device along with a customized message based on the results of sentiment analysis, allowing the user to obtain information with greater peace of mind.

[0440] Specific examples

[0441] The user types "Tell me about the xx benefit" in the chat window and sends it.

[0442] The server responds with, "Please tell me where you live." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "interested."

[0443] The user enters "Chiyoda-ku, Tokyo" and submits.

[0444] The server sends the message "Please tell me your annual income." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "in a bit of a hurry."

[0445] The user enters "5 million yen" and submits.

[0446] The server searches for the relevant assistance and generates the following information:

[0447] xx Benefit: Up to 100,000 yen

[0448] xx Eco Points: Up to 30,000 points

[0449] Required documents for application: Proof of address, Proof of income, Proof of identity

[0450] The sentiment engine adds a message to reassure users: "Don't worry, this information is official."

[0451] The server sends the above information to the user terminal.

[0452] The user's device displays the transmitted information, along with a customized message to reassure the user.

[0453] Examples of prompt statements

[0454] The user's emotional tone was analyzed as "anxious."

[0455] The current transaction is for a settlement of 10,000 yen.

[0456] Generate appropriate feedback messages.

[0457] This system allows users to conduct transactions with peace of mind and makes obtaining local government support information easy and safe.

[0458] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0459] Step 1:

[0460] The user inputs a request message via the user terminal. For example, the user inputs and sends the message "Tell me about the xx benefit amount." This message becomes the initial request message of the system. The input data is the user's request, and the request message is sent to the server as output.

[0461] Step 2:

[0462] The server receives a request message from the user, then generates a message asking for the required information (e.g., address) and sends it to the user terminal. At the same time, the emotion engine analyzes the emotional tone of the user's request message. The input data is the user's request message, and the generated message and emotional tone are included as outputs.

[0463] Step 3:

[0464] The user terminal displays a message from the server and allows the user to input address information. For example, the user inputs "Chiyoda-ku, Tokyo." The input data is the user's address information, and the address information is sent to the server as output.

[0465] Step 4:

[0466] The server receives the address information and generates a message based on it, asking for the next required information (e.g., annual income), and sends it to the user's device. The emotion engine also analyzes the emotional tone of the user's input message at this stage. The input data is the user's address information, and the output includes the address information and the generated message.

[0467] Step 5:

[0468] The user terminal displays a message from the server and allows the user to input annual income information. For example, enter "5 million yen." The input data is the user's annual income information, and the annual income information is sent to the server as output.

[0469] Step 6:

[0470] The server receives and records the annual income information. It then searches a database of local government support information based on the address and annual income information to extract applicable support information. The emotion engine optimizes the response message based on the user's emotional state. The input data is address information and annual income information, and the output includes filtered support information.

[0471] Step 7:

[0472] The server generates a list of filtered support content and the corresponding documents required for application. It generates a customized message based on the results of sentiment analysis and sends it to the user's terminal. The input data is the filtered support content and the results of sentiment analysis, and the output includes the generated message and application document information.

[0473] Step 8:

[0474] The user terminal displays the information sent from the server, including the filtered support content, document information required for application, and response messages customized by the emotion engine. The input data is the message generated by the server, and the output is displayed to the user. The user confirms the information and feels reassured.

[0475] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0476] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0477] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0478] [Second embodiment]

[0479] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0480] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0481] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0482] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0483] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0484] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0485] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0486] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0487] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0488] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0489] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0490] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0491] MODE FOR CARRYING OUT THE INVENTION

[0492] The present invention is a chat-based local government support service that utilizes a generative AI model and is a system that allows users to easily obtain local government support information. This system receives input from a user's terminal and provides relevant support information based on that input. Specific embodiments of the present invention are described in detail below.

[0493] Natural language explanation of program processing

[0494] Receiving the initial request

[0495] The user sends a request message via the user terminal requesting information about local government support, for example, by typing "Tell me about xx subsidies."

[0496] The server receives this request message and sends a message to the user terminal saying "Please tell us where you live."

[0497] Obtaining address information

[0498] The user terminal prompts the user to enter address information, and when the user enters the address, it sends it to the server. For example, the user enters "Chiyoda-ku, Tokyo."

[0499] The server receives the address information, generates a message based on it asking "What is your annual income?" and sends it to the user's terminal.

[0500] Obtaining annual income information

[0501] The user terminal prompts the user to input annual income information, and when the user inputs their annual income, for example, "5 million yen," the input annual income information is sent to the server.

[0502] The server receives the annual income information and searches the database together with the address information to extract applicable support information.

[0503] Support information filtering

[0504] The server filters the support content based on address and annual income information and lists relevant support programs.

[0505] For example, if your address is Chiyoda-ku, Tokyo and your annual income is 5 million yen, the following support activities will be filtered:

[0506] xx Benefit: Up to 100,000 yen

[0507] xx Eco Points: Up to 30,000 points

[0508] Providing support

[0509] The server generates a list of the filtered support items and the corresponding documents required for application. For example, it generates the following information:

[0510] xx Benefit: Up to 100,000 yen

[0511] xx Eco Points: Up to 30,000 points

[0512] Required documents for application: Proof of address, Proof of income, Proof of identity

[0513] The server sends this information to the user terminal.

[0514] The user terminal displays the support information and necessary documents that have been sent to the user so that the user can check them.

[0515] Specific examples

[0516] 1. The user types "Tell me about the xx benefit" in the chat window and sends it.

[0517] 2. The server responds, "Please tell us where you live."

[0518] 3. The user enters "Chiyoda-ku, Tokyo" and submits.

[0519] 4. The server sends a message asking, "What is your annual income?"

[0520] 5. The user enters "5 million yen" and submits.

[0521] 6. The server searches for the relevant assistance and generates the following information:

[0522] xx Benefit: Up to 100,000 yen

[0523] xx Eco Points: Up to 30,000 points

[0524] Required documents for application: Proof of address, Proof of income, Proof of identity

[0525] 7. The server sends the above information to the user terminal.

[0526] 8. The user terminal displays the sent information and asks the user to confirm it.

[0527] In this way, the present invention enables users to easily obtain support information provided by local governments and smoothly make the necessary applications.

[0528] The processing flow will be explained below.

[0529] Step 1:

[0530] The user's device starts up, and the user enters a message in the chat window requesting information about local government support. For example, the user types, "Tell me about the xx subsidy," and sends it.

[0531] Step 2:

[0532] The server analyzes the request message received from the user terminal and generates a message requesting the address, which is the next required information. It then sends the message "Please tell me where you live" to the user terminal.

[0533] Step 3:

[0534] The user terminal receives the message sent from the server and prompts the user to enter address information. The user enters "Chiyoda-ku, Tokyo" and sends the message.

[0535] Step 4:

[0536] The server receives the address information from the user terminal, records it, and simultaneously generates a message requesting the next required piece of information, annual income, and sends the message "Please tell me your annual income" to the user terminal.

[0537] Step 5:

[0538] The user terminal receives the message sent from the server and prompts the user to enter their annual income information. The user enters "5 million yen" and submits the message.

[0539] Step 6:

[0540] The server receives and records annual income information from the user's device. It then searches the database based on the address and annual income information to identify support information for the relevant local government.

[0541] Step 7:

[0542] The server uses a generative AI model to filter the information on local government support obtained from the database, resulting in a list of support options that match the address and annual income.

[0543] Step 8:

[0544] The server generates a message containing the filtered support details and the document information required for application. For example, it contains information such as "xx benefit: up to 100,000 yen," "xx eco points: up to 30,000 points," and "documents required for application: address certificate, income certificate, and ID card."

[0545] Step 9:

[0546] The server transmits the generated information to the user terminal.

[0547] Step 10:

[0548] The user terminal receives the support information sent from the server and displays it to the user, who then checks the support information and necessary documents.

[0549] Example 1

[0550] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0551] In modern society, there is a demand for a means to quickly and accurately obtain a variety of support information provided by public organizations. However, many users do not know the proper procedures for searching for support information and applying for the necessary support. This makes the process of obtaining support information and applying for it cumbersome and difficult to proceed efficiently.

[0552] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0553] In this invention, the server includes means for providing a chat-style service using a generative algorithm model that provides information on public organization support based on a request message received from a user terminal, means for acquiring address information from the user, means for searching for support information from relevant public organizations based on the address information, means for acquiring income information from the user, means for filtering support content based on the address information and income information, and means for transmitting the filtered support content and document information required for application to the user terminal. This enables users to easily and efficiently acquire support information that suits their requirements and make appropriate applications.

[0554] "User terminal" refers to an electronic device that is directly operated by a user to input and receive information.

[0555] "Request message" refers to a message containing instructions sent by a terminal by a user seeking particular information or service.

[0556] "Generative algorithmic model" refers to an artificial intelligence technique used to generate an appropriate response to a given input.

[0557] "Chat-style service" means a service in which users and the system interact through text messages.

[0558] "Address information" refers to information indicating where a user lives.

[0559] "Public body" refers to a public organization such as a local government or government agency.

[0560] "Support information" refers to information about support such as subsidies and welfare benefits provided by public organizations.

[0561] "Income Information" refers to information regarding a User's income amount.

[0562] "Filtering" refers to the process of sorting and organizing information based on specific criteria.

[0563] "Documentation required for application" refers to the list of official documents required to receive a particular assistance.

[0564] MODE FOR CARRYING OUT THE INVENTION

[0565] The present invention is a chat-based public organization support service that utilizes a generative AI model and is a system that allows users to easily obtain public organization support information. This system receives input from a user's terminal and provides relevant support information based on that input. Specific embodiments of the present invention are described in detail below.

[0566] Hardware and software used

[0567] server:

[0568] Hardware: A server with a powerful CPU and sufficient memory (e.g., Intel Xeon, AMD EPYC)

[0569] Software: Web servers (e.g., Apache, Nginx), databases (e.g., MySQL, PostgreSQL), generative AI models (e.g., OpenAI GPT-3)

[0570] User device:

[0571] Hardware: Smartphones, tablets, PCs, etc.

[0572] Software: Web browser (e.g., Chrome, Firefox), chat interface (e.g., custom web app)

[0573] Detailed Description of the Invention

[0574] This system allows users to obtain public organization support information using a chat interface. Specifically, users enter and send a request message in the chat window. The server then uses a generative AI model to generate an appropriate response and prompts the user to enter the required information sequentially. Based on the response, the server filters the support information and finally provides the required information to the user's device.

[0575] Specific examples

[0576] 1. The user types "Tell me about the xx benefit" in the chat window and sends it.

[0577] 2. The server responds, "Where do you live?"

[0578] 3. The user enters "Chiyoda-ku, Tokyo" and submits.

[0579] 4. The server sends a message asking, "What is your annual income?"

[0580] 5. The user enters "5 million yen" and submits.

[0581] 6. The server searches for the relevant assistance and generates the following information:

[0582] xx Benefit: Up to 100,000 yen

[0583] xx Eco Points: Up to 30,000 points

[0584] Required documents for application: Proof of address, Proof of income, Proof of identity

[0585] 7. The server sends the above information to the user terminal.

[0586] 8. The user terminal displays the sent information and asks the user to confirm it.

[0587] By utilizing a generative AI model, this system can quickly and efficiently provide specific support information that users need. In addition, because it is easy for users to operate, they can obtain the necessary information without any hassle.

[0588] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0589] Step 1:

[0590] The user enters a request message in the chat window, such as "Tell me about the xx benefit," and sends it.

[0591] Specific action: The user types a text message through the chat interface and presses the send button.

[0592] Input: User request message "Tell me about xx benefits"

[0593] Output: The message is sent to the server

[0594] Step 2:

[0595] The server parses the request message received from the user and generates the prompt "Where do you live?"

[0596] What happens: The server uses the generative AI model to parse the request message and then generates the appropriate prompt to retrieve the required information.

[0597] Input: User request message "Tell me about xx benefits"

[0598] Data processing / calculation: Generative AI models are used to generate optimal prompts

[0599] Output: Prompt message "Where do you live?"

[0600] Step 3:

[0601] The server generates a prompt message and sends it to the user terminal.

[0602] Specific operation: The server performs network communication to send the generated message to the user terminal.

[0603] Input: Prompt message "Where do you live?"

[0604] Output: The message is displayed on the user's terminal.

[0605] Step 4:

[0606] The user terminal displays the received prompt message to the user.

[0607] What it does: A message from the server will be displayed in the chat interface.

[0608] Input: Prompt message sent from the server

[0609] Output: The user is prompted with "Where do you live?"

[0610] Step 5:

[0611] The user enters the address information "Chiyoda-ku, Tokyo" and submits it.

[0612] Specific behavior: The user enters address information in the chat window and presses the send button again.

[0613] Input: Address information "Chiyoda-ku, Tokyo"

[0614] Output: The message is sent to the server

[0615] Step 6:

[0616] The server parses the received address information and generates a prompt asking, "What is your annual income?"

[0617] Specific operation: The server analyzes the address information and then generates a message to obtain the required information (annual income).

[0618] Input: Address information "Chiyoda-ku, Tokyo"

[0619] Data processing / computation: Generate prompt messages using generative AI models

[0620] Output: Prompt message "What is your annual salary?"

[0621] Step 7:

[0622] The server generates a prompt message and sends it to the user terminal.

[0623] Specific operation: The server performs network communication to send the generated message to the user terminal.

[0624] Input: Prompt message "What is your annual salary?"

[0625] Output: The message is displayed on the user's terminal.

[0626] Step 8:

[0627] The user terminal displays the received prompt message to the user.

[0628] What it does: A message from the server will be displayed in the chat interface.

[0629] Input: Prompt message sent from the server

[0630] Output: The user is prompted with the message "What is your annual income?"

[0631] Step 9:

[0632] The user enters the annual income information "5 million yen" and submits it.

[0633] Specific behavior: The user enters annual salary information in the chat window and presses the send button again.

[0634] Input: Annual income information "5 million yen"

[0635] Output: The message is sent to the server

[0636] Step 10:

[0637] The server searches the database based on the received annual income information and address information and extracts the relevant support information.

[0638] Specific operation: The server checks the address information and annual income information against the database to search for the appropriate support program.

[0639] Input: Address information "Chiyoda-ku, Tokyo", Annual income information "5 million yen"

[0640] Data processing / calculation: Execute database queries to extract relevant support information

[0641] Output: Filtered support information list (e.g., xx grant up to 100,000 yen, xx eco points up to 30,000 points)

[0642] Step 11:

[0643] The server generates the filtered support content and document information required for application and sends it to the user's terminal.

[0644] Specific operation: The server creates a list of appropriate support information and documents required for application and sends it to the user's terminal in the form of a message.

[0645] Input: Filtered support information (xx benefit up to 100,000 yen, xx eco points up to 30,000 points)

[0646] Output: Support information and a list of required documents (Proof of Address, Proof of Income, Proof of Identity) are sent to the user's device.

[0647] Step 12:

[0648] The user terminal displays the received support information and required document information to the user.

[0649] Specific behavior: Support information and required documents will be displayed on the chat interface.

[0650] Input: Support information and required document list sent from the server

[0651] Output: User is presented with support information and required documentation

[0652] In this way, there are clear inputs and outputs at each step, and appropriate support information is provided to the user using a generative AI model and database search.

[0653] (Application example 1)

[0654] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0655] There is a problem that there is a lack of means for users to easily obtain information about local government support. In particular, there is a need for a means for customers in physical stores to quickly and accurately grasp the local government support information that applies to them. In order to obtain such information, various conditions must be met, and the process is complicated, which places a heavy burden on users.

[0656] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0657] In this invention, the server includes means for acquiring address information from a user, means for searching for support information from applicable local governments based on the address information, means for acquiring annual income information from the user, means for filtering support content based on the address information and annual income information, means for transmitting the filtered support content and document information required for application to a user terminal, and means for customers at physical stores to acquire support information from local governments using their smartphones or smart glasses. This allows customers to efficiently and quickly acquire applicable local government support information when they visit physical stores, thereby reducing the effort required for application procedures.

[0658] A "user terminal" is a device that a user directly operates to input and display information, and includes smartphones, smart glasses, and the like.

[0659] A "generative AI model" is an artificial intelligence model that generates appropriate answers based on user input, and is specialized in providing information on supporting local governments.

[0660] A "chat-style service" is a service that provides an interface for users and systems to exchange information in a dialogue format.

[0661] "Address information" is geographical data that a user inputs to indicate their place of residence.

[0662] "Support information" refers to information about grants, points, and other support programs provided by local governments.

[0663] "Annual income information" is data indicating the user's annual income.

[0664] "Filtering" is the process of extracting and selecting relevant information based on the user's specific criteria.

[0665] "Document information required for application" is a list of documents that must be submitted in order to receive local government support.

[0666] "Brick and mortar store" refers to a commercial establishment that exists in a physical location and can be visited by customers.

[0667] "Smart glasses" are eyeglass-type electronic devices worn by a user that can display or input information.

[0668] "Support details" refers to details of benefits, points, and other support programs provided as a result of filtering.

[0669] The present invention provides a system that enables users to easily obtain local government support information using a chat format that utilizes a generative AI model. Specific embodiments of this system are described in detail below.

[0670] Hardware and Software Configuration

[0671] This system is implemented using the following hardware and software:

[0672] User device: smartphone, smart glasses, or computer

[0673] Server: A computer server for hosting the database and generative AI models.

[0674] software:

[0675] Flask (Web framework)

[0676] Requests (a library for processing HTTP requests)

[0677] System operation flow

[0678] 1. Receiving the initial request:

[0679] The user terminal transmits a request message from the user (for example, "Tell me about xx benefit amount") to the server.

[0680] The server receives this request and sends a message to the user terminal saying "Please tell me where you live."

[0681] 2. Obtaining address information:

[0682] The user terminal provides an interface for the user to input address information, and when the user inputs "Chiyoda-ku, Tokyo," this is sent to the server.

[0683] 3. Obtaining annual income information:

[0684] The user terminal prompts the user to input annual income information, and when the user inputs "5 million yen," it sends this to the server.

[0685] 4. Filtering support information:

[0686] The server searches the database based on the address and annual income information and extracts the relevant support information.

[0687] 5. Provision of support:

[0688] The server generates the filtered support content and document information required for application and transmits them to the user terminal.

[0689] The user terminal displays the received information to the user so that the user can check it.

[0690] Specific examples

[0691] Below is a concrete example of a user using smart glasses in a brick-and-mortar store to obtain local government support information:

[0692] 1. The customer uses the voice command on their smart glasses to say, "Tell me about support information from the local government."

[0693] 2. The smart glasses display the message "Please tell us your address," and the customer answers by voice, "Chiyoda-ku, Tokyo."

[0694] 3. The smart glasses display the message, "Please tell us your annual income," and the customer answers by voice, "5 million yen."

[0695] 4. The smart glasses send the information to the server and search for the relevant support information.

[0696] 5. The server generates assistance information and sends it to the smart glasses.

[0697] 6. The smart glasses will display support information to the customer, including "xx benefit: up to 100,000 yen," "xx eco points: up to 30,000 points," and "Documents required for application: address proof, income proof, identification card."

[0698] This will allow customers to efficiently and quickly obtain applicable local government support information when they visit a physical store, reducing the hassle of the application process.

[0699] Prompt Sentence Examples

[0700] "Please tell me your address."

[0701] "Please tell me your annual income."

[0702] "Display relevant support information."

[0703] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0704] Step 1:

[0705] The user terminal receives a request message from the user (e.g., "Tell me about the xx benefit amount") as input. The terminal sends this message to the server. The server receives this request message, generates a message saying "Please tell me where you live" and sends it to the user terminal. This prompt sentence is intended to prompt the user for the next input.

[0706] Step 2:

[0707] The user terminal provides an interface for the user to input address information. When the user inputs the address information (e.g., "Chiyoda-ku, Tokyo"), it sends it to the server. The server receives the address information, generates a message based on it saying, "Please tell us your annual income," and sends it to the user terminal. This prepares the server to obtain the next input data.

[0708] Step 3:

[0709] The user terminal provides an interface for the user to input annual income information. When the user inputs the annual income information (e.g., "5 million yen"), it is sent to the server. The server receives the annual income information and searches the database based on this information along with the address information. This allows data processing to extract the relevant support information from the database.

[0710] Step 4:

[0711] The server searches for and filters the corresponding support information in the database based on the received address information and annual income information. For example, if the address is "Chiyoda-ku, Tokyo" and the annual income is "5 million yen," the server extracts support information that applies (e.g., "xx benefit: up to 100,000 yen," "xx eco points: up to 30,000 points"). The filtered information is then prepared for provision to the user.

[0712] Step 5:

[0713] The server generates the filtered support information and the corresponding document information required for the application (e.g., address certificate, income certificate, identity certificate), and sends this information to the user's terminal. The user's terminal displays the received information to the user so that they can confirm it. This output helps the user obtain the necessary local government support information and complete the application procedure.

[0714] Step 6:

[0715] When a user visits a physical store, they use smart glasses to obtain local government support information. When the user issues a voice command (e.g., "Tell me about local government support information"), the smart glasses send a request message to the server. The server generates information based on this request and displays it on the smart glasses. This allows the user to quickly obtain support information at the physical store.

[0716] Through these processing steps, users can efficiently and quickly obtain local government support information that is applicable to them.

[0717] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0718] MODE FOR CARRYING OUT THE INVENTION

[0719] The present invention relates to a chat-based local government support service that utilizes a generative AI model and further combines it with an emotion engine that recognizes the user's emotions to improve the user experience. This system includes a user terminal, a server, a generative AI model, and an emotion engine, and is implemented by the following specific processing steps.

[0720] Natural language explanation of program processing

[0721] Receiving the initial request

[0722] The user inputs a request message via the user terminal requesting information on local government support. For example, the user inputs "Tell me about xx benefits" and sends it.

[0723] The server receives this request message and sends the message "Please tell me where you live" to the user terminal. At the same time, the emotion engine analyzes the emotional tone of the user's input message.

[0724] Obtaining address information

[0725] The user terminal prompts the user to enter address information, and when the user enters the address, it sends it to the server. For example, the user enters "Chiyoda-ku, Tokyo."

[0726] The server receives the address information, generates a message based on it, such as "Please tell me your annual income," and sends it to the user's device. The emotion engine also analyzes and adapts the emotional tone of the user's input message at this stage.

[0727] Obtaining annual income information

[0728] The user terminal prompts the user to input annual income information, and when the user inputs their annual income, for example, "5 million yen," the input annual income information is sent to the server.

[0729] The server receives and records the annual income information. It searches the database based on the address and annual income information to extract applicable support information. The emotion engine optimizes the response message based on the user's emotional state.

[0730] Support information filtering

[0731] The server uses a generative AI model to filter the support content based on address and annual income information, and lists relevant support programs.

[0732] For example, if your address is Chiyoda-ku, Tokyo and your annual income is 5 million yen, the following support activities will be filtered:

[0733] xx Benefit: Up to 100,000 yen

[0734] xx Eco Points: Up to 30,000 points

[0735] Generating support content and responding to emotions

[0736] The server generates a list of the filtered support items and the corresponding documents required for application. For example, it generates the following information:

[0737] xx Benefit: Up to 100,000 yen

[0738] xx Eco Points: Up to 30,000 points

[0739] Required documents for application: Proof of address, Proof of income, Proof of identity

[0740] The emotion engine adds customization to the generated response based on the user's emotional state, for example, if the user is feeling anxious, it generates an additional message such as "Don't worry, this information is official."

[0741] Providing and responding to support

[0742] The server sends this information to the user terminal.

[0743] The user terminal displays the support information and necessary documents sent to the user for the user to confirm, and also displays a response message customized by the emotion engine.

[0744] Specific examples

[0745] 1. The user types "Tell me about the xx benefit" in the chat window and sends it.

[0746] 2. The server responds with, "Please tell me where you live." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "interested."

[0747] 3. The user enters "Chiyoda-ku, Tokyo" and submits.

[0748] 4. The server sends the message "Please tell me your annual income." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "in a bit of a hurry."

[0749] 5. The user enters "5 million yen" and submits.

[0750] 6. The server searches for the relevant assistance and generates the following information:

[0751] xx Benefit: Up to 100,000 yen

[0752] xx Eco Points: Up to 30,000 points

[0753] Required documents for application: Proof of address, Proof of income, Proof of identity

[0754] The sentiment engine adds a message to reassure users: "Don't worry, this information is official."

[0755] 7. The server sends the above information to the user terminal.

[0756] 8. The user device displays the information sent, along with a customized message to reassure the user.

[0757] By combining a generative AI model and an emotion engine, the present invention provides a system that allows users to easily and safely obtain local government support information.

[0758] The processing flow will be explained below.

[0759] Step 1:

[0760] The user's device starts up, and the user enters a message in the chat window requesting information about local government support. For example, the user types, "Tell me about the xx subsidy," and sends it.

[0761] Step 2:

[0762] The server analyzes the request message received from the user device and generates a message requesting the address, which is the next required information. It sends the message "Please tell me where you live" to the user device. At the same time, the emotion engine analyzes the emotional tone of the user's input message.

[0763] Step 3:

[0764] The user terminal receives the message sent from the server and prompts the user to enter address information. The user enters "Chiyoda-ku, Tokyo" and sends the message.

[0765] Step 4:

[0766] The server receives address information from the user's device and records it. At the same time, it generates a message requesting the next required piece of information, annual income, and sends the message "Please tell me your annual income" to the user's device. At this stage, the emotion engine also analyzes the emotional tone of the user's input message and responds by conveying a sense of "friendliness" and "comfort."

[0767] Step 5:

[0768] The user terminal receives the message sent from the server and prompts the user to enter their annual income information. The user enters "5 million yen" and submits the message.

[0769] Step 6:

[0770] The server receives and records annual income information from the user's device. It searches a database based on the address and annual income information to extract applicable support information. The emotion engine optimizes the response message based on the user's emotional state.

[0771] Step 7:

[0772] The server uses a generative AI model to filter the information on local government support obtained from the database, resulting in a list of support options that match the address and annual income.

[0773] Step 8:

[0774] The server generates the filtered support content and document information required for application, and uses an emotion engine to reinforce messages based on the user's emotional state, for example, adding a message such as "Don't worry, this information is official."

[0775] Step 9:

[0776] The server transmits the generated information to the user terminal.

[0777] Step 10:

[0778] The user terminal displays the support information and necessary documents sent from the server to the user, along with the emotion-responsive message, and the user confirms the support information and necessary documents.

[0779] Example 2

[0780] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0781] Currently, many local government support services do not take the user's emotional state into consideration when providing information, resulting in a uniform user experience. Furthermore, there is a need to provide more personalized services by understanding the user's emotions during the support information provision process and providing appropriate feedback accordingly.

[0782] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring address information from the user, means for searching for support information for the relevant local government based on the address information, and means for acquiring annual income information from the user. This improves the user experience and makes it possible to provide appropriate local government support information. Furthermore, by including means including an emotion engine that analyzes the user's emotional state and means for generating a customized response according to the user's emotion using the emotion engine, it is possible to provide a personalized service that allows the user to acquire local government support information with peace of mind.

[0783] A "user terminal" is a device through which a user inputs information and communicates with a server or other system.

[0784] A "request message" is a text message sent by a user requesting particular information or services.

[0785] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to generate information based on specific prompts.

[0786] "Local government support information" refers to information on various types of support provided by local governments, such as grants and point programs.

[0787] An "emotion engine" is software or a system for analyzing a user's input message and inferring their emotional state.

[0788] "Address information" is information that indicates the geographical location where the user lives.

[0789] "Annual income information" is information indicating the user's annual income.

[0790] "Filtering" is the process of sorting or narrowing down information based on specific criteria.

[0791] "Document information required for application" is a list of documents that must be submitted to receive specific assistance.

[0792] A "customized response" is a personalized response message that is generated based on the user's emotional state or specific situation.

[0793] "Error Message" means a notification message that is displayed if the information entered is invalid or incorrect.

[0794] The present invention relates to a chat-based local government support service that utilizes a generative AI model and further combines it with an emotion engine that recognizes the user's emotions to improve the user experience. This system includes a user terminal, a server, a generative AI model, and an emotion engine, and is implemented by the following specific processing steps.

[0795] Hardware and software used

[0796] User devices: communication devices such as smartphones, tablets, and PCs

[0797] Server: Cloud server or on-premise server

[0798] Generative AI model: An AI model that enables natural language processing

[0799] Emotion Engine: Software that analyzes the emotional tone of users' messages

[0800] Specific processing method of the system

[0801] The user inputs a request message into the chat window via the user terminal, requesting information about local government support. For example, they input "Tell me about xx subsidies" and send it. This request message is sent to the server.

[0802] The server receives the user's request message, generates an initial response message saying "Please tell me where you live" and sends it to the user's device. At the same time, the emotion engine analyzes the emotional tone of the request message. For example, at this stage, the emotion engine determines the user's emotion as "interested."

[0803] The user enters address information in the chat window and sends it. For example, they enter "Chiyoda-ku, Tokyo." The terminal then sends the entered address information to the server.

[0804] The server receives the address information, generates a message saying, "Please tell me your annual income," and sends it to the user's device. The emotion engine also analyzes the user's emotional tone at this stage and determines that the user is "in a bit of a hurry."

[0805] The user then enters and submits their annual income information. For example, they enter "5 million yen." The terminal then sends the annual income information to the server.

[0806] The server searches the database based on annual income and address information to extract applicable support information. During this search process, the generative AI model is used to filter the support content. For example, the following support content will be filtered for a user who lives in Chiyoda Ward, Tokyo, and has an annual income of 5 million yen:

[0807] xx Benefit: Up to 100,000 yen

[0808] xx Eco Points: Up to 30,000 points

[0809] The server generates a list of the filtered support items and the corresponding documents required for the application. For example, it generates the following information:

[0810] xx Benefit: Up to 100,000 yen

[0811] xx Eco Points: Up to 30,000 points

[0812] Required documents for application: Proof of address, Proof of income, Proof of identity

[0813] Based on the generated response, the emotion engine adds a customized message depending on the user's emotional state: if the user is feeling anxious, it generates a message like "Don't worry, this information is official."

[0814] The server sends the generated support details, required document list, and customized message to the user's terminal, which displays this information for the user to check.

[0815] Examples of prompt statements

[0816] User: "Tell me about the xx benefit."

[0817] Server: "Where do you live?"

[0818] User: "Chiyoda-ku, Tokyo"

[0819] Server: "What is your annual salary?"

[0820] User: "5 million yen"

[0821] Server: "xx Benefit: Up to 100,000 yen, xx Eco Points: Up to 30,000 points, Documents required for application: Address proof, Income proof, ID card, Rest assured, this information is official."

[0822] By combining a generative AI model and an emotion engine, the present invention provides a system that allows users to easily and safely obtain local government support information.

[0823] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0824] Step 1:

[0825] The user uses the user terminal to input a request message into the chat window requesting information about local government support. The specific prompt text is "Tell me about the xx benefit." This is the input.

[0826] The terminal sends the user's request message to the server. The output is the request message.

[0827] Step 2:

[0828] The server receives the user's request message, which is the input.

[0829] As an initial response, the server generates a message saying "Please tell me where you live" and sends it to the user's device. At the same time, the emotion engine analyzes the emotional tone of the request message and determines that the user is "interested." This analysis result is also saved as data. The output is the response message and the emotional tone analysis result.

[0830] Step 3:

[0831] The terminal displays the response message received from the server to the user. The input is the response message from the server. The user is shown "Please tell me where you live."

[0832] The user enters address information into the chat window and submits it. For example, they enter "Chiyoda-ku, Tokyo." This becomes the input data.

[0833] The terminal sends the input address information to the server, and the output is the address information.

[0834] Step 4:

[0835] The server receives the address information. The input data is the address information.

[0836] Based on the received address information, the server generates a message asking "What is your annual income?" and sends it to the user's device. The emotion engine also analyzes the user's emotional tone and determines that the user is "in a bit of a hurry." This analysis result is also saved. The output is a message inquiring about annual income and the emotional tone analysis result.

[0837] Step 5:

[0838] The terminal displays messages received from the server to the user, and the input is the message sent by the server.

[0839] The user enters their annual income information into the chat window and submits it. For example, they enter "5 million yen." This is the input data.

[0840] The terminal sends annual income information to the server, and the output is annual income information.

[0841] Step 6:

[0842] The server receives the annual income information. The input data is the annual income information.

[0843] The server searches the local government support database based on the received annual income and address information. It processes the data and performs search operations to extract relevant support information from the database. The emotion engine also analyzes the user's emotional tone and prepares appropriate feedback. The output is the filtered support information and the results of the emotional tone analysis.

[0844] Step 7:

[0845] The server uses the generative AI model to generate filtered support content and a list of documents required for the corresponding application. The input data is the filtered support information.

[0846] For example, the following will be generated:

[0847] xx Benefit: Up to 100,000 yen

[0848] xx Eco Points: Up to 30,000 points

[0849] Required documents for application: Proof of address, Proof of income, Proof of identity

[0850] A customized response from the emotion engine is added to this information. For example, if it determines that the user is feeling anxious, the message "Don't worry, this information is official" is added. The output is the generated support information, a list of required documents, and a customized message.

[0851] Step 8:

[0852] The server transmits the generated support information, required document list, and customized message to the user terminal. The input data are the generated support information, required document list, and customized message.

[0853] The terminal receives this information and displays it to the user, and the output is support information and customized messages.

[0854] (Application example 2)

[0855] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0856] With the current local government support information system, users have to spend time searching for information and understanding the information required for applications, and they are prone to becoming frustrated when error messages appear when the information they enter is inappropriate. Furthermore, users often feel uneasy when making payments or other electronic transactions, which contributes to a poor user experience. In these circumstances, there is a need for a system that allows users to use the service without feeling burdened and with peace of mind.

[0857] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for providing a chat-style service using a generative AI model that provides information on local government support based on a request message received from a user terminal, means for acquiring address information from the user, means for searching for support information for the relevant local government based on the address information, means for acquiring annual income information from the user, means for filtering support content based on the address information and annual income information, means for transmitting the filtered support content and document information required for application to the user terminal, and means for analyzing the user's emotional state in real time and generating a response message according to the results. This makes it possible to provide a system that allows users to conduct transactions and obtain information with peace of mind.

[0858] A "user terminal" is a device that a user uses to input and receive information, and includes smartphones, tablets, personal computers, and the like.

[0859] A "generative AI model" is an artificial intelligence model trained using large datasets to generate appropriate responses to user requests.

[0860] "Emotional state" refers to the emotional state analyzed from the user's input, facial expression, voice, etc., and includes, for example, relief, anxiety, interest, etc.

[0861] A "chat-style service" is a service in which a user and a system communicate in a text-based, interactive format.

[0862] "Address information" is information for identifying the user's place of residence, and includes, for example, city, ward, town, village, area name, and the like.

[0863] "Local government support information" is information about various types of support and services provided by local governments, including grants, subsidies, eco-points, etc.

[0864] "Annual income information" is information indicating the user's annual income, and is used to determine the scope of application of the assistance program.

[0865] "Filtering" refers to the process of selecting and narrowing down information based on specific conditions, and is a means of providing appropriate information to users.

[0866] "Information about documents required for application" is information showing a list of documents that must be submitted when applying for a support program.

[0867] An "error message" is a message that is displayed when there is an error in the information entered by the user, and is displayed to prompt the user to make appropriate corrections.

[0868] "Means for analyzing the user's emotional state in real time" refers to technology that instantly analyzes the user's input content, facial expressions, etc., and grasps their emotional state.

[0869] This invention relates to a system that uses a generative AI model to provide information on local government support, and analyzes the user's emotional state in real time to improve the user experience. The system mainly includes a user terminal, a server, a generative AI model, and an emotion engine.

[0870] System configuration

[0871] 1. User Device:

[0872] A device that allows users to input and receive information, including smartphones, tablets, and PCs.

[0873] 2. Server:

[0874] We use generative AI models using multiple methods to provide local government support information.

[0875] 3. Generative AI Model:

[0876] It is an artificial intelligence model trained using large datasets to generate appropriate responses to user requests.

[0877] 4. Emotion Engine:

[0878] It is an engine that analyzes emotional states from user input, facial expressions, voice, etc. It uses, for example, Google Cloud Natural Language API, Microsoft Azure Text Analytics service, OpenCV, AWS Rekognition, etc.

[0879] Data Flow and Processing

[0880] 1. Receiving the initial request:

[0881] A user inputs a specific request message via the user terminal. When a user wants to know specific information, for example, they input and send "Tell me about xx benefits." The server receives this request message and then sends the required information (for example, address) to the user terminal, while the emotion engine analyzes the emotional tone of the user's input message.

[0882] 2. Obtaining address information:

[0883] The user device prompts the user to enter address information, and once the user has entered the address, it sends that information to the server. The server receives the address information and sends the next required information (e.g., annual income) to the user device based on that information. The emotion engine also analyzes the emotional tone of the user's input message at this stage.

[0884] 3. Obtaining annual income information:

[0885] The user device prompts the user to enter their annual income information, which is then sent to the server. The server receives the information and filters out local government support information based on the address and income information. The emotion engine optimizes the response message according to the user's emotional state.

[0886] 4. Providing support information:

[0887] The server generates a list of the filtered support content and the corresponding documents required for application, and then sends it to the user's device along with a customized message based on the results of sentiment analysis, allowing the user to obtain information with greater peace of mind.

[0888] Specific examples

[0889] The user types "Tell me about the xx benefit" in the chat window and sends it.

[0890] The server responds with, "Please tell me where you live." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "interested."

[0891] The user enters "Chiyoda-ku, Tokyo" and submits.

[0892] The server sends the message "Please tell me your annual income." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "in a bit of a hurry."

[0893] The user enters "5 million yen" and submits.

[0894] The server searches for the relevant assistance and generates the following information:

[0895] xx Benefit: Up to 100,000 yen

[0896] xx Eco Points: Up to 30,000 points

[0897] Required documents for application: Proof of address, Proof of income, Proof of identity

[0898] The sentiment engine adds a message to reassure users: "Don't worry, this information is official."

[0899] The server sends the above information to the user terminal.

[0900] The user's device displays the transmitted information, along with a customized message to reassure the user.

[0901] Examples of prompt statements

[0902] The user's emotional tone was analyzed as "anxious."

[0903] The current transaction is for a settlement of 10,000 yen.

[0904] Generate appropriate feedback messages.

[0905] This system allows users to conduct transactions with peace of mind and makes obtaining local government support information easy and safe.

[0906] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0907] Step 1:

[0908] The user inputs a request message via the user terminal. For example, the user inputs and sends the message "Tell me about the xx benefit amount." This message becomes the initial request message of the system. The input data is the user's request, and the request message is sent to the server as output.

[0909] Step 2:

[0910] The server receives a request message from the user, then generates a message asking for the required information (e.g., address) and sends it to the user terminal. At the same time, the emotion engine analyzes the emotional tone of the user's request message. The input data is the user's request message, and the generated message and emotional tone are included as outputs.

[0911] Step 3:

[0912] The user terminal displays a message from the server and allows the user to input address information. For example, the user inputs "Chiyoda-ku, Tokyo." The input data is the user's address information, and the address information is sent to the server as output.

[0913] Step 4:

[0914] The server receives the address information and generates a message based on it, asking for the next required information (e.g., annual income), and sends it to the user's device. The emotion engine also analyzes the emotional tone of the user's input message at this stage. The input data is the user's address information, and the output includes the address information and the generated message.

[0915] Step 5:

[0916] The user terminal displays a message from the server and allows the user to input annual income information. For example, enter "5 million yen." The input data is the user's annual income information, and the annual income information is sent to the server as output.

[0917] Step 6:

[0918] The server receives and records the annual income information. It then searches a database of local government support information based on the address and annual income information to extract applicable support information. The emotion engine optimizes the response message based on the user's emotional state. The input data is address information and annual income information, and the output includes filtered support information.

[0919] Step 7:

[0920] The server generates a list of filtered support content and the corresponding documents required for application. It generates a customized message based on the results of sentiment analysis and sends it to the user's terminal. The input data is the filtered support content and the results of sentiment analysis, and the output includes the generated message and application document information.

[0921] Step 8:

[0922] The user terminal displays the information sent from the server, including the filtered support content, document information required for application, and response messages customized by the emotion engine. The input data is the message generated by the server, and the output is displayed to the user. The user confirms the information and feels reassured.

[0923] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0924] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0925] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0926] [Third embodiment]

[0927] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0928] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0929] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0930] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0931] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0932] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0933] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0934] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0935] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0936] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0937] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0938] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0939] MODE FOR CARRYING OUT THE INVENTION

[0940] The present invention is a chat-based local government support service that utilizes a generative AI model and is a system that allows users to easily obtain local government support information. This system receives input from a user's terminal and provides relevant support information based on that input. Specific embodiments of the present invention are described in detail below.

[0941] Natural language explanation of program processing

[0942] Receiving the initial request

[0943] The user sends a request message via the user terminal requesting information about local government support, for example, by typing "Tell me about xx subsidies."

[0944] The server receives this request message and sends a message to the user terminal saying "Please tell us where you live."

[0945] Obtaining address information

[0946] The user terminal prompts the user to enter address information, and when the user enters the address, it sends it to the server. For example, the user enters "Chiyoda-ku, Tokyo."

[0947] The server receives the address information, generates a message based on it asking "What is your annual income?" and sends it to the user's terminal.

[0948] Obtaining annual income information

[0949] The user terminal prompts the user to input annual income information, and when the user inputs their annual income, for example, "5 million yen," the input annual income information is sent to the server.

[0950] The server receives the annual income information and searches the database together with the address information to extract applicable support information.

[0951] Support information filtering

[0952] The server filters the support content based on address and annual income information and lists relevant support programs.

[0953] For example, if your address is Chiyoda-ku, Tokyo and your annual income is 5 million yen, the following support activities will be filtered:

[0954] xx Benefit: Up to 100,000 yen

[0955] xx Eco Points: Up to 30,000 points

[0956] Providing support

[0957] The server generates a list of the filtered support items and the corresponding documents required for application. For example, it generates the following information:

[0958] xx Benefit: Up to 100,000 yen

[0959] xx Eco Points: Up to 30,000 points

[0960] Required documents for application: Proof of address, Proof of income, Proof of identity

[0961] The server sends this information to the user terminal.

[0962] The user terminal displays the support information and necessary documents that have been sent to the user so that the user can check them.

[0963] Specific examples

[0964] 1. The user types "Tell me about the xx benefit" in the chat window and sends it.

[0965] 2. The server responds, "Please tell us where you live."

[0966] 3. The user enters "Chiyoda-ku, Tokyo" and submits.

[0967] 4. The server sends a message asking, "What is your annual income?"

[0968] 5. The user enters "5 million yen" and submits.

[0969] 6. The server searches for the relevant assistance and generates the following information:

[0970] xx Benefit: Up to 100,000 yen

[0971] xx Eco Points: Up to 30,000 points

[0972] Required documents for application: Proof of address, Proof of income, Proof of identity

[0973] 7. The server sends the above information to the user terminal.

[0974] 8. The user terminal displays the sent information and asks the user to confirm it.

[0975] In this way, the present invention enables users to easily obtain support information provided by local governments and smoothly make the necessary applications.

[0976] The processing flow will be explained below.

[0977] Step 1:

[0978] The user's device starts up, and the user enters a message in the chat window requesting information about local government support. For example, the user types, "Tell me about the xx subsidy," and sends it.

[0979] Step 2:

[0980] The server analyzes the request message received from the user terminal and generates a message requesting the address, which is the next required information. It then sends the message "Please tell me where you live" to the user terminal.

[0981] Step 3:

[0982] The user terminal receives the message sent from the server and prompts the user to enter address information. The user enters "Chiyoda-ku, Tokyo" and sends the message.

[0983] Step 4:

[0984] The server receives the address information from the user terminal, records it, and simultaneously generates a message requesting the next required piece of information, annual income, and sends the message "Please tell me your annual income" to the user terminal.

[0985] Step 5:

[0986] The user terminal receives the message sent from the server and prompts the user to enter their annual income information. The user enters "5 million yen" and submits the message.

[0987] Step 6:

[0988] The server receives and records annual income information from the user's device. It then searches the database based on the address and annual income information to identify support information for the relevant local government.

[0989] Step 7:

[0990] The server uses a generative AI model to filter the information on local government support obtained from the database, resulting in a list of support options that match the address and annual income.

[0991] Step 8:

[0992] The server generates a message containing the filtered support details and the document information required for application. For example, it contains information such as "xx benefit: up to 100,000 yen," "xx eco points: up to 30,000 points," and "documents required for application: address certificate, income certificate, and ID card."

[0993] Step 9:

[0994] The server transmits the generated information to the user terminal.

[0995] Step 10:

[0996] The user terminal receives the support information sent from the server and displays it to the user, who then checks the support information and necessary documents.

[0997] Example 1

[0998] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0999] In modern society, there is a demand for a means to quickly and accurately obtain a variety of support information provided by public organizations. However, many users do not know the proper procedures for searching for support information and applying for the necessary support. This makes the process of obtaining support information and applying for it cumbersome and difficult to proceed efficiently.

[1000] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1001] In this invention, the server includes means for providing a chat-style service using a generative algorithm model that provides information on public organization support based on a request message received from a user terminal, means for acquiring address information from the user, means for searching for support information from relevant public organizations based on the address information, means for acquiring income information from the user, means for filtering support content based on the address information and income information, and means for transmitting the filtered support content and document information required for application to the user terminal. This enables users to easily and efficiently acquire support information that suits their requirements and make appropriate applications.

[1002] "User terminal" refers to an electronic device that is directly operated by a user to input and receive information.

[1003] "Request message" refers to a message containing instructions sent by a terminal by a user seeking particular information or service.

[1004] "Generative algorithmic model" refers to an artificial intelligence technique used to generate an appropriate response to a given input.

[1005] "Chat-style service" means a service in which users and the system interact through text messages.

[1006] "Address information" refers to information indicating where a user lives.

[1007] "Public body" refers to a public organization such as a local government or government agency.

[1008] "Support information" refers to information about support such as subsidies and welfare benefits provided by public organizations.

[1009] "Income Information" refers to information regarding a User's income amount.

[1010] "Filtering" refers to the process of sorting and organizing information based on specific criteria.

[1011] "Documentation required for application" refers to the list of official documents required to receive a particular assistance.

[1012] MODE FOR CARRYING OUT THE INVENTION

[1013] The present invention is a chat-based public organization support service that utilizes a generative AI model and is a system that allows users to easily obtain public organization support information. This system receives input from a user's terminal and provides relevant support information based on that input. Specific embodiments of the present invention are described in detail below.

[1014] Hardware and software used

[1015] server:

[1016] Hardware: A server with a powerful CPU and sufficient memory (e.g., Intel Xeon, AMD EPYC)

[1017] Software: Web servers (e.g., Apache, Nginx), databases (e.g., MySQL, PostgreSQL), generative AI models (e.g., OpenAI GPT-3)

[1018] User device:

[1019] Hardware: Smartphones, tablets, PCs, etc.

[1020] Software: Web browser (e.g., Chrome, Firefox), chat interface (e.g., custom web app)

[1021] Detailed Description of the Invention

[1022] This system allows users to obtain public organization support information using a chat interface. Specifically, users enter and send a request message in the chat window. The server then uses a generative AI model to generate an appropriate response and prompts the user to enter the required information sequentially. Based on the response, the server filters the support information and finally provides the required information to the user's device.

[1023] Specific examples

[1024] 1. The user types "Tell me about the xx benefit" in the chat window and sends it.

[1025] 2. The server responds, "Where do you live?"

[1026] 3. The user enters "Chiyoda-ku, Tokyo" and submits.

[1027] 4. The server sends a message asking, "What is your annual income?"

[1028] 5. The user enters "5 million yen" and submits.

[1029] 6. The server searches for the relevant assistance and generates the following information:

[1030] xx Benefit: Up to 100,000 yen

[1031] xx Eco Points: Up to 30,000 points

[1032] Required documents for application: Proof of address, Proof of income, Proof of identity

[1033] 7. The server sends the above information to the user terminal.

[1034] 8. The user terminal displays the sent information and asks the user to confirm it.

[1035] By utilizing a generative AI model, this system can quickly and efficiently provide specific support information that users need. In addition, because it is easy for users to operate, they can obtain the necessary information without any hassle.

[1036] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1037] Step 1:

[1038] The user enters a request message in the chat window, such as "Tell me about the xx benefit," and sends it.

[1039] Specific action: The user types a text message through the chat interface and presses the send button.

[1040] Input: User request message "Tell me about xx benefits"

[1041] Output: The message is sent to the server

[1042] Step 2:

[1043] The server parses the request message received from the user and generates the prompt "Where do you live?"

[1044] What happens: The server uses the generative AI model to parse the request message and then generates the appropriate prompt to retrieve the required information.

[1045] Input: User request message "Tell me about xx benefits"

[1046] Data processing / calculation: Generative AI models are used to generate optimal prompts

[1047] Output: Prompt message "Where do you live?"

[1048] Step 3:

[1049] The server generates a prompt message and sends it to the user terminal.

[1050] Specific operation: The server performs network communication to send the generated message to the user terminal.

[1051] Input: Prompt message "Where do you live?"

[1052] Output: The message is displayed on the user's terminal.

[1053] Step 4:

[1054] The user terminal displays the received prompt message to the user.

[1055] What it does: A message from the server will be displayed in the chat interface.

[1056] Input: Prompt message sent from the server

[1057] Output: The user is prompted with "Where do you live?"

[1058] Step 5:

[1059] The user enters the address information "Chiyoda-ku, Tokyo" and submits it.

[1060] Specific behavior: The user enters address information in the chat window and presses the send button again.

[1061] Input: Address information "Chiyoda-ku, Tokyo"

[1062] Output: The message is sent to the server

[1063] Step 6:

[1064] The server parses the received address information and generates a prompt asking, "What is your annual income?"

[1065] Specific operation: The server analyzes the address information and then generates a message to obtain the required information (annual income).

[1066] Input: Address information "Chiyoda-ku, Tokyo"

[1067] Data processing / computation: Generate prompt messages using generative AI models

[1068] Output: Prompt message "What is your annual salary?"

[1069] Step 7:

[1070] The server generates a prompt message and sends it to the user terminal.

[1071] Specific operation: The server performs network communication to send the generated message to the user terminal.

[1072] Input: Prompt message "What is your annual salary?"

[1073] Output: The message is displayed on the user's terminal.

[1074] Step 8:

[1075] The user terminal displays the received prompt message to the user.

[1076] What it does: A message from the server will be displayed in the chat interface.

[1077] Input: Prompt message sent from the server

[1078] Output: The user is prompted with the message "What is your annual income?"

[1079] Step 9:

[1080] The user enters the annual income information "5 million yen" and submits it.

[1081] Specific behavior: The user enters annual salary information in the chat window and presses the send button again.

[1082] Input: Annual income information "5 million yen"

[1083] Output: The message is sent to the server

[1084] Step 10:

[1085] The server searches the database based on the received annual income information and address information and extracts the relevant support information.

[1086] Specific operation: The server checks the address information and annual income information against the database to search for the appropriate support program.

[1087] Input: Address information "Chiyoda-ku, Tokyo", Annual income information "5 million yen"

[1088] Data processing / calculation: Execute database queries to extract relevant support information

[1089] Output: Filtered support information list (e.g., xx grant up to 100,000 yen, xx eco points up to 30,000 points)

[1090] Step 11:

[1091] The server generates the filtered support content and document information required for application and sends it to the user's terminal.

[1092] Specific operation: The server creates a list of appropriate support information and documents required for application and sends it to the user's terminal in the form of a message.

[1093] Input: Filtered support information (xx benefit up to 100,000 yen, xx eco points up to 30,000 points)

[1094] Output: Support information and a list of required documents (Proof of Address, Proof of Income, Proof of Identity) are sent to the user's device.

[1095] Step 12:

[1096] The user terminal displays the received support information and required document information to the user.

[1097] Specific behavior: Support information and required documents will be displayed on the chat interface.

[1098] Input: Support information and required document list sent from the server

[1099] Output: User is presented with support information and required documentation

[1100] In this way, there are clear inputs and outputs at each step, and appropriate support information is provided to the user using a generative AI model and database search.

[1101] (Application example 1)

[1102] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1103] There is a problem that there is a lack of means for users to easily obtain information about local government support. In particular, there is a need for a means for customers in physical stores to quickly and accurately grasp the local government support information that applies to them. In order to obtain such information, various conditions must be met, and the process is complicated, which places a heavy burden on users.

[1104] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1105] In this invention, the server includes means for acquiring address information from a user, means for searching for support information from applicable local governments based on the address information, means for acquiring annual income information from the user, means for filtering support content based on the address information and annual income information, means for transmitting the filtered support content and document information required for application to a user terminal, and means for customers at physical stores to acquire support information from local governments using their smartphones or smart glasses. This allows customers to efficiently and quickly acquire applicable local government support information when they visit physical stores, thereby reducing the effort required for application procedures.

[1106] A "user terminal" is a device that a user directly operates to input and display information, and includes smartphones, smart glasses, and the like.

[1107] A "generative AI model" is an artificial intelligence model that generates appropriate answers based on user input, and is specialized in providing information on supporting local governments.

[1108] A "chat-style service" is a service that provides an interface for users and systems to exchange information in a dialogue format.

[1109] "Address information" is geographical data that a user inputs to indicate their place of residence.

[1110] "Support information" refers to information about grants, points, and other support programs provided by local governments.

[1111] "Annual income information" is data indicating the user's annual income.

[1112] "Filtering" is the process of extracting and selecting relevant information based on the user's specific criteria.

[1113] "Document information required for application" is a list of documents that must be submitted in order to receive local government support.

[1114] "Brick and mortar store" refers to a commercial establishment that exists in a physical location and can be visited by customers.

[1115] "Smart glasses" are eyeglass-type electronic devices worn by a user that can display or input information.

[1116] "Support details" refers to details of benefits, points, and other support programs provided as a result of filtering.

[1117] The present invention provides a system that enables users to easily obtain local government support information using a chat format that utilizes a generative AI model. Specific embodiments of this system are described in detail below.

[1118] Hardware and Software Configuration

[1119] This system is implemented using the following hardware and software:

[1120] User device: smartphone, smart glasses, or computer

[1121] Server: A computer server for hosting the database and generative AI models.

[1122] software:

[1123] Flask (Web framework)

[1124] Requests (a library for processing HTTP requests)

[1125] System operation flow

[1126] 1. Receiving the initial request:

[1127] The user terminal transmits a request message from the user (for example, "Tell me about xx benefit amount") to the server.

[1128] The server receives this request and sends a message to the user terminal saying "Please tell me where you live."

[1129] 2. Obtaining address information:

[1130] The user terminal provides an interface for the user to input address information, and when the user inputs "Chiyoda-ku, Tokyo," this is sent to the server.

[1131] 3. Obtaining annual income information:

[1132] The user terminal prompts the user to input annual income information, and when the user inputs "5 million yen," it sends this to the server.

[1133] 4. Filtering support information:

[1134] The server searches the database based on the address and annual income information and extracts the relevant support information.

[1135] 5. Provision of support:

[1136] The server generates the filtered support content and document information required for application and transmits them to the user terminal.

[1137] The user terminal displays the received information to the user so that the user can check it.

[1138] Specific examples

[1139] Below is a concrete example of a user using smart glasses in a brick-and-mortar store to obtain local government support information:

[1140] 1. The customer uses the voice command on their smart glasses to say, "Tell me about support information from the local government."

[1141] 2. The smart glasses display the message "Please tell us your address," and the customer answers by voice, "Chiyoda-ku, Tokyo."

[1142] 3. The smart glasses display the message, "Please tell us your annual income," and the customer answers by voice, "5 million yen."

[1143] 4. The smart glasses send the information to the server and search for the relevant support information.

[1144] 5. The server generates assistance information and sends it to the smart glasses.

[1145] 6. The smart glasses will display support information to the customer, including "xx benefit: up to 100,000 yen," "xx eco points: up to 30,000 points," and "Documents required for application: address proof, income proof, identification card."

[1146] This will allow customers to efficiently and quickly obtain applicable local government support information when they visit a physical store, reducing the hassle of the application process.

[1147] Prompt Sentence Examples

[1148] "Please tell me your address."

[1149] "Please tell me your annual income."

[1150] "Display relevant support information."

[1151] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1152] Step 1:

[1153] The user terminal receives a request message from the user (e.g., "Tell me about the xx benefit amount") as input. The terminal sends this message to the server. The server receives this request message, generates a message saying "Please tell me where you live" and sends it to the user terminal. This prompt sentence is intended to prompt the user for the next input.

[1154] Step 2:

[1155] The user terminal provides an interface for the user to input address information. When the user inputs the address information (e.g., "Chiyoda-ku, Tokyo"), it sends it to the server. The server receives the address information, generates a message based on it saying, "Please tell us your annual income," and sends it to the user terminal. This prepares the server to obtain the next input data.

[1156] Step 3:

[1157] The user terminal provides an interface for the user to input annual income information. When the user inputs the annual income information (e.g., "5 million yen"), it is sent to the server. The server receives the annual income information and searches the database based on this information along with the address information. This allows data processing to extract the relevant support information from the database.

[1158] Step 4:

[1159] The server searches for and filters the corresponding support information in the database based on the received address information and annual income information. For example, if the address is "Chiyoda-ku, Tokyo" and the annual income is "5 million yen," the server extracts support information that applies (e.g., "xx benefit: up to 100,000 yen," "xx eco points: up to 30,000 points"). The filtered information is then prepared for provision to the user.

[1160] Step 5:

[1161] The server generates the filtered support information and the corresponding document information required for the application (e.g., address certificate, income certificate, identity certificate), and sends this information to the user's terminal. The user's terminal displays the received information to the user so that they can confirm it. This output helps the user obtain the necessary local government support information and complete the application procedure.

[1162] Step 6:

[1163] When a user visits a physical store, they use smart glasses to obtain local government support information. When the user issues a voice command (e.g., "Tell me about local government support information"), the smart glasses send a request message to the server. The server generates information based on this request and displays it on the smart glasses. This allows the user to quickly obtain support information at the physical store.

[1164] Through these processing steps, users can efficiently and quickly obtain local government support information that is applicable to them.

[1165] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1166] MODE FOR CARRYING OUT THE INVENTION

[1167] The present invention relates to a chat-based local government support service that utilizes a generative AI model and further combines it with an emotion engine that recognizes the user's emotions to improve the user experience. This system includes a user terminal, a server, a generative AI model, and an emotion engine, and is implemented by the following specific processing steps.

[1168] Natural language explanation of program processing

[1169] Receiving the initial request

[1170] The user inputs a request message via the user terminal requesting information on local government support. For example, the user inputs "Tell me about xx benefits" and sends it.

[1171] The server receives this request message and sends the message "Please tell me where you live" to the user terminal. At the same time, the emotion engine analyzes the emotional tone of the user's input message.

[1172] Obtaining address information

[1173] The user terminal prompts the user to enter address information, and when the user enters the address, it sends it to the server. For example, the user enters "Chiyoda-ku, Tokyo."

[1174] The server receives the address information, generates a message based on it, such as "Please tell me your annual income," and sends it to the user's device. The emotion engine also analyzes and adapts the emotional tone of the user's input message at this stage.

[1175] Obtaining annual income information

[1176] The user terminal prompts the user to input annual income information, and when the user inputs their annual income, for example, "5 million yen," the input annual income information is sent to the server.

[1177] The server receives and records the annual income information. It searches the database based on the address and annual income information to extract applicable support information. The emotion engine optimizes the response message based on the user's emotional state.

[1178] Support information filtering

[1179] The server uses a generative AI model to filter the support content based on address and annual income information, and lists relevant support programs.

[1180] For example, if your address is Chiyoda-ku, Tokyo and your annual income is 5 million yen, the following support activities will be filtered:

[1181] xx Benefit: Up to 100,000 yen

[1182] xx Eco Points: Up to 30,000 points

[1183] Generating support content and responding to emotions

[1184] The server generates a list of the filtered support items and the corresponding documents required for application. For example, it generates the following information:

[1185] xx Benefit: Up to 100,000 yen

[1186] xx Eco Points: Up to 30,000 points

[1187] Required documents for application: Proof of address, Proof of income, Proof of identity

[1188] The emotion engine adds customization to the generated response based on the user's emotional state, for example, if the user is feeling anxious, it generates an additional message such as "Don't worry, this information is official."

[1189] Providing and responding to support

[1190] The server sends this information to the user terminal.

[1191] The user terminal displays the support information and necessary documents sent to the user for the user to confirm, and also displays a response message customized by the emotion engine.

[1192] Specific examples

[1193] 1. The user types "Tell me about the xx benefit" in the chat window and sends it.

[1194] 2. The server responds with, "Please tell me where you live." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "interested."

[1195] 3. The user enters "Chiyoda-ku, Tokyo" and submits.

[1196] 4. The server sends the message "Please tell me your annual income." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "in a bit of a hurry."

[1197] 5. The user enters "5 million yen" and submits.

[1198] 6. The server searches for the relevant assistance and generates the following information:

[1199] xx Benefit: Up to 100,000 yen

[1200] xx Eco Points: Up to 30,000 points

[1201] Required documents for application: Proof of address, Proof of income, Proof of identity

[1202] The sentiment engine adds a message to reassure users: "Don't worry, this information is official."

[1203] 7. The server sends the above information to the user terminal.

[1204] 8. The user device displays the information sent, along with a customized message to reassure the user.

[1205] By combining a generative AI model and an emotion engine, the present invention provides a system that allows users to easily and safely obtain local government support information.

[1206] The processing flow will be explained below.

[1207] Step 1:

[1208] The user's device starts up, and the user enters a message in the chat window requesting information about local government support. For example, the user types, "Tell me about the xx subsidy," and sends it.

[1209] Step 2:

[1210] The server analyzes the request message received from the user device and generates a message requesting the address, which is the next required information. It sends the message "Please tell me where you live" to the user device. At the same time, the emotion engine analyzes the emotional tone of the user's input message.

[1211] Step 3:

[1212] The user terminal receives the message sent from the server and prompts the user to enter address information. The user enters "Chiyoda-ku, Tokyo" and sends the message.

[1213] Step 4:

[1214] The server receives address information from the user's device and records it. At the same time, it generates a message requesting the next required piece of information, annual income, and sends the message "Please tell me your annual income" to the user's device. At this stage, the emotion engine also analyzes the emotional tone of the user's input message and responds by conveying a sense of "friendliness" and "comfort."

[1215] Step 5:

[1216] The user terminal receives the message sent from the server and prompts the user to enter their annual income information. The user enters "5 million yen" and submits the message.

[1217] Step 6:

[1218] The server receives and records annual income information from the user's device. It searches a database based on the address and annual income information to extract applicable support information. The emotion engine optimizes the response message based on the user's emotional state.

[1219] Step 7:

[1220] The server uses a generative AI model to filter the information on local government support obtained from the database, resulting in a list of support options that match the address and annual income.

[1221] Step 8:

[1222] The server generates the filtered support content and document information required for application, and uses an emotion engine to reinforce messages based on the user's emotional state, for example, adding a message such as "Don't worry, this information is official."

[1223] Step 9:

[1224] The server transmits the generated information to the user terminal.

[1225] Step 10:

[1226] The user terminal displays the support information and necessary documents sent from the server to the user, along with the emotion-responsive message, and the user confirms the support information and necessary documents.

[1227] Example 2

[1228] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1229] Currently, many local government support services do not take the user's emotional state into consideration when providing information, resulting in a uniform user experience. Furthermore, there is a need to provide more personalized services by understanding the user's emotions during the support information provision process and providing appropriate feedback accordingly.

[1230] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring address information from the user, means for searching for support information for the relevant local government based on the address information, and means for acquiring annual income information from the user. This improves the user experience and makes it possible to provide appropriate local government support information. Furthermore, by including means including an emotion engine that analyzes the user's emotional state and means for generating a customized response according to the user's emotion using the emotion engine, it is possible to provide a personalized service that allows the user to acquire local government support information with peace of mind.

[1231] A "user terminal" is a device through which a user inputs information and communicates with a server or other system.

[1232] A "request message" is a text message sent by a user requesting particular information or services.

[1233] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to generate information based on specific prompts.

[1234] "Local government support information" refers to information on various types of support provided by local governments, such as grants and point programs.

[1235] An "emotion engine" is software or a system for analyzing a user's input message and inferring their emotional state.

[1236] "Address information" is information that indicates the geographical location where the user lives.

[1237] "Annual income information" is information indicating the user's annual income.

[1238] "Filtering" is the process of sorting or narrowing down information based on specific criteria.

[1239] "Document information required for application" is a list of documents that must be submitted to receive specific assistance.

[1240] A "customized response" is a personalized response message that is generated based on the user's emotional state or specific situation.

[1241] "Error Message" means a notification message that is displayed if the information entered is invalid or incorrect.

[1242] The present invention relates to a chat-based local government support service that utilizes a generative AI model and further combines it with an emotion engine that recognizes the user's emotions to improve the user experience. This system includes a user terminal, a server, a generative AI model, and an emotion engine, and is implemented by the following specific processing steps.

[1243] Hardware and software used

[1244] User devices: communication devices such as smartphones, tablets, and PCs

[1245] Server: Cloud server or on-premise server

[1246] Generative AI model: An AI model that enables natural language processing

[1247] Emotion Engine: Software that analyzes the emotional tone of users' messages

[1248] Specific processing method of the system

[1249] The user inputs a request message into the chat window via the user terminal, requesting information about local government support. For example, they input "Tell me about xx subsidies" and send it. This request message is sent to the server.

[1250] The server receives the user's request message, generates an initial response message saying "Please tell me where you live" and sends it to the user's device. At the same time, the emotion engine analyzes the emotional tone of the request message. For example, at this stage, the emotion engine determines the user's emotion as "interested."

[1251] The user enters address information in the chat window and sends it. For example, they enter "Chiyoda-ku, Tokyo." The terminal then sends the entered address information to the server.

[1252] The server receives the address information, generates a message saying, "Please tell me your annual income," and sends it to the user's device. The emotion engine also analyzes the user's emotional tone at this stage and determines that the user is "in a bit of a hurry."

[1253] The user then enters and submits their annual income information. For example, they enter "5 million yen." The terminal then sends the annual income information to the server.

[1254] The server searches the database based on annual income and address information to extract applicable support information. During this search process, the generative AI model is used to filter the support content. For example, the following support content will be filtered for a user who lives in Chiyoda Ward, Tokyo, and has an annual income of 5 million yen:

[1255] xx Benefit: Up to 100,000 yen

[1256] xx Eco Points: Up to 30,000 points

[1257] The server generates a list of the filtered support items and the corresponding documents required for the application. For example, it generates the following information:

[1258] xx Benefit: Up to 100,000 yen

[1259] xx Eco Points: Up to 30,000 points

[1260] Required documents for application: Proof of address, Proof of income, Proof of identity

[1261] Based on the generated response, the emotion engine adds a customized message depending on the user's emotional state: if the user is feeling anxious, it generates a message like "Don't worry, this information is official."

[1262] The server sends the generated support details, required document list, and customized message to the user's terminal, which displays this information for the user to check.

[1263] Examples of prompt statements

[1264] User: "Tell me about the xx benefit."

[1265] Server: "Where do you live?"

[1266] User: "Chiyoda-ku, Tokyo"

[1267] Server: "What is your annual salary?"

[1268] User: "5 million yen"

[1269] Server: "xx Benefit: Up to 100,000 yen, xx Eco Points: Up to 30,000 points, Documents required for application: Address proof, Income proof, ID card, Rest assured, this information is official."

[1270] By combining a generative AI model and an emotion engine, the present invention provides a system that allows users to easily and safely obtain local government support information.

[1271] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1272] Step 1:

[1273] The user uses the user terminal to input a request message into the chat window requesting information about local government support. The specific prompt text is "Tell me about the xx benefit." This is the input.

[1274] The terminal sends the user's request message to the server. The output is the request message.

[1275] Step 2:

[1276] The server receives the user's request message, which is the input.

[1277] As an initial response, the server generates a message saying "Please tell me where you live" and sends it to the user's device. At the same time, the emotion engine analyzes the emotional tone of the request message and determines that the user is "interested." This analysis result is also saved as data. The output is the response message and the emotional tone analysis result.

[1278] Step 3:

[1279] The terminal displays the response message received from the server to the user. The input is the response message from the server. The user is shown "Please tell me where you live."

[1280] The user enters address information into the chat window and submits it. For example, they enter "Chiyoda-ku, Tokyo." This becomes the input data.

[1281] The terminal sends the input address information to the server, and the output is the address information.

[1282] Step 4:

[1283] The server receives the address information. The input data is the address information.

[1284] Based on the received address information, the server generates a message asking "What is your annual income?" and sends it to the user's device. The emotion engine also analyzes the user's emotional tone and determines that the user is "in a bit of a hurry." This analysis result is also saved. The output is a message inquiring about annual income and the emotional tone analysis result.

[1285] Step 5:

[1286] The terminal displays messages received from the server to the user, and the input is the message sent by the server.

[1287] The user enters their annual income information into the chat window and submits it. For example, they enter "5 million yen." This is the input data.

[1288] The terminal sends annual income information to the server, and the output is annual income information.

[1289] Step 6:

[1290] The server receives the annual income information. The input data is the annual income information.

[1291] The server searches the local government support database based on the received annual income and address information. It processes the data and performs search operations to extract relevant support information from the database. The emotion engine also analyzes the user's emotional tone and prepares appropriate feedback. The output is the filtered support information and the results of the emotional tone analysis.

[1292] Step 7:

[1293] The server uses the generative AI model to generate filtered support content and a list of documents required for the corresponding application. The input data is the filtered support information.

[1294] For example, the following will be generated:

[1295] xx Benefit: Up to 100,000 yen

[1296] xx Eco Points: Up to 30,000 points

[1297] Required documents for application: Proof of address, Proof of income, Proof of identity

[1298] A customized response from the emotion engine is added to this information. For example, if it determines that the user is feeling anxious, the message "Don't worry, this information is official" is added. The output is the generated support information, a list of required documents, and a customized message.

[1299] Step 8:

[1300] The server transmits the generated support information, required document list, and customized message to the user terminal. The input data are the generated support information, required document list, and customized message.

[1301] The terminal receives this information and displays it to the user, and the output is support information and customized messages.

[1302] (Application example 2)

[1303] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1304] With the current local government support information system, users have to spend time searching for information and understanding the information required for applications, and they are prone to becoming frustrated when error messages appear when the information they enter is inappropriate. Furthermore, users often feel uneasy when making payments or other electronic transactions, which contributes to a poor user experience. In these circumstances, there is a need for a system that allows users to use the service without feeling burdened and with peace of mind.

[1305] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for providing a chat-style service using a generative AI model that provides information on local government support based on a request message received from a user terminal, means for acquiring address information from the user, means for searching for support information for the relevant local government based on the address information, means for acquiring annual income information from the user, means for filtering support content based on the address information and annual income information, means for transmitting the filtered support content and document information required for application to the user terminal, and means for analyzing the user's emotional state in real time and generating a response message according to the results. This makes it possible to provide a system that allows users to conduct transactions and obtain information with peace of mind.

[1306] A "user terminal" is a device that a user uses to input and receive information, and includes smartphones, tablets, personal computers, and the like.

[1307] A "generative AI model" is an artificial intelligence model trained using large datasets to generate appropriate responses to user requests.

[1308] "Emotional state" refers to the emotional state analyzed from the user's input, facial expression, voice, etc., and includes, for example, relief, anxiety, interest, etc.

[1309] A "chat-style service" is a service in which a user and a system communicate in a text-based, interactive format.

[1310] "Address information" is information for identifying the user's place of residence, and includes, for example, city, ward, town, village, area name, and the like.

[1311] "Local government support information" is information about various types of support and services provided by local governments, including grants, subsidies, eco-points, etc.

[1312] "Annual income information" is information indicating the user's annual income, and is used to determine the scope of application of the assistance program.

[1313] "Filtering" refers to the process of selecting and narrowing down information based on specific conditions, and is a means of providing appropriate information to users.

[1314] "Information about documents required for application" is information showing a list of documents that must be submitted when applying for a support program.

[1315] An "error message" is a message that is displayed when there is an error in the information entered by the user, and is displayed to prompt the user to make appropriate corrections.

[1316] "Means for analyzing the user's emotional state in real time" refers to technology that instantly analyzes the user's input content, facial expressions, etc., and grasps their emotional state.

[1317] This invention relates to a system that uses a generative AI model to provide information on local government support, and analyzes the user's emotional state in real time to improve the user experience. The system mainly includes a user terminal, a server, a generative AI model, and an emotion engine.

[1318] System configuration

[1319] 1. User Device:

[1320] A device that allows users to input and receive information, including smartphones, tablets, and PCs.

[1321] 2. Server:

[1322] We use generative AI models using multiple methods to provide local government support information.

[1323] 3. Generative AI Model:

[1324] It is an artificial intelligence model trained using large datasets to generate appropriate responses to user requests.

[1325] 4. Emotion Engine:

[1326] It is an engine that analyzes emotional states from user input, facial expressions, voice, etc. It uses, for example, Google Cloud Natural Language API, Microsoft Azure Text Analytics service, OpenCV, AWS Rekognition, etc.

[1327] Data Flow and Processing

[1328] 1. Receiving the initial request:

[1329] A user inputs a specific request message via the user terminal. When a user wants to know specific information, for example, they input and send "Tell me about xx benefits." The server receives this request message and then sends the required information (for example, address) to the user terminal, while the emotion engine analyzes the emotional tone of the user's input message.

[1330] 2. Obtaining address information:

[1331] The user device prompts the user to enter address information, and once the user has entered the address, it sends that information to the server. The server receives the address information and sends the next required information (e.g., annual income) to the user device based on that information. The emotion engine also analyzes the emotional tone of the user's input message at this stage.

[1332] 3. Obtaining annual income information:

[1333] The user device prompts the user to enter their annual income information, which is then sent to the server. The server receives the information and filters out local government support information based on the address and income information. The emotion engine optimizes the response message according to the user's emotional state.

[1334] 4. Providing support information:

[1335] The server generates a list of the filtered support content and the corresponding documents required for application, and then sends it to the user's device along with a customized message based on the results of sentiment analysis, allowing the user to obtain information with greater peace of mind.

[1336] Specific examples

[1337] The user types "Tell me about the xx benefit" in the chat window and sends it.

[1338] The server responds with, "Please tell me where you live." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "interested."

[1339] The user enters "Chiyoda-ku, Tokyo" and submits.

[1340] The server sends the message "Please tell me your annual income." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "in a bit of a hurry."

[1341] The user enters "5 million yen" and submits.

[1342] The server searches for the relevant assistance and generates the following information:

[1343] xx Benefit: Up to 100,000 yen

[1344] xx Eco Points: Up to 30,000 points

[1345] Required documents for application: Proof of address, Proof of income, Proof of identity

[1346] The sentiment engine adds a message to reassure users: "Don't worry, this information is official."

[1347] The server sends the above information to the user terminal.

[1348] The user's device displays the transmitted information, along with a customized message to reassure the user.

[1349] Examples of prompt statements

[1350] The user's emotional tone was analyzed as "anxious."

[1351] The current transaction is for a settlement of 10,000 yen.

[1352] Generate appropriate feedback messages.

[1353] This system allows users to conduct transactions with peace of mind and makes obtaining local government support information easy and safe.

[1354] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1355] Step 1:

[1356] The user inputs a request message via the user terminal. For example, the user inputs and sends the message "Tell me about the xx benefit amount." This message becomes the initial request message of the system. The input data is the user's request, and the request message is sent to the server as output.

[1357] Step 2:

[1358] The server receives a request message from the user, then generates a message asking for the required information (e.g., address) and sends it to the user terminal. At the same time, the emotion engine analyzes the emotional tone of the user's request message. The input data is the user's request message, and the generated message and emotional tone are included as outputs.

[1359] Step 3:

[1360] The user terminal displays a message from the server and allows the user to input address information. For example, the user inputs "Chiyoda-ku, Tokyo." The input data is the user's address information, and the address information is sent to the server as output.

[1361] Step 4:

[1362] The server receives the address information and generates a message based on it, asking for the next required information (e.g., annual income), and sends it to the user's device. The emotion engine also analyzes the emotional tone of the user's input message at this stage. The input data is the user's address information, and the output includes the address information and the generated message.

[1363] Step 5:

[1364] The user terminal displays a message from the server and allows the user to input annual income information. For example, enter "5 million yen." The input data is the user's annual income information, and the annual income information is sent to the server as output.

[1365] Step 6:

[1366] The server receives and records the annual income information. It then searches a database of local government support information based on the address and annual income information to extract applicable support information. The emotion engine optimizes the response message based on the user's emotional state. The input data is address information and annual income information, and the output includes filtered support information.

[1367] Step 7:

[1368] The server generates a list of filtered support content and the corresponding documents required for application. It generates a customized message based on the results of sentiment analysis and sends it to the user's terminal. The input data is the filtered support content and the results of sentiment analysis, and the output includes the generated message and application document information.

[1369] Step 8:

[1370] The user terminal displays the information sent from the server, including the filtered support content, document information required for application, and response messages customized by the emotion engine. The input data is the message generated by the server, and the output is displayed to the user. The user confirms the information and feels reassured.

[1371] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1372] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1373] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1374] [Fourth embodiment]

[1375] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1376] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1377] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1378] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1379] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1380] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1381] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1382] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1383] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1384] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1385] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1386] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1387] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1388] MODE FOR CARRYING OUT THE INVENTION

[1389] The present invention is a chat-based local government support service that utilizes a generative AI model and is a system that allows users to easily obtain local government support information. This system receives input from a user's terminal and provides relevant support information based on that input. Specific embodiments of the present invention are described in detail below.

[1390] Natural language explanation of program processing

[1391] Receiving the initial request

[1392] The user sends a request message via the user terminal requesting information about local government support, for example, by typing "Tell me about xx subsidies."

[1393] The server receives this request message and sends a message to the user terminal saying "Please tell us where you live."

[1394] Obtaining address information

[1395] The user terminal prompts the user to enter address information, and when the user enters the address, it sends it to the server. For example, the user enters "Chiyoda-ku, Tokyo."

[1396] The server receives the address information, generates a message based on it asking "What is your annual income?" and sends it to the user's terminal.

[1397] Obtaining annual income information

[1398] The user terminal prompts the user to input annual income information, and when the user inputs their annual income, for example, "5 million yen," the input annual income information is sent to the server.

[1399] The server receives the annual income information and searches the database together with the address information to extract applicable support information.

[1400] Support information filtering

[1401] The server filters the support content based on address and annual income information and lists relevant support programs.

[1402] For example, if your address is Chiyoda-ku, Tokyo and your annual income is 5 million yen, the following support activities will be filtered:

[1403] xx Benefit: Up to 100,000 yen

[1404] xx Eco Points: Up to 30,000 points

[1405] Providing support

[1406] The server generates a list of the filtered support items and the corresponding documents required for application. For example, it generates the following information:

[1407] xx Benefit: Up to 100,000 yen

[1408] xx Eco Points: Up to 30,000 points

[1409] Required documents for application: Proof of address, Proof of income, Proof of identity

[1410] The server sends this information to the user terminal.

[1411] The user terminal displays the support information and necessary documents that have been sent to the user so that the user can check them.

[1412] Specific examples

[1413] 1. The user types "Tell me about the xx benefit" in the chat window and sends it.

[1414] 2. The server responds, "Please tell us where you live."

[1415] 3. The user enters "Chiyoda-ku, Tokyo" and submits.

[1416] 4. The server sends a message asking, "What is your annual income?"

[1417] 5. The user enters "5 million yen" and submits.

[1418] 6. The server searches for the relevant assistance and generates the following information:

[1419] xx Benefit: Up to 100,000 yen

[1420] xx Eco Points: Up to 30,000 points

[1421] Required documents for application: Proof of address, Proof of income, Proof of identity

[1422] 7. The server sends the above information to the user terminal.

[1423] 8. The user terminal displays the sent information and asks the user to confirm it.

[1424] In this way, the present invention enables users to easily obtain support information provided by local governments and smoothly make the necessary applications.

[1425] The processing flow will be explained below.

[1426] Step 1:

[1427] The user's device starts up, and the user enters a message in the chat window requesting information about local government support. For example, the user types, "Tell me about the xx subsidy," and sends it.

[1428] Step 2:

[1429] The server analyzes the request message received from the user terminal and generates a message requesting the address, which is the next required information. It then sends the message "Please tell me where you live" to the user terminal.

[1430] Step 3:

[1431] The user terminal receives the message sent from the server and prompts the user to enter address information. The user enters "Chiyoda-ku, Tokyo" and sends the message.

[1432] Step 4:

[1433] The server receives the address information from the user terminal, records it, and simultaneously generates a message requesting the next required piece of information, annual income, and sends the message "Please tell me your annual income" to the user terminal.

[1434] Step 5:

[1435] The user terminal receives the message sent from the server and prompts the user to enter their annual income information. The user enters "5 million yen" and submits the message.

[1436] Step 6:

[1437] The server receives and records annual income information from the user's device. It then searches the database based on the address and annual income information to identify support information for the relevant local government.

[1438] Step 7:

[1439] The server uses a generative AI model to filter the information on local government support obtained from the database, resulting in a list of support options that match the address and annual income.

[1440] Step 8:

[1441] The server generates a message containing the filtered support details and the document information required for application. For example, it contains information such as "xx benefit: up to 100,000 yen," "xx eco points: up to 30,000 points," and "documents required for application: address certificate, income certificate, and ID card."

[1442] Step 9:

[1443] The server transmits the generated information to the user terminal.

[1444] Step 10:

[1445] The user terminal receives the support information sent from the server and displays it to the user, who then checks the support information and necessary documents.

[1446] Example 1

[1447] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1448] In modern society, there is a demand for a means to quickly and accurately obtain a variety of support information provided by public organizations. However, many users do not know the proper procedures for searching for support information and applying for the necessary support. This makes the process of obtaining support information and applying for it cumbersome and difficult to proceed efficiently.

[1449] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1450] In this invention, the server includes means for providing a chat-style service using a generative algorithm model that provides information on public organization support based on a request message received from a user terminal, means for acquiring address information from the user, means for searching for support information from relevant public organizations based on the address information, means for acquiring income information from the user, means for filtering support content based on the address information and income information, and means for transmitting the filtered support content and document information required for application to the user terminal. This enables users to easily and efficiently acquire support information that suits their requirements and make appropriate applications.

[1451] "User terminal" refers to an electronic device that is directly operated by a user to input and receive information.

[1452] "Request message" refers to a message containing instructions sent by a terminal by a user seeking particular information or service.

[1453] "Generative algorithmic model" refers to an artificial intelligence technique used to generate an appropriate response to a given input.

[1454] "Chat-style service" means a service in which users and the system interact through text messages.

[1455] "Address information" refers to information indicating where a user lives.

[1456] "Public body" refers to a public organization such as a local government or government agency.

[1457] "Support information" refers to information about support such as subsidies and welfare benefits provided by public organizations.

[1458] "Income Information" refers to information regarding a User's income amount.

[1459] "Filtering" refers to the process of sorting and organizing information based on specific criteria.

[1460] "Documentation required for application" refers to the list of official documents required to receive a particular assistance.

[1461] MODE FOR CARRYING OUT THE INVENTION

[1462] The present invention is a chat-based public organization support service that utilizes a generative AI model and is a system that allows users to easily obtain public organization support information. This system receives input from a user's terminal and provides relevant support information based on that input. Specific embodiments of the present invention are described in detail below.

[1463] Hardware and software used

[1464] server:

[1465] Hardware: A server with a powerful CPU and sufficient memory (e.g., Intel Xeon, AMD EPYC)

[1466] Software: Web servers (e.g., Apache, Nginx), databases (e.g., MySQL, PostgreSQL), generative AI models (e.g., OpenAI GPT-3)

[1467] User device:

[1468] Hardware: Smartphones, tablets, PCs, etc.

[1469] Software: Web browser (e.g., Chrome, Firefox), chat interface (e.g., custom web app)

[1470] Detailed Description of the Invention

[1471] This system allows users to obtain public organization support information using a chat interface. Specifically, users enter and send a request message in the chat window. The server then uses a generative AI model to generate an appropriate response and prompts the user to enter the required information sequentially. Based on the response, the server filters the support information and finally provides the required information to the user's device.

[1472] Specific examples

[1473] 1. The user types "Tell me about the xx benefit" in the chat window and sends it.

[1474] 2. The server responds, "Where do you live?"

[1475] 3. The user enters "Chiyoda-ku, Tokyo" and submits.

[1476] 4. The server sends a message asking, "What is your annual income?"

[1477] 5. The user enters "5 million yen" and submits.

[1478] 6. The server searches for the relevant assistance and generates the following information:

[1479] xx Benefit: Up to 100,000 yen

[1480] xx Eco Points: Up to 30,000 points

[1481] Required documents for application: Proof of address, Proof of income, Proof of identity

[1482] 7. The server sends the above information to the user terminal.

[1483] 8. The user terminal displays the sent information and asks the user to confirm it.

[1484] By utilizing a generative AI model, this system can quickly and efficiently provide specific support information that users need. In addition, because it is easy for users to operate, they can obtain the necessary information without any hassle.

[1485] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1486] Step 1:

[1487] The user enters a request message in the chat window, such as "Tell me about the xx benefit," and sends it.

[1488] Specific action: The user types a text message through the chat interface and presses the send button.

[1489] Input: User request message "Tell me about xx benefits"

[1490] Output: The message is sent to the server

[1491] Step 2:

[1492] The server parses the request message received from the user and generates the prompt "Where do you live?"

[1493] What happens: The server uses the generative AI model to parse the request message and then generates the appropriate prompt to retrieve the required information.

[1494] Input: User request message "Tell me about xx benefits"

[1495] Data processing / calculation: Generative AI models are used to generate optimal prompts

[1496] Output: Prompt message "Where do you live?"

[1497] Step 3:

[1498] The server generates a prompt message and sends it to the user terminal.

[1499] Specific operation: The server performs network communication to send the generated message to the user terminal.

[1500] Input: Prompt message "Where do you live?"

[1501] Output: The message is displayed on the user's terminal.

[1502] Step 4:

[1503] The user terminal displays the received prompt message to the user.

[1504] What it does: A message from the server will be displayed in the chat interface.

[1505] Input: Prompt message sent from the server

[1506] Output: The user is prompted with "Where do you live?"

[1507] Step 5:

[1508] The user enters the address information "Chiyoda-ku, Tokyo" and submits it.

[1509] Specific behavior: The user enters address information in the chat window and presses the send button again.

[1510] Input: Address information "Chiyoda-ku, Tokyo"

[1511] Output: The message is sent to the server

[1512] Step 6:

[1513] The server parses the received address information and generates a prompt asking, "What is your annual income?"

[1514] Specific operation: The server analyzes the address information and then generates a message to obtain the required information (annual income).

[1515] Input: Address information "Chiyoda-ku, Tokyo"

[1516] Data processing / computation: Generate prompt messages using generative AI models

[1517] Output: Prompt message "What is your annual salary?"

[1518] Step 7:

[1519] The server generates a prompt message and sends it to the user terminal.

[1520] Specific operation: The server performs network communication to send the generated message to the user terminal.

[1521] Input: Prompt message "What is your annual salary?"

[1522] Output: The message is displayed on the user's terminal.

[1523] Step 8:

[1524] The user terminal displays the received prompt message to the user.

[1525] What it does: A message from the server will be displayed in the chat interface.

[1526] Input: Prompt message sent from the server

[1527] Output: The user is prompted with the message "What is your annual income?"

[1528] Step 9:

[1529] The user enters the annual income information "5 million yen" and submits it.

[1530] Specific behavior: The user enters annual salary information in the chat window and presses the send button again.

[1531] Input: Annual income information "5 million yen"

[1532] Output: The message is sent to the server

[1533] Step 10:

[1534] The server searches the database based on the received annual income information and address information and extracts the relevant support information.

[1535] Specific operation: The server checks the address information and annual income information against the database to search for the appropriate support program.

[1536] Input: Address information "Chiyoda-ku, Tokyo", Annual income information "5 million yen"

[1537] Data processing / calculation: Execute database queries to extract relevant support information

[1538] Output: Filtered support information list (e.g., xx grant up to 100,000 yen, xx eco points up to 30,000 points)

[1539] Step 11:

[1540] The server generates the filtered support content and document information required for application and sends it to the user's terminal.

[1541] Specific operation: The server creates a list of appropriate support information and documents required for application and sends it to the user's terminal in the form of a message.

[1542] Input: Filtered support information (xx benefit up to 100,000 yen, xx eco points up to 30,000 points)

[1543] Output: Support information and a list of required documents (Proof of Address, Proof of Income, Proof of Identity) are sent to the user's device.

[1544] Step 12:

[1545] The user terminal displays the received support information and required document information to the user.

[1546] Specific behavior: Support information and required documents will be displayed on the chat interface.

[1547] Input: Support information and required document list sent from the server

[1548] Output: User is presented with support information and required documentation

[1549] In this way, there are clear inputs and outputs at each step, and appropriate support information is provided to the user using a generative AI model and database search.

[1550] (Application example 1)

[1551] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1552] There is a problem that there is a lack of means for users to easily obtain information about local government support. In particular, there is a need for a means for customers in physical stores to quickly and accurately grasp the local government support information that applies to them. In order to obtain such information, various conditions must be met, and the process is complicated, which places a heavy burden on users.

[1553] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1554] In this invention, the server includes means for acquiring address information from a user, means for searching for support information from applicable local governments based on the address information, means for acquiring annual income information from the user, means for filtering support content based on the address information and annual income information, means for transmitting the filtered support content and document information required for application to a user terminal, and means for customers at physical stores to acquire support information from local governments using their smartphones or smart glasses. This allows customers to efficiently and quickly acquire applicable local government support information when they visit physical stores, thereby reducing the effort required for application procedures.

[1555] A "user terminal" is a device that a user directly operates to input and display information, and includes smartphones, smart glasses, and the like.

[1556] A "generative AI model" is an artificial intelligence model that generates appropriate answers based on user input, and is specialized in providing information on supporting local governments.

[1557] A "chat-style service" is a service that provides an interface for users and systems to exchange information in a dialogue format.

[1558] "Address information" is geographical data that a user inputs to indicate their place of residence.

[1559] "Support information" refers to information about grants, points, and other support programs provided by local governments.

[1560] "Annual income information" is data indicating the user's annual income.

[1561] "Filtering" is the process of extracting and selecting relevant information based on the user's specific criteria.

[1562] "Document information required for application" is a list of documents that must be submitted in order to receive local government support.

[1563] "Brick and mortar store" refers to a commercial establishment that exists in a physical location and can be visited by customers.

[1564] "Smart glasses" are eyeglass-type electronic devices worn by a user that can display or input information.

[1565] "Support details" refers to details of benefits, points, and other support programs provided as a result of filtering.

[1566] The present invention provides a system that enables users to easily obtain local government support information using a chat format that utilizes a generative AI model. Specific embodiments of this system are described in detail below.

[1567] Hardware and Software Configuration

[1568] This system is implemented using the following hardware and software:

[1569] User device: smartphone, smart glasses, or computer

[1570] Server: A computer server for hosting the database and generative AI models.

[1571] software:

[1572] Flask (Web framework)

[1573] Requests (a library for processing HTTP requests)

[1574] System operation flow

[1575] 1. Receiving the initial request:

[1576] The user terminal transmits a request message from the user (for example, "Tell me about xx benefit amount") to the server.

[1577] The server receives this request and sends a message to the user terminal saying "Please tell me where you live."

[1578] 2. Obtaining address information:

[1579] The user terminal provides an interface for the user to input address information, and when the user inputs "Chiyoda-ku, Tokyo," this is sent to the server.

[1580] 3. Obtaining annual income information:

[1581] The user terminal prompts the user to input annual income information, and when the user inputs "5 million yen," it sends this to the server.

[1582] 4. Filtering support information:

[1583] The server searches the database based on the address and annual income information and extracts the relevant support information.

[1584] 5. Provision of support:

[1585] The server generates the filtered support content and document information required for application and transmits them to the user terminal.

[1586] The user terminal displays the received information to the user so that the user can check it.

[1587] Specific examples

[1588] Below is a concrete example of a user using smart glasses in a brick-and-mortar store to obtain local government support information:

[1589] 1. The customer uses the voice command on their smart glasses to say, "Tell me about support information from the local government."

[1590] 2. The smart glasses display the message "Please tell us your address," and the customer answers by voice, "Chiyoda-ku, Tokyo."

[1591] 3. The smart glasses display the message, "Please tell us your annual income," and the customer answers by voice, "5 million yen."

[1592] 4. The smart glasses send the information to the server and search for the relevant support information.

[1593] 5. The server generates assistance information and sends it to the smart glasses.

[1594] 6. The smart glasses will display support information to the customer, including "xx benefit: up to 100,000 yen," "xx eco points: up to 30,000 points," and "Documents required for application: address proof, income proof, identification card."

[1595] This will allow customers to efficiently and quickly obtain applicable local government support information when they visit a physical store, reducing the hassle of the application process.

[1596] Prompt Sentence Examples

[1597] "Please tell me your address."

[1598] "Please tell me your annual income."

[1599] "Display relevant support information."

[1600] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1601] Step 1:

[1602] The user terminal receives a request message from the user (e.g., "Tell me about the xx benefit amount") as input. The terminal sends this message to the server. The server receives this request message, generates a message saying "Please tell me where you live" and sends it to the user terminal. This prompt sentence is intended to prompt the user for the next input.

[1603] Step 2:

[1604] The user terminal provides an interface for the user to input address information. When the user inputs the address information (e.g., "Chiyoda-ku, Tokyo"), it sends it to the server. The server receives the address information, generates a message based on it saying, "Please tell us your annual income," and sends it to the user terminal. This prepares the server to obtain the next input data.

[1605] Step 3:

[1606] The user terminal provides an interface for the user to input annual income information. When the user inputs the annual income information (e.g., "5 million yen"), it is sent to the server. The server receives the annual income information and searches the database based on this information along with the address information. This allows data processing to extract the relevant support information from the database.

[1607] Step 4:

[1608] The server searches for and filters the corresponding support information in the database based on the received address information and annual income information. For example, if the address is "Chiyoda-ku, Tokyo" and the annual income is "5 million yen," the server extracts support information that applies (e.g., "xx benefit: up to 100,000 yen," "xx eco points: up to 30,000 points"). The filtered information is then prepared for provision to the user.

[1609] Step 5:

[1610] The server generates the filtered support information and the corresponding document information required for the application (e.g., address certificate, income certificate, identity certificate), and sends this information to the user's terminal. The user's terminal displays the received information to the user so that they can confirm it. This output helps the user obtain the necessary local government support information and complete the application procedure.

[1611] Step 6:

[1612] When a user visits a physical store, they use smart glasses to obtain local government support information. When the user issues a voice command (e.g., "Tell me about local government support information"), the smart glasses send a request message to the server. The server generates information based on this request and displays it on the smart glasses. This allows the user to quickly obtain support information at the physical store.

[1613] Through these processing steps, users can efficiently and quickly obtain local government support information that is applicable to them.

[1614] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1615] MODE FOR CARRYING OUT THE INVENTION

[1616] The present invention relates to a chat-based local government support service that utilizes a generative AI model and further combines it with an emotion engine that recognizes the user's emotions to improve the user experience. This system includes a user terminal, a server, a generative AI model, and an emotion engine, and is implemented by the following specific processing steps.

[1617] Natural language explanation of program processing

[1618] Receiving the initial request

[1619] The user inputs a request message via the user terminal requesting information on local government support. For example, the user inputs "Tell me about xx benefits" and sends it.

[1620] The server receives this request message and sends the message "Please tell me where you live" to the user terminal. At the same time, the emotion engine analyzes the emotional tone of the user's input message.

[1621] Obtaining address information

[1622] The user terminal prompts the user to enter address information, and when the user enters the address, it sends it to the server. For example, the user enters "Chiyoda-ku, Tokyo."

[1623] The server receives the address information, generates a message based on it, such as "Please tell me your annual income," and sends it to the user's device. The emotion engine also analyzes and adapts the emotional tone of the user's input message at this stage.

[1624] Obtaining annual income information

[1625] The user terminal prompts the user to input annual income information, and when the user inputs their annual income, for example, "5 million yen," the input annual income information is sent to the server.

[1626] The server receives and records the annual income information. It searches the database based on the address and annual income information to extract applicable support information. The emotion engine optimizes the response message based on the user's emotional state.

[1627] Support information filtering

[1628] The server uses a generative AI model to filter the support content based on address and annual income information, and lists relevant support programs.

[1629] For example, if your address is Chiyoda-ku, Tokyo and your annual income is 5 million yen, the following support activities will be filtered:

[1630] xx Benefit: Up to 100,000 yen

[1631] xx Eco Points: Up to 30,000 points

[1632] Generating support content and responding to emotions

[1633] The server generates a list of the filtered support items and the corresponding documents required for application. For example, it generates the following information:

[1634] xx Benefit: Up to 100,000 yen

[1635] xx Eco Points: Up to 30,000 points

[1636] Required documents for application: Proof of address, Proof of income, Proof of identity

[1637] The emotion engine adds customization to the generated response based on the user's emotional state, for example, if the user is feeling anxious, it generates an additional message such as "Don't worry, this information is official."

[1638] Providing and responding to support

[1639] The server sends this information to the user terminal.

[1640] The user terminal displays the support information and necessary documents sent to the user for the user to confirm, and also displays a response message customized by the emotion engine.

[1641] Specific examples

[1642] 1. The user types "Tell me about the xx benefit" in the chat window and sends it.

[1643] 2. The server responds with, "Please tell me where you live." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "interested."

[1644] 3. The user enters "Chiyoda-ku, Tokyo" and submits.

[1645] 4. The server sends the message "Please tell me your annual income." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "in a bit of a hurry."

[1646] 5. The user enters "5 million yen" and submits.

[1647] 6. The server searches for the relevant assistance and generates the following information:

[1648] xx Benefit: Up to 100,000 yen

[1649] xx Eco Points: Up to 30,000 points

[1650] Required documents for application: Proof of address, Proof of income, Proof of identity

[1651] The sentiment engine adds a message to reassure users: "Don't worry, this information is official."

[1652] 7. The server sends the above information to the user terminal.

[1653] 8. The user device displays the information sent, along with a customized message to reassure the user.

[1654] By combining a generative AI model and an emotion engine, the present invention provides a system that allows users to easily and safely obtain local government support information.

[1655] The processing flow will be explained below.

[1656] Step 1:

[1657] The user's device starts up, and the user enters a message in the chat window requesting information about local government support. For example, the user types, "Tell me about the xx subsidy," and sends it.

[1658] Step 2:

[1659] The server analyzes the request message received from the user device and generates a message requesting the address, which is the next required information. It sends the message "Please tell me where you live" to the user device. At the same time, the emotion engine analyzes the emotional tone of the user's input message.

[1660] Step 3:

[1661] The user terminal receives the message sent from the server and prompts the user to enter address information. The user enters "Chiyoda-ku, Tokyo" and sends the message.

[1662] Step 4:

[1663] The server receives address information from the user's device and records it. At the same time, it generates a message requesting the next required piece of information, annual income, and sends the message "Please tell me your annual income" to the user's device. At this stage, the emotion engine also analyzes the emotional tone of the user's input message and responds by conveying a sense of "friendliness" and "comfort."

[1664] Step 5:

[1665] The user terminal receives the message sent from the server and prompts the user to enter their annual income information. The user enters "5 million yen" and submits the message.

[1666] Step 6:

[1667] The server receives and records annual income information from the user's device. It searches a database based on the address and annual income information to extract applicable support information. The emotion engine optimizes the response message based on the user's emotional state.

[1668] Step 7:

[1669] The server uses a generative AI model to filter the information on local government support obtained from the database, resulting in a list of support options that match the address and annual income.

[1670] Step 8:

[1671] The server generates the filtered support content and document information required for application, and uses an emotion engine to reinforce messages based on the user's emotional state, for example, adding a message such as "Don't worry, this information is official."

[1672] Step 9:

[1673] The server transmits the generated information to the user terminal.

[1674] Step 10:

[1675] The user terminal displays the support information and necessary documents sent from the server to the user, along with the emotion-responsive message, and the user confirms the support information and necessary documents.

[1676] Example 2

[1677] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1678] Currently, many local government support services do not take the user's emotional state into consideration when providing information, resulting in a uniform user experience. Furthermore, there is a need to provide more personalized services by understanding the user's emotions during the support information provision process and providing appropriate feedback accordingly.

[1679] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring address information from the user, means for searching for support information for the relevant local government based on the address information, and means for acquiring annual income information from the user. This improves the user experience and makes it possible to provide appropriate local government support information. Furthermore, by including means including an emotion engine that analyzes the user's emotional state and means for generating a customized response according to the user's emotion using the emotion engine, it is possible to provide a personalized service that allows the user to acquire local government support information with peace of mind.

[1680] A "user terminal" is a device through which a user inputs information and communicates with a server or other system.

[1681] A "request message" is a text message sent by a user requesting particular information or services.

[1682] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to generate information based on specific prompts.

[1683] "Local government support information" refers to information on various types of support provided by local governments, such as grants and point programs.

[1684] An "emotion engine" is software or a system for analyzing a user's input message and inferring their emotional state.

[1685] "Address information" is information that indicates the geographical location where the user lives.

[1686] "Annual income information" is information indicating the user's annual income.

[1687] "Filtering" is the process of sorting or narrowing down information based on specific criteria.

[1688] "Document information required for application" is a list of documents that must be submitted to receive specific assistance.

[1689] A "customized response" is a personalized response message that is generated based on the user's emotional state or specific situation.

[1690] "Error Message" means a notification message that is displayed if the information entered is invalid or incorrect.

[1691] The present invention relates to a chat-based local government support service that utilizes a generative AI model and further combines it with an emotion engine that recognizes the user's emotions to improve the user experience. This system includes a user terminal, a server, a generative AI model, and an emotion engine, and is implemented by the following specific processing steps.

[1692] Hardware and software used

[1693] User devices: communication devices such as smartphones, tablets, and PCs

[1694] Server: Cloud server or on-premise server

[1695] Generative AI model: An AI model that enables natural language processing

[1696] Emotion Engine: Software that analyzes the emotional tone of users' messages

[1697] Specific processing method of the system

[1698] The user inputs a request message into the chat window via the user terminal, requesting information about local government support. For example, they input "Tell me about xx subsidies" and send it. This request message is sent to the server.

[1699] The server receives the user's request message, generates an initial response message saying "Please tell me where you live" and sends it to the user's device. At the same time, the emotion engine analyzes the emotional tone of the request message. For example, at this stage, the emotion engine determines the user's emotion as "interested."

[1700] The user enters address information in the chat window and sends it. For example, they enter "Chiyoda-ku, Tokyo." The terminal then sends the entered address information to the server.

[1701] The server receives the address information, generates a message saying, "Please tell me your annual income," and sends it to the user's device. The emotion engine also analyzes the user's emotional tone at this stage and determines that the user is "in a bit of a hurry."

[1702] The user then enters and submits their annual income information. For example, they enter "5 million yen." The terminal then sends the annual income information to the server.

[1703] The server searches the database based on annual income and address information to extract applicable support information. During this search process, the generative AI model is used to filter the support content. For example, the following support content will be filtered for a user who lives in Chiyoda Ward, Tokyo, and has an annual income of 5 million yen:

[1704] xx Benefit: Up to 100,000 yen

[1705] xx Eco Points: Up to 30,000 points

[1706] The server generates a list of the filtered support items and the corresponding documents required for the application. For example, it generates the following information:

[1707] xx Benefit: Up to 100,000 yen

[1708] xx Eco Points: Up to 30,000 points

[1709] Required documents for application: Proof of address, Proof of income, Proof of identity

[1710] Based on the generated response, the emotion engine adds a customized message depending on the user's emotional state: if the user is feeling anxious, it generates a message like "Don't worry, this information is official."

[1711] The server sends the generated support details, required document list, and customized message to the user's terminal, which displays this information for the user to check.

[1712] Examples of prompt statements

[1713] User: "Tell me about the xx benefit."

[1714] Server: "Where do you live?"

[1715] User: "Chiyoda-ku, Tokyo"

[1716] Server: "What is your annual salary?"

[1717] User: "5 million yen"

[1718] Server: "xx Benefit: Up to 100,000 yen, xx Eco Points: Up to 30,000 points, Documents required for application: Address proof, Income proof, ID card, Rest assured, this information is official."

[1719] By combining a generative AI model and an emotion engine, the present invention provides a system that allows users to easily and safely obtain local government support information.

[1720] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1721] Step 1:

[1722] The user uses the user terminal to input a request message into the chat window requesting information about local government support. The specific prompt text is "Tell me about the xx benefit." This is the input.

[1723] The terminal sends the user's request message to the server. The output is the request message.

[1724] Step 2:

[1725] The server receives the user's request message, which is the input.

[1726] As an initial response, the server generates a message saying "Please tell me where you live" and sends it to the user's device. At the same time, the emotion engine analyzes the emotional tone of the request message and determines that the user is "interested." This analysis result is also saved as data. The output is the response message and the emotional tone analysis result.

[1727] Step 3:

[1728] The terminal displays the response message received from the server to the user. The input is the response message from the server. The user is shown "Please tell me where you live."

[1729] The user enters address information into the chat window and submits it. For example, they enter "Chiyoda-ku, Tokyo." This becomes the input data.

[1730] The terminal sends the input address information to the server, and the output is the address information.

[1731] Step 4:

[1732] The server receives the address information. The input data is the address information.

[1733] Based on the received address information, the server generates a message asking "What is your annual income?" and sends it to the user's device. The emotion engine also analyzes the user's emotional tone and determines that the user is "in a bit of a hurry." This analysis result is also saved. The output is a message inquiring about annual income and the emotional tone analysis result.

[1734] Step 5:

[1735] The terminal displays messages received from the server to the user, and the input is the message sent by the server.

[1736] The user enters their annual income information into the chat window and submits it. For example, they enter "5 million yen." This is the input data.

[1737] The terminal sends annual income information to the server, and the output is annual income information.

[1738] Step 6:

[1739] The server receives the annual income information. The input data is the annual income information.

[1740] The server searches the local government support database based on the received annual income and address information. It processes the data and performs search operations to extract relevant support information from the database. The emotion engine also analyzes the user's emotional tone and prepares appropriate feedback. The output is the filtered support information and the results of the emotional tone analysis.

[1741] Step 7:

[1742] The server uses the generative AI model to generate filtered support content and a list of documents required for the corresponding application. The input data is the filtered support information.

[1743] For example, the following will be generated:

[1744] xx Benefit: Up to 100,000 yen

[1745] xx Eco Points: Up to 30,000 points

[1746] Required documents for application: Proof of address, Proof of income, Proof of identity

[1747] A customized response from the emotion engine is added to this information. For example, if it determines that the user is feeling anxious, the message "Don't worry, this information is official" is added. The output is the generated support information, a list of required documents, and a customized message.

[1748] Step 8:

[1749] The server transmits the generated support information, required document list, and customized message to the user terminal. The input data are the generated support information, required document list, and customized message.

[1750] The terminal receives this information and displays it to the user, and the output is support information and customized messages.

[1751] (Application example 2)

[1752] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1753] With the current local government support information system, users have to spend time searching for information and understanding the information required for applications, and they are prone to becoming frustrated when error messages appear when the information they enter is inappropriate. Furthermore, users often feel uneasy when making payments or other electronic transactions, which contributes to a poor user experience. In these circumstances, there is a need for a system that allows users to use the service without feeling burdened and with peace of mind.

[1754] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for providing a chat-style service using a generative AI model that provides information on local government support based on a request message received from a user terminal, means for acquiring address information from the user, means for searching for support information for the relevant local government based on the address information, means for acquiring annual income information from the user, means for filtering support content based on the address information and annual income information, means for transmitting the filtered support content and document information required for application to the user terminal, and means for analyzing the user's emotional state in real time and generating a response message according to the results. This makes it possible to provide a system that allows users to conduct transactions and obtain information with peace of mind.

[1755] A "user terminal" is a device that a user uses to input and receive information, and includes smartphones, tablets, personal computers, and the like.

[1756] A "generative AI model" is an artificial intelligence model trained using large datasets to generate appropriate responses to user requests.

[1757] "Emotional state" refers to the emotional state analyzed from the user's input, facial expression, voice, etc., and includes, for example, relief, anxiety, interest, etc.

[1758] A "chat-style service" is a service in which a user and a system communicate in a text-based, interactive format.

[1759] "Address information" is information for identifying the user's place of residence, and includes, for example, city, ward, town, village, area name, and the like.

[1760] "Local government support information" is information about various types of support and services provided by local governments, including grants, subsidies, eco-points, etc.

[1761] "Annual income information" is information indicating the user's annual income, and is used to determine the scope of application of the assistance program.

[1762] "Filtering" refers to the process of selecting and narrowing down information based on specific conditions, and is a means of providing appropriate information to users.

[1763] "Information about documents required for application" is information showing a list of documents that must be submitted when applying for a support program.

[1764] An "error message" is a message that is displayed when there is an error in the information entered by the user, and is displayed to prompt the user to make appropriate corrections.

[1765] "Means for analyzing the user's emotional state in real time" refers to technology that instantly analyzes the user's input content, facial expressions, etc., and grasps their emotional state.

[1766] This invention relates to a system that uses a generative AI model to provide information on local government support, and analyzes the user's emotional state in real time to improve the user experience. The system mainly includes a user terminal, a server, a generative AI model, and an emotion engine.

[1767] System configuration

[1768] 1. User Device:

[1769] A device that allows users to input and receive information, including smartphones, tablets, and PCs.

[1770] 2. Server:

[1771] We use generative AI models using multiple methods to provide local government support information.

[1772] 3. Generative AI Model:

[1773] It is an artificial intelligence model trained using large datasets to generate appropriate responses to user requests.

[1774] 4. Emotion Engine:

[1775] It is an engine that analyzes emotional states from user input, facial expressions, voice, etc. It uses, for example, Google Cloud Natural Language API, Microsoft Azure Text Analytics service, OpenCV, AWS Rekognition, etc.

[1776] Data Flow and Processing

[1777] 1. Receiving the initial request:

[1778] A user inputs a specific request message via the user terminal. When a user wants to know specific information, for example, they input and send "Tell me about xx benefits." The server receives this request message and then sends the required information (for example, address) to the user terminal, while the emotion engine analyzes the emotional tone of the user's input message.

[1779] 2. Obtaining address information:

[1780] The user device prompts the user to enter address information, and once the user has entered the address, it sends that information to the server. The server receives the address information and sends the next required information (e.g., annual income) to the user device based on that information. The emotion engine also analyzes the emotional tone of the user's input message at this stage.

[1781] 3. Obtaining annual income information:

[1782] The user device prompts the user to enter their annual income information, which is then sent to the server. The server receives the information and filters out local government support information based on the address and income information. The emotion engine optimizes the response message according to the user's emotional state.

[1783] 4. Providing support information:

[1784] The server generates a list of the filtered support content and the corresponding documents required for application, and then sends it to the user's device along with a customized message based on the results of sentiment analysis, allowing the user to obtain information with greater peace of mind.

[1785] Specific examples

[1786] The user types "Tell me about the xx benefit" in the chat window and sends it.

[1787] The server responds with, "Please tell me where you live." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "interested."

[1788] The user enters "Chiyoda-ku, Tokyo" and submits.

[1789] The server sends the message "Please tell me your annual income." At the same time, the emotion engine analyzes the user's input tone and determines that the user is "in a bit of a hurry."

[1790] The user enters "5 million yen" and submits.

[1791] The server searches for the relevant assistance and generates the following information:

[1792] xx Benefit: Up to 100,000 yen

[1793] xx Eco Points: Up to 30,000 points

[1794] Required documents for application: Proof of address, Proof of income, Proof of identity

[1795] The sentiment engine adds a message to reassure users: "Don't worry, this information is official."

[1796] The server sends the above information to the user terminal.

[1797] The user's device displays the transmitted information, along with a customized message to reassure the user.

[1798] Examples of prompt statements

[1799] The user's emotional tone was analyzed as "anxious."

[1800] The current transaction is for a settlement of 10,000 yen.

[1801] Generate appropriate feedback messages.

[1802] This system allows users to conduct transactions with peace of mind and makes obtaining local government support information easy and safe.

[1803] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1804] Step 1:

[1805] The user inputs a request message via the user terminal. For example, the user inputs and sends the message "Tell me about the xx benefit amount." This message becomes the initial request message of the system. The input data is the user's request, and the request message is sent to the server as output.

[1806] Step 2:

[1807] The server receives a request message from the user, then generates a message asking for the required information (e.g., address) and sends it to the user terminal. At the same time, the emotion engine analyzes the emotional tone of the user's request message. The input data is the user's request message, and the generated message and emotional tone are included as outputs.

[1808] Step 3:

[1809] The user terminal displays a message from the server and allows the user to input address information. For example, the user inputs "Chiyoda-ku, Tokyo." The input data is the user's address information, and the address information is sent to the server as output.

[1810] Step 4:

[1811] The server receives the address information and generates a message based on it, asking for the next required information (e.g., annual income), and sends it to the user's device. The emotion engine also analyzes the emotional tone of the user's input message at this stage. The input data is the user's address information, and the output includes the address information and the generated message.

[1812] Step 5:

[1813] The user terminal displays a message from the server and allows the user to input annual income information. For example, enter "5 million yen." The input data is the user's annual income information, and the annual income information is sent to the server as output.

[1814] Step 6:

[1815] The server receives and records the annual income information. It then searches a database of local government support information based on the address and annual income information to extract applicable support information. The emotion engine optimizes the response message based on the user's emotional state. The input data is address information and annual income information, and the output includes filtered support information.

[1816] Step 7:

[1817] The server generates a list of filtered support content and the corresponding documents required for application. It generates a customized message based on the results of sentiment analysis and sends it to the user's terminal. The input data is the filtered support content and the results of sentiment analysis, and the output includes the generated message and application document information.

[1818] Step 8:

[1819] The user terminal displays the information sent from the server, including the filtered support content, document information required for application, and response messages customized by the emotion engine. The input data is the message generated by the server, and the output is displayed to the user. The user confirms the information and feels reassured.

[1820] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1821] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1822] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1823] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1824] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1825] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1826] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1827] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1828] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1829] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1830] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1831] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1832] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1833] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1834] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1835] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1836] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1837] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1838] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1839] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1840] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1841] The following is further disclosed regarding the above embodiment.

[1842] (Claim 1)

[1843] A system that provides a chat-style service using a generative AI model that provides information on local government support based on a request message received from a user terminal,

[1844] means for obtaining address information from a user;

[1845] A means for searching for support information for the relevant local government based on address information;

[1846] A means for obtaining annual income information from a user;

[1847] A means of filtering support content based on address information and annual income information;

[1848] means for transmitting the filtered support content and document information required for application to a user terminal;

[1849] A system including:

[1850] (Claim 2)

[1851] The system according to claim 1, wherein the filtered support content includes xx grants and xx eco points.

[1852] (Claim 3)

[1853] 10. The system of claim 1, further comprising means for validating the address information and annual income information obtained from the user terminal and generating an error message for invalid information.

[1854] "Example 1"

[1855] (Claim 1)

[1856] A system for providing a chat-style service using a generative algorithm model that provides information on public organization support based on a request message received from a user terminal, comprising:

[1857] means for obtaining address information from a user;

[1858] A means for searching for support information of a relevant public organization based on address information;

[1859] means for obtaining income information from a user;

[1860] A means of filtering assistance based on address and income information;

[1861] means for transmitting the filtered support content and document information required for application to a user terminal;

[1862] A system including:

[1863] (Claim 2)

[1864] 2. The system according to claim 1, wherein the filtered support content includes grants and eco points.

[1865] (Claim 3)

[1866] 10. The system of claim 1, further comprising means for validating the address and income information obtained from the user terminal and generating an error message for invalid information.

[1867] "Application Example 1"

[1868] (Claim 1)

[1869] A system that provides a chat-style service using a generative AI model that provides information on local government support based on a request message received from a user terminal,

[1870] means for obtaining address information from a user;

[1871] A means for searching for support information for the relevant local government based on address information;

[1872] A means for obtaining annual income information from a user;

[1873] A means of filtering support content based on address information and annual income information;

[1874] means for transmitting the filtered support content and document information required for application to a user terminal;

[1875] A means for customers to access support information from local governments using their smartphones or smart glasses in physical stores;

[1876] A system including:

[1877] (Claim 2)

[1878] 2. The system according to claim 1, wherein the filtered support content includes grants and points.

[1879] (Claim 3)

[1880] 10. The system of claim 1, further comprising means for validating the address information and annual income information obtained from the user terminal and generating an error message for invalid information.

[1881] "Example 2: Combining Emotion Engines"

[1882] (Claim 1)

[1883] A system that provides a chat-style service using a generative AI model that provides information on local government support based on a request message received from a user terminal,

[1884] means for obtaining address information from a user;

[1885] A means for searching for support information for the relevant local government based on address information;

[1886] A means for obtaining annual income information from a user;

[1887] A means of filtering support content based on address information and annual income information;

[1888] means for transmitting the filtered support content and document information required for application to a user terminal;

[1889] means including an emotion engine for analyzing an emotional state of a user;

[1890] means for generating a customized response according to the user's emotion using an emotion engine;

[1891] A system including:

[1892] (Claim 2)

[1893] The system according to claim 1, wherein the filtered support content includes grants and point programs.

[1894] (Claim 3)

[1895] 10. The system of claim 1, further comprising means for validating the address information and annual income information obtained from the user terminal and generating an error message for invalid information.

[1896] "Application example 2 when combining emotion engines"

[1897] (Claim 1)

[1898] A system that provides a chat-style service using a generative AI model that provides information on local government support based on a request message received from a user terminal,

[1899] means for obtaining address information from a user;

[1900] A means for searching for support information for the relevant local government based on address information;

[1901] A means for obtaining annual income information from a user;

[1902] A means of filtering support content based on address information and annual income information;

[1903] means for transmitting the filtered support content and document information required for application to a user terminal;

[1904] means for analyzing the user's emotional state in real time and generating a response message in accordance with the result of the analysis;

[1905] A system including:

[1906] (Claim 2)

[1907] 2. The system according to claim 1, wherein the filtered support content includes grants and points.

[1908] (Claim 3)

[1909] 10. The system of claim 1, further comprising means for validating the address information and annual income information obtained from the user terminal and generating an error message for invalid information. [Explanation of symbols]

[1910] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A system that provides a chat-style service using a generative AI model that provides information on local government support based on a request message received from a user terminal, means for obtaining address information from a user; A means for searching for support information for the relevant local government based on address information; A means for obtaining annual income information from a user; A means of filtering support content based on address information and annual income information; means for transmitting the filtered support content and document information required for application to a user terminal; A system including:

2. The system according to claim 1, wherein the filtered support content includes xx subsidies and xx eco points.

3. 10. The system of claim 1, further comprising means for validating address information and annual income information obtained from the user terminal and generating an error message for invalid information.

Images