system

Abstract

Provide a system. A method for receiving a question from a user includes: means for analyzing the received question by natural language processing and generating an answer; means for returning the generated answer to the user; a means for storing the questions and generated answers; A means of analyzing saved questions and answers and extracting common issues; and means for transmitting the extracted issues to a public institution.

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] Parents face a wide range of problems and worries when it comes to raising children. However, there are currently no effective ways to resolve these worries, nor are there any systems in place to link these solutions to measures to combat the declining birthrate. Furthermore, there are no established methods for collecting information to identify specific issues related to childcare in each region or the country as a whole and to implement countermeasures. There is a need to quickly resolve parents' childcare worries, consolidate and analyze the resulting data, and use it to combat the declining birthrate. [Means for solving the problem]

[0005] The present invention provides a system that receives questions from users, analyzes them using natural language processing, generates appropriate answers, and returns them to the users. Furthermore, this system stores the questions and generated answers in a database and periodically analyzes the data to extract common issues. The extracted issues are sent to public institutions and used in considering measures to combat the declining birthrate. Specifically, the system comprises the following means:

[0006] (1) a means for receiving a question from a user;

[0007] (2) A means for analyzing received questions using natural language processing and generating answers;

[0008] (3) a means for returning the generated answer to the user;

[0009] (4) a means of storing questions and generated answers;

[0010] (5) A means of analyzing saved questions and answers and extracting common issues;

[0011] (6) A means of transmitting the extracted issues to public institutions.

[0012] This kills two birds with one stone: users can easily seek childcare advice, and the data obtained can be used to combat the declining birthrate.

[0013] "User" refers to an individual or organization that uses the system to input questions or inquiries.

[0014] "Questions" refer to information or inquiries about childcare or other concerns that users input into the system.

[0015] "Receiving" refers to the process by which the system takes in questions and data sent by users.

[0016] "Natural language processing" refers to the technology that allows computers to understand and analyze human language.

[0017] "Analysis" refers to the process of understanding and extracting meaning from the received question.

[0018] An "answer" refers to a response generated in response to a question.

[0019] "Generation" refers to the process of using natural language processing to create the best answer to a question.

[0020] "Return" refers to the process of sending the generated answer back to the user.

[0021] "Storage" refers to the act of recording and storing question and answer data in a database.

[0022] "Database" refers to a system for systematically storing and managing question and answer data.

[0023] "Analysis" (second time) refers to the process of organizing the data stored in the database and discovering common issues.

[0024] "Extraction" refers to the act of extracting common issues discovered through analysis.

[0025] "Public institutions" refer to organizations and institutions that are responsible for the public interest, such as national and local governments.

[0026] "Submission" refers to the process of sending the extracted issues to a public institution.

[0027] "Measures to combat the declining birthrate" refers to policies and measures to stop the decline in the birth rate and increase it.

[0028] "Policy consideration" refers to the process of considering specific countermeasures to issues and creating implementation plans. [Brief explanation of the drawings]

[0029] [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

[0030] 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.

[0031] First, the terms used in the following description will be explained.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] [First embodiment]

[0038] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0039] 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.

[0040] 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).

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0046] 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.

[0047] 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.

[0048] 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.

[0049] 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."

[0050] This invention is a system that receives questions and inquiries from users, analyzes the questions using natural language processing, and generates appropriate answers. The generated answers are returned to the users, and all question and answer data is stored in a database. This data is periodically analyzed, and common issues are extracted and sent to public institutions. Through this process, we are able to respond to inquiries about childcare and take measures to combat the declining birthrate.

[0051] Explanation of program processing

[0052] 1. Enter and submit your question

[0053] User

[0054] The user uses the terminal to input questions or inquiries about childcare into the input field.

[0055] For example: "What should I do if my child refuses to eat?"

[0056] 2. Sending input data

[0057] Terminal

[0058] Convert the input question into JSON format.

[0059] The converted data is sent to the server via a secure communication method (e.g., HTTPS).

[0060] 3. Receiving and analyzing questions

[0061] server

[0062] The server receives the query data sent from the terminal.

[0063] The format and content of the received data are validated, and if normal, it is passed to the natural language processing engine.

[0064] Generative AI

[0065] Analyze the question data and generate appropriate answers.

[0066] For example: "If your child is reluctant to eat, it's a good idea to start by offering them small amounts of their favorite foods. It's also important to find ways to make eating enjoyable."

[0067] 4. Receiving and returning responses

[0068] server

[0069] Receive response data from the generative AI.

[0070] The received response data is validated again and formatted to be returned to the terminal.

[0071] Terminal

[0072] The formatted answer data is received and displayed on the screen in a format that is easy for the user to view.

[0073] Example: Displayed answer: "If your child is reluctant to eat, it's a good idea to start by offering them small amounts of their favorite foods. It's also important to find ways to make eating enjoyable."

[0074] 5. Data storage and analysis

[0075] server

[0076] Save the questions and generated answers in a database.

[0077] All data stored in the database is periodically extracted and analyzed to detect common issues.

[0078] 6. Extract and submit assignments

[0079] server

[0080] Based on the results of the analysis, common issues and trends are extracted.

[0081] The extracted issues and trend information will be sent to public institutions as a report.

[0082] Examples: "There has been an increase in consultations regarding diet," "There are many consultations regarding night crying in certain areas," etc.

[0083] Specific examples

[0084] context

[0085] The user uses the terminal to input a question about a child-rearing problem.

[0086] Sample question: "What should I do if my child cries at night?"

[0087] Processing Flow

[0088] 1. The user types a question into the terminal.

[0089] 2. The device sends the question to the server in JSON format.

[0090] 3. The server passes the question to a generative AI, which generates an answer.

[0091] 4. The generative AI generated the answer, "Effective ways to deal with nighttime crying include adjusting your baby's sleep rhythm and creating a relaxing environment."

[0092] 5. The server generates the answer and sends it back to the user's device.

[0093] 6. The device displays the answer to the user.

[0094] 7. The server stores the question and answer data in a database.

[0095] 8. Regularly analyze the data and identify the issue of "many inquiries about nighttime crying."

[0096] 9. The server sends this issue as a report to the public agency.

[0097] In this way, the system provides a mechanism for quickly responding to user questions and utilizing the collected data to combat the declining birthrate. This system is both convenient for users and a valuable source of information for public institutions.

[0098] The processing flow will be explained below.

[0099] Step 1:

[0100] The user uses the device to enter a question or inquiry about childcare into the input field. For example, "What should I do if my child refuses to eat?"

[0101] Step 2:

[0102] The device converts the entered question into an appropriate data format, such as JSON. Specifically, it converts it into the following format: json { "question": "What should I do if my child refuses to eat?"}

[0103] Step 3:

[0104] The device sends the converted data to the server using a secure communication method such as HTTPS. The data is encrypted and managed to reach the server safely.

[0105] Step 4:

[0106] The server receives the query data sent from the terminal, validates the format and content of the received data, and eliminates invalid data.

[0107] Step 5:

[0108] The server passes the received question data to a natural language processing engine (e.g., a generative AI). The engine is called via an API endpoint and analyzes the question and generates an answer.

[0109] Step 6:

[0110] Generative AI analyzes question data and generates appropriate answers, such as, "If your child doesn't like to eat, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find ways to make eating fun."

[0111] Step 7:

[0112] The server then validates the answer data received from the generative AI and formats it into the appropriate format. Validation includes checking the consistency and quality of the answer text.

[0113] Step 8:

[0114] The server returns the formatted response data to the terminal, usually via HTTPS.

[0115] Step 9:

[0116] The device receives the response data sent from the server and displays it in an easy-to-understand manner to the user. For example, it displays, "If your child doesn't like to eat, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find ways to make eating fun."

[0117] Step 10:

[0118] The server stores the questions and generated answers in a database. The data is stored as pairs of question and answer.

[0119] Step 11:

[0120] The server periodically runs jobs that analyze the question and answer data stored in the database, sometimes using machine learning algorithms.

[0121] Step 12:

[0122] The server extracts common issues and trends from the analysis results. For example, it finds patterns from data such as "there are many consultations about nighttime crying" or "the number of consultations about eating is increasing."

[0123] Step 13:

[0124] The server compiles the extracted issues and trend information into a report format and sends it to the public institution via API or secure data transmission methods.

[0125] Step 14:

[0126] Based on the data received, public institutions will consider and implement measures to combat the declining birthrate. Specific countermeasures will be planned and implemented for the issues identified.

[0127] Example 1

[0128] 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."

[0129] Currently, many childcare-related questions and inquiries are handled individually, without effective data analysis or sharing. This makes it difficult to effectively utilize this data and link it to improving childcare support and measures to combat the declining birthrate. Furthermore, there is a lack of a system for providing prompt, appropriate answers to user questions.

[0130] 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.

[0131] In this invention, the server includes means for receiving questions from users, means for converting the received questions into a data format and transmitting the data, means for validating the format and content of the received data and, if normal, passing the data to an analysis engine, means for analyzing the question data using a generative AI model and generating an appropriate answer, means for returning the generated answer to the user, means for saving the questions and the generated answers, means for analyzing the saved questions and answers and extracting common issues, and means for sending the extracted issues to public institutions. This makes it possible to provide users with prompt and appropriate answers and to utilize data to support childcare and address the declining birthrate.

[0132] "User" refers to a person who inputs questions or inquiries about childcare into the system.

[0133] A "terminal" is a device used by a user to input questions or inquiries, and includes smartphones, personal computers, etc.

[0134] "Server" refers to a central processing unit for receiving user questions, passing the data to the analysis engine, and transmitting generated answers.

[0135] A "question" refers to a childcare-related question that a user enters into an input field.

[0136] "Received data" refers to the data that the server receives after converting the question entered by the user into a data format such as JSON.

[0137] "Validation" refers to the process of checking that received data is in the correct format and contains expected content.

[0138] "Analytics Engine" refers to software or algorithms that analyze incoming data and generate appropriate answers.

[0139] A "generative AI model" refers to a machine learning model that uses generative AI to generate appropriate answers to user questions.

[0140] "Answer" refers to the information generated by a generative AI model and returned in response to a user's question.

[0141] "Saving" refers to the act of storing the question and its generated answer in a database.

[0142] "Database" means a digital storage system for managing and storing saved question and answer data.

[0143] "Analysis" refers to the process of analyzing stored data to extract common issues.

[0144] "Common issues" refers to themes or issues that frequently emerge from multiple questions and their answers.

[0145] A "public institution" refers to an organization that operates for the public good, such as a government or local government.

[0146] The present invention is a system that receives questions and inquiries about childcare from users, analyzes them, and generates answers. The system includes a device used by the user, a server that processes and stores data, and a generative AI model that performs natural language processing.

[0147] The user uses the device to input a question or inquiry. The user opens a browser on their smartphone or PC, accesses a dedicated web form, and enters the question in the input field. For example, they might enter, "What should I do if my child refuses to eat?" and click the send button.

[0148] The device converts the question entered by the user into JSON format, for example, {"question": "What should I do if my child refuses to eat?"}. The converted data is securely sent to the server using the HTTPS protocol.

[0149] The server receives the question data sent from the device. It validates the format and content of the received data, and if it is normal, passes it to the analysis engine. After format checks and XSS attack countermeasures, it passes the question data to the generative AI model as a prompt text. Examples of prompt text are as follows:

[0150] "Question: What should I do if my child refuses to eat? Generate an appropriate answer."

[0151] A generative AI model (e.g., OpenAI® GPT-4®) receives a prompt and generates an answer based on the training data, such as, "If your child refuses to eat, it's a good idea to offer them a small amount of their favorite food first. It's also important to find ways to make eating enjoyable."

[0152] The server receives the answer data from the generative AI model. The received answer data is validated again, and if normal, it is formatted to be sent back to the device. The content of the answer data is checked and formatted, for example, {"answer": "If a child doesn't like eating, it's a good idea to first offer them a small amount of their favorite food. It's also important to find a way to make eating enjoyable."}

[0153] The device analyzes the response data received from the server and displays it on the screen in an easy-to-read format for the user. An example of what is displayed is, "If your child doesn't like to eat, it's a good idea to first offer them a small amount of their favorite food. It's also important to find ways to make eating fun."

[0154] The server saves the question and the generated answer in a database. The question and answer are stored in the database in JSON format. For example, it is saved as follows: {"question": "What should I do if my child refuses to eat?", "answer": "If a child refuses to eat, it is a good idea to start by offering them a small amount of their favorite food. It is also important to find ways to make eating enjoyable."}

[0155] The system periodically extracts and analyzes all data stored in the database to detect common issues. The server runs a regularly scheduled task to retrieve past questions and answers from the database and uses natural language processing technology to extract common topics and trends. For example, it detects an increase in questions related to night crying.

[0156] Based on the analysis results, the extracted issues and trend information are sent to the public institution as a report. The generated report is formatted in PDF or CSV format and sent to the API endpoint or email address specified by the public institution. For example, a report containing content such as "Recent trend: Increase in the number of consultations about nighttime crying" is sent.

[0157] This system provides users with quick and appropriate answers, and also provides a mechanism that makes it possible to utilize data to support childcare and implement measures to combat the declining birthrate.

[0158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0159] Step 1:

[0160] The user uses the device to enter a question or request for advice about childcare into an input field. Specifically, the user opens a browser on their smartphone or PC, accesses a dedicated web form, enters "What should I do if my child refuses to eat?" into the input field, and clicks the send button. The input is the question from the user, and the output is saved on the device as this question data.

[0161] Step 2:

[0162] The terminal converts the question entered by the user into JSON format. Specifically, the terminal parses the user's input text and converts it into a JSON object of key-value pairs (e.g., {"question": "What should I do if my child refuses to eat?"}). The input is the text entered by the user, and the output is question data in JSON format.

[0163] Step 3:

[0164] The terminal sends the converted JSON data to the server using the HTTPS protocol. Specifically, the terminal includes the generated JSON object in the HTTPS request body and sends a POST request to the specified endpoint on the server. The input is the question data in JSON format, and the data is sent to the server as the output.

[0165] Step 4:

[0166] The server receives the question data sent from the terminal. Specifically, the server receives the HTTPS request and extracts JSON data from the request body. The input is the received HTTPS request, and the output is the extracted JSON-formatted question data.

[0167] Step 5:

[0168] The server validates the format and content of the received data. Specific operations include format checks (e.g., checking the existence of keys) and XSS attack prevention. The input is JSON-formatted question data, and the output is validated JSON data. If this validated data is valid, it is passed to the analysis engine.

[0169] Step 6:

[0170] If everything is normal, the server passes the question data to the generative AI model as a prompt text. Specifically, it generates a prompt text and sends it to the generative AI model. An example of a prompt text is: "Question: What should I do if my child refuses to eat? Please generate an appropriate answer." The input is validated JSON data, and the output is a prompt text.

[0171] Step 7:

[0172] A generative AI model receives a prompt, analyzes the question data, and generates an appropriate answer. Specifically, a generative AI model (e.g., OpenAI GPT-4) analyzes the prompt and generates an answer based on the training data. An example of a generated answer is: "If a child doesn't like eating, it's a good idea to first offer them a small amount of their favorite food. It's also important to find a way to make eating enjoyable." The input is a prompt, and the output is a generated answer.

[0173] Step 8:

[0174] The server receives the answer data from the generative AI model. Specifically, the server receives the answer generated from the API of the generative AI model. The generated answer data is the input, and it is saved on the server as the output.

[0175] Step 9:

[0176] The server revalidates the received response data. Specifically, it checks the content of the response data (e.g., whether it contains any undesirable content). The input is the generated response data, and the output is the validated response data.

[0177] Step 10:

[0178] The server formats the validated answer data into a format to be sent back to the device. Specifically, it formats the answer in JSON format, for example, {"answer": "If a child doesn't like eating, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find ways to make eating enjoyable."}. The input is the validated answer data, and the output is the formatted answer data.

[0179] Step 11:

[0180] The device analyzes the response data received from the server and displays it on the screen in a format that is easy for the user to view. Specifically, the device analyzes the JSON data received from the server and displays the response in the browser's display area. An example of what is displayed is, "If your child doesn't like to eat, it's a good idea to first offer them a small amount of their favorite food. It's also important to find a way to make eating enjoyable." The input is the formatted response data, and the output is displayed to the user.

[0181] Step 12:

[0182] The server saves the question and the generated answer in a database. Specifically, the question and answer are stored in the database in JSON format. Example of saved data: {"question": "What should I do if my child doesn't want to eat?", "answer": "If a child doesn't want to eat, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find a way to make eating enjoyable."}. The input is the question and the generated answer data, and the output is saved in the database.

[0183] Step 13:

[0184] The server periodically extracts and analyzes all data stored in the database to detect common issues. Specifically, the server executes a regularly scheduled task to retrieve past questions and answers from the database and uses natural language processing technology to extract common topics and trends. For example, it detects an increase in questions related to nighttime crying. The input is the question and answer data stored in the database, and the output is the detection of common issues.

[0185] Step 14:

[0186] Based on the results of the analysis, the server sends the extracted issues and trend information to the public institution as a report. Specifically, the generated report is formatted in PDF or CSV format and sent to an API endpoint or email address specified by the public institution. For example, a report titled "Recent trends: Increase in the number of consultations about nighttime crying" is sent. Common issues and trend information are input, and the report is sent to the public institution as output.

[0187] (Application example 1)

[0188] 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."

[0189] One issue facing brick-and-mortar stores is the lack of a way for customers to quickly and appropriately resolve questions about childcare or products without having to ask staff directly. There is also a need for a system that accumulates and analyzes customer question data and provides the information to public institutions to contribute to childcare support measures and measures to combat the declining birthrate throughout society.

[0190] 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.

[0191] In this invention, the server includes means for receiving questions from users, means for analyzing the received questions using natural language processing and generating answers, means for returning the generated answers to the users, means for saving the questions and the generated answers, means for analyzing the saved questions and answers and extracting common issues, means for sending the extracted issues to public institutions, means for responding to customer questions in physical stores, and means for displaying the generated answers on the customer's terminal. This makes it possible to quickly and appropriately respond to customer questions in physical stores, and to analyze the accumulated data and utilize it for childcare support measures and measures to combat the declining birthrate throughout society.

[0192] "User" means an individual or organization that uses the system to ask questions or make inquiries.

[0193] A "question" is a question or inquiry submitted by a user to the system.

[0194] "Natural language processing" is a technology that allows a machine to understand input questions or consultation content and generate appropriate answers.

[0195] An "answer" is a response generated in response to a question analyzed by natural language processing.

[0196] The "receiving means" refers to a mechanism or device for receiving a question from a user.

[0197] A "return mechanism" is a mechanism or device for returning the generated answer to the user.

[0198] A "storage means" is a mechanism or device for storing questions and generated answers for a certain period of time.

[0199] "Analysis means" refers to a mechanism or device for analyzing stored questions and answers.

[0200] "Issue extraction means" refers to mechanisms or devices for identifying common problems or trends based on analysis.

[0201] "Public agency transmission means" refers to the mechanism or device for transmitting the identified issues to the relevant public agencies.

[0202] A "brick and mortar store" is a physical commercial establishment where customers visit and purchase goods in person.

[0203] "Response methods" refer to mechanisms and devices that allow a physical store to respond quickly to customer questions.

[0204] A "terminal" is an electronic device that a user uses to enter questions and receive answers.

[0205] This invention realizes a system that receives questions from customers in a physical store, processes them, answers them, and returns them. The specific implementation method and operation of this system are described below.

[0206] System Overview

[0207] This system is realized using a user device (such as a smartphone), a server, and a generative AI model. The main hardware and software components and their roles are described below.

[0208] Hardware and Software Used

[0209] User device: The device on which customers enter their questions and receive answers. This could be a smartphone or tablet.

[0210] Server: The central component that receives questions, generates answers, stores and analyzes data, and sends reports to public authorities.

[0211] Usage example: Cloud server (Amazon Web Services, Google (registered trademark) Cloud Platform)

[0212] Generative AI model: Analyzes questions and generates appropriate answers. The following natural language processing engines are used:

[0213] Usage examples: Amazon Lex, Google Dialogflow

[0214] Program processing overview

[0215] 1. Enter and submit your question

[0216] A user uses a smartphone app in a physical store to input a question, for example, "Is it better to have a lightweight stroller?"

[0217] 2. Sending input data

[0218] The device converts the entered question into JSON format and sends it to the server using HTTPS.

[0219] 3. Receiving and analyzing questions

[0220] The server receives the input data, validates the format and content, and if there are no problems, passes it to the natural language processing engine.

[0221] A generative AI model (e.g., Amazon Lex) analyzes the question and generates an appropriate answer, such as, "A lightweight stroller is easy to use, but durability should also be considered."

[0222] 4. Receiving and returning responses

[0223] The server receives the generated response, validates it, and then formats it into a format to be sent back to the user's terminal.

[0224] The terminal receives the response data and displays it in an easy-to-read format for the customer.

[0225] 5. Data storage and analysis

[0226] The server stores the questions and generated answers in a database.

[0227] The contents of the database are analyzed periodically to extract common issues.

[0228] 6. Extract and submit assignments

[0229] Based on the analysis results, the server extracts common issues and trends and sends them to public institutions as a report.

[0230] Specific examples

[0231] Enter your question

[0232] A user types a question in a physical store.

[0233] For example: "Is a lighter stroller better?"

[0234] Prompt Sentence Examples

[0235] A user asked: "Is a lighter stroller better?"

[0236] Context for Answer Generation: Generate an answer about the balance between lightweight and sturdy strollers.

[0237] This system will enable physical stores to respond quickly and appropriately to customer questions, and the accumulated data will enable public institutions to understand consumer needs and implement effective childcare support measures and countermeasures against the declining birthrate.

[0238] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0239] Step 1:

[0240] A user uses a smartphone app to input a question in a physical store. For example, the question might be input in the form of "Is a lightweight stroller better?" The input question is saved in text format in a data input field in the application.

[0241] Step 2:

[0242] The terminal receives a question entered by the user and converts it into JSON format. The converted data is sent to the server via a secure communication method (e.g., HTTPS). The input is text data, and the output is JSON format data. This data processing makes it easy for the server to process the question content.

[0243] Step 3:

[0244] The server receives JSON-formatted question data sent from the terminal. It validates the format and content of the received data, and if it is normal, passes it to the natural language processing engine. The input is JSON-formatted question data, and the output is validated data. The data calculations performed here check the data format and confirm the content.

[0245] Step 4:

[0246] The generative AI model analyzes the question data and generates an appropriate answer. The generation process uses a pre-prepared prompt (e.g., "Please generate an answer about the balance between lightness and durability of strollers"). The input is validated question data, and the output is the answer text. This data calculation generates answers based on natural language processing.

[0247] Step 5:

[0248] The server revalidates the answer data received from the generative AI and formats it for return to the terminal. The input is the generated answer text, and the output is the formatted data. The data processing performed here involves checking the answer data and converting its format.

[0249] Step 6:

[0250] The terminal receives the formatted response data and displays it on the screen in a format that is easy for the user to see. The input is the formatted response data, and the output is a display format that the user can visually recognize. The data processing performed here is to make the received data into a format that can be displayed.

[0251] Step 7:

[0252] The server saves the question and generated answer in a database. The input is the question and generated answer data, and the output is the saved data in the database. This process involves a write operation to the database.

[0253] Step 8:

[0254] The server periodically extracts and analyzes all data stored in the database to detect common issues. The input is past question and answer data extracted from the database, and the output is the analysis results. The data calculations performed here involve data analysis and trend extraction.

[0255] Step 9:

[0256] Based on the analysis results, the server sends common issues and trend information to public institutions as a report. The input is the analysis results, and the output is the sent report. This process involves report generation and transmission operations.

[0257] The above is a specific processing flow of the system that realizes the application example.

[0258] 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.

[0259] This invention combines a system that receives questions and inquiries from users, analyzes the questions using natural language processing, and generates appropriate answers, with an emotion engine that recognizes the user's emotions. The generated answers are optimized based on the user's emotional state and returned to the user. Furthermore, all question and answer data is stored in a database and periodically analyzed to extract common issues that are then sent to public institutions. This not only enables childcare consultations and measures to combat the declining birthrate, but also makes it possible to provide individual responses that take the user's emotions into consideration.

[0260] Explanation of program processing

[0261] 1. Question input and emotion recognition

[0262] User

[0263] The user uses the terminal to input a question or inquiry about childcare into the input field. For example, the user inputs something like, "What should I do if my child refuses to eat?"

[0264] 2. Sending input data and emotion data

[0265] Terminal

[0266] The input question is converted into JSON format. The emotion engine also recognizes the user's emotion from the input and sends the emotion data along with the question.

[0267] The converted data is sent to the server via a secure connection (e.g. HTTPS). Example: json { "question": "What should I do if my child refuses to eat?", "emotion": "frustration"}

[0268] 3. Receiving and analyzing question and emotion data

[0269] server

[0270] The server receives the question and emotion data sent from the device, validates the format and content of the received data, and eliminates invalid data.The data is then passed to the natural language processing engine and emotion engine.

[0271] Generative AI and Emotion Engines

[0272] The generative AI analyzes question data and generates appropriate answers, while the emotion engine uses user emotional data to optimize the generated answers.

[0273] For example, in response to the question, "What should I do if my child refuses to eat?"

[0274] When the emotional data "frustration" is included, it is optimized to say, "When your child refuses to eat something, first stay calm. Then, it is effective to offer them a small amount of their favorite food."

[0275] 4. Receiving and returning responses

[0276] server

[0277] The response data received from the generative AI and emotion engine is validated again and formatted appropriately, after which it is sent back to the device.

[0278] Terminal

[0279] The formatted response data is received and displayed to the user in an easy-to-understand format. For example, "When a child refuses to do something, first try to stay calm. Then, it can be effective to offer them a small amount of their favorite food."

[0280] 5. Data storage and analysis

[0281] server

[0282] The questions, generated answers, and emotion data are stored in a database. The data is stored as pairs of question content, answer content, and emotion data.

[0283] 6. Regular data analysis and problem extraction

[0284] server

[0285] All data stored in the database is periodically extracted and analyzed to detect common issues and trends, sometimes using machine learning algorithms.

[0286] 7. Extract and submit assignments

[0287] server

[0288] Common issues and trends are extracted from the analysis results and compiled into a report. This report is then sent to public institutions. Examples include "There are many inquiries about nighttime crying" or "There is an increase in inquiries about meals in certain areas."

[0289] Specific examples

[0290] context

[0291] When a user uses a terminal to input a question about a child-rearing problem, the user's emotions are also recognized.

[0292] Processing Flow

[0293] 1. The user enters a question into the device, and the emotion associated with the question is automatically recognized. For example, "What should I do if my child cries at night?" is entered, and the emotion indicated is "tired."

[0294] 2. The device sends the question and emotion data in JSON format to the server.

[0295] 3. The server passes the question and emotion data to the generative AI and emotion engine to generate an answer.

[0296] 4. The generative AI generates answers such as "regulate your sleep rhythm and create a relaxing environment," and the emotion engine takes "fatigue" into consideration and emphasizes the advice.

[0297] 5. The server generates the answer and sends it back to the user's device.

[0298] 6. The device displays the answer to the user. For example, "When your child cries at night, first check to see if you are tired. Then, it is effective to regulate your sleep rhythm and create a relaxing environment."

[0299] 7. The server stores the questions, answers, and emotion data in a database.

[0300] 8. Regularly analyze data to detect issues such as "many inquiries about nighttime crying."

[0301] 9. The server sends these issues as a report to the public agency.

[0302] This system not only enables quick responses to user questions and individual responses based on emotions, but also makes it possible to use the collected data to combat the declining birthrate.

[0303] The processing flow will be explained below.

[0304] Step 1:

[0305] The user uses the terminal to input a question or inquiry about childcare into the input field. For example, the user inputs a question such as "What should I do if my child refuses to eat?"

[0306] Step 2:

[0307] The device receives the input question as text data and uses an emotion engine to recognize the user's emotions. For example, it identifies the emotion "frustration" from the context of the input.

[0308] Step 3:

[0309] The device converts the question data and emotion data into JSON format. For example, it converts it into the following data format: json { "question": "What should I do if my child refuses to eat?", "emotion": "frustration"}

[0310] Step 4:

[0311] The device sends the converted data to the server using a secure communication method such as HTTPS, and the data is encrypted before transmission.

[0312] Step 5:

[0313] The server receives the question data and emotion data sent from the device, checks the format and content of the received data, and verifies that the format is correct.

[0314] Step 6:

[0315] The server passes the received question data and emotion data to a natural language processing engine (generative AI), which is called via an API endpoint.

[0316] Step 7:

[0317] Generative AI analyzes the question data and generates an appropriate answer, such as, "If your child doesn't like eating, it's important to first offer them small amounts of their favorite foods and find ways to make eating enjoyable."

[0318] Step 8:

[0319] The emotion engine uses the emotional data to optimize the generated answers. For example, if the emotional data includes "frustration," the response will be optimized to something like, "First, calm yourself down. Then, it's important to offer a small amount of your favorite food and find a way to make your meal enjoyable."

[0320] Step 9:

[0321] The server then performs a validation check on the optimized response data again and formats it into a format to be sent back to the terminal.

[0322] Step 10:

[0323] The server returns the formatted response data to the device using HTTPS, a secure method of communication.

[0324] Step 11:

[0325] The device receives the response data sent from the server and displays it to the user, such as, "First, calm yourself down. Then, it's important to find a way to enjoy your meal by offering small amounts of your favorite foods."

[0326] Step 12:

[0327] The server stores the questions, generated answers, and emotion data in a database. The stored data includes the question content, the answer content, and the emotion data.

[0328] Step 13:

[0329] The server periodically runs a job that analyzes all the data stored in the database, sometimes using machine learning algorithms.

[0330] Step 14:

[0331] The server extracts common issues and trends from the analysis results, for example, discovering common issues such as "there are many inquiries about nighttime crying" or "there is an increase in inquiries about meals in certain areas."

[0332] Step 15:

[0333] The server compiles the extracted issues and trend information into a report and sends it to the public institution. The data is sent securely using an API.

[0334] Step 16:

[0335] Based on the data received, public institutions will consider and implement measures to combat the declining birthrate. For example, they will plan and implement specific countermeasures, such as holding childcare consultation sessions in specific areas.

[0336] Example 2

[0337] 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."

[0338] Conventional systems were unable to consider the user's emotions when providing answers to user questions, resulting in a lack of individualized support. Furthermore, there was no established mechanism for effectively analyzing collected question and answer data to identify common issues and provide feedback to public institutions. This resulted in insufficient support for childcare consultations and in ineffective measures to combat the declining birthrate.

[0339] 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 receiving a question and emotion data from a user, means for analyzing the received question and emotion data using natural language processing and an emotion recognition engine to generate an answer, and means for optimizing the generated answer based on the user's emotion data and returning it to the user. This makes it possible to provide an individual response that takes the user's emotion into consideration, and also establishes a mechanism for storing the question, the generated answer, and the emotion data and periodically analyzing them to extract common issues and send them to public institutions.

[0340] A "user" is a person who uses the system to input questions or inquiries.

[0341] A "question" is a problem or inquiry about childcare that is input by a user.

[0342] "Emotion data" is emotional information analyzed from the questions and consultation contents entered by the user.

[0343] "Natural language processing" is a technology that analyzes text data, understands its meaning, and generates appropriate answers.

[0344] An "emotion recognition engine" is a technology that detects emotions from the user's input text and provides those emotions as data.

[0345] "Generative AI" is artificial intelligence that uses natural language processing to generate answers to user questions.

[0346] An "answer" is a system-generated answer or advice to a user's question.

[0347] "Optimization" refers to adjusting and improving answers by taking into account the user's emotional data.

[0348] "Saving" means storing the question data, answer data, and emotion data in a database.

[0349] A "database" is a system for structuring, storing, and managing questions, answers, and emotional data.

[0350] "Periodic analysis" refers to the process of extracting data stored in the database at regular intervals to detect common issues and trends.

[0351] A "common issue" is a common problem or trend that becomes apparent when analyzing data collected from multiple users.

[0352] "Public institutions" are government or administrative agencies that provide childcare support and take measures to combat the declining birthrate.

[0353] "Feedback" refers to the act of reporting and providing analysis results and common issues to public institutions.

[0354] This invention combines a system that receives questions and inquiries from users, analyzes the questions using natural language processing, and generates appropriate answers, with an emotion engine that recognizes the user's emotions. The answers generated by this system are optimized based on the user's emotional data and returned to the user. In addition, all question and answer data is stored in a database and periodically analyzed to extract common issues that are then sent to public institutions. This system not only enables childcare consultations and measures to combat the declining birthrate, but also enables individual responses that take the user's emotions into consideration.

[0355] First, the user uses the device to enter a question or request for advice about childcare into an input field. For example, they might enter something like, "What should I do if my child refuses to eat?" The entered question is converted into JSON format on the device, and at the same time, an emotion engine analyzes the user's input and recognizes the emotion. This converted data is then sent to the server using a secure communication method (e.g., HTTPS).

[0356] The server receives the question and emotion data sent from the device and performs validation checks on the data format and content. If the received data is valid, it is passed to the natural language processing engine and emotion engine. A generative AI model analyzes the question data and generates an appropriate answer. The emotion engine also uses the user's emotion data to optimize the generated answer based on the emotion data. For example, if the question "What should I do if my child refuses to eat?" contains the emotion data "frustration," the answer will be optimized to "When a child refuses to eat, first stay calm. Then, it can be effective to offer them a small amount of their favorite food."

[0357] The server then validates the response data received from the generative AI and emotion engine, formats it appropriately, and sends it back to the device. The device receives the formatted response data and displays it in a format that is easy for the user to understand. For example, it might say, "When your child is refusing to do something, first try to stay calm. Then, it can be effective to offer them a small amount of their favorite food."

[0358] Furthermore, the server stores the questions, generated answers, and emotion data in a database. This data is stored as pairs of question content, answer content, and emotion data. The server periodically accesses the database, extracts and analyzes all stored data. Data analysis may use machine learning algorithms to detect common issues and trends. Issues extracted based on this are compiled into a report and sent to public institutions. This provides data that can be used to improve childcare consultation services and address the declining birthrate.

[0359] As a concrete example, we will show how the system recognizes the user's emotions when they use a device to input a question about a parenting problem. For example, if the user inputs, "What should I do if my child cries at night?" and indicates "fatigue" as their emotion, this data is sent to the server in JSON format. The server receives the data and passes it to a natural language processing engine and emotion engine. The generative AI model generates an answer such as "regulate your sleep rhythm and create a relaxing environment," and the emotion engine emphasizes the answer by taking "fatigue" into account. The server reconfirms this and sends it back to the device. The device then displays the answer to the user: "When your child cries at night, first check whether you are tired. Then, it is effective to regulate your sleep rhythm and create a relaxing environment." All questions, answers, and emotion data collected during this process are stored in a database and used for later analysis.

[0360] In this way, the system of the present invention makes it possible to respond in a way that takes into account the user's emotions, and the collected data can be used to combat the declining birthrate.

[0361] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0362] Step 1:

[0363] The user enters a question into the terminal.

[0364] Input: The user types "What should I do if my child refuses to eat?" into the device's input field.

[0365] Operation: The terminal interface monitors the user's input, detects when the input is complete, and prepares to send it.

[0366] Output: User question text data.

[0367] Step 2:

[0368] The device analyzes the emotion data, converts it into JSON format, and sends it to the server.

[0369] Input: User question text data.

[0370] How it works: The emotion engine analyzes the user's text data and recognizes the user's emotions.

[0371] Output: json { "question": "What should I do if my child refuses to eat?", "emotion": "frustration"} The data converted to JSON format is sent to the server via HTTPS.

[0372] Step 3:

[0373] The server receives the question and emotion data and performs a validation check.

[0374] Input: JSON format data sent from the terminal.

[0375] Behavior: The server checks the received JSON data for formatting and content errors. If there are any invalid or missing data, it logs it and stops parsing.

[0376] Output: Question and sentiment data in legal JSON format.

[0377] Step 4:

[0378] The server passes the data to a natural language processing engine and an emotion engine to generate an answer.

[0379] Input: Question and sentiment data in legal JSON format.

[0380] How it works: The generative AI model analyzes the question and generates an initial answer. Meanwhile, the emotion engine optimizes the answer based on the user's emotional data. For example, based on the emotional data "frustration," it generates an answer such as, "When your child refuses to do something, first stay calm. Then, it's effective to offer them a small amount of their favorite food."

[0381] Output: Optimized answer data.

[0382] Step 5:

[0383] The server validates the generated response data and returns it to the terminal.

[0384] Input: Optimized response data.

[0385] Operation: The server formats the response data, performs a validation check again to ensure there are no errors in the format or content, and then returns the response data to the device via HTTPS.

[0386] Output: The response data sent to the device.

[0387] Step 6:

[0388] The terminal receives the response data and displays it to the user.

[0389] Input: The response data sent from the server.

[0390] What it does: The device interface parses the received response data and displays it to the user in a user-friendly format.

[0391] Output: "When your child refuses to eat something, first stay calm. Then, offering them a small amount of their favorite food can be effective."

[0392] Step 7:

[0393] The server stores the questions, answers, and emotion data in a database.

[0394] Input: Question data, generated answer data, sentiment data.

[0395] How it works: The server structures and stores this data in a database.

[0396] Output: Questions, answers, and sentiment data recorded in a database.

[0397] Step 8:

[0398] The server periodically analyzes the data in the database and extracts common issues.

[0399] Input: Saved question data, answer data, and sentiment data.

[0400] How it works: The server uses machine learning algorithms to analyze the data and detect common issues and trends, for example, "There are a lot of inquiries about nighttime crying."

[0401] Output: Report data as the analysis result.

[0402] Step 9:

[0403] The server sends common issues to the public agency in the form of a report.

[0404] Input: Analysis result report data.

[0405] How it works: The server generates a report and sends it to the public agency using secure communications.

[0406] Output: Report sent to public authorities.

[0407] (Application example 2)

[0408] 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."

[0409] In food delivery services, it is difficult for customers to receive appropriate and sensitive responses when they experience delays or problems with their orders. Furthermore, service providers lack sufficient means to proactively utilize customer feedback to improve their services. Furthermore, there is a lack of a system for systematically identifying common issues and incorporating them into service improvements.

[0410] The identification process 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 receiving a question from a user, means for analyzing the received question using natural language processing and generating an answer, means for returning the generated answer to the user, means for saving the question and the generated answer, means for analyzing the saved question and answer and extracting common issues, means for sending the extracted issues to a public institution, emotion recognition means for recognizing the emotion of the user when entering the question, and means for optimizing the generated answer by taking the user's emotion into consideration. This enables customers to receive prompt and emotionally sensitive service, and enables service providers to improve the quality of their services by utilizing the collected data.

[0411] "User" refers to an individual, corporation, or service user who uses the system to ask questions or ask for advice.

[0412] The "means for receiving a question" refers to a function for the server to receive question data sent from a user via the Internet or a mobile application.

[0413] "Natural language processing" refers to the technology of using a computer to analyze natural human language, understand its meaning, and generate appropriate answers.

[0414] "Means for generating an answer" refers to a function for analyzing a received question and automatically generating an appropriate answer to that question.

[0415] "Means for returning an answer" refers to a function for sending the generated answer to the user's device and displaying it to the user.

[0416] "Means for storing questions and answers" refers to a function for storing received questions and generated answers in a database.

[0417] "Means of analyzing saved questions and answers and extracting common issues" refers to a function that periodically analyzes data stored in the database to find problems and areas for improvement common to multiple questions and answers.

[0418] "Means for sending issues to public institutions" refers to the function for compiling extracted issues and trends into a report format and sending it to public institutions, etc.

[0419] "Emotion recognition means" refers to a function for analyzing and recognizing the emotion expressed by the user when entering a question.

[0420] The "means for optimizing the generated answer by taking emotions into consideration" refers to a function for adjusting the generated answer to a more appropriate form according to the user's emotions.

[0421] "Food delivery service" refers to a service that allows users to order meals online and have the meals delivered.

[0422] This invention provides a system for providing a food delivery service that responds to user questions quickly and with consideration for their feelings. A specific implementation method of this system will be described below.

[0423] First, a user uses a smartphone or tablet to input a question or complaint about the food delivery service. When inputting a question, the emotion recognition means analyzes the emotion from the user's input and transmits the emotion data along with the question. The question and emotion data are then converted into JSON format and transmitted to the server using a secure communication method (e.g., HTTPS).

[0424] The server validates the received question and emotion data and passes the data to the natural language processing engine, generative AI model, and emotion recognition engine. The natural language processing engine analyzes the question data and generates an appropriate answer. Meanwhile, the emotion recognition engine uses the user's emotion data to optimize the generated answer. This makes it possible to provide an appropriate answer that takes the user's emotions into consideration.

[0425] The generated answer is validated again, formatted into an appropriate format, and sent back to the user's device. The device receives the formatted answer data and displays it in an easy-to-understand format for the user.

[0426] Furthermore, the questions, generated answers, and sentiment data are stored in a database. The server periodically analyzes the data and detects common issues and trends from the stored data. This allows food delivery service providers to identify areas for improvement and take necessary measures.

[0427] As a concrete example, consider the case where a user sends a question such as, "My order is late. When will it arrive?" In response to this question, the emotion recognition means detects "frustration," and the generative AI model generates the answer, "It will arrive in 15 to 20 minutes." The emotion recognition engine then optimizes the answer to, "We apologize for the inconvenience, but it will arrive in 15 to 20 minutes." This allows for a prompt and appropriate response to be provided to the user.

[0428] An example prompt is:

[0429] If the emotion recognition result for the question "My order is delayed. When will it arrive?" is "frustration," the generative AI model will generate the answer "It will arrive in 15 to 20 minutes." Then, as a result of optimization by the emotion recognition engine, the final answer will be provided: "We apologize for the inconvenience, but your order is expected to arrive in 15 to 20 minutes."

[0430] The main hardware used includes user devices (smartphones and tablets), cloud servers, and network equipment. The software used includes ANDROID (registered trademark) / iOS apps, Python, TENSORFLOW (registered trademark), Watson (registered trademark) NLP services, and Emotion Recognition API. Combining these components makes it possible to efficiently implement a question-answering system for food delivery services.

[0431] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0432] Step 1:

[0433] A user uses a smartphone or tablet device to input questions or complaints about food delivery services. When the user enters a question in the input field and presses the send button, the question is received by the device. At this time, the emotion recognition means analyzes the emotion from the user's input. The input is made by the user, and the output is question data accompanied by analyzed emotion data.

[0434] Step 2:

[0435] The device converts the input question and emotion data into JSON format. The converted data is sent to the server using a secure communication method (e.g., HTTPS). The input is the user's question data and emotion data, and the output is the data converted into JSON format.

[0436] Step 3:

[0437] The server performs validation checks on the questions and emotion data it receives. After filtering out invalid data, it passes the data to the natural language processing engine, generative AI model, and emotion recognition engine. The input is question data and emotion data in JSON format, and the output is the data required for analysis and optimization.

[0438] Step 4:

[0439] The natural language processing engine analyzes the question data and generates an appropriate answer. The generative AI model analyzes the question content and suggests the most appropriate answer. The input is validated question data, and the output is the generated answer data.

[0440] Step 5:

[0441] The emotion recognition engine uses the user's emotional data to optimize the generated answer, adjusting the wording and approach according to the user's emotions. The input is the generated answer data and emotional data, and the output is the optimized answer data.

[0442] Step 6:

[0443] The server revalidates the response data received from the generative AI and emotion recognition engine and formats it appropriately. It then returns the response data to the device. The input is the optimized response data, and the output is the formatted response data.

[0444] Step 7:

[0445] The terminal displays the formatted answer data received from the server in an easy-to-understand manner to the user. The user checks the answer displayed on the terminal screen. The input is the formatted answer data, and the output is the displayed answer.

[0446] Step 8:

[0447] The server stores the question, the generated answer, and the emotion data in a database. The data is stored as pairs of question content, answer content, and emotion data. The input is the question data, answer data, and emotion data, and the output is the stored data.

[0448] Step 9:

[0449] The server periodically extracts and analyzes all data stored in the database to detect common issues and trends. Machine learning algorithms may be used for data analysis. The input is the data in the database, and the output is the analysis results.

[0450] Step 10:

[0451] The server extracts common issues and trends from the analysis results and compiles them into a report, which is then sent to public institutions and food delivery service providers. The input is the analysis results, and the output is a summary in report format and its transmission.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] [Second embodiment]

[0456] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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).

[0462] 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.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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."

[0468] This invention is a system that receives questions and inquiries from users, analyzes the questions using natural language processing, and generates appropriate answers. The generated answers are returned to the users, and all question and answer data is stored in a database. This data is periodically analyzed, and common issues are extracted and sent to public institutions. Through this process, we are able to respond to inquiries about childcare and take measures to combat the declining birthrate.

[0469] Explanation of program processing

[0470] 1. Enter and submit your question

[0471] User

[0472] The user uses the terminal to input questions or inquiries about childcare into the input field.

[0473] For example: "What should I do if my child refuses to eat?"

[0474] 2. Sending input data

[0475] Terminal

[0476] Convert the input question into JSON format.

[0477] The converted data is sent to the server via a secure communication method (e.g., HTTPS).

[0478] 3. Receiving and analyzing questions

[0479] server

[0480] The server receives the query data sent from the terminal.

[0481] The format and content of the received data are validated, and if normal, it is passed to the natural language processing engine.

[0482] Generative AI

[0483] Analyze the question data and generate appropriate answers.

[0484] For example: "If your child is reluctant to eat, it's a good idea to start by offering them small amounts of their favorite foods. It's also important to find ways to make eating enjoyable."

[0485] 4. Receiving and returning responses

[0486] server

[0487] Receive response data from the generative AI.

[0488] The received response data is validated again and formatted to be returned to the terminal.

[0489] Terminal

[0490] The formatted answer data is received and displayed on the screen in a format that is easy for the user to view.

[0491] Example: Displayed answer: "If your child is reluctant to eat, it's a good idea to start by offering them small amounts of their favorite foods. It's also important to find ways to make eating enjoyable."

[0492] 5. Data storage and analysis

[0493] server

[0494] Save the questions and generated answers in a database.

[0495] All data stored in the database is periodically extracted and analyzed to detect common issues.

[0496] 6. Extract and submit assignments

[0497] server

[0498] Based on the results of the analysis, common issues and trends are extracted.

[0499] The extracted issues and trend information will be sent to public institutions as a report.

[0500] Examples: "There has been an increase in consultations regarding diet," "There are many consultations regarding night crying in certain areas," etc.

[0501] Specific examples

[0502] context

[0503] The user uses the terminal to input a question about a child-rearing problem.

[0504] Sample question: "What should I do if my child cries at night?"

[0505] Processing Flow

[0506] 1. The user types a question into the terminal.

[0507] 2. The device sends the question to the server in JSON format.

[0508] 3. The server passes the question to a generative AI, which generates an answer.

[0509] 4. The generative AI generated the answer, "Effective ways to deal with nighttime crying include adjusting your baby's sleep rhythm and creating a relaxing environment."

[0510] 5. The server generates the answer and sends it back to the user's device.

[0511] 6. The device displays the answer to the user.

[0512] 7. The server stores the question and answer data in a database.

[0513] 8. Regularly analyze the data and identify the issue of "many inquiries about nighttime crying."

[0514] 9. The server sends this issue as a report to the public agency.

[0515] In this way, the system provides a mechanism for quickly responding to user questions and utilizing the collected data to combat the declining birthrate. This system is both convenient for users and a valuable source of information for public institutions.

[0516] The processing flow will be explained below.

[0517] Step 1:

[0518] The user uses the device to enter a question or inquiry about childcare into the input field. For example, "What should I do if my child refuses to eat?"

[0519] Step 2:

[0520] The device converts the entered question into an appropriate data format, such as JSON. Specifically, it converts it into the following format: json { "question": "What should I do if my child refuses to eat?"}

[0521] Step 3:

[0522] The device sends the converted data to the server using a secure communication method such as HTTPS. The data is encrypted and managed to reach the server safely.

[0523] Step 4:

[0524] The server receives the query data sent from the terminal, validates the format and content of the received data, and eliminates invalid data.

[0525] Step 5:

[0526] The server passes the received question data to a natural language processing engine (e.g., a generative AI). The engine is called via an API endpoint and analyzes the question and generates an answer.

[0527] Step 6:

[0528] Generative AI analyzes question data and generates appropriate answers, such as, "If your child doesn't like to eat, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find ways to make eating fun."

[0529] Step 7:

[0530] The server then validates the answer data received from the generative AI and formats it into the appropriate format. Validation includes checking the consistency and quality of the answer text.

[0531] Step 8:

[0532] The server returns the formatted response data to the terminal, usually via HTTPS.

[0533] Step 9:

[0534] The device receives the response data sent from the server and displays it in an easy-to-understand manner to the user. For example, it displays, "If your child doesn't like to eat, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find ways to make eating fun."

[0535] Step 10:

[0536] The server stores the questions and generated answers in a database. The data is stored as pairs of question and answer.

[0537] Step 11:

[0538] The server periodically runs jobs that analyze the question and answer data stored in the database, sometimes using machine learning algorithms.

[0539] Step 12:

[0540] The server extracts common issues and trends from the analysis results. For example, it finds patterns from data such as "there are many consultations about nighttime crying" or "the number of consultations about eating is increasing."

[0541] Step 13:

[0542] The server compiles the extracted issues and trend information into a report format and sends it to the public institution via API or secure data transmission methods.

[0543] Step 14:

[0544] Based on the data received, public institutions will consider and implement measures to combat the declining birthrate. Specific countermeasures will be planned and implemented for the issues identified.

[0545] Example 1

[0546] 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."

[0547] Currently, many childcare-related questions and inquiries are handled individually, without effective data analysis or sharing. This makes it difficult to effectively utilize this data and link it to improving childcare support and measures to combat the declining birthrate. Furthermore, there is a lack of a system for providing prompt, appropriate answers to user questions.

[0548] 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.

[0549] In this invention, the server includes means for receiving questions from users, means for converting the received questions into a data format and transmitting the data, means for validating the format and content of the received data and, if normal, passing the data to an analysis engine, means for analyzing the question data using a generative AI model and generating an appropriate answer, means for returning the generated answer to the user, means for saving the questions and the generated answers, means for analyzing the saved questions and answers and extracting common issues, and means for sending the extracted issues to public institutions. This makes it possible to provide users with prompt and appropriate answers and to utilize data to support childcare and address the declining birthrate.

[0550] "User" refers to a person who inputs questions or inquiries about childcare into the system.

[0551] A "terminal" is a device used by a user to input questions or inquiries, and includes smartphones, personal computers, etc.

[0552] "Server" refers to a central processing unit for receiving user questions, passing the data to the analysis engine, and transmitting generated answers.

[0553] A "question" refers to a childcare-related question that a user enters into an input field.

[0554] "Received data" refers to the data that the server receives after converting the question entered by the user into a data format such as JSON.

[0555] "Validation" refers to the process of checking that received data is in the correct format and contains expected content.

[0556] "Analytics Engine" refers to software or algorithms that analyze incoming data and generate appropriate answers.

[0557] A "generative AI model" refers to a machine learning model that uses generative AI to generate appropriate answers to user questions.

[0558] "Answer" refers to the information generated by a generative AI model and returned in response to a user's question.

[0559] "Saving" refers to the act of storing the question and its generated answer in a database.

[0560] "Database" means a digital storage system for managing and storing saved question and answer data.

[0561] "Analysis" refers to the process of analyzing stored data to extract common issues.

[0562] "Common issues" refers to themes or issues that frequently emerge from multiple questions and their answers.

[0563] A "public institution" refers to an organization that operates for the public good, such as a government or local government.

[0564] The present invention is a system that receives questions and inquiries about childcare from users, analyzes them, and generates answers. The system includes a device used by the user, a server that processes and stores data, and a generative AI model that performs natural language processing.

[0565] The user uses the device to input a question or inquiry. The user opens a browser on their smartphone or PC, accesses a dedicated web form, and enters the question in the input field. For example, they might enter, "What should I do if my child refuses to eat?" and click the send button.

[0566] The device converts the question entered by the user into JSON format, for example, {"question": "What should I do if my child refuses to eat?"}. The converted data is securely sent to the server using the HTTPS protocol.

[0567] The server receives the question data sent from the device. It validates the format and content of the received data, and if it is normal, passes it to the analysis engine. After format checks and XSS attack countermeasures, it passes the question data to the generative AI model as a prompt text. Examples of prompt text are as follows:

[0568] "Question: What should I do if my child refuses to eat? Generate an appropriate answer."

[0569] A generative AI model (e.g., OpenAI GPT-4) receives a prompt and generates an answer based on the training data, such as, "If your child refuses to eat, it's a good idea to offer them a small amount of their favorite food first. It's also important to find ways to make eating enjoyable."

[0570] The server receives the answer data from the generative AI model. The received answer data is validated again, and if normal, it is formatted to be sent back to the device. The content of the answer data is checked and formatted, for example, {"answer": "If a child doesn't like eating, it's a good idea to first offer them a small amount of their favorite food. It's also important to find a way to make eating enjoyable."}

[0571] The device analyzes the response data received from the server and displays it on the screen in an easy-to-read format for the user. An example of what is displayed is, "If your child doesn't like to eat, it's a good idea to first offer them a small amount of their favorite food. It's also important to find ways to make eating fun."

[0572] The server saves the question and the generated answer in a database. The question and answer are stored in the database in JSON format. For example, it is saved as follows: {"question": "What should I do if my child refuses to eat?", "answer": "If a child refuses to eat, it is a good idea to start by offering them a small amount of their favorite food. It is also important to find ways to make eating enjoyable."}

[0573] The system periodically extracts and analyzes all data stored in the database to detect common issues. The server runs a regularly scheduled task to retrieve past questions and answers from the database and uses natural language processing technology to extract common topics and trends. For example, it detects an increase in questions related to night crying.

[0574] Based on the analysis results, the extracted issues and trend information are sent to the public institution as a report. The generated report is formatted in PDF or CSV format and sent to the API endpoint or email address specified by the public institution. For example, a report containing content such as "Recent trend: Increase in the number of consultations about nighttime crying" is sent.

[0575] This system provides users with quick and appropriate answers, and also provides a mechanism that makes it possible to utilize data to support childcare and implement measures to combat the declining birthrate.

[0576] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0577] Step 1:

[0578] The user uses the device to enter a question or request for advice about childcare into an input field. Specifically, the user opens a browser on their smartphone or PC, accesses a dedicated web form, enters "What should I do if my child refuses to eat?" into the input field, and clicks the send button. The input is the question from the user, and the output is saved on the device as this question data.

[0579] Step 2:

[0580] The terminal converts the question entered by the user into JSON format. Specifically, the terminal parses the user's input text and converts it into a JSON object of key-value pairs (e.g., {"question": "What should I do if my child refuses to eat?"}). The input is the text entered by the user, and the output is question data in JSON format.

[0581] Step 3:

[0582] The terminal sends the converted JSON data to the server using the HTTPS protocol. Specifically, the terminal includes the generated JSON object in the HTTPS request body and sends a POST request to the specified endpoint on the server. The input is the question data in JSON format, and the data is sent to the server as the output.

[0583] Step 4:

[0584] The server receives the question data sent from the terminal. Specifically, the server receives the HTTPS request and extracts JSON data from the request body. The input is the received HTTPS request, and the output is the extracted JSON-formatted question data.

[0585] Step 5:

[0586] The server validates the format and content of the received data. Specific operations include format checks (e.g., checking the existence of keys) and XSS attack prevention. The input is JSON-formatted question data, and the output is validated JSON data. If this validated data is valid, it is passed to the analysis engine.

[0587] Step 6:

[0588] If everything is normal, the server passes the question data to the generative AI model as a prompt text. Specifically, it generates a prompt text and sends it to the generative AI model. An example of a prompt text is: "Question: What should I do if my child refuses to eat? Please generate an appropriate answer." The input is validated JSON data, and the output is a prompt text.

[0589] Step 7:

[0590] A generative AI model receives a prompt, analyzes the question data, and generates an appropriate answer. Specifically, a generative AI model (e.g., OpenAI GPT-4) analyzes the prompt and generates an answer based on the training data. An example of a generated answer is: "If a child doesn't like eating, it's a good idea to first offer them a small amount of their favorite food. It's also important to find a way to make eating enjoyable." The input is a prompt, and the output is a generated answer.

[0591] Step 8:

[0592] The server receives the answer data from the generative AI model. Specifically, the server receives the answer generated from the API of the generative AI model. The generated answer data is the input, and it is saved on the server as the output.

[0593] Step 9:

[0594] The server revalidates the received response data. Specifically, it checks the content of the response data (e.g., whether it contains any undesirable content). The input is the generated response data, and the output is the validated response data.

[0595] Step 10:

[0596] The server formats the validated answer data into a format to be sent back to the device. Specifically, it formats the answer in JSON format, for example, {"answer": "If a child doesn't like eating, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find ways to make eating enjoyable."}. The input is the validated answer data, and the output is the formatted answer data.

[0597] Step 11:

[0598] The device analyzes the response data received from the server and displays it on the screen in a format that is easy for the user to view. Specifically, the device analyzes the JSON data received from the server and displays the response in the browser's display area. An example of what is displayed is, "If your child doesn't like to eat, it's a good idea to first offer them a small amount of their favorite food. It's also important to find a way to make eating enjoyable." The input is the formatted response data, and the output is displayed to the user.

[0599] Step 12:

[0600] The server saves the question and the generated answer in a database. Specifically, the question and answer are stored in the database in JSON format. Example of saved data: {"question": "What should I do if my child doesn't want to eat?", "answer": "If a child doesn't want to eat, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find a way to make eating enjoyable."}. The input is the question and the generated answer data, and the output is saved in the database.

[0601] Step 13:

[0602] The server periodically extracts and analyzes all data stored in the database to detect common issues. Specifically, the server executes a regularly scheduled task to retrieve past questions and answers from the database and uses natural language processing technology to extract common topics and trends. For example, it detects an increase in questions related to nighttime crying. The input is the question and answer data stored in the database, and the output is the detection of common issues.

[0603] Step 14:

[0604] Based on the results of the analysis, the server sends the extracted issues and trend information to the public institution as a report. Specifically, the generated report is formatted in PDF or CSV format and sent to an API endpoint or email address specified by the public institution. For example, a report titled "Recent trends: Increase in the number of consultations about nighttime crying" is sent. Common issues and trend information are input, and the report is sent to the public institution as output.

[0605] (Application example 1)

[0606] 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."

[0607] One issue facing brick-and-mortar stores is the lack of a way for customers to quickly and appropriately resolve questions about childcare or products without having to ask staff directly. There is also a need for a system that accumulates and analyzes customer question data and provides the information to public institutions to contribute to childcare support measures and measures to combat the declining birthrate throughout society.

[0608] 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.

[0609] In this invention, the server includes means for receiving questions from users, means for analyzing the received questions using natural language processing and generating answers, means for returning the generated answers to the users, means for saving the questions and the generated answers, means for analyzing the saved questions and answers and extracting common issues, means for sending the extracted issues to public institutions, means for responding to customer questions in physical stores, and means for displaying the generated answers on the customer's terminal. This makes it possible to quickly and appropriately respond to customer questions in physical stores, and to analyze the accumulated data and utilize it for childcare support measures and measures to combat the declining birthrate throughout society.

[0610] "User" means an individual or organization that uses the system to ask questions or make inquiries.

[0611] A "question" is a question or inquiry submitted by a user to the system.

[0612] "Natural language processing" is a technology that allows a machine to understand input questions or consultation content and generate appropriate answers.

[0613] An "answer" is a response generated in response to a question analyzed by natural language processing.

[0614] The "receiving means" refers to a mechanism or device for receiving a question from a user.

[0615] A "return mechanism" is a mechanism or device for returning the generated answer to the user.

[0616] A "storage means" is a mechanism or device for storing questions and generated answers for a certain period of time.

[0617] "Analysis means" refers to a mechanism or device for analyzing stored questions and answers.

[0618] "Issue extraction means" refers to mechanisms or devices for identifying common problems or trends based on analysis.

[0619] "Public agency transmission means" refers to the mechanism or device for transmitting the identified issues to the relevant public agencies.

[0620] A "brick and mortar store" is a physical commercial establishment where customers visit and purchase goods in person.

[0621] "Response methods" refer to mechanisms and devices that allow a physical store to respond quickly to customer questions.

[0622] A "terminal" is an electronic device that a user uses to enter questions and receive answers.

[0623] This invention realizes a system that receives questions from customers in a physical store, processes them, answers them, and returns them. The specific implementation method and operation of this system are described below.

[0624] System Overview

[0625] This system is realized using a user device (such as a smartphone), a server, and a generative AI model. The main hardware and software components and their roles are described below.

[0626] Hardware and Software Used

[0627] User device: The device on which customers enter their questions and receive answers. This could be a smartphone or tablet.

[0628] Server: The central component that receives questions, generates answers, stores and analyzes data, and sends reports to public authorities.

[0629] Usage example: Cloud servers (Amazon Web Services, Google Cloud Platform)

[0630] Generative AI model: Analyzes questions and generates appropriate answers. The following natural language processing engines are used:

[0631] Usage examples: Amazon Lex, Google Dialogflow

[0632] Program processing overview

[0633] 1. Enter and submit your question

[0634] A user uses a smartphone app in a physical store to input a question, for example, "Is it better to have a lightweight stroller?"

[0635] 2. Sending input data

[0636] The device converts the entered question into JSON format and sends it to the server using HTTPS.

[0637] 3. Receiving and analyzing questions

[0638] The server receives the input data, validates the format and content, and if there are no problems, passes it to the natural language processing engine.

[0639] A generative AI model (e.g., Amazon Lex) analyzes the question and generates an appropriate answer, such as, "A lightweight stroller is easy to use, but durability should also be considered."

[0640] 4. Receiving and returning responses

[0641] The server receives the generated response, validates it, and then formats it into a format to be sent back to the user's terminal.

[0642] The terminal receives the response data and displays it in an easy-to-read format for the customer.

[0643] 5. Data storage and analysis

[0644] The server stores the questions and generated answers in a database.

[0645] The contents of the database are analyzed periodically to extract common issues.

[0646] 6. Extract and submit assignments

[0647] Based on the analysis results, the server extracts common issues and trends and sends them to public institutions as a report.

[0648] Specific examples

[0649] Enter your question

[0650] A user types a question in a physical store.

[0651] For example: "Is a lighter stroller better?"

[0652] Prompt Sentence Examples

[0653] A user asked: "Is a lighter stroller better?"

[0654] Context for Answer Generation: Generate an answer about the balance between lightweight and sturdy strollers.

[0655] This system will enable physical stores to respond quickly and appropriately to customer questions, and the accumulated data will enable public institutions to understand consumer needs and implement effective childcare support measures and countermeasures against the declining birthrate.

[0656] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0657] Step 1:

[0658] A user uses a smartphone app to input a question in a physical store. For example, the question might be input in the form of "Is a lightweight stroller better?" The input question is saved in text format in a data input field in the application.

[0659] Step 2:

[0660] The terminal receives a question entered by the user and converts it into JSON format. The converted data is sent to the server via a secure communication method (e.g., HTTPS). The input is text data, and the output is JSON format data. This data processing makes it easy for the server to process the question content.

[0661] Step 3:

[0662] The server receives JSON-formatted question data sent from the terminal. It validates the format and content of the received data, and if it is normal, passes it to the natural language processing engine. The input is JSON-formatted question data, and the output is validated data. The data calculations performed here check the data format and confirm the content.

[0663] Step 4:

[0664] The generative AI model analyzes the question data and generates an appropriate answer. The generation process uses a pre-prepared prompt (e.g., "Please generate an answer about the balance between lightness and durability of strollers"). The input is validated question data, and the output is the answer text. This data calculation generates answers based on natural language processing.

[0665] Step 5:

[0666] The server revalidates the answer data received from the generative AI and formats it for return to the terminal. The input is the generated answer text, and the output is the formatted data. The data processing performed here involves checking the answer data and converting its format.

[0667] Step 6:

[0668] The terminal receives the formatted response data and displays it on the screen in a format that is easy for the user to see. The input is the formatted response data, and the output is a display format that the user can visually recognize. The data processing performed here is to make the received data into a format that can be displayed.

[0669] Step 7:

[0670] The server saves the question and generated answer in a database. The input is the question and generated answer data, and the output is the saved data in the database. This process involves a write operation to the database.

[0671] Step 8:

[0672] The server periodically extracts and analyzes all data stored in the database to detect common issues. The input is past question and answer data extracted from the database, and the output is the analysis results. The data calculations performed here involve data analysis and trend extraction.

[0673] Step 9:

[0674] Based on the analysis results, the server sends common issues and trend information to public institutions as a report. The input is the analysis results, and the output is the sent report. This process involves report generation and transmission operations.

[0675] The above is a specific processing flow of the system that realizes the application example.

[0676] 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.

[0677] This invention combines a system that receives questions and inquiries from users, analyzes the questions using natural language processing, and generates appropriate answers, with an emotion engine that recognizes the user's emotions. The generated answers are optimized based on the user's emotional state and returned to the user. Furthermore, all question and answer data is stored in a database and periodically analyzed to extract common issues that are then sent to public institutions. This not only enables childcare consultations and measures to combat the declining birthrate, but also makes it possible to provide individual responses that take the user's emotions into consideration.

[0678] Explanation of program processing

[0679] 1. Question input and emotion recognition

[0680] User

[0681] The user uses the terminal to input a question or inquiry about childcare into the input field. For example, the user inputs something like, "What should I do if my child refuses to eat?"

[0682] 2. Sending input data and emotion data

[0683] Terminal

[0684] The input question is converted into JSON format. The emotion engine also recognizes the user's emotion from the input and sends the emotion data along with the question.

[0685] The converted data is sent to the server via a secure connection (e.g. HTTPS). Example: json { "question": "What should I do if my child refuses to eat?", "emotion": "frustration"}

[0686] 3. Receiving and analyzing question and emotion data

[0687] server

[0688] The server receives the question and emotion data sent from the device, validates the format and content of the received data, and eliminates invalid data.The data is then passed to the natural language processing engine and emotion engine.

[0689] Generative AI and Emotion Engines

[0690] The generative AI analyzes question data and generates appropriate answers, while the emotion engine uses user emotional data to optimize the generated answers.

[0691] For example, in response to the question, "What should I do if my child refuses to eat?"

[0692] When the emotional data "frustration" is included, it is optimized to say, "When your child refuses to eat something, first stay calm. Then, it is effective to offer them a small amount of their favorite food."

[0693] 4. Receiving and returning responses

[0694] server

[0695] The response data received from the generative AI and emotion engine is validated again and formatted appropriately, after which it is sent back to the device.

[0696] Terminal

[0697] The formatted response data is received and displayed to the user in an easy-to-understand format. For example, "When a child refuses to do something, first try to stay calm. Then, it can be effective to offer them a small amount of their favorite food."

[0698] 5. Data storage and analysis

[0699] server

[0700] The questions, generated answers, and emotion data are stored in a database. The data is stored as pairs of question content, answer content, and emotion data.

[0701] 6. Regular data analysis and problem extraction

[0702] server

[0703] All data stored in the database is periodically extracted and analyzed to detect common issues and trends, sometimes using machine learning algorithms.

[0704] 7. Extract and submit assignments

[0705] server

[0706] Common issues and trends are extracted from the analysis results and compiled into a report. This report is then sent to public institutions. Examples include "There are many inquiries about nighttime crying" or "There is an increase in inquiries about meals in certain areas."

[0707] Specific examples

[0708] context

[0709] When a user uses a terminal to input a question about a child-rearing problem, the user's emotions are also recognized.

[0710] Processing Flow

[0711] 1. The user enters a question into the device, and the emotion associated with the question is automatically recognized. For example, "What should I do if my child cries at night?" is entered, and the emotion indicated is "tired."

[0712] 2. The device sends the question and emotion data in JSON format to the server.

[0713] 3. The server passes the question and emotion data to the generative AI and emotion engine to generate an answer.

[0714] 4. The generative AI generates answers such as "regulate your sleep rhythm and create a relaxing environment," and the emotion engine takes "fatigue" into consideration and emphasizes the advice.

[0715] 5. The server generates the answer and sends it back to the user's device.

[0716] 6. The device displays the answer to the user. For example, "When your child cries at night, first check to see if you are tired. Then, it is effective to regulate your sleep rhythm and create a relaxing environment."

[0717] 7. The server stores the questions, answers, and emotion data in a database.

[0718] 8. Regularly analyze data to detect issues such as "many inquiries about nighttime crying."

[0719] 9. The server sends these issues as a report to the public agency.

[0720] This system not only enables quick responses to user questions and individual responses based on emotions, but also makes it possible to use the collected data to combat the declining birthrate.

[0721] The processing flow will be explained below.

[0722] Step 1:

[0723] The user uses the terminal to input a question or inquiry about childcare into the input field. For example, the user inputs a question such as "What should I do if my child refuses to eat?"

[0724] Step 2:

[0725] The device receives the input question as text data and uses an emotion engine to recognize the user's emotions. For example, it identifies the emotion "frustration" from the context of the input.

[0726] Step 3:

[0727] The device converts the question data and emotion data into JSON format. For example, it converts it into the following data format: json { "question": "What should I do if my child refuses to eat?", "emotion": "frustration"}

[0728] Step 4:

[0729] The device sends the converted data to the server using a secure communication method such as HTTPS, and the data is encrypted before transmission.

[0730] Step 5:

[0731] The server receives the question data and emotion data sent from the device, checks the format and content of the received data, and verifies that the format is correct.

[0732] Step 6:

[0733] The server passes the received question data and emotion data to a natural language processing engine (generative AI), which is called via an API endpoint.

[0734] Step 7:

[0735] Generative AI analyzes the question data and generates an appropriate answer, such as, "If your child doesn't like eating, it's important to first offer them small amounts of their favorite foods and find ways to make eating enjoyable."

[0736] Step 8:

[0737] The emotion engine uses the emotional data to optimize the generated answers. For example, if the emotional data includes "frustration," the response will be optimized to something like, "First, calm yourself down. Then, it's important to offer a small amount of your favorite food and find a way to make your meal enjoyable."

[0738] Step 9:

[0739] The server then performs a validation check on the optimized response data again and formats it into a format to be sent back to the terminal.

[0740] Step 10:

[0741] The server returns the formatted response data to the device using HTTPS, a secure method of communication.

[0742] Step 11:

[0743] The device receives the response data sent from the server and displays it to the user, such as, "First, calm yourself down. Then, it's important to find a way to enjoy your meal by offering small amounts of your favorite foods."

[0744] Step 12:

[0745] The server stores the questions, generated answers, and emotion data in a database. The stored data includes the question content, the answer content, and the emotion data.

[0746] Step 13:

[0747] The server periodically runs a job that analyzes all the data stored in the database, sometimes using machine learning algorithms.

[0748] Step 14:

[0749] The server extracts common issues and trends from the analysis results, for example, discovering common issues such as "there are many inquiries about nighttime crying" or "there is an increase in inquiries about meals in certain areas."

[0750] Step 15:

[0751] The server compiles the extracted issues and trend information into a report and sends it to the public institution. The data is sent securely using an API.

[0752] Step 16:

[0753] Based on the data received, public institutions will consider and implement measures to combat the declining birthrate. For example, they will plan and implement specific countermeasures, such as holding childcare consultation sessions in specific areas.

[0754] Example 2

[0755] 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."

[0756] Conventional systems were unable to consider the user's emotions when providing answers to user questions, resulting in a lack of individualized support. Furthermore, there was no established mechanism for effectively analyzing collected question and answer data to identify common issues and provide feedback to public institutions. This resulted in insufficient support for childcare consultations and in ineffective measures to combat the declining birthrate.

[0757] 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 receiving a question and emotion data from a user, means for analyzing the received question and emotion data using natural language processing and an emotion recognition engine to generate an answer, and means for optimizing the generated answer based on the user's emotion data and returning it to the user. This makes it possible to provide an individual response that takes the user's emotion into consideration, and also establishes a mechanism for storing the question, the generated answer, and the emotion data and periodically analyzing them to extract common issues and send them to public institutions.

[0758] A "user" is a person who uses the system to input questions or inquiries.

[0759] A "question" is a problem or inquiry about childcare that is input by a user.

[0760] "Emotion data" is emotional information analyzed from the questions and consultation contents entered by the user.

[0761] "Natural language processing" is a technology that analyzes text data, understands its meaning, and generates appropriate answers.

[0762] An "emotion recognition engine" is a technology that detects emotions from the user's input text and provides those emotions as data.

[0763] "Generative AI" is artificial intelligence that uses natural language processing to generate answers to user questions.

[0764] An "answer" is a system-generated answer or advice to a user's question.

[0765] "Optimization" refers to adjusting and improving answers by taking into account the user's emotional data.

[0766] "Saving" means storing the question data, answer data, and emotion data in a database.

[0767] A "database" is a system for structuring, storing, and managing questions, answers, and emotional data.

[0768] "Periodic analysis" refers to the process of extracting data stored in the database at regular intervals to detect common issues and trends.

[0769] A "common issue" is a common problem or trend that becomes apparent when analyzing data collected from multiple users.

[0770] "Public institutions" are government or administrative agencies that provide childcare support and take measures to combat the declining birthrate.

[0771] "Feedback" refers to the act of reporting and providing analysis results and common issues to public institutions.

[0772] This invention combines a system that receives questions and inquiries from users, analyzes the questions using natural language processing, and generates appropriate answers, with an emotion engine that recognizes the user's emotions. The answers generated by this system are optimized based on the user's emotional data and returned to the user. In addition, all question and answer data is stored in a database and periodically analyzed to extract common issues that are then sent to public institutions. This system not only enables childcare consultations and measures to combat the declining birthrate, but also enables individual responses that take the user's emotions into consideration.

[0773] First, the user uses the device to enter a question or request for advice about childcare into an input field. For example, they might enter something like, "What should I do if my child refuses to eat?" The entered question is converted into JSON format on the device, and at the same time, an emotion engine analyzes the user's input and recognizes the emotion. This converted data is then sent to the server using a secure communication method (e.g., HTTPS).

[0774] The server receives the question and emotion data sent from the device and performs validation checks on the data format and content. If the received data is valid, it is passed to the natural language processing engine and emotion engine. A generative AI model analyzes the question data and generates an appropriate answer. The emotion engine also uses the user's emotion data to optimize the generated answer based on the emotion data. For example, if the question "What should I do if my child refuses to eat?" contains the emotion data "frustration," the answer will be optimized to "When a child refuses to eat, first stay calm. Then, it can be effective to offer them a small amount of their favorite food."

[0775] The server then validates the response data received from the generative AI and emotion engine, formats it appropriately, and sends it back to the device. The device receives the formatted response data and displays it in a format that is easy for the user to understand. For example, it might say, "When your child is refusing to do something, first try to stay calm. Then, it can be effective to offer them a small amount of their favorite food."

[0776] Furthermore, the server stores the questions, generated answers, and emotion data in a database. This data is stored as pairs of question content, answer content, and emotion data. The server periodically accesses the database, extracts and analyzes all stored data. Data analysis may use machine learning algorithms to detect common issues and trends. Issues extracted based on this are compiled into a report and sent to public institutions. This provides data that can be used to improve childcare consultation services and address the declining birthrate.

[0777] As a concrete example, we will show how the system recognizes the user's emotions when they use a device to input a question about a parenting problem. For example, if the user inputs, "What should I do if my child cries at night?" and indicates "fatigue" as their emotion, this data is sent to the server in JSON format. The server receives the data and passes it to a natural language processing engine and emotion engine. The generative AI model generates an answer such as "regulate your sleep rhythm and create a relaxing environment," and the emotion engine emphasizes the answer by taking "fatigue" into account. The server reconfirms this and sends it back to the device. The device then displays the answer to the user: "When your child cries at night, first check whether you are tired. Then, it is effective to regulate your sleep rhythm and create a relaxing environment." All questions, answers, and emotion data collected during this process are stored in a database and used for later analysis.

[0778] In this way, the system of the present invention makes it possible to respond in a way that takes into account the user's emotions, and the collected data can be used to combat the declining birthrate.

[0779] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0780] Step 1:

[0781] The user enters a question into the terminal.

[0782] Input: The user types "What should I do if my child refuses to eat?" into the device's input field.

[0783] Operation: The terminal interface monitors the user's input, detects when the input is complete, and prepares to send it.

[0784] Output: User question text data.

[0785] Step 2:

[0786] The device analyzes the emotion data, converts it into JSON format, and sends it to the server.

[0787] Input: User question text data.

[0788] How it works: The emotion engine analyzes the user's text data and recognizes the user's emotions.

[0789] Output: json { "question": "What should I do if my child refuses to eat?", "emotion": "frustration"} The data converted to JSON format is sent to the server via HTTPS.

[0790] Step 3:

[0791] The server receives the question and emotion data and performs a validation check.

[0792] Input: JSON format data sent from the terminal.

[0793] Behavior: The server checks the received JSON data for formatting and content errors. If there are any invalid or missing data, it logs it and stops parsing.

[0794] Output: Question and sentiment data in legal JSON format.

[0795] Step 4:

[0796] The server passes the data to a natural language processing engine and an emotion engine to generate an answer.

[0797] Input: Question and sentiment data in legal JSON format.

[0798] How it works: The generative AI model analyzes the question and generates an initial answer. Meanwhile, the emotion engine optimizes the answer based on the user's emotional data. For example, based on the emotional data "frustration," it generates an answer such as, "When your child refuses to do something, first stay calm. Then, it's effective to offer them a small amount of their favorite food."

[0799] Output: Optimized answer data.

[0800] Step 5:

[0801] The server validates the generated response data and returns it to the terminal.

[0802] Input: Optimized response data.

[0803] Operation: The server formats the response data, performs a validation check again to ensure there are no errors in the format or content, and then returns the response data to the device via HTTPS.

[0804] Output: The response data sent to the device.

[0805] Step 6:

[0806] The terminal receives the response data and displays it to the user.

[0807] Input: The response data sent from the server.

[0808] What it does: The device interface parses the received response data and displays it to the user in a user-friendly format.

[0809] Output: "When your child refuses to eat something, first stay calm. Then, offering them a small amount of their favorite food can be effective."

[0810] Step 7:

[0811] The server stores the questions, answers, and emotion data in a database.

[0812] Input: Question data, generated answer data, sentiment data.

[0813] How it works: The server structures and stores this data in a database.

[0814] Output: Questions, answers, and sentiment data recorded in a database.

[0815] Step 8:

[0816] The server periodically analyzes the data in the database and extracts common issues.

[0817] Input: Saved question data, answer data, and sentiment data.

[0818] How it works: The server uses machine learning algorithms to analyze the data and detect common issues and trends, for example, "There are a lot of inquiries about nighttime crying."

[0819] Output: Report data as the analysis result.

[0820] Step 9:

[0821] The server sends common issues to the public agency in the form of a report.

[0822] Input: Analysis result report data.

[0823] How it works: The server generates a report and sends it to the public agency using secure communications.

[0824] Output: Report sent to public authorities.

[0825] (Application example 2)

[0826] 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."

[0827] In food delivery services, it is difficult for customers to receive appropriate and sensitive responses when they experience delays or problems with their orders. Furthermore, service providers lack sufficient means to proactively utilize customer feedback to improve their services. Furthermore, there is a lack of a system for systematically identifying common issues and incorporating them into service improvements.

[0828] The identification process 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 receiving a question from a user, means for analyzing the received question using natural language processing and generating an answer, means for returning the generated answer to the user, means for saving the question and the generated answer, means for analyzing the saved question and answer and extracting common issues, means for sending the extracted issues to a public institution, emotion recognition means for recognizing the emotion of the user when entering the question, and means for optimizing the generated answer by taking the user's emotion into consideration. This enables customers to receive prompt and emotionally sensitive service, and enables service providers to improve the quality of their services by utilizing the collected data.

[0829] "User" refers to an individual, corporation, or service user who uses the system to ask questions or ask for advice.

[0830] The "means for receiving a question" refers to a function for the server to receive question data sent from a user via the Internet or a mobile application.

[0831] "Natural language processing" refers to the technology of using a computer to analyze natural human language, understand its meaning, and generate appropriate answers.

[0832] "Means for generating an answer" refers to a function for analyzing a received question and automatically generating an appropriate answer to that question.

[0833] "Means for returning an answer" refers to a function for sending the generated answer to the user's device and displaying it to the user.

[0834] "Means for storing questions and answers" refers to a function for storing received questions and generated answers in a database.

[0835] "Means of analyzing saved questions and answers and extracting common issues" refers to a function that periodically analyzes data stored in the database to find problems and areas for improvement common to multiple questions and answers.

[0836] "Means for sending issues to public institutions" refers to the function for compiling extracted issues and trends into a report format and sending it to public institutions, etc.

[0837] "Emotion recognition means" refers to a function for analyzing and recognizing the emotion expressed by the user when entering a question.

[0838] The "means for optimizing the generated answer by taking emotions into consideration" refers to a function for adjusting the generated answer to a more appropriate form according to the user's emotions.

[0839] "Food delivery service" refers to a service that allows users to order meals online and have the meals delivered.

[0840] This invention provides a system for providing a food delivery service that responds to user questions quickly and with consideration for their feelings. A specific implementation method of this system will be described below.

[0841] First, a user uses a smartphone or tablet to input a question or complaint about the food delivery service. When inputting a question, the emotion recognition means analyzes the emotion from the user's input and transmits the emotion data along with the question. The question and emotion data are then converted into JSON format and transmitted to the server using a secure communication method (e.g., HTTPS).

[0842] The server validates the received question and emotion data and passes the data to the natural language processing engine, generative AI model, and emotion recognition engine. The natural language processing engine analyzes the question data and generates an appropriate answer. Meanwhile, the emotion recognition engine uses the user's emotion data to optimize the generated answer. This makes it possible to provide an appropriate answer that takes the user's emotions into consideration.

[0843] The generated answer is validated again, formatted into an appropriate format, and sent back to the user's device. The device receives the formatted answer data and displays it in an easy-to-understand format for the user.

[0844] Furthermore, the questions, generated answers, and sentiment data are stored in a database. The server periodically analyzes the data and detects common issues and trends from the stored data. This allows food delivery service providers to identify areas for improvement and take necessary measures.

[0845] As a concrete example, consider the case where a user sends a question such as, "My order is late. When will it arrive?" In response to this question, the emotion recognition means detects "frustration," and the generative AI model generates the answer, "It will arrive in 15 to 20 minutes." The emotion recognition engine then optimizes the answer to, "We apologize for the inconvenience, but it will arrive in 15 to 20 minutes." This allows for a prompt and appropriate response to be provided to the user.

[0846] An example prompt is:

[0847] If the emotion recognition result for the question "My order is delayed. When will it arrive?" is "frustration," the generative AI model will generate the answer "It will arrive in 15 to 20 minutes." Then, as a result of optimization by the emotion recognition engine, the final answer will be provided: "We apologize for the inconvenience, but your order is expected to arrive in 15 to 20 minutes."

[0848] The main hardware used includes user devices (smartphones and tablets), cloud servers, and network equipment. The software used includes Android / iOS apps, Python, Tensorflow, Watson NLP services, and Emotion Recognition API. Combining these components makes it possible to efficiently implement a question-answering system for food delivery services.

[0849] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0850] Step 1:

[0851] A user uses a smartphone or tablet device to input questions or complaints about food delivery services. When the user enters a question in the input field and presses the send button, the question is received by the device. At this time, the emotion recognition means analyzes the emotion from the user's input. The input is made by the user, and the output is question data accompanied by analyzed emotion data.

[0852] Step 2:

[0853] The device converts the input question and emotion data into JSON format. The converted data is sent to the server using a secure communication method (e.g., HTTPS). The input is the user's question data and emotion data, and the output is the data converted into JSON format.

[0854] Step 3:

[0855] The server performs validation checks on the questions and emotion data it receives. After filtering out invalid data, it passes the data to the natural language processing engine, generative AI model, and emotion recognition engine. The input is question data and emotion data in JSON format, and the output is the data required for analysis and optimization.

[0856] Step 4:

[0857] The natural language processing engine analyzes the question data and generates an appropriate answer. The generative AI model analyzes the question content and suggests the most appropriate answer. The input is validated question data, and the output is the generated answer data.

[0858] Step 5:

[0859] The emotion recognition engine uses the user's emotional data to optimize the generated answer, adjusting the wording and approach according to the user's emotions. The input is the generated answer data and emotional data, and the output is the optimized answer data.

[0860] Step 6:

[0861] The server revalidates the response data received from the generative AI and emotion recognition engine and formats it appropriately. It then returns the response data to the device. The input is the optimized response data, and the output is the formatted response data.

[0862] Step 7:

[0863] The terminal displays the formatted answer data received from the server in an easy-to-understand manner to the user. The user checks the answer displayed on the terminal screen. The input is the formatted answer data, and the output is the displayed answer.

[0864] Step 8:

[0865] The server stores the question, the generated answer, and the emotion data in a database. The data is stored as pairs of question content, answer content, and emotion data. The input is the question data, answer data, and emotion data, and the output is the stored data.

[0866] Step 9:

[0867] The server periodically extracts and analyzes all data stored in the database to detect common issues and trends. Machine learning algorithms may be used for data analysis. The input is the data in the database, and the output is the analysis results.

[0868] Step 10:

[0869] The server extracts common issues and trends from the analysis results and compiles them into a report, which is then sent to public institutions and food delivery service providers. The input is the analysis results, and the output is a summary in report format and its transmission.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] [Third embodiment]

[0874] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0875] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0876] 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).

[0877] 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.

[0878] 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.

[0879] 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).

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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."

[0886] This invention is a system that receives questions and inquiries from users, analyzes the questions using natural language processing, and generates appropriate answers. The generated answers are returned to the users, and all question and answer data is stored in a database. This data is periodically analyzed, and common issues are extracted and sent to public institutions. Through this process, we are able to respond to inquiries about childcare and take measures to combat the declining birthrate.

[0887] Explanation of program processing

[0888] 1. Enter and submit your question

[0889] User

[0890] The user uses the terminal to input questions or inquiries about childcare into the input field.

[0891] For example: "What should I do if my child refuses to eat?"

[0892] 2. Sending input data

[0893] Terminal

[0894] Convert the input question into JSON format.

[0895] The converted data is sent to the server via a secure communication method (e.g., HTTPS).

[0896] 3. Receiving and analyzing questions

[0897] server

[0898] The server receives the query data sent from the terminal.

[0899] The format and content of the received data are validated, and if normal, it is passed to the natural language processing engine.

[0900] Generative AI

[0901] Analyze the question data and generate appropriate answers.

[0902] For example: "If your child is reluctant to eat, it's a good idea to start by offering them small amounts of their favorite foods. It's also important to find ways to make eating enjoyable."

[0903] 4. Receiving and returning responses

[0904] server

[0905] Receive response data from the generative AI.

[0906] The received response data is validated again and formatted to be returned to the terminal.

[0907] Terminal

[0908] The formatted answer data is received and displayed on the screen in a format that is easy for the user to view.

[0909] Example: Displayed answer: "If your child is reluctant to eat, it's a good idea to start by offering them small amounts of their favorite foods. It's also important to find ways to make eating enjoyable."

[0910] 5. Data storage and analysis

[0911] server

[0912] Save the questions and generated answers in a database.

[0913] All data stored in the database is periodically extracted and analyzed to detect common issues.

[0914] 6. Extract and submit assignments

[0915] server

[0916] Based on the results of the analysis, common issues and trends are extracted.

[0917] The extracted issues and trend information will be sent to public institutions as a report.

[0918] Examples: "There has been an increase in consultations regarding diet," "There are many consultations regarding night crying in certain areas," etc.

[0919] Specific examples

[0920] context

[0921] The user uses the terminal to input a question about a child-rearing problem.

[0922] Sample question: "What should I do if my child cries at night?"

[0923] Processing Flow

[0924] 1. The user types a question into the terminal.

[0925] 2. The device sends the question to the server in JSON format.

[0926] 3. The server passes the question to a generative AI, which generates an answer.

[0927] 4. The generative AI generated the answer, "Effective ways to deal with nighttime crying include adjusting your baby's sleep rhythm and creating a relaxing environment."

[0928] 5. The server generates the answer and sends it back to the user's device.

[0929] 6. The device displays the answer to the user.

[0930] 7. The server stores the question and answer data in a database.

[0931] 8. Regularly analyze the data and identify the issue of "many inquiries about nighttime crying."

[0932] 9. The server sends this issue as a report to the public agency.

[0933] In this way, the system provides a mechanism for quickly responding to user questions and utilizing the collected data to combat the declining birthrate. This system is both convenient for users and a valuable source of information for public institutions.

[0934] The processing flow will be explained below.

[0935] Step 1:

[0936] The user uses the device to enter a question or inquiry about childcare into the input field. For example, "What should I do if my child refuses to eat?"

[0937] Step 2:

[0938] The device converts the entered question into an appropriate data format, such as JSON. Specifically, it converts it into the following format: json { "question": "What should I do if my child refuses to eat?"}

[0939] Step 3:

[0940] The device sends the converted data to the server using a secure communication method such as HTTPS. The data is encrypted and managed to reach the server safely.

[0941] Step 4:

[0942] The server receives the query data sent from the terminal, validates the format and content of the received data, and eliminates invalid data.

[0943] Step 5:

[0944] The server passes the received question data to a natural language processing engine (e.g., a generative AI). The engine is called via an API endpoint and analyzes the question and generates an answer.

[0945] Step 6:

[0946] Generative AI analyzes question data and generates appropriate answers, such as, "If your child doesn't like to eat, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find ways to make eating fun."

[0947] Step 7:

[0948] The server then validates the answer data received from the generative AI and formats it into the appropriate format. Validation includes checking the consistency and quality of the answer text.

[0949] Step 8:

[0950] The server returns the formatted response data to the terminal, usually via HTTPS.

[0951] Step 9:

[0952] The device receives the response data sent from the server and displays it in an easy-to-understand manner to the user. For example, it displays, "If your child doesn't like to eat, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find ways to make eating fun."

[0953] Step 10:

[0954] The server stores the questions and generated answers in a database. The data is stored as pairs of question and answer.

[0955] Step 11:

[0956] The server periodically runs jobs that analyze the question and answer data stored in the database, sometimes using machine learning algorithms.

[0957] Step 12:

[0958] The server extracts common issues and trends from the analysis results. For example, it finds patterns from data such as "there are many consultations about nighttime crying" or "the number of consultations about eating is increasing."

[0959] Step 13:

[0960] The server compiles the extracted issues and trend information into a report format and sends it to the public institution via API or secure data transmission methods.

[0961] Step 14:

[0962] Based on the data received, public institutions will consider and implement measures to combat the declining birthrate. Specific countermeasures will be planned and implemented for the issues identified.

[0963] Example 1

[0964] 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."

[0965] Currently, many childcare-related questions and inquiries are handled individually, without effective data analysis or sharing. This makes it difficult to effectively utilize this data and link it to improving childcare support and measures to combat the declining birthrate. Furthermore, there is a lack of a system for providing prompt, appropriate answers to user questions.

[0966] 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.

[0967] In this invention, the server includes means for receiving questions from users, means for converting the received questions into a data format and transmitting the data, means for validating the format and content of the received data and, if normal, passing the data to an analysis engine, means for analyzing the question data using a generative AI model and generating an appropriate answer, means for returning the generated answer to the user, means for saving the questions and the generated answers, means for analyzing the saved questions and answers and extracting common issues, and means for sending the extracted issues to public institutions. This makes it possible to provide users with prompt and appropriate answers and to utilize data to support childcare and address the declining birthrate.

[0968] "User" refers to a person who inputs questions or inquiries about childcare into the system.

[0969] A "terminal" is a device used by a user to input questions or inquiries, and includes smartphones, personal computers, etc.

[0970] "Server" refers to a central processing unit for receiving user questions, passing the data to the analysis engine, and transmitting generated answers.

[0971] A "question" refers to a childcare-related question that a user enters into an input field.

[0972] "Received data" refers to the data that the server receives after converting the question entered by the user into a data format such as JSON.

[0973] "Validation" refers to the process of checking that received data is in the correct format and contains expected content.

[0974] "Analytics Engine" refers to software or algorithms that analyze incoming data and generate appropriate answers.

[0975] A "generative AI model" refers to a machine learning model that uses generative AI to generate appropriate answers to user questions.

[0976] "Answer" refers to the information generated by a generative AI model and returned in response to a user's question.

[0977] "Saving" refers to the act of storing the question and its generated answer in a database.

[0978] "Database" means a digital storage system for managing and storing saved question and answer data.

[0979] "Analysis" refers to the process of analyzing stored data to extract common issues.

[0980] "Common issues" refers to themes or issues that frequently emerge from multiple questions and their answers.

[0981] A "public institution" refers to an organization that operates for the public good, such as a government or local government.

[0982] The present invention is a system that receives questions and inquiries about childcare from users, analyzes them, and generates answers. The system includes a device used by the user, a server that processes and stores data, and a generative AI model that performs natural language processing.

[0983] The user uses the device to input a question or inquiry. The user opens a browser on their smartphone or PC, accesses a dedicated web form, and enters the question in the input field. For example, they might enter, "What should I do if my child refuses to eat?" and click the send button.

[0984] The device converts the question entered by the user into JSON format, for example, {"question": "What should I do if my child refuses to eat?"}. The converted data is securely sent to the server using the HTTPS protocol.

[0985] The server receives the question data sent from the device. It validates the format and content of the received data, and if it is normal, passes it to the analysis engine. After format checks and XSS attack countermeasures, it passes the question data to the generative AI model as a prompt text. Examples of prompt text are as follows:

[0986] "Question: What should I do if my child refuses to eat? Generate an appropriate answer."

[0987] A generative AI model (e.g., OpenAI GPT-4) receives a prompt and generates an answer based on the training data, such as, "If your child refuses to eat, it's a good idea to offer them a small amount of their favorite food first. It's also important to find ways to make eating enjoyable."

[0988] The server receives the answer data from the generative AI model. The received answer data is validated again, and if normal, it is formatted to be sent back to the device. The content of the answer data is checked and formatted, for example, {"answer": "If a child doesn't like eating, it's a good idea to first offer them a small amount of their favorite food. It's also important to find a way to make eating enjoyable."}

[0989] The device analyzes the response data received from the server and displays it on the screen in an easy-to-read format for the user. An example of what is displayed is, "If your child doesn't like to eat, it's a good idea to first offer them a small amount of their favorite food. It's also important to find ways to make eating fun."

[0990] The server saves the question and the generated answer in a database. The question and answer are stored in the database in JSON format. For example, it is saved as follows: {"question": "What should I do if my child refuses to eat?", "answer": "If a child refuses to eat, it is a good idea to start by offering them a small amount of their favorite food. It is also important to find ways to make eating enjoyable."}

[0991] The system periodically extracts and analyzes all data stored in the database to detect common issues. The server runs a regularly scheduled task to retrieve past questions and answers from the database and uses natural language processing technology to extract common topics and trends. For example, it detects an increase in questions related to night crying.

[0992] Based on the analysis results, the extracted issues and trend information are sent to the public institution as a report. The generated report is formatted in PDF or CSV format and sent to the API endpoint or email address specified by the public institution. For example, a report containing content such as "Recent trend: Increase in the number of consultations about nighttime crying" is sent.

[0993] This system provides users with quick and appropriate answers, and also provides a mechanism that makes it possible to utilize data to support childcare and implement measures to combat the declining birthrate.

[0994] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0995] Step 1:

[0996] The user uses the device to enter a question or request for advice about childcare into an input field. Specifically, the user opens a browser on their smartphone or PC, accesses a dedicated web form, enters "What should I do if my child refuses to eat?" into the input field, and clicks the send button. The input is the question from the user, and the output is saved on the device as this question data.

[0997] Step 2:

[0998] The terminal converts the question entered by the user into JSON format. Specifically, the terminal parses the user's input text and converts it into a JSON object of key-value pairs (e.g., {"question": "What should I do if my child refuses to eat?"}). The input is the text entered by the user, and the output is question data in JSON format.

[0999] Step 3:

[1000] The terminal sends the converted JSON data to the server using the HTTPS protocol. Specifically, the terminal includes the generated JSON object in the HTTPS request body and sends a POST request to the specified endpoint on the server. The input is the question data in JSON format, and the data is sent to the server as the output.

[1001] Step 4:

[1002] The server receives the question data sent from the terminal. Specifically, the server receives the HTTPS request and extracts JSON data from the request body. The input is the received HTTPS request, and the output is the extracted JSON-formatted question data.

[1003] Step 5:

[1004] The server validates the format and content of the received data. Specific operations include format checks (e.g., checking the existence of keys) and XSS attack prevention. The input is JSON-formatted question data, and the output is validated JSON data. If this validated data is valid, it is passed to the analysis engine.

[1005] Step 6:

[1006] If everything is normal, the server passes the question data to the generative AI model as a prompt text. Specifically, it generates a prompt text and sends it to the generative AI model. An example of a prompt text is: "Question: What should I do if my child refuses to eat? Please generate an appropriate answer." The input is validated JSON data, and the output is a prompt text.

[1007] Step 7:

[1008] A generative AI model receives a prompt, analyzes the question data, and generates an appropriate answer. Specifically, a generative AI model (e.g., OpenAI GPT-4) analyzes the prompt and generates an answer based on the training data. An example of a generated answer is: "If a child doesn't like eating, it's a good idea to first offer them a small amount of their favorite food. It's also important to find a way to make eating enjoyable." The input is a prompt, and the output is a generated answer.

[1009] Step 8:

[1010] The server receives the answer data from the generative AI model. Specifically, the server receives the answer generated from the API of the generative AI model. The generated answer data is the input, and it is saved on the server as the output.

[1011] Step 9:

[1012] The server revalidates the received response data. Specifically, it checks the content of the response data (e.g., whether it contains any undesirable content). The input is the generated response data, and the output is the validated response data.

[1013] Step 10:

[1014] The server formats the validated answer data into a format to be sent back to the device. Specifically, it formats the answer in JSON format, for example, {"answer": "If a child doesn't like eating, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find ways to make eating enjoyable."}. The input is the validated answer data, and the output is the formatted answer data.

[1015] Step 11:

[1016] The device analyzes the response data received from the server and displays it on the screen in a format that is easy for the user to view. Specifically, the device analyzes the JSON data received from the server and displays the response in the browser's display area. An example of what is displayed is, "If your child doesn't like to eat, it's a good idea to first offer them a small amount of their favorite food. It's also important to find a way to make eating enjoyable." The input is the formatted response data, and the output is displayed to the user.

[1017] Step 12:

[1018] The server saves the question and the generated answer in a database. Specifically, the question and answer are stored in the database in JSON format. Example of saved data: {"question": "What should I do if my child doesn't want to eat?", "answer": "If a child doesn't want to eat, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find a way to make eating enjoyable."}. The input is the question and the generated answer data, and the output is saved in the database.

[1019] Step 13:

[1020] The server periodically extracts and analyzes all data stored in the database to detect common issues. Specifically, the server executes a regularly scheduled task to retrieve past questions and answers from the database and uses natural language processing technology to extract common topics and trends. For example, it detects an increase in questions related to nighttime crying. The input is the question and answer data stored in the database, and the output is the detection of common issues.

[1021] Step 14:

[1022] Based on the results of the analysis, the server sends the extracted issues and trend information to the public institution as a report. Specifically, the generated report is formatted in PDF or CSV format and sent to an API endpoint or email address specified by the public institution. For example, a report titled "Recent trends: Increase in the number of consultations about nighttime crying" is sent. Common issues and trend information are input, and the report is sent to the public institution as output.

[1023] (Application example 1)

[1024] 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."

[1025] One issue facing brick-and-mortar stores is the lack of a way for customers to quickly and appropriately resolve questions about childcare or products without having to ask staff directly. There is also a need for a system that accumulates and analyzes customer question data and provides the information to public institutions to contribute to childcare support measures and measures to combat the declining birthrate throughout society.

[1026] 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.

[1027] In this invention, the server includes means for receiving questions from users, means for analyzing the received questions using natural language processing and generating answers, means for returning the generated answers to the users, means for saving the questions and the generated answers, means for analyzing the saved questions and answers and extracting common issues, means for sending the extracted issues to public institutions, means for responding to customer questions in physical stores, and means for displaying the generated answers on the customer's terminal. This makes it possible to quickly and appropriately respond to customer questions in physical stores, and to analyze the accumulated data and utilize it for childcare support measures and measures to combat the declining birthrate throughout society.

[1028] "User" means an individual or organization that uses the system to ask questions or make inquiries.

[1029] A "question" is a question or inquiry submitted by a user to the system.

[1030] "Natural language processing" is a technology that allows a machine to understand input questions or consultation content and generate appropriate answers.

[1031] An "answer" is a response generated in response to a question analyzed by natural language processing.

[1032] The "receiving means" refers to a mechanism or device for receiving a question from a user.

[1033] A "return mechanism" is a mechanism or device for returning the generated answer to the user.

[1034] A "storage means" is a mechanism or device for storing questions and generated answers for a certain period of time.

[1035] "Analysis means" refers to a mechanism or device for analyzing stored questions and answers.

[1036] "Issue extraction means" refers to mechanisms or devices for identifying common problems or trends based on analysis.

[1037] "Public agency transmission means" refers to the mechanism or device for transmitting the identified issues to the relevant public agencies.

[1038] A "brick and mortar store" is a physical commercial establishment where customers visit and purchase goods in person.

[1039] "Response methods" refer to mechanisms and devices that allow a physical store to respond quickly to customer questions.

[1040] A "terminal" is an electronic device that a user uses to enter questions and receive answers.

[1041] This invention realizes a system that receives questions from customers in a physical store, processes them, answers them, and returns them. The specific implementation method and operation of this system are described below.

[1042] System Overview

[1043] This system is realized using a user device (such as a smartphone), a server, and a generative AI model. The main hardware and software components and their roles are described below.

[1044] Hardware and Software Used

[1045] User device: The device on which customers enter their questions and receive answers. This could be a smartphone or tablet.

[1046] Server: The central component that receives questions, generates answers, stores and analyzes data, and sends reports to public authorities.

[1047] Usage example: Cloud servers (Amazon Web Services, Google Cloud Platform)

[1048] Generative AI model: Analyzes questions and generates appropriate answers. The following natural language processing engines are used:

[1049] Usage examples: Amazon Lex, Google Dialogflow

[1050] Program processing overview

[1051] 1. Enter and submit your question

[1052] A user uses a smartphone app in a physical store to input a question, for example, "Is it better to have a lightweight stroller?"

[1053] 2. Sending input data

[1054] The device converts the entered question into JSON format and sends it to the server using HTTPS.

[1055] 3. Receiving and analyzing questions

[1056] The server receives the input data, validates the format and content, and if there are no problems, passes it to the natural language processing engine.

[1057] A generative AI model (e.g., Amazon Lex) analyzes the question and generates an appropriate answer, such as, "A lightweight stroller is easy to use, but durability should also be considered."

[1058] 4. Receiving and returning responses

[1059] The server receives the generated response, validates it, and then formats it into a format to be sent back to the user's terminal.

[1060] The terminal receives the response data and displays it in an easy-to-read format for the customer.

[1061] 5. Data storage and analysis

[1062] The server stores the questions and generated answers in a database.

[1063] The contents of the database are analyzed periodically to extract common issues.

[1064] 6. Extract and submit assignments

[1065] Based on the analysis results, the server extracts common issues and trends and sends them to public institutions as a report.

[1066] Specific examples

[1067] Enter your question

[1068] A user types a question in a physical store.

[1069] For example: "Is a lighter stroller better?"

[1070] Prompt Sentence Examples

[1071] A user asked: "Is a lighter stroller better?"

[1072] Context for Answer Generation: Generate an answer about the balance between lightweight and sturdy strollers.

[1073] This system will enable physical stores to respond quickly and appropriately to customer questions, and the accumulated data will enable public institutions to understand consumer needs and implement effective childcare support measures and countermeasures against the declining birthrate.

[1074] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1075] Step 1:

[1076] A user uses a smartphone app to input a question in a physical store. For example, the question might be input in the form of "Is a lightweight stroller better?" The input question is saved in text format in a data input field in the application.

[1077] Step 2:

[1078] The terminal receives a question entered by the user and converts it into JSON format. The converted data is sent to the server via a secure communication method (e.g., HTTPS). The input is text data, and the output is JSON format data. This data processing makes it easy for the server to process the question content.

[1079] Step 3:

[1080] The server receives JSON-formatted question data sent from the terminal. It validates the format and content of the received data, and if it is normal, passes it to the natural language processing engine. The input is JSON-formatted question data, and the output is validated data. The data calculations performed here check the data format and confirm the content.

[1081] Step 4:

[1082] The generative AI model analyzes the question data and generates an appropriate answer. The generation process uses a pre-prepared prompt (e.g., "Please generate an answer about the balance between lightness and durability of strollers"). The input is validated question data, and the output is the answer text. This data calculation generates answers based on natural language processing.

[1083] Step 5:

[1084] The server revalidates the answer data received from the generative AI and formats it for return to the terminal. The input is the generated answer text, and the output is the formatted data. The data processing performed here involves checking the answer data and converting its format.

[1085] Step 6:

[1086] The terminal receives the formatted response data and displays it on the screen in a format that is easy for the user to see. The input is the formatted response data, and the output is a display format that the user can visually recognize. The data processing performed here is to make the received data into a format that can be displayed.

[1087] Step 7:

[1088] The server saves the question and generated answer in a database. The input is the question and generated answer data, and the output is the saved data in the database. This process involves a write operation to the database.

[1089] Step 8:

[1090] The server periodically extracts and analyzes all data stored in the database to detect common issues. The input is past question and answer data extracted from the database, and the output is the analysis results. The data calculations performed here involve data analysis and trend extraction.

[1091] Step 9:

[1092] Based on the analysis results, the server sends common issues and trend information to public institutions as a report. The input is the analysis results, and the output is the sent report. This process involves report generation and transmission operations.

[1093] The above is a specific processing flow of the system that realizes the application example.

[1094] 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.

[1095] This invention combines a system that receives questions and inquiries from users, analyzes the questions using natural language processing, and generates appropriate answers, with an emotion engine that recognizes the user's emotions. The generated answers are optimized based on the user's emotional state and returned to the user. Furthermore, all question and answer data is stored in a database and periodically analyzed to extract common issues that are then sent to public institutions. This not only enables childcare consultations and measures to combat the declining birthrate, but also makes it possible to provide individual responses that take the user's emotions into consideration.

[1096] Explanation of program processing

[1097] 1. Question input and emotion recognition

[1098] User

[1099] The user uses the terminal to input a question or inquiry about childcare into the input field. For example, the user inputs something like, "What should I do if my child refuses to eat?"

[1100] 2. Sending input data and emotion data

[1101] Terminal

[1102] The input question is converted into JSON format. The emotion engine also recognizes the user's emotion from the input and sends the emotion data along with the question.

[1103] The converted data is sent to the server via a secure connection (e.g. HTTPS). Example: json { "question": "What should I do if my child refuses to eat?", "emotion": "frustration"}

[1104] 3. Receiving and analyzing question and emotion data

[1105] server

[1106] The server receives the question and emotion data sent from the device, validates the format and content of the received data, and eliminates invalid data.The data is then passed to the natural language processing engine and emotion engine.

[1107] Generative AI and Emotion Engines

[1108] The generative AI analyzes question data and generates appropriate answers, while the emotion engine uses user emotional data to optimize the generated answers.

[1109] For example, in response to the question, "What should I do if my child refuses to eat?"

[1110] When the emotional data "frustration" is included, it is optimized to say, "When your child refuses to eat something, first stay calm. Then, it is effective to offer them a small amount of their favorite food."

[1111] 4. Receiving and returning responses

[1112] server

[1113] The response data received from the generative AI and emotion engine is validated again and formatted appropriately, after which it is sent back to the device.

[1114] Terminal

[1115] The formatted response data is received and displayed to the user in an easy-to-understand format. For example, "When a child refuses to do something, first try to stay calm. Then, it can be effective to offer them a small amount of their favorite food."

[1116] 5. Data storage and analysis

[1117] server

[1118] The questions, generated answers, and emotion data are stored in a database. The data is stored as pairs of question content, answer content, and emotion data.

[1119] 6. Regular data analysis and problem extraction

[1120] server

[1121] All data stored in the database is periodically extracted and analyzed to detect common issues and trends, sometimes using machine learning algorithms.

[1122] 7. Extract and submit assignments

[1123] server

[1124] Common issues and trends are extracted from the analysis results and compiled into a report. This report is then sent to public institutions. Examples include "There are many inquiries about nighttime crying" or "There is an increase in inquiries about meals in certain areas."

[1125] Specific examples

[1126] context

[1127] When a user uses a terminal to input a question about a child-rearing problem, the user's emotions are also recognized.

[1128] Processing Flow

[1129] 1. The user enters a question into the device, and the emotion associated with the question is automatically recognized. For example, "What should I do if my child cries at night?" is entered, and the emotion indicated is "tired."

[1130] 2. The device sends the question and emotion data in JSON format to the server.

[1131] 3. The server passes the question and emotion data to the generative AI and emotion engine to generate an answer.

[1132] 4. The generative AI generates answers such as "regulate your sleep rhythm and create a relaxing environment," and the emotion engine takes "fatigue" into consideration and emphasizes the advice.

[1133] 5. The server generates the answer and sends it back to the user's device.

[1134] 6. The device displays the answer to the user. For example, "When your child cries at night, first check to see if you are tired. Then, it is effective to regulate your sleep rhythm and create a relaxing environment."

[1135] 7. The server stores the questions, answers, and emotion data in a database.

[1136] 8. Regularly analyze data to detect issues such as "many inquiries about nighttime crying."

[1137] 9. The server sends these issues as a report to the public agency.

[1138] This system not only enables quick responses to user questions and individual responses based on emotions, but also makes it possible to use the collected data to combat the declining birthrate.

[1139] The processing flow will be explained below.

[1140] Step 1:

[1141] The user uses the terminal to input a question or inquiry about childcare into the input field. For example, the user inputs a question such as "What should I do if my child refuses to eat?"

[1142] Step 2:

[1143] The device receives the input question as text data and uses an emotion engine to recognize the user's emotions. For example, it identifies the emotion "frustration" from the context of the input.

[1144] Step 3:

[1145] The device converts the question data and emotion data into JSON format. For example, it converts it into the following data format: json { "question": "What should I do if my child refuses to eat?", "emotion": "frustration"}

[1146] Step 4:

[1147] The device sends the converted data to the server using a secure communication method such as HTTPS, and the data is encrypted before transmission.

[1148] Step 5:

[1149] The server receives the question data and emotion data sent from the device, checks the format and content of the received data, and verifies that the format is correct.

[1150] Step 6:

[1151] The server passes the received question data and emotion data to a natural language processing engine (generative AI), which is called via an API endpoint.

[1152] Step 7:

[1153] Generative AI analyzes the question data and generates an appropriate answer, such as, "If your child doesn't like eating, it's important to first offer them small amounts of their favorite foods and find ways to make eating enjoyable."

[1154] Step 8:

[1155] The emotion engine uses the emotional data to optimize the generated answers. For example, if the emotional data includes "frustration," the response will be optimized to something like, "First, calm yourself down. Then, it's important to offer a small amount of your favorite food and find a way to make your meal enjoyable."

[1156] Step 9:

[1157] The server then performs a validation check on the optimized response data again and formats it into a format to be sent back to the terminal.

[1158] Step 10:

[1159] The server returns the formatted response data to the device using HTTPS, a secure method of communication.

[1160] Step 11:

[1161] The device receives the response data sent from the server and displays it to the user, such as, "First, calm yourself down. Then, it's important to find a way to enjoy your meal by offering small amounts of your favorite foods."

[1162] Step 12:

[1163] The server stores the questions, generated answers, and emotion data in a database. The stored data includes the question content, the answer content, and the emotion data.

[1164] Step 13:

[1165] The server periodically runs a job that analyzes all the data stored in the database, sometimes using machine learning algorithms.

[1166] Step 14:

[1167] The server extracts common issues and trends from the analysis results, for example, discovering common issues such as "there are many inquiries about nighttime crying" or "there is an increase in inquiries about meals in certain areas."

[1168] Step 15:

[1169] The server compiles the extracted issues and trend information into a report and sends it to the public institution. The data is sent securely using an API.

[1170] Step 16:

[1171] Based on the data received, public institutions will consider and implement measures to combat the declining birthrate. For example, they will plan and implement specific countermeasures, such as holding childcare consultation sessions in specific areas.

[1172] Example 2

[1173] 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."

[1174] Conventional systems were unable to consider the user's emotions when providing answers to user questions, resulting in a lack of individualized support. Furthermore, there was no established mechanism for effectively analyzing collected question and answer data to identify common issues and provide feedback to public institutions. This resulted in insufficient support for childcare consultations and in ineffective measures to combat the declining birthrate.

[1175] 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 receiving a question and emotion data from a user, means for analyzing the received question and emotion data using natural language processing and an emotion recognition engine to generate an answer, and means for optimizing the generated answer based on the user's emotion data and returning it to the user. This makes it possible to provide an individual response that takes the user's emotion into consideration, and also establishes a mechanism for storing the question, the generated answer, and the emotion data and periodically analyzing them to extract common issues and send them to public institutions.

[1176] A "user" is a person who uses the system to input questions or inquiries.

[1177] A "question" is a problem or inquiry about childcare that is input by a user.

[1178] "Emotion data" is emotional information analyzed from the questions and consultation contents entered by the user.

[1179] "Natural language processing" is a technology that analyzes text data, understands its meaning, and generates appropriate answers.

[1180] An "emotion recognition engine" is a technology that detects emotions from the user's input text and provides those emotions as data.

[1181] "Generative AI" is artificial intelligence that uses natural language processing to generate answers to user questions.

[1182] An "answer" is a system-generated answer or advice to a user's question.

[1183] "Optimization" refers to adjusting and improving answers by taking into account the user's emotional data.

[1184] "Saving" means storing the question data, answer data, and emotion data in a database.

[1185] A "database" is a system for structuring, storing, and managing questions, answers, and emotional data.

[1186] "Periodic analysis" refers to the process of extracting data stored in the database at regular intervals to detect common issues and trends.

[1187] A "common issue" is a common problem or trend that becomes apparent when analyzing data collected from multiple users.

[1188] "Public institutions" are government or administrative agencies that provide childcare support and take measures to combat the declining birthrate.

[1189] "Feedback" refers to the act of reporting and providing analysis results and common issues to public institutions.

[1190] This invention combines a system that receives questions and inquiries from users, analyzes the questions using natural language processing, and generates appropriate answers, with an emotion engine that recognizes the user's emotions. The answers generated by this system are optimized based on the user's emotional data and returned to the user. In addition, all question and answer data is stored in a database and periodically analyzed to extract common issues that are then sent to public institutions. This system not only enables childcare consultations and measures to combat the declining birthrate, but also enables individual responses that take the user's emotions into consideration.

[1191] First, the user uses the device to enter a question or request for advice about childcare into an input field. For example, they might enter something like, "What should I do if my child refuses to eat?" The entered question is converted into JSON format on the device, and at the same time, an emotion engine analyzes the user's input and recognizes the emotion. This converted data is then sent to the server using a secure communication method (e.g., HTTPS).

[1192] The server receives the question and emotion data sent from the device and performs validation checks on the data format and content. If the received data is valid, it is passed to the natural language processing engine and emotion engine. A generative AI model analyzes the question data and generates an appropriate answer. The emotion engine also uses the user's emotion data to optimize the generated answer based on the emotion data. For example, if the question "What should I do if my child refuses to eat?" contains the emotion data "frustration," the answer will be optimized to "When a child refuses to eat, first stay calm. Then, it can be effective to offer them a small amount of their favorite food."

[1193] The server then validates the response data received from the generative AI and emotion engine, formats it appropriately, and sends it back to the device. The device receives the formatted response data and displays it in a format that is easy for the user to understand. For example, it might say, "When your child is refusing to do something, first try to stay calm. Then, it can be effective to offer them a small amount of their favorite food."

[1194] Furthermore, the server stores the questions, generated answers, and emotion data in a database. This data is stored as pairs of question content, answer content, and emotion data. The server periodically accesses the database, extracts and analyzes all stored data. Data analysis may use machine learning algorithms to detect common issues and trends. Issues extracted based on this are compiled into a report and sent to public institutions. This provides data that can be used to improve childcare consultation services and address the declining birthrate.

[1195] As a concrete example, we will show how the system recognizes the user's emotions when they use a device to input a question about a parenting problem. For example, if the user inputs, "What should I do if my child cries at night?" and indicates "fatigue" as their emotion, this data is sent to the server in JSON format. The server receives the data and passes it to a natural language processing engine and emotion engine. The generative AI model generates an answer such as "regulate your sleep rhythm and create a relaxing environment," and the emotion engine emphasizes the answer by taking "fatigue" into account. The server reconfirms this and sends it back to the device. The device then displays the answer to the user: "When your child cries at night, first check whether you are tired. Then, it is effective to regulate your sleep rhythm and create a relaxing environment." All questions, answers, and emotion data collected during this process are stored in a database and used for later analysis.

[1196] In this way, the system of the present invention makes it possible to respond in a way that takes into account the user's emotions, and the collected data can be used to combat the declining birthrate.

[1197] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1198] Step 1:

[1199] The user enters a question into the terminal.

[1200] Input: The user types "What should I do if my child refuses to eat?" into the device's input field.

[1201] Operation: The terminal interface monitors the user's input, detects when the input is complete, and prepares to send it.

[1202] Output: User question text data.

[1203] Step 2:

[1204] The device analyzes the emotion data, converts it into JSON format, and sends it to the server.

[1205] Input: User question text data.

[1206] How it works: The emotion engine analyzes the user's text data and recognizes the user's emotions.

[1207] Output: json { "question": "What should I do if my child refuses to eat?", "emotion": "frustration"} The data converted to JSON format is sent to the server via HTTPS.

[1208] Step 3:

[1209] The server receives the question and emotion data and performs a validation check.

[1210] Input: JSON format data sent from the terminal.

[1211] Behavior: The server checks the received JSON data for formatting and content errors. If there are any invalid or missing data, it logs it and stops parsing.

[1212] Output: Question and sentiment data in legal JSON format.

[1213] Step 4:

[1214] The server passes the data to a natural language processing engine and an emotion engine to generate an answer.

[1215] Input: Question and sentiment data in legal JSON format.

[1216] How it works: The generative AI model analyzes the question and generates an initial answer. Meanwhile, the emotion engine optimizes the answer based on the user's emotional data. For example, based on the emotional data "frustration," it generates an answer such as, "When your child refuses to do something, first stay calm. Then, it's effective to offer them a small amount of their favorite food."

[1217] Output: Optimized answer data.

[1218] Step 5:

[1219] The server validates the generated response data and returns it to the terminal.

[1220] Input: Optimized response data.

[1221] Operation: The server formats the response data, performs a validation check again to ensure there are no errors in the format or content, and then returns the response data to the device via HTTPS.

[1222] Output: The response data sent to the device.

[1223] Step 6:

[1224] The terminal receives the response data and displays it to the user.

[1225] Input: The response data sent from the server.

[1226] What it does: The device interface parses the received response data and displays it to the user in a user-friendly format.

[1227] Output: "When your child refuses to eat something, first stay calm. Then, offering them a small amount of their favorite food can be effective."

[1228] Step 7:

[1229] The server stores the questions, answers, and emotion data in a database.

[1230] Input: Question data, generated answer data, sentiment data.

[1231] How it works: The server structures and stores this data in a database.

[1232] Output: Questions, answers, and sentiment data recorded in a database.

[1233] Step 8:

[1234] The server periodically analyzes the data in the database and extracts common issues.

[1235] Input: Saved question data, answer data, and sentiment data.

[1236] How it works: The server uses machine learning algorithms to analyze the data and detect common issues and trends, for example, "There are a lot of inquiries about nighttime crying."

[1237] Output: Report data as the analysis result.

[1238] Step 9:

[1239] The server sends common issues to the public agency in the form of a report.

[1240] Input: Analysis result report data.

[1241] How it works: The server generates a report and sends it to the public agency using secure communications.

[1242] Output: Report sent to public authorities.

[1243] (Application example 2)

[1244] 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."

[1245] In food delivery services, it is difficult for customers to receive appropriate and sensitive responses when they experience delays or problems with their orders. Furthermore, service providers lack sufficient means to proactively utilize customer feedback to improve their services. Furthermore, there is a lack of a system for systematically identifying common issues and incorporating them into service improvements.

[1246] The identification process 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 receiving a question from a user, means for analyzing the received question using natural language processing and generating an answer, means for returning the generated answer to the user, means for saving the question and the generated answer, means for analyzing the saved question and answer and extracting common issues, means for sending the extracted issues to a public institution, emotion recognition means for recognizing the emotion of the user when entering the question, and means for optimizing the generated answer by taking the user's emotion into consideration. This enables customers to receive prompt and emotionally sensitive service, and enables service providers to improve the quality of their services by utilizing the collected data.

[1247] "User" refers to an individual, corporation, or service user who uses the system to ask questions or ask for advice.

[1248] The "means for receiving a question" refers to a function for the server to receive question data sent from a user via the Internet or a mobile application.

[1249] "Natural language processing" refers to the technology of using a computer to analyze natural human language, understand its meaning, and generate appropriate answers.

[1250] "Means for generating an answer" refers to a function for analyzing a received question and automatically generating an appropriate answer to that question.

[1251] "Means for returning an answer" refers to a function for sending the generated answer to the user's device and displaying it to the user.

[1252] "Means for storing questions and answers" refers to a function for storing received questions and generated answers in a database.

[1253] "Means of analyzing saved questions and answers and extracting common issues" refers to a function that periodically analyzes data stored in the database to find problems and areas for improvement common to multiple questions and answers.

[1254] "Means for sending issues to public institutions" refers to the function for compiling extracted issues and trends into a report format and sending it to public institutions, etc.

[1255] "Emotion recognition means" refers to a function for analyzing and recognizing the emotion expressed by the user when entering a question.

[1256] The "means for optimizing the generated answer by taking emotions into consideration" refers to a function for adjusting the generated answer to a more appropriate form according to the user's emotions.

[1257] "Food delivery service" refers to a service that allows users to order meals online and have the meals delivered.

[1258] This invention provides a system for providing a food delivery service that responds to user questions quickly and with consideration for their feelings. A specific implementation method of this system will be described below.

[1259] First, a user uses a smartphone or tablet to input a question or complaint about the food delivery service. When inputting a question, the emotion recognition means analyzes the emotion from the user's input and transmits the emotion data along with the question. The question and emotion data are then converted into JSON format and transmitted to the server using a secure communication method (e.g., HTTPS).

[1260] The server validates the received question and emotion data and passes the data to the natural language processing engine, generative AI model, and emotion recognition engine. The natural language processing engine analyzes the question data and generates an appropriate answer. Meanwhile, the emotion recognition engine uses the user's emotion data to optimize the generated answer. This makes it possible to provide an appropriate answer that takes the user's emotions into consideration.

[1261] The generated answer is validated again, formatted into an appropriate format, and sent back to the user's device. The device receives the formatted answer data and displays it in an easy-to-understand format for the user.

[1262] Furthermore, the questions, generated answers, and sentiment data are stored in a database. The server periodically analyzes the data and detects common issues and trends from the stored data. This allows food delivery service providers to identify areas for improvement and take necessary measures.

[1263] As a concrete example, consider the case where a user sends a question such as, "My order is late. When will it arrive?" In response to this question, the emotion recognition means detects "frustration," and the generative AI model generates the answer, "It will arrive in 15 to 20 minutes." The emotion recognition engine then optimizes the answer to, "We apologize for the inconvenience, but it will arrive in 15 to 20 minutes." This allows for a prompt and appropriate response to be provided to the user.

[1264] An example prompt is:

[1265] If the emotion recognition result for the question "My order is delayed. When will it arrive?" is "frustration," the generative AI model will generate the answer "It will arrive in 15 to 20 minutes." Then, as a result of optimization by the emotion recognition engine, the final answer will be provided: "We apologize for the inconvenience, but your order is expected to arrive in 15 to 20 minutes."

[1266] The main hardware used includes user devices (smartphones and tablets), cloud servers, and network equipment. The software used includes Android / iOS apps, Python, Tensorflow, Watson NLP services, and Emotion Recognition API. Combining these components makes it possible to efficiently implement a question-answering system for food delivery services.

[1267] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1268] Step 1:

[1269] A user uses a smartphone or tablet device to input questions or complaints about food delivery services. When the user enters a question in the input field and presses the send button, the question is received by the device. At this time, the emotion recognition means analyzes the emotion from the user's input. The input is made by the user, and the output is question data accompanied by analyzed emotion data.

[1270] Step 2:

[1271] The device converts the input question and emotion data into JSON format. The converted data is sent to the server using a secure communication method (e.g., HTTPS). The input is the user's question data and emotion data, and the output is the data converted into JSON format.

[1272] Step 3:

[1273] The server performs validation checks on the questions and emotion data it receives. After filtering out invalid data, it passes the data to the natural language processing engine, generative AI model, and emotion recognition engine. The input is question data and emotion data in JSON format, and the output is the data required for analysis and optimization.

[1274] Step 4:

[1275] The natural language processing engine analyzes the question data and generates an appropriate answer. The generative AI model analyzes the question content and suggests the most appropriate answer. The input is validated question data, and the output is the generated answer data.

[1276] Step 5:

[1277] The emotion recognition engine uses the user's emotional data to optimize the generated answer, adjusting the wording and approach according to the user's emotions. The input is the generated answer data and emotional data, and the output is the optimized answer data.

[1278] Step 6:

[1279] The server revalidates the response data received from the generative AI and emotion recognition engine and formats it appropriately. It then returns the response data to the device. The input is the optimized response data, and the output is the formatted response data.

[1280] Step 7:

[1281] The terminal displays the formatted answer data received from the server in an easy-to-understand manner to the user. The user checks the answer displayed on the terminal screen. The input is the formatted answer data, and the output is the displayed answer.

[1282] Step 8:

[1283] The server stores the question, the generated answer, and the emotion data in a database. The data is stored as pairs of question content, answer content, and emotion data. The input is the question data, answer data, and emotion data, and the output is the stored data.

[1284] Step 9:

[1285] The server periodically extracts and analyzes all data stored in the database to detect common issues and trends. Machine learning algorithms may be used for data analysis. The input is the data in the database, and the output is the analysis results.

[1286] Step 10:

[1287] The server extracts common issues and trends from the analysis results and compiles them into a report, which is then sent to public institutions and food delivery service providers. The input is the analysis results, and the output is a summary in report format and its transmission.

[1288] 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.

[1289] 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.

[1290] 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.

[1291] [Fourth embodiment]

[1292] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1293] 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.

[1294] 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).

[1295] 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.

[1296] 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.

[1297] 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).

[1298] 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.

[1299] 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.

[1300] 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.

[1301] 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.

[1302] 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.

[1303] 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.

[1304] 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."

[1305] This invention is a system that receives questions and inquiries from users, analyzes the questions using natural language processing, and generates appropriate answers. The generated answers are returned to the users, and all question and answer data is stored in a database. This data is periodically analyzed, and common issues are extracted and sent to public institutions. Through this process, we are able to respond to inquiries about childcare and take measures to combat the declining birthrate.

[1306] Explanation of program processing

[1307] 1. Enter and submit your question

[1308] User

[1309] The user uses the terminal to input questions or inquiries about childcare into the input field.

[1310] For example: "What should I do if my child refuses to eat?"

[1311] 2. Sending input data

[1312] Terminal

[1313] Convert the input question into JSON format.

[1314] The converted data is sent to the server via a secure communication method (e.g., HTTPS).

[1315] 3. Receiving and analyzing questions

[1316] server

[1317] The server receives the query data sent from the terminal.

[1318] The format and content of the received data are validated, and if normal, it is passed to the natural language processing engine.

[1319] Generative AI

[1320] Analyze the question data and generate appropriate answers.

[1321] For example: "If your child is reluctant to eat, it's a good idea to start by offering them small amounts of their favorite foods. It's also important to find ways to make eating enjoyable."

[1322] 4. Receiving and returning responses

[1323] server

[1324] Receive response data from the generative AI.

[1325] The received response data is validated again and formatted to be returned to the terminal.

[1326] Terminal

[1327] The formatted answer data is received and displayed on the screen in a format that is easy for the user to view.

[1328] Example: Displayed answer: "If your child is reluctant to eat, it's a good idea to start by offering them small amounts of their favorite foods. It's also important to find ways to make eating enjoyable."

[1329] 5. Data storage and analysis

[1330] server

[1331] Save the questions and generated answers in a database.

[1332] All data stored in the database is periodically extracted and analyzed to detect common issues.

[1333] 6. Extract and submit assignments

[1334] server

[1335] Based on the results of the analysis, common issues and trends are extracted.

[1336] The extracted issues and trend information will be sent to public institutions as a report.

[1337] Examples: "There has been an increase in consultations regarding diet," "There are many consultations regarding night crying in certain areas," etc.

[1338] Specific examples

[1339] context

[1340] The user uses the terminal to input a question about a child-rearing problem.

[1341] Sample question: "What should I do if my child cries at night?"

[1342] Processing Flow

[1343] 1. The user types a question into the terminal.

[1344] 2. The device sends the question to the server in JSON format.

[1345] 3. The server passes the question to a generative AI, which generates an answer.

[1346] 4. The generative AI generated the answer, "Effective ways to deal with nighttime crying include adjusting your baby's sleep rhythm and creating a relaxing environment."

[1347] 5. The server generates the answer and sends it back to the user's device.

[1348] 6. The device displays the answer to the user.

[1349] 7. The server stores the question and answer data in a database.

[1350] 8. Regularly analyze the data and identify the issue of "many inquiries about nighttime crying."

[1351] 9. The server sends this issue as a report to the public agency.

[1352] In this way, the system provides a mechanism for quickly responding to user questions and utilizing the collected data to combat the declining birthrate. This system is both convenient for users and a valuable source of information for public institutions.

[1353] The processing flow will be explained below.

[1354] Step 1:

[1355] The user uses the device to enter a question or inquiry about childcare into the input field. For example, "What should I do if my child refuses to eat?"

[1356] Step 2:

[1357] The device converts the entered question into an appropriate data format, such as JSON. Specifically, it converts it into the following format: json { "question": "What should I do if my child refuses to eat?"}

[1358] Step 3:

[1359] The device sends the converted data to the server using a secure communication method such as HTTPS. The data is encrypted and managed to reach the server safely.

[1360] Step 4:

[1361] The server receives the query data sent from the terminal, validates the format and content of the received data, and eliminates invalid data.

[1362] Step 5:

[1363] The server passes the received question data to a natural language processing engine (e.g., a generative AI). The engine is called via an API endpoint and analyzes the question and generates an answer.

[1364] Step 6:

[1365] Generative AI analyzes question data and generates appropriate answers, such as, "If your child doesn't like to eat, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find ways to make eating fun."

[1366] Step 7:

[1367] The server then validates the answer data received from the generative AI and formats it into the appropriate format. Validation includes checking the consistency and quality of the answer text.

[1368] Step 8:

[1369] The server returns the formatted response data to the terminal, usually via HTTPS.

[1370] Step 9:

[1371] The device receives the response data sent from the server and displays it in an easy-to-understand manner to the user. For example, it displays, "If your child doesn't like to eat, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find ways to make eating fun."

[1372] Step 10:

[1373] The server stores the questions and generated answers in a database. The data is stored as pairs of question and answer.

[1374] Step 11:

[1375] The server periodically runs jobs that analyze the question and answer data stored in the database, sometimes using machine learning algorithms.

[1376] Step 12:

[1377] The server extracts common issues and trends from the analysis results. For example, it finds patterns from data such as "there are many consultations about nighttime crying" or "the number of consultations about eating is increasing."

[1378] Step 13:

[1379] The server compiles the extracted issues and trend information into a report format and sends it to the public institution via API or secure data transmission methods.

[1380] Step 14:

[1381] Based on the data received, public institutions will consider and implement measures to combat the declining birthrate. Specific countermeasures will be planned and implemented for the issues identified.

[1382] Example 1

[1383] 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."

[1384] Currently, many childcare-related questions and inquiries are handled individually, without effective data analysis or sharing. This makes it difficult to effectively utilize this data and link it to improving childcare support and measures to combat the declining birthrate. Furthermore, there is a lack of a system for providing prompt, appropriate answers to user questions.

[1385] 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.

[1386] In this invention, the server includes means for receiving questions from users, means for converting the received questions into a data format and transmitting the data, means for validating the format and content of the received data and, if normal, passing the data to an analysis engine, means for analyzing the question data using a generative AI model and generating an appropriate answer, means for returning the generated answer to the user, means for saving the questions and the generated answers, means for analyzing the saved questions and answers and extracting common issues, and means for sending the extracted issues to public institutions. This makes it possible to provide users with prompt and appropriate answers and to utilize data to support childcare and address the declining birthrate.

[1387] "User" refers to a person who inputs questions or inquiries about childcare into the system.

[1388] A "terminal" is a device used by a user to input questions or inquiries, and includes smartphones, personal computers, etc.

[1389] "Server" refers to a central processing unit for receiving user questions, passing the data to the analysis engine, and transmitting generated answers.

[1390] A "question" refers to a childcare-related question that a user enters into an input field.

[1391] "Received data" refers to the data that the server receives after converting the question entered by the user into a data format such as JSON.

[1392] "Validation" refers to the process of checking that received data is in the correct format and contains expected content.

[1393] "Analytics Engine" refers to software or algorithms that analyze incoming data and generate appropriate answers.

[1394] A "generative AI model" refers to a machine learning model that uses generative AI to generate appropriate answers to user questions.

[1395] "Answer" refers to the information generated by a generative AI model and returned in response to a user's question.

[1396] "Saving" refers to the act of storing the question and its generated answer in a database.

[1397] "Database" means a digital storage system for managing and storing saved question and answer data.

[1398] "Analysis" refers to the process of analyzing stored data to extract common issues.

[1399] "Common issues" refers to themes or issues that frequently emerge from multiple questions and their answers.

[1400] A "public institution" refers to an organization that operates for the public good, such as a government or local government.

[1401] The present invention is a system that receives questions and inquiries about childcare from users, analyzes them, and generates answers. The system includes a device used by the user, a server that processes and stores data, and a generative AI model that performs natural language processing.

[1402] The user uses the device to input a question or inquiry. The user opens a browser on their smartphone or PC, accesses a dedicated web form, and enters the question in the input field. For example, they might enter, "What should I do if my child refuses to eat?" and click the send button.

[1403] The device converts the question entered by the user into JSON format, for example, {"question": "What should I do if my child refuses to eat?"}. The converted data is securely sent to the server using the HTTPS protocol.

[1404] The server receives the question data sent from the device. It validates the format and content of the received data, and if it is normal, passes it to the analysis engine. After format checks and XSS attack countermeasures, it passes the question data to the generative AI model as a prompt text. Examples of prompt text are as follows:

[1405] "Question: What should I do if my child refuses to eat? Generate an appropriate answer."

[1406] A generative AI model (e.g., OpenAI GPT-4) receives a prompt and generates an answer based on the training data, such as, "If your child refuses to eat, it's a good idea to offer them a small amount of their favorite food first. It's also important to find ways to make eating enjoyable."

[1407] The server receives the answer data from the generative AI model. The received answer data is validated again, and if normal, it is formatted to be sent back to the device. The content of the answer data is checked and formatted, for example, {"answer": "If a child doesn't like eating, it's a good idea to first offer them a small amount of their favorite food. It's also important to find a way to make eating enjoyable."}

[1408] The device analyzes the response data received from the server and displays it on the screen in an easy-to-read format for the user. An example of what is displayed is, "If your child doesn't like to eat, it's a good idea to first offer them a small amount of their favorite food. It's also important to find ways to make eating fun."

[1409] The server saves the question and the generated answer in a database. The question and answer are stored in the database in JSON format. For example, it is saved as follows: {"question": "What should I do if my child refuses to eat?", "answer": "If a child refuses to eat, it is a good idea to start by offering them a small amount of their favorite food. It is also important to find ways to make eating enjoyable."}

[1410] The system periodically extracts and analyzes all data stored in the database to detect common issues. The server runs a regularly scheduled task to retrieve past questions and answers from the database and uses natural language processing technology to extract common topics and trends. For example, it detects an increase in questions related to night crying.

[1411] Based on the analysis results, the extracted issues and trend information are sent to the public institution as a report. The generated report is formatted in PDF or CSV format and sent to the API endpoint or email address specified by the public institution. For example, a report containing content such as "Recent trend: Increase in the number of consultations about nighttime crying" is sent.

[1412] This system provides users with quick and appropriate answers, and also provides a mechanism that makes it possible to utilize data to support childcare and implement measures to combat the declining birthrate.

[1413] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1414] Step 1:

[1415] The user uses the device to enter a question or request for advice about childcare into an input field. Specifically, the user opens a browser on their smartphone or PC, accesses a dedicated web form, enters "What should I do if my child refuses to eat?" into the input field, and clicks the send button. The input is the question from the user, and the output is saved on the device as this question data.

[1416] Step 2:

[1417] The terminal converts the question entered by the user into JSON format. Specifically, the terminal parses the user's input text and converts it into a JSON object of key-value pairs (e.g., {"question": "What should I do if my child refuses to eat?"}). The input is the text entered by the user, and the output is question data in JSON format.

[1418] Step 3:

[1419] The terminal sends the converted JSON data to the server using the HTTPS protocol. Specifically, the terminal includes the generated JSON object in the HTTPS request body and sends a POST request to the specified endpoint on the server. The input is the question data in JSON format, and the data is sent to the server as the output.

[1420] Step 4:

[1421] The server receives the question data sent from the terminal. Specifically, the server receives the HTTPS request and extracts JSON data from the request body. The input is the received HTTPS request, and the output is the extracted JSON-formatted question data.

[1422] Step 5:

[1423] The server validates the format and content of the received data. Specific operations include format checks (e.g., checking the existence of keys) and XSS attack prevention. The input is JSON-formatted question data, and the output is validated JSON data. If this validated data is valid, it is passed to the analysis engine.

[1424] Step 6:

[1425] If everything is normal, the server passes the question data to the generative AI model as a prompt text. Specifically, it generates a prompt text and sends it to the generative AI model. An example of a prompt text is: "Question: What should I do if my child refuses to eat? Please generate an appropriate answer." The input is validated JSON data, and the output is a prompt text.

[1426] Step 7:

[1427] A generative AI model receives a prompt, analyzes the question data, and generates an appropriate answer. Specifically, a generative AI model (e.g., OpenAI GPT-4) analyzes the prompt and generates an answer based on the training data. An example of a generated answer is: "If a child doesn't like eating, it's a good idea to first offer them a small amount of their favorite food. It's also important to find a way to make eating enjoyable." The input is a prompt, and the output is a generated answer.

[1428] Step 8:

[1429] The server receives the answer data from the generative AI model. Specifically, the server receives the answer generated from the API of the generative AI model. The generated answer data is the input, and it is saved on the server as the output.

[1430] Step 9:

[1431] The server revalidates the received response data. Specifically, it checks the content of the response data (e.g., whether it contains any undesirable content). The input is the generated response data, and the output is the validated response data.

[1432] Step 10:

[1433] The server formats the validated answer data into a format to be sent back to the device. Specifically, it formats the answer in JSON format, for example, {"answer": "If a child doesn't like eating, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find ways to make eating enjoyable."}. The input is the validated answer data, and the output is the formatted answer data.

[1434] Step 11:

[1435] The device analyzes the response data received from the server and displays it on the screen in a format that is easy for the user to view. Specifically, the device analyzes the JSON data received from the server and displays the response in the browser's display area. An example of what is displayed is, "If your child doesn't like to eat, it's a good idea to first offer them a small amount of their favorite food. It's also important to find a way to make eating enjoyable." The input is the formatted response data, and the output is displayed to the user.

[1436] Step 12:

[1437] The server saves the question and the generated answer in a database. Specifically, the question and answer are stored in the database in JSON format. Example of saved data: {"question": "What should I do if my child doesn't want to eat?", "answer": "If a child doesn't want to eat, it's a good idea to start by offering them a small amount of their favorite food. It's also important to find a way to make eating enjoyable."}. The input is the question and the generated answer data, and the output is saved in the database.

[1438] Step 13:

[1439] The server periodically extracts and analyzes all data stored in the database to detect common issues. Specifically, the server executes a regularly scheduled task to retrieve past questions and answers from the database and uses natural language processing technology to extract common topics and trends. For example, it detects an increase in questions related to nighttime crying. The input is the question and answer data stored in the database, and the output is the detection of common issues.

[1440] Step 14:

[1441] Based on the results of the analysis, the server sends the extracted issues and trend information to the public institution as a report. Specifically, the generated report is formatted in PDF or CSV format and sent to an API endpoint or email address specified by the public institution. For example, a report titled "Recent trends: Increase in the number of consultations about nighttime crying" is sent. Common issues and trend information are input, and the report is sent to the public institution as output.

[1442] (Application example 1)

[1443] 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."

[1444] One issue facing brick-and-mortar stores is the lack of a way for customers to quickly and appropriately resolve questions about childcare or products without having to ask staff directly. There is also a need for a system that accumulates and analyzes customer question data and provides the information to public institutions to contribute to childcare support measures and measures to combat the declining birthrate throughout society.

[1445] 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.

[1446] In this invention, the server includes means for receiving questions from users, means for analyzing the received questions using natural language processing and generating answers, means for returning the generated answers to the users, means for saving the questions and the generated answers, means for analyzing the saved questions and answers and extracting common issues, means for sending the extracted issues to public institutions, means for responding to customer questions in physical stores, and means for displaying the generated answers on the customer's terminal. This makes it possible to quickly and appropriately respond to customer questions in physical stores, and to analyze the accumulated data and utilize it for childcare support measures and measures to combat the declining birthrate throughout society.

[1447] "User" means an individual or organization that uses the system to ask questions or make inquiries.

[1448] A "question" is a question or inquiry submitted by a user to the system.

[1449] "Natural language processing" is a technology that allows a machine to understand input questions or consultation content and generate appropriate answers.

[1450] An "answer" is a response generated in response to a question analyzed by natural language processing.

[1451] The "receiving means" refers to a mechanism or device for receiving a question from a user.

[1452] A "return mechanism" is a mechanism or device for returning the generated answer to the user.

[1453] A "storage means" is a mechanism or device for storing questions and generated answers for a certain period of time.

[1454] "Analysis means" refers to a mechanism or device for analyzing stored questions and answers.

[1455] "Issue extraction means" refers to mechanisms or devices for identifying common problems or trends based on analysis.

[1456] "Public agency transmission means" refers to the mechanism or device for transmitting the identified issues to the relevant public agencies.

[1457] A "brick and mortar store" is a physical commercial establishment where customers visit and purchase goods in person.

[1458] "Response methods" refer to mechanisms and devices that allow a physical store to respond quickly to customer questions.

[1459] A "terminal" is an electronic device that a user uses to enter questions and receive answers.

[1460] This invention realizes a system that receives questions from customers in a physical store, processes them, answers them, and returns them. The specific implementation method and operation of this system are described below.

[1461] System Overview

[1462] This system is realized using a user device (such as a smartphone), a server, and a generative AI model. The main hardware and software components and their roles are described below.

[1463] Hardware and Software Used

[1464] User device: The device on which customers enter their questions and receive answers. This could be a smartphone or tablet.

[1465] Server: The central component that receives questions, generates answers, stores and analyzes data, and sends reports to public authorities.

[1466] Usage example: Cloud servers (Amazon Web Services, Google Cloud Platform)

[1467] Generative AI model: Analyzes questions and generates appropriate answers. The following natural language processing engines are used:

[1468] Usage examples: Amazon Lex, Google Dialogflow

[1469] Program processing overview

[1470] 1. Enter and submit your question

[1471] A user uses a smartphone app in a physical store to input a question, for example, "Is it better to have a lightweight stroller?"

[1472] 2. Sending input data

[1473] The device converts the entered question into JSON format and sends it to the server using HTTPS.

[1474] 3. Receiving and analyzing questions

[1475] The server receives the input data, validates the format and content, and if there are no problems, passes it to the natural language processing engine.

[1476] A generative AI model (e.g., Amazon Lex) analyzes the question and generates an appropriate answer, such as, "A lightweight stroller is easy to use, but durability should also be considered."

[1477] 4. Receiving and returning responses

[1478] The server receives the generated response, validates it, and then formats it into a format to be sent back to the user's terminal.

[1479] The terminal receives the response data and displays it in an easy-to-read format for the customer.

[1480] 5. Data storage and analysis

[1481] The server stores the questions and generated answers in a database.

[1482] The contents of the database are analyzed periodically to extract common issues.

[1483] 6. Extract and submit assignments

[1484] Based on the analysis results, the server extracts common issues and trends and sends them to public institutions as a report.

[1485] Specific examples

[1486] Enter your question

[1487] A user types a question in a physical store.

[1488] For example: "Is a lighter stroller better?"

[1489] Prompt Sentence Examples

[1490] A user asked: "Is a lighter stroller better?"

[1491] Context for Answer Generation: Generate an answer about the balance between lightweight and sturdy strollers.

[1492] This system will enable physical stores to respond quickly and appropriately to customer questions, and the accumulated data will enable public institutions to understand consumer needs and implement effective childcare support measures and countermeasures against the declining birthrate.

[1493] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1494] Step 1:

[1495] A user uses a smartphone app to input a question in a physical store. For example, the question might be input in the form of "Is a lightweight stroller better?" The input question is saved in text format in a data input field in the application.

[1496] Step 2:

[1497] The terminal receives a question entered by the user and converts it into JSON format. The converted data is sent to the server via a secure communication method (e.g., HTTPS). The input is text data, and the output is JSON format data. This data processing makes it easy for the server to process the question content.

[1498] Step 3:

[1499] The server receives JSON-formatted question data sent from the terminal. It validates the format and content of the received data, and if it is normal, passes it to the natural language processing engine. The input is JSON-formatted question data, and the output is validated data. The data calculations performed here check the data format and confirm the content.

[1500] Step 4:

[1501] The generative AI model analyzes the question data and generates an appropriate answer. The generation process uses a pre-prepared prompt (e.g., "Please generate an answer about the balance between lightness and durability of strollers"). The input is validated question data, and the output is the answer text. This data calculation generates answers based on natural language processing.

[1502] Step 5:

[1503] The server revalidates the answer data received from the generative AI and formats it for return to the terminal. The input is the generated answer text, and the output is the formatted data. The data processing performed here involves checking the answer data and converting its format.

[1504] Step 6:

[1505] The terminal receives the formatted response data and displays it on the screen in a format that is easy for the user to see. The input is the formatted response data, and the output is a display format that the user can visually recognize. The data processing performed here is to make the received data into a format that can be displayed.

[1506] Step 7:

[1507] The server saves the question and generated answer in a database. The input is the question and generated answer data, and the output is the saved data in the database. This process involves a write operation to the database.

[1508] Step 8:

[1509] The server periodically extracts and analyzes all data stored in the database to detect common issues. The input is past question and answer data extracted from the database, and the output is the analysis results. The data calculations performed here involve data analysis and trend extraction.

[1510] Step 9:

[1511] Based on the analysis results, the server sends common issues and trend information to public institutions as a report. The input is the analysis results, and the output is the sent report. This process involves report generation and transmission operations.

[1512] The above is a specific processing flow of the system that realizes the application example.

[1513] 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.

[1514] This invention combines a system that receives questions and inquiries from users, analyzes the questions using natural language processing, and generates appropriate answers, with an emotion engine that recognizes the user's emotions. The generated answers are optimized based on the user's emotional state and returned to the user. Furthermore, all question and answer data is stored in a database and periodically analyzed to extract common issues that are then sent to public institutions. This not only enables childcare consultations and measures to combat the declining birthrate, but also makes it possible to provide individual responses that take the user's emotions into consideration.

[1515] Explanation of program processing

[1516] 1. Question input and emotion recognition

[1517] User

[1518] The user uses the terminal to input a question or inquiry about childcare into the input field. For example, the user inputs something like, "What should I do if my child refuses to eat?"

[1519] 2. Sending input data and emotion data

[1520] Terminal

[1521] The input question is converted into JSON format. The emotion engine also recognizes the user's emotion from the input and sends the emotion data along with the question.

[1522] The converted data is sent to the server via a secure connection (e.g. HTTPS). Example: json { "question": "What should I do if my child refuses to eat?", "emotion": "frustration"}

[1523] 3. Receiving and analyzing question and emotion data

[1524] server

[1525] The server receives the question and emotion data sent from the device, validates the format and content of the received data, and eliminates invalid data.The data is then passed to the natural language processing engine and emotion engine.

[1526] Generative AI and Emotion Engines

[1527] The generative AI analyzes question data and generates appropriate answers, while the emotion engine uses user emotional data to optimize the generated answers.

[1528] For example, in response to the question, "What should I do if my child refuses to eat?"

[1529] When the emotional data "frustration" is included, it is optimized to say, "When your child refuses to eat something, first stay calm. Then, it is effective to offer them a small amount of their favorite food."

[1530] 4. Receiving and returning responses

[1531] server

[1532] The response data received from the generative AI and emotion engine is validated again and formatted appropriately, after which it is sent back to the device.

[1533] Terminal

[1534] The formatted response data is received and displayed to the user in an easy-to-understand format. For example, "When a child refuses to do something, first try to stay calm. Then, it can be effective to offer them a small amount of their favorite food."

[1535] 5. Data storage and analysis

[1536] server

[1537] The questions, generated answers, and emotion data are stored in a database. The data is stored as pairs of question content, answer content, and emotion data.

[1538] 6. Regular data analysis and problem extraction

[1539] server

[1540] All data stored in the database is periodically extracted and analyzed to detect common issues and trends, sometimes using machine learning algorithms.

[1541] 7. Extract and submit assignments

[1542] server

[1543] Common issues and trends are extracted from the analysis results and compiled into a report. This report is then sent to public institutions. Examples include "There are many inquiries about nighttime crying" or "There is an increase in inquiries about meals in certain areas."

[1544] Specific examples

[1545] context

[1546] When a user uses a terminal to input a question about a child-rearing problem, the user's emotions are also recognized.

[1547] Processing Flow

[1548] 1. The user enters a question into the device, and the emotion associated with the question is automatically recognized. For example, "What should I do if my child cries at night?" is entered, and the emotion indicated is "tired."

[1549] 2. The device sends the question and emotion data in JSON format to the server.

[1550] 3. The server passes the question and emotion data to the generative AI and emotion engine to generate an answer.

[1551] 4. The generative AI generates answers such as "regulate your sleep rhythm and create a relaxing environment," and the emotion engine takes "fatigue" into consideration and emphasizes the advice.

[1552] 5. The server generates the answer and sends it back to the user's device.

[1553] 6. The device displays the answer to the user. For example, "When your child cries at night, first check to see if you are tired. Then, it is effective to regulate your sleep rhythm and create a relaxing environment."

[1554] 7. The server stores the questions, answers, and emotion data in a database.

[1555] 8. Regularly analyze data to detect issues such as "many inquiries about nighttime crying."

[1556] 9. The server sends these issues as a report to the public agency.

[1557] This system not only enables quick responses to user questions and individual responses based on emotions, but also makes it possible to use the collected data to combat the declining birthrate.

[1558] The processing flow will be explained below.

[1559] Step 1:

[1560] The user uses the terminal to input a question or inquiry about childcare into the input field. For example, the user inputs a question such as "What should I do if my child refuses to eat?"

[1561] Step 2:

[1562] The device receives the input question as text data and uses an emotion engine to recognize the user's emotions. For example, it identifies the emotion "frustration" from the context of the input.

[1563] Step 3:

[1564] The device converts the question data and emotion data into JSON format. For example, it converts it into the following data format: json { "question": "What should I do if my child refuses to eat?", "emotion": "frustration"}

[1565] Step 4:

[1566] The device sends the converted data to the server using a secure communication method such as HTTPS, and the data is encrypted before transmission.

[1567] Step 5:

[1568] The server receives the question data and emotion data sent from the device, checks the format and content of the received data, and verifies that the format is correct.

[1569] Step 6:

[1570] The server passes the received question data and emotion data to a natural language processing engine (generative AI), which is called via an API endpoint.

[1571] Step 7:

[1572] Generative AI analyzes the question data and generates an appropriate answer, such as, "If your child doesn't like eating, it's important to first offer them small amounts of their favorite foods and find ways to make eating enjoyable."

[1573] Step 8:

[1574] The emotion engine uses the emotional data to optimize the generated answers. For example, if the emotional data includes "frustration," the response will be optimized to something like, "First, calm yourself down. Then, it's important to offer a small amount of your favorite food and find a way to make your meal enjoyable."

[1575] Step 9:

[1576] The server then performs a validation check on the optimized response data again and formats it into a format to be sent back to the terminal.

[1577] Step 10:

[1578] The server returns the formatted response data to the device using HTTPS, a secure method of communication.

[1579] Step 11:

[1580] The device receives the response data sent from the server and displays it to the user, such as, "First, calm yourself down. Then, it's important to find a way to enjoy your meal by offering small amounts of your favorite foods."

[1581] Step 12:

[1582] The server stores the questions, generated answers, and emotion data in a database. The stored data includes the question content, the answer content, and the emotion data.

[1583] Step 13:

[1584] The server periodically runs a job that analyzes all the data stored in the database, sometimes using machine learning algorithms.

[1585] Step 14:

[1586] The server extracts common issues and trends from the analysis results, for example, discovering common issues such as "there are many inquiries about nighttime crying" or "there is an increase in inquiries about meals in certain areas."

[1587] Step 15:

[1588] The server compiles the extracted issues and trend information into a report and sends it to the public institution. The data is sent securely using an API.

[1589] Step 16:

[1590] Based on the data received, public institutions will consider and implement measures to combat the declining birthrate. For example, they will plan and implement specific countermeasures, such as holding childcare consultation sessions in specific areas.

[1591] Example 2

[1592] 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."

[1593] Conventional systems were unable to consider the user's emotions when providing answers to user questions, resulting in a lack of individualized support. Furthermore, there was no established mechanism for effectively analyzing collected question and answer data to identify common issues and provide feedback to public institutions. This resulted in insufficient support for childcare consultations and in ineffective measures to combat the declining birthrate.

[1594] 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 receiving a question and emotion data from a user, means for analyzing the received question and emotion data using natural language processing and an emotion recognition engine to generate an answer, and means for optimizing the generated answer based on the user's emotion data and returning it to the user. This makes it possible to provide an individual response that takes the user's emotion into consideration, and also establishes a mechanism for storing the question, the generated answer, and the emotion data and periodically analyzing them to extract common issues and send them to public institutions.

[1595] A "user" is a person who uses the system to input questions or inquiries.

[1596] A "question" is a problem or inquiry about childcare that is input by a user.

[1597] "Emotion data" is emotional information analyzed from the questions and consultation contents entered by the user.

[1598] "Natural language processing" is a technology that analyzes text data, understands its meaning, and generates appropriate answers.

[1599] An "emotion recognition engine" is a technology that detects emotions from the user's input text and provides those emotions as data.

[1600] "Generative AI" is artificial intelligence that uses natural language processing to generate answers to user questions.

[1601] An "answer" is a system-generated answer or advice to a user's question.

[1602] "Optimization" refers to adjusting and improving answers by taking into account the user's emotional data.

[1603] "Saving" means storing the question data, answer data, and emotion data in a database.

[1604] A "database" is a system for structuring, storing, and managing questions, answers, and emotional data.

[1605] "Periodic analysis" refers to the process of extracting data stored in the database at regular intervals to detect common issues and trends.

[1606] A "common issue" is a common problem or trend that becomes apparent when analyzing data collected from multiple users.

[1607] "Public institutions" are government or administrative agencies that provide childcare support and take measures to combat the declining birthrate.

[1608] "Feedback" refers to the act of reporting and providing analysis results and common issues to public institutions.

[1609] This invention combines a system that receives questions and inquiries from users, analyzes the questions using natural language processing, and generates appropriate answers, with an emotion engine that recognizes the user's emotions. The answers generated by this system are optimized based on the user's emotional data and returned to the user. In addition, all question and answer data is stored in a database and periodically analyzed to extract common issues that are then sent to public institutions. This system not only enables childcare consultations and measures to combat the declining birthrate, but also enables individual responses that take the user's emotions into consideration.

[1610] First, the user uses the device to enter a question or request for advice about childcare into an input field. For example, they might enter something like, "What should I do if my child refuses to eat?" The entered question is converted into JSON format on the device, and at the same time, an emotion engine analyzes the user's input and recognizes the emotion. This converted data is then sent to the server using a secure communication method (e.g., HTTPS).

[1611] The server receives the question and emotion data sent from the device and performs validation checks on the data format and content. If the received data is valid, it is passed to the natural language processing engine and emotion engine. A generative AI model analyzes the question data and generates an appropriate answer. The emotion engine also uses the user's emotion data to optimize the generated answer based on the emotion data. For example, if the question "What should I do if my child refuses to eat?" contains the emotion data "frustration," the answer will be optimized to "When a child refuses to eat, first stay calm. Then, it can be effective to offer them a small amount of their favorite food."

[1612] The server then validates the response data received from the generative AI and emotion engine, formats it appropriately, and sends it back to the device. The device receives the formatted response data and displays it in a format that is easy for the user to understand. For example, it might say, "When your child is refusing to do something, first try to stay calm. Then, it can be effective to offer them a small amount of their favorite food."

[1613] Furthermore, the server stores the questions, generated answers, and emotion data in a database. This data is stored as pairs of question content, answer content, and emotion data. The server periodically accesses the database, extracts and analyzes all stored data. Data analysis may use machine learning algorithms to detect common issues and trends. Issues extracted based on this are compiled into a report and sent to public institutions. This provides data that can be used to improve childcare consultation services and address the declining birthrate.

[1614] As a concrete example, we will show how the system recognizes the user's emotions when they use a device to input a question about a parenting problem. For example, if the user inputs, "What should I do if my child cries at night?" and indicates "fatigue" as their emotion, this data is sent to the server in JSON format. The server receives the data and passes it to a natural language processing engine and emotion engine. The generative AI model generates an answer such as "regulate your sleep rhythm and create a relaxing environment," and the emotion engine emphasizes the answer by taking "fatigue" into account. The server reconfirms this and sends it back to the device. The device then displays the answer to the user: "When your child cries at night, first check whether you are tired. Then, it is effective to regulate your sleep rhythm and create a relaxing environment." All questions, answers, and emotion data collected during this process are stored in a database and used for later analysis.

[1615] In this way, the system of the present invention makes it possible to respond in a way that takes into account the user's emotions, and the collected data can be used to combat the declining birthrate.

[1616] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1617] Step 1:

[1618] The user enters a question into the terminal.

[1619] Input: The user types "What should I do if my child refuses to eat?" into the device's input field.

[1620] Operation: The terminal interface monitors the user's input, detects when the input is complete, and prepares to send it.

[1621] Output: User question text data.

[1622] Step 2:

[1623] The device analyzes the emotion data, converts it into JSON format, and sends it to the server.

[1624] Input: User question text data.

[1625] How it works: The emotion engine analyzes the user's text data and recognizes the user's emotions.

[1626] Output: json { "question": "What should I do if my child refuses to eat?", "emotion": "frustration"} The data converted to JSON format is sent to the server via HTTPS.

[1627] Step 3:

[1628] The server receives the question and emotion data and performs a validation check.

[1629] Input: JSON format data sent from the terminal.

[1630] Behavior: The server checks the received JSON data for formatting and content errors. If there are any invalid or missing data, it logs it and stops parsing.

[1631] Output: Question and sentiment data in legal JSON format.

[1632] Step 4:

[1633] The server passes the data to a natural language processing engine and an emotion engine to generate an answer.

[1634] Input: Question and sentiment data in legal JSON format.

[1635] How it works: The generative AI model analyzes the question and generates an initial answer. Meanwhile, the emotion engine optimizes the answer based on the user's emotional data. For example, based on the emotional data "frustration," it generates an answer such as, "When your child refuses to do something, first stay calm. Then, it's effective to offer them a small amount of their favorite food."

[1636] Output: Optimized answer data.

[1637] Step 5:

[1638] The server validates the generated response data and returns it to the terminal.

[1639] Input: Optimized response data.

[1640] Operation: The server formats the response data, performs a validation check again to ensure there are no errors in the format or content, and then returns the response data to the device via HTTPS.

[1641] Output: The response data sent to the device.

[1642] Step 6:

[1643] The terminal receives the response data and displays it to the user.

[1644] Input: The response data sent from the server.

[1645] What it does: The device interface parses the received response data and displays it to the user in a user-friendly format.

[1646] Output: "When your child refuses to eat something, first stay calm. Then, offering them a small amount of their favorite food can be effective."

[1647] Step 7:

[1648] The server stores the questions, answers, and emotion data in a database.

[1649] Input: Question data, generated answer data, sentiment data.

[1650] How it works: The server structures and stores this data in a database.

[1651] Output: Questions, answers, and sentiment data recorded in a database.

[1652] Step 8:

[1653] The server periodically analyzes the data in the database and extracts common issues.

[1654] Input: Saved question data, answer data, and sentiment data.

[1655] How it works: The server uses machine learning algorithms to analyze the data and detect common issues and trends, for example, "There are a lot of inquiries about nighttime crying."

[1656] Output: Report data as the analysis result.

[1657] Step 9:

[1658] The server sends common issues to the public agency in the form of a report.

[1659] Input: Analysis result report data.

[1660] How it works: The server generates a report and sends it to the public agency using secure communications.

[1661] Output: Report sent to public authorities.

[1662] (Application example 2)

[1663] 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."

[1664] In food delivery services, it is difficult for customers to receive appropriate and sensitive responses when they experience delays or problems with their orders. Furthermore, service providers lack sufficient means to proactively utilize customer feedback to improve their services. Furthermore, there is a lack of a system for systematically identifying common issues and incorporating them into service improvements.

[1665] The identification process 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 receiving a question from a user, means for analyzing the received question using natural language processing and generating an answer, means for returning the generated answer to the user, means for saving the question and the generated answer, means for analyzing the saved question and answer and extracting common issues, means for sending the extracted issues to a public institution, emotion recognition means for recognizing the emotion of the user when entering the question, and means for optimizing the generated answer by taking the user's emotion into consideration. This enables customers to receive prompt and emotionally sensitive service, and enables service providers to improve the quality of their services by utilizing the collected data.

[1666] "User" refers to an individual, corporation, or service user who uses the system to ask questions or ask for advice.

[1667] The "means for receiving a question" refers to a function for the server to receive question data sent from a user via the Internet or a mobile application.

[1668] "Natural language processing" refers to the technology of using a computer to analyze natural human language, understand its meaning, and generate appropriate answers.

[1669] "Means for generating an answer" refers to a function for analyzing a received question and automatically generating an appropriate answer to that question.

[1670] "Means for returning an answer" refers to a function for sending the generated answer to the user's device and displaying it to the user.

[1671] "Means for storing questions and answers" refers to a function for storing received questions and generated answers in a database.

[1672] "Means of analyzing saved questions and answers and extracting common issues" refers to a function that periodically analyzes data stored in the database to find problems and areas for improvement common to multiple questions and answers.

[1673] "Means for sending issues to public institutions" refers to the function for compiling extracted issues and trends into a report format and sending it to public institutions, etc.

[1674] "Emotion recognition means" refers to a function for analyzing and recognizing the emotion expressed by the user when entering a question.

[1675] The "means for optimizing the generated answer by taking emotions into consideration" refers to a function for adjusting the generated answer to a more appropriate form according to the user's emotions.

[1676] "Food delivery service" refers to a service that allows users to order meals online and have the meals delivered.

[1677] This invention provides a system for providing a food delivery service that responds to user questions quickly and with consideration for their feelings. A specific implementation method of this system will be described below.

[1678] First, a user uses a smartphone or tablet to input a question or complaint about the food delivery service. When inputting a question, the emotion recognition means analyzes the emotion from the user's input and transmits the emotion data along with the question. The question and emotion data are then converted into JSON format and transmitted to the server using a secure communication method (e.g., HTTPS).

[1679] The server validates the received question and emotion data and passes the data to the natural language processing engine, generative AI model, and emotion recognition engine. The natural language processing engine analyzes the question data and generates an appropriate answer. Meanwhile, the emotion recognition engine uses the user's emotion data to optimize the generated answer. This makes it possible to provide an appropriate answer that takes the user's emotions into consideration.

[1680] The generated answer is validated again, formatted into an appropriate format, and sent back to the user's device. The device receives the formatted answer data and displays it in an easy-to-understand format for the user.

[1681] Furthermore, the questions, generated answers, and sentiment data are stored in a database. The server periodically analyzes the data and detects common issues and trends from the stored data. This allows food delivery service providers to identify areas for improvement and take necessary measures.

[1682] As a concrete example, consider the case where a user sends a question such as, "My order is late. When will it arrive?" In response to this question, the emotion recognition means detects "frustration," and the generative AI model generates the answer, "It will arrive in 15 to 20 minutes." The emotion recognition engine then optimizes the answer to, "We apologize for the inconvenience, but it will arrive in 15 to 20 minutes." This allows for a prompt and appropriate response to be provided to the user.

[1683] An example prompt is:

[1684] If the emotion recognition result for the question "My order is delayed. When will it arrive?" is "frustration," the generative AI model will generate the answer "It will arrive in 15 to 20 minutes." Then, as a result of optimization by the emotion recognition engine, the final answer will be provided: "We apologize for the inconvenience, but your order is expected to arrive in 15 to 20 minutes."

[1685] The main hardware used includes user devices (smartphones and tablets), cloud servers, and network equipment. The software used includes Android / iOS apps, Python, Tensorflow, Watson NLP services, and Emotion Recognition API. Combining these components makes it possible to efficiently implement a question-answering system for food delivery services.

[1686] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1687] Step 1:

[1688] A user uses a smartphone or tablet device to input questions or complaints about food delivery services. When the user enters a question in the input field and presses the send button, the question is received by the device. At this time, the emotion recognition means analyzes the emotion from the user's input. The input is made by the user, and the output is question data accompanied by analyzed emotion data.

[1689] Step 2:

[1690] The device converts the input question and emotion data into JSON format. The converted data is sent to the server using a secure communication method (e.g., HTTPS). The input is the user's question data and emotion data, and the output is the data converted into JSON format.

[1691] Step 3:

[1692] The server performs validation checks on the questions and emotion data it receives. After filtering out invalid data, it passes the data to the natural language processing engine, generative AI model, and emotion recognition engine. The input is question data and emotion data in JSON format, and the output is the data required for analysis and optimization.

[1693] Step 4:

[1694] The natural language processing engine analyzes the question data and generates an appropriate answer. The generative AI model analyzes the question content and suggests the most appropriate answer. The input is validated question data, and the output is the generated answer data.

[1695] Step 5:

[1696] The emotion recognition engine uses the user's emotional data to optimize the generated answer, adjusting the wording and approach according to the user's emotions. The input is the generated answer data and emotional data, and the output is the optimized answer data.

[1697] Step 6:

[1698] The server revalidates the response data received from the generative AI and emotion recognition engine and formats it appropriately. It then returns the response data to the device. The input is the optimized response data, and the output is the formatted response data.

[1699] Step 7:

[1700] The terminal displays the formatted answer data received from the server in an easy-to-understand manner to the user. The user checks the answer displayed on the terminal screen. The input is the formatted answer data, and the output is the displayed answer.

[1701] Step 8:

[1702] The server stores the question, the generated answer, and the emotion data in a database. The data is stored as pairs of question content, answer content, and emotion data. The input is the question data, answer data, and emotion data, and the output is the stored data.

[1703] Step 9:

[1704] The server periodically extracts and analyzes all data stored in the database to detect common issues and trends. Machine learning algorithms may be used for data analysis. The input is the data in the database, and the output is the analysis results.

[1705] Step 10:

[1706] The server extracts common issues and trends from the analysis results and compiles them into a report, which is then sent to public institutions and food delivery service providers. The input is the analysis results, and the output is a summary in report format and its transmission.

[1707] 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.

[1708] 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.

[1709] 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.

[1710] 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.

[1711] 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.

[1712] 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.

[1713] 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).

[1714] 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.

[1715] 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."

[1716] 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.

[1717] 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).

[1718] 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.

[1719] 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.

[1720] 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.

[1721] 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.

[1722] 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.

[1723] 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.

[1724] 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.

[1725] 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.

[1726] 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.

[1727] 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.

[1728] The following is further disclosed regarding the above embodiment.

[1729] (Claim 1)

[1730] means for receiving a query from a user;

[1731] means for analyzing the received question by natural language processing and generating an answer;

[1732] means for returning the generated answer to the user;

[1733] a means for storing the questions and generated answers;

[1734] A means of analyzing saved questions and answers and extracting common issues;

[1735] The system includes a means for transmitting the extracted issues to a public agency.

[1736] (Claim 2)

[1737] 2. The system according to claim 1, further comprising means for periodically analyzing the saved questions and answers and extracting common issues.

[1738] (Claim 3)

[1739] 10. The system of claim 1, further comprising means for storing the questions and generated answers in a database.

[1740] "Example 1"

[1741] (Claim 1)

[1742] means for receiving a query from a user;

[1743] means for converting the received questions into a data format and transmitting the data;

[1744] A means to validate the format and content of the received data and, if normal, pass it to the analysis engine.

[1745] A means for analyzing question data using a generative AI model and generating appropriate answers;

[1746] means for returning the generated answer to the user;

[1747] a means for storing the questions and generated answers;

[1748] A means of analyzing saved questions and answers and extracting common issues;

[1749] The system includes a means for transmitting the extracted issues to a public agency.

[1750] (Claim 2)

[1751] 2. The system according to claim 1, further comprising means for periodically analyzing the saved questions and answers and extracting common issues.

[1752] (Claim 3)

[1753] 10. The system of claim 1, further comprising means for storing the questions and generated answers in a database.

[1754] "Application Example 1"

[1755] (Claim 1)

[1756] means for receiving a query from a user;

[1757] means for analyzing the received question by natural language processing and generating an answer;

[1758] means for returning the generated answer to the user;

[1759] a means for storing the questions and generated answers;

[1760] A means of analyzing saved questions and answers and extracting common issues;

[1761] a means for transmitting the extracted issues to a public institution;

[1762] A way to respond to customer questions in physical stores;

[1763] A means of displaying the generated answers on the customer's device

[1764] A system including:

[1765] (Claim 2)

[1766] 2. The system according to claim 1, further comprising means for periodically analyzing the saved questions and answers and extracting common issues.

[1767] (Claim 3)

[1768] 10. The system of claim 1, further comprising means for storing the questions and generated answers in a database.

[1769] "Example 2: Combining Emotion Engines"

[1770] (Claim 1)

[1771] means for receiving questions and emotion data from a user;

[1772] means for analyzing the received question and emotion data using a natural language processing and emotion recognition engine to generate an answer;

[1773] a means for optimizing the generated answer based on the user's emotion data and returning the answer to the user;

[1774] a means for storing questions, generated answers, and sentiment data;

[1775] A means for periodically analyzing the saved questions, answers, and sentiment data to extract common issues;

[1776] The system includes a means for transmitting the extracted issues to a public agency.

[1777] (Claim 2)

[1778] 2. The system according to claim 1, further comprising means for periodically analyzing the stored questions, answers and sentiment data to extract common issues.

[1779] (Claim 3)

[1780] 10. The system of claim 1, further comprising means for storing the questions, answers and emotion data in a database.

[1781] "Application example 2 when combining emotion engines"

[1782] (Claim 1)

[1783] means for receiving a query from a user;

[1784] means for analyzing the received question by natural language processing and generating an answer;

[1785] means for returning the generated answer to the user;

[1786] a means for storing the questions and generated answers;

[1787] A means of analyzing saved questions and answers and extracting common issues;

[1788] a means for transmitting the extracted issues to a public institution;

[1789] emotion recognition means for recognizing the emotion of the user when inputting a question;

[1790] A system including means for optimizing generated answers by taking into account user sentiment.

[1791] (Claim 2)

[1792] 2. The system according to claim 1, further comprising means for periodically analyzing the saved questions and answers and extracting common issues.

[1793] (Claim 3)

[1794] 10. The system of claim 1, further comprising means for storing the questions and generated answers in a database. [Explanation of symbols]

[1795] 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. means for receiving a query from a user; means for analyzing the received question by natural language processing and generating an answer; means for returning the generated answer to the user; a means for storing the questions and generated answers; A means of analyzing saved questions and answers and extracting common issues; and means for transmitting the extracted issues to a public institution.

2. 2. The system according to claim 1, further comprising means for periodically analyzing the saved questions and answers to extract common issues.

3. 10. The system of claim 1, further comprising means for storing the questions and generated answers in a database.

Images