system

Abstract

A system is provided.SOLUTION: The system includes a means for receiving a question from a user, a means for analyzing the question by a natural language processing engine, a means for classifying the question into categories based on the analysis result, a means for retrieving related information from a database or an external API according to the question category, a means for generating an answer to the user based on a retrieval result, a means for transmitting the generated answer to the user, and a means for arranging a related service as necessary.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Many families raising children today have little connection with local governments or relatives, and often lack sufficient support to deal with sudden problems or emergencies. Situations that require a quick and appropriate response frequently arise, such as when a child suddenly develops a fever, when picking up the child from daycare, or when finding a place to look after the child while the parents are at work. To address these issues, a system is needed that can provide accurate information and quickly arrange for the necessary services. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides a system including the following means. First, the system includes a means for receiving a question from a user, and then a means for analyzing the question using a natural language processing engine and understanding the content of the question. The system includes a means for classifying the question into categories (e.g., health, childcare support, education, etc.) based on the analysis results, and for searching for related information from databases or external APIs according to each category. The system includes a means for generating an answer to the user based on the searched information and sending the generated answer to the user. The system also includes a means for arranging related services (e.g., dispatching an ambulance or a service to pick up children from daycare) as needed. This configuration makes it possible to respond quickly and accurately to user questions and provide appropriate services.

[0006] "User" refers to a user who uses the system to enter questions and receive answers and services.

[0007] The term "means for receiving a question" refers to a component having an interface or function for receiving an input question.

[0008] A "natural language processing engine" refers to a collection of algorithms and software that analyzes input text data and understands its meaning and context.

[0009] "Means for analyzing" refers to a component that analyzes text using a natural language processing engine to understand the content of the question.

[0010] "Categorization method" refers to the logic or algorithm used to assign the content of a question to a specific category (e.g., health, childcare support, education, etc.).

[0011] A "database" refers to a system for storing related information in a structured manner.

[0012] "External API" refers to an application programming interface for connecting with external systems and services.

[0013] "Means for searching related information" refers to components that have the functionality to search and retrieve information related to a query from databases and external APIs.

[0014] "Means for generating an answer" refers to the functions and algorithms for creating an answer to be provided to the user based on the acquired information.

[0015] "Means for sending a response" refers to a communication function or protocol for sending the generated response to the user's terminal.

[0016] "Means for arranging related services" refers to functions and processes for arranging necessary services (e.g., arranging an ambulance, picking up children from daycare, etc.) depending on the user's question or situation. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The system of the present invention is a system for quickly and accurately responding to childcare-related problems that users face on a daily basis. This system has the function of receiving and analyzing questions from users, and providing optimal answers and arranging services. Specific embodiments of the system are described below.

[0039] 1. Receiving questions from users

[0040] First, a user uses a terminal (a device such as a smartphone or PC) to input a question to the system. For example, a user might ask, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This question is sent to the server via the terminal.

[0041] 2. Question analysis and classification

[0042] The server receives the user's question and analyzes it using a natural language processing engine. This analysis involves tokenizing the text, extracting subjects, predicates, and objects, and analyzing sentiment. Based on this information, the server classifies the question into an appropriate category. For example, a question like "My child suddenly developed a fever in the middle of the night" would be classified as a health-related category.

[0043] 3. Information Search

[0044] After parsing and classification is complete, the server searches for information from databases or external APIs related to the relevant category. For health-related questions, it searches for information on the nearest emergency clinic or emergency response advice. The search results are quickly retrieved and passed on to subsequent processing steps.

[0045] 4. Answer Generation

[0046] Based on the information obtained, the server generates a specific answer for the user. This answer can be based on a fixed template or a customized message. For example, the server might generate an answer like, "The nearest emergency clinic is at XX Hospital. If your symptoms worsen, please call an ambulance."

[0047] 5. Arrangements for Service

[0048] If necessary, the server arranges for additional services. For example, if a user asks, "I have an emergency and will be late to pick up my child from daycare. Can someone pick me up?", the server searches for relevant childcare services and proceeds with the arrangements.

[0049] 6. Sending the response to the user

[0050] Finally, the server sends the generated response and the status of the service arrangement to the user's device, which receives it and displays it to the user. The user can then check the specific countermeasures and the arranged services on the device.

[0051] For example, if a user asks about childcare services, the terminal displays a list such as "Pick-up services are available. Available services are listed below."

[0052] ---

[0053] The components of this system work together to enable quick and accurate responses to user questions. This invention enables effective responses to everyday childcare problems and emergencies.

[0054] The processing flow will be explained below.

[0055] Step 1: User enters question

[0056] A user uses a terminal to input and send a question, for example, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?"

[0057] Step 2: The device sends a question

[0058] The terminal transmits the input question data to the server.

[0059] Step 3: The server receives the query

[0060] The server receives the query data from the terminal.

[0061] Step 4: The server parses the question

[0062] The server analyzes the received question using a natural language processing engine to extract important keywords (e.g., "child," "fever," "ambulance") and contextual information.

[0063] Step 5: The server categorizes the question

[0064] The server classifies the question into an appropriate category (e.g., "health-related") based on the analysis results.

[0065] Step 6: The server searches for relevant information

[0066] Depending on the question category, the server searches for relevant information from internal databases or external APIs, such as the nearest emergency clinic or emergency response guidelines.

[0067] Step 7: The server aggregates the search results

[0068] The server aggregates the search results it has obtained and organizes them into a series of information to provide to the user.

[0069] Step 8: Server Generates Answer

[0070] The server generates an answer to provide to the user based on the organized information. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0071] Step 9: The server considers arranging for service.

[0072] The server determines the need for additional services (e.g., dispatching an ambulance) based on the user's question.

[0073] Step 10: The server arranges for related services

[0074] If necessary, the server may request an ambulance from a service provider that it works with.

[0075] Step 11: Server sends response

[0076] The server sends the generated response and the arranged service information to the user's terminal.

[0077] Step 12: The device notifies the user of the answer

[0078] The device notifies the user of the received response and service information and displays it on the screen. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0079] Example 1

[0080] 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."

[0081] In childcare, users often face many problems and emergencies on a daily basis. Accessing information and services that allow them to quickly and appropriately respond to these issues is important to users, and effective methods are needed to improve the quality of childcare support. However, current systems have issues with difficulty responding promptly to user questions, and the efficiency of information retrieval and answer generation is low. Furthermore, they often fail to properly assess the specificity and urgency of questions and respond accordingly.

[0082] 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.

[0083] In this invention, the server includes means for receiving questions from users, means for analyzing the questions with a natural language processing engine, means for categorizing the questions based on the analysis results, means for searching for related information from a database or an external API according to the question category, means for generating answers to the users based on the search results, means for sending the generated answers to the users, means for arranging related services as needed, and means for tokenization, extracting subjects, predicates, and objects, and performing sentiment analysis. This enables a system that can respond quickly and accurately to user questions.

[0084] The "means for receiving questions from users" refers to the technical means by which the server receives questions from users sent from terminals.

[0085] "Means for analyzing questions using a natural language processing engine" refers to technical means for performing tokenization, grammar analysis, sentiment analysis, etc. on questions received by the server using natural language processing technology.

[0086] "Means for categorizing questions based on analysis results" refers to technical means for categorizing questions into predefined categories (e.g., health, childcare, education, etc.) based on analysis results obtained through natural language processing.

[0087] "Means for searching for relevant information from databases or external APIs according to question categories" refers to technical means for searching for relevant information from internal databases or external APIs based on the category into which a question is classified.

[0088] "Means for generating answers to users based on search results" refers to technical means for automatically generating specific answers based on information obtained from searches.

[0089] The "means for transmitting the generated answer to the user" refers to the technical means for transmitting the answer generated by the server to the user's terminal and displaying it.

[0090] The "means for arranging related services as needed" refers to a technical means for searching for and arranging additional related services based on the content of the user's inquiry.

[0091] "Tokenization" is a natural language processing process that breaks up the text of a question into words and phrases.

[0092] "Means for extracting subjects, predicates, and objects" refers to technical means for analyzing the grammatical structure of a question and identifying the subject, predicate, and object therefrom.

[0093] "Means for performing sentiment analysis" refers to technical means for assessing the user's sentiment and urgency from the question text.

[0094] The system of the present invention is designed to quickly and accurately respond to childcare-related problems that users face on a daily basis. This system uses various technical means to receive and analyze questions from users and provide optimal answers and service arrangements. Specific embodiments of the system are described below.

[0095] First, a user inputs a question into the system using a device such as a smartphone or PC. The input question is sent to the server via the device. For example, a user might input a question such as, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This question is sent to the server.

[0096] The server then uses a natural language processing engine (e.g., SpaCy, NLTK) to parse the received question. This involves tokenizing the text, extracting subjects, predicates, and objects, and performing sentiment analysis. This process helps understand the content and urgency of the question and categorize it into the appropriate category (e.g., health, parenting, education, etc.).

[0097] For each classified question, the server searches for relevant information from databases or external APIs (e.g., Google® Maps API, medical data API). For example, if the user's question is about health, it searches for information on the nearest emergency clinics and emergency response guidelines. Based on the information obtained, the server generates a specific answer. This answer may be based on a fixed template or a customized message format.

[0098] The generated answer is sent from the server to the user's device, where the user receives it and checks it. For example, it displays specific countermeasures such as, "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0099] If necessary, the server can also arrange for related services. For example, if a user asks, "I have an emergency and will be late to pick up my child from daycare. Can someone pick me up for me?", the server will search for related childcare services and proceed with the arrangements.

[0100] The system's components work together to provide users with fast and accurate responses, allowing them to effectively respond to everyday parenting issues and emergencies.

[0101] For example, if a user asks "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?", the server analyzes the question and classifies it into a health category. The server then searches for information on night-time emergency clinics and generates a response such as "The nearest night-time emergency clinic is XX Hospital. If the symptoms worsen, please call an ambulance." and sends it to the user's device.

[0102] Example prompt sentence:

[0103] What is the appropriate response when a user asks, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" Please generate an answer that includes information about night clinics and emergency procedures.

[0104] This system allows users to deal with childcare-related issues quickly and accurately, thereby improving the quality of childcare support.

[0105] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0106] Step 1: User enters question

[0107] The user uses a device (smartphone or PC) to input a question into the system. For example, they might input a question like, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" The device then sends the user's input data to the server.

[0108] Input: Question text from user

[0109] Output: Sending the query data to the server

[0110] Specific operation: The user enters a question into the terminal application or web interface and presses the send button.

[0111] Step 2: The server receives and analyzes the query

[0112] The server receives the question sent from the device and analyzes it using a natural language processing engine (e.g., SpaCy, NLTK). The analysis involves tokenizing the text, extracting subjects, predicates, and objects, and analyzing sentiment.

[0113] Input: Question data sent from the terminal

[0114] Output: Analysis data (tokenization, subject, predicate, object, sentiment analysis results)

[0115] Specific operation: The server receives the question data and passes it to the natural language processing engine for analysis.

[0116] Step 3: Server classifies the question

[0117] Based on the analysis results, the server classifies the question into an appropriate category (e.g., health, childcare, education, etc.) and prepares to search for appropriate information according to the category.

[0118] Input: Analysis data

[0119] Output: Question category

[0120] Specific operation: The server classifies questions into categories such as "health" or "childcare" based on the results of subject, predicate, object, and sentiment analysis.

[0121] Step 4: Server Looks Up Information

[0122] Based on the question category, the server searches for relevant information from internal databases or external APIs (e.g., Google Maps API, medical data API). For example, for the health category, the server searches for information on the nearest emergency clinics.

[0123] Input: Question Category

[0124] Output: Related information (e.g., a list of emergency clinics open overnight)

[0125] Specific operation: The server sends a query to a database or external API to obtain the necessary information.

[0126] Step 5: Server Generates Answer

[0127] The server uses the information obtained from the search to generate specific answers for the user, which can be in the form of fixed templates or customized messages.

[0128] Input: Related Information

[0129] Output: Specific answer

[0130] Specific operation: The server uses the template to generate a response such as, "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0131] Step 6: Arranging for service by the server

[0132] If necessary, the server arranges for additional services, for example, if the user wants to use childcare services, it searches for and arranges for relevant service providers.

[0133] Input: Add user request

[0134] Output: Arranged service information

[0135] Specific operation: The server searches for information on relevant service providers and makes reservations and arrangements for services on behalf of the user.

[0136] Step 7: Server sends response to user

[0137] The server sends the generated response and the status of the arranged service to the user's terminal, where the user receives and checks it.

[0138] Input: Generated answers, arranged service information

[0139] Output: Notification to user terminal

[0140] Specific operation: The server sends the answer to the user's device, which displays it. For example, it displays a list such as "Pick-up service is available. Available services are listed below."

[0141] This system allows users to respond quickly and accurately to child-rearing-related issues, enabling them to receive smooth child-rearing support.

[0142] (Application example 1)

[0143] 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."

[0144] When users encounter childcare-related issues, there is still no system in place to quickly and accurately respond to those issues. In particular, there is a lack of systems to assist users in selecting childcare products and arranging appropriate services in physical stores. As a result, users have to spend a lot of time and effort searching for information and finding the best products and services themselves.

[0145] 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.

[0146] In this invention, the server includes means for receiving questions from users, means for analyzing the questions with a natural language processing engine, means for categorizing the questions based on the analysis results, means for searching for related information from a database or external API according to the question category, means for generating an answer to the user based on the search results, means for sending the generated answer to the user, means for arranging related services as needed, and means for searching for products and services based on the user's question and providing information on corresponding products in physical stores. This enables even busy parents to respond quickly and accurately to child-rearing-related issues.

[0147] The "means for receiving questions from users" is a function for sending questions input by users via their terminals to the server.

[0148] "Means for analyzing questions using a natural language processing engine" refers to a function that analyzes input questions using natural language processing technology and converts them into structured information.

[0149] The "means for classifying questions into categories based on the analysis results" is a function for classifying the analyzed question content into predetermined categories and associating them with specific domains.

[0150] "Means of searching for relevant information from databases or external APIs according to question categories" refers to a function that retrieves relevant information from an internal database or external API service based on classified categories.

[0151] The "means for generating a response to the user based on the search results" is a function for generating a specific response to be provided to the user based on the acquired information.

[0152] The "means for transmitting the generated answer to the user" is a function for transferring the generated answer to the user's terminal and displaying it.

[0153] The "means for arranging related services as needed" is a function for arranging additional services (for example, childcare support or emergency response) based on the user's request and managing the status of the arrangement.

[0154] "A means for searching for products and services based on a user's question and providing relevant product information in physical stores" is a function that searches for related products and services in physical stores based on the question entered by the user and provides the user with relevant information.

[0155] The present invention is a system for quickly and accurately dealing with childcare-related problems. Detailed embodiments of the present invention will be described below.

[0156] 1. System Configuration

[0157] This system consists of user terminals, a server, a database, and an external API. User terminals include mobile devices such as smartphones and tablets. The server plays a central role in performing advanced data processing and calculations.

[0158] 2. Hardware and Software

[0159] Hardware: Smartphones (iOS / ANDROID devices), tablets, servers

[0160] software:

[0161] Natural language processing libraries (Google Cloud Natural Language API, spaCy, NLTK, etc.)

[0162] Product information database (Firebase, MySQL (registered trademark), etc.)

[0163] Push notification service (Firebase Cloud Messaging)

[0164] User Interface (React Native)

[0165] 3. System Implementation

[0166] 1. Receiving questions from users

[0167] A user uses a smartphone or tablet to voice or text a question into the application.

[0168] 2. Question Analysis

[0169] The server analyzes the input question using a natural language processing engine (e.g., Google Cloud Natural Language API), performing tokenization, part-of-speech tagging, and sentiment analysis.

[0170] 3. Question Classification

[0171] Based on the analysis, the server categorizes the questions into specific categories, such as health-related, childcare support-related, education-related, etc.

[0172] 4. Information Search

[0173] The server searches for related information from databases or external APIs according to the category. For example, if the question is about childcare products, it searches for the relevant product from a product information database.

[0174] 5. Answer Generation

[0175] Based on the search results, the server generates specific answers for the user, including standard phrases and customized messages.

[0176] 6. Submit your response

[0177] The generated answer is sent from the server to the user's terminal and displayed on the user's terminal.

[0178] 7. Arrangement of related services

[0179] If necessary, the server arranges for additional services (e.g., childcare or emergency response), and this information is sent to the user's device.

[0180] 4. Specific Examples

[0181] When a user asks the app, "What is the appropriate size of diaper?", the system analyzes the question and provides the most appropriate product information (e.g., for newborns, medium-sized diapers, etc.) along with the location of the item in the store. It also provides advice on how to choose the right size based on the baby's weight and age.

[0182] 5. Examples of prompts

[0183] What is the correct size of diaper?

[0184] As described above, the system of the present invention quickly and accurately analyzes user questions about child-rearing and provides optimal information and service arrangements, thereby reducing the burden on users even in physical stores and realizing efficient child-rearing support.

[0185] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0186] Step 1:

[0187] The user inputs a question into the terminal.

[0188] Input: The user uses a smartphone or tablet to enter a question using text or voice.

[0189] What happens: The application receives user input and sends that data to the server for analysis.

[0190] Step 2:

[0191] The server analyzes the entered question.

[0192] Input: User question text data sent from the terminal.

[0193] What it does: The server uses a natural language processing engine (e.g., Google Cloud Natural Language API) to tokenize the question and perform part-of-speech tagging, subject-predicate-object recognition, and sentiment analysis.

[0194] Output: Parsed structured data of the question.

[0195] Step 3:

[0196] The server categorizes the questions based on the analysis results.

[0197] Input: Parsed question structured data.

[0198] What it does: The server uses the analysis results to apply an algorithm that categorizes the question into the appropriate category (e.g., childcare support, health-related, education, etc.).

[0199] Output: Categorized question data.

[0200] Step 4:

[0201] The server searches for information according to the question category.

[0202] Input: Categorized question data.

[0203] What it does: The server uses internal databases (e.g., Firebase, MySQL) and external APIs (e.g., Google Places API) to find the information most relevant to the question.

[0204] Output: Search result data.

[0205] Step 5:

[0206] The server generates an answer for the user based on the search results.

[0207] Input: Search result data.

[0208] Specific Action: The server generates a specific response using a template-based approach or an algorithm that generates customized messages.

[0209] Output: The generated response data.

[0210] Step 6:

[0211] The server generates a response and sends it to the user.

[0212] Input: The generated response data.

[0213] Specific operation: The server sends the generated answer to the user's device and notifies them via push notification or in-app message.

[0214] Output: The answer displayed on the user's terminal.

[0215] Step 7:

[0216] The server arranges for related services as needed.

[0217] Input: User request or additional information.

[0218] Specific operation: The server arranges related services and manages the arrangement status. Service arrangement includes API calls and staff notifications.

[0219] Output: Notification of order status and feedback of service execution status.

[0220] Through the above steps, the system can quickly and accurately provide childcare-related information and arrange services based on questions entered by the user.

[0221] 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.

[0222] The system of the present invention is a system for quickly and accurately responding to childcare-related problems that users face on a daily basis, and is characterized by incorporating an emotion engine that recognizes the user's emotions. This system has the function of receiving and analyzing questions from users, recognizing their emotions, and providing optimal answers and arranging services. Specific embodiments of the system are described below.

[0223] 1. Receiving questions from users

[0224] First, a user uses a terminal (a device such as a smartphone or PC) to input a question to the system. For example, a user might ask, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This question is sent to the server via the terminal.

[0225] 2. Question Analysis and Emotion Recognition

[0226] The server receives the user's question and analyzes it using a natural language processing engine. This analysis involves tokenizing the text, extracting subjects, predicates, and objects, and then using an emotion engine to recognize emotions contained in the question (e.g., urgency, impatience, worry, etc.) and adjust the analysis results accordingly.

[0227] 3. Question classification and information search

[0228] Based on the emotion recognition and analysis results, the server classifies the question into an appropriate category (e.g., health-related). The server then searches for information from databases or external APIs related to that category. If the question is health-related, it searches for information on the nearest emergency clinic or emergency response advice. The search results are quickly retrieved and passed on to subsequent processing steps.

[0229] 4. Answer generation and emotion-based adjustment

[0230] Based on the acquired information, the server generates a specific response for the user. This response can be based on a fixed template or a customized message. For example, the response might be, "The nearest emergency clinic is XX Hospital. If your symptoms worsen, please call an ambulance." The tone and content of the response are also adjusted appropriately based on the results of the emotion engine.

[0231] 5. Arranging for service and determining the level of urgency

[0232] If necessary, the server arranges for additional services. If the emotion engine recognizes a high level of urgency, related services (for example, arranging for an ambulance) are given priority. If a user asks, "I'm going to be late to pick up my child from daycare due to an emergency. Can someone pick me up for me?", the server searches for related childcare services and proceeds with the arrangements.

[0233] 6. Sending the response to the user

[0234] Finally, the server sends the generated response and the status of the service arrangement to the user's device, which receives it and displays it to the user. The user can then check the specific countermeasures and the arranged services on the device.

[0235] For example, if a user becomes anxious and asks about childcare services, the device will display a list such as, "Pick-up services are available. Available services are listed below," and notify the user in a reassuring tone.

[0236] ---

[0237] Each component of this system also includes an emotion engine, which enables it to respond quickly and accurately to user questions and provide appropriate services that take emotions into consideration. This invention enables effective responses to everyday childcare troubles and emergencies while recognizing the user's emotions.

[0238] The processing flow will be explained below.

[0239] Step 1: User enters question

[0240] A user uses a terminal to input and send a question, for example, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?"

[0241] Step 2: The device sends a question

[0242] The terminal transmits the input question data to the server.

[0243] Step 3: The server receives the query

[0244] The server receives the query data from the terminal.

[0245] Step 4: The server parses the question

[0246] The server analyzes the received question using a natural language processing engine to extract important keywords (e.g., "child," "fever," "ambulance") and contextual information.

[0247] Step 5: The server recognizes the user's emotion

[0248] The server uses an emotion engine to recognize the emotion (e.g., "worry" or "urgency") contained in the question.

[0249] Step 6: The server categorizes the question

[0250] The server classifies the question into an appropriate category (e.g., "health-related") based on the analysis and emotion recognition results.

[0251] Step 7: The server searches for relevant information

[0252] Depending on the question category, the server searches for relevant information from internal databases or external APIs, for example, the nearest emergency clinic or emergency response guidelines.

[0253] Step 8: The server aggregates the search results

[0254] The server aggregates the search results it has obtained and organizes them into a series of information to provide to the user.

[0255] Step 9: Server Generates Answer

[0256] The server generates an answer to provide to the user based on the organized information. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0257] Step 10: The server adjusts the answer based on the sentiment

[0258] The server then adjusts the tone and content of the generated response appropriately based on the emotion recognition results. For example, if the emotion is strong, it may include additional advice such as, "Don't worry, here's how to deal with it first."

[0259] Step 11: The server considers arranging for service

[0260] The server determines the need for additional services (e.g., dispatching an ambulance) based on the user's question and the emotion recognition results.

[0261] Step 12: The server arranges for related services

[0262] If necessary, the server may request an ambulance from a service provider that it works with.

[0263] Step 13: The server sends the response and the dispatch result.

[0264] The server sends the generated response and the arranged service information to the user's terminal.

[0265] Step 14: The device notifies the user of the answer

[0266] The device notifies the user of the received response and service information and displays it on the screen. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0267] Example 2

[0268] 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."

[0269] In today's childcare environment, parents face a variety of problems. Many of these problems are highly urgent and involve emotional stress. However, conventional systems have had difficulty accurately capturing users' emotions and responding quickly and appropriately. In particular, there is a demand for systems that can recognize emotions and respond to childcare-related worries and emergencies. Therefore, the challenge is to provide a childcare support system that can take users' emotions into consideration and provide optimal services.

[0270] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0271] In this invention, the server includes means for receiving questions from users, means for analyzing the questions with a natural language processing engine, means for categorizing the questions based on the analysis results, means for searching for related information from a database or an external API according to the question category, means for generating answers to the users based on the search results, means for sending the generated answers to the users, means for arranging related services as needed, means for recognizing emotions contained in the questions using an emotion engine, and means for adjusting the tone and content of the answers based on the recognized emotions. This makes it possible to respond to child-rearing issues quickly and accurately while taking the user's emotions into consideration.

[0272] "User" refers to an individual who uses this system to enter questions and receive answers and services.

[0273] "Terminal" refers to the device (smartphone, PC, etc.) that a user uses to enter a question.

[0274] "Server" refers to a computer system that receives questions from users and performs processes such as analysis, classification, answer generation, and service arrangement.

[0275] A "natural language processing engine" refers to software that analyzes questions entered by users and performs tasks such as understanding grammatical structures and tokenizing them.

[0276] An "emotion engine" refers to software that recognizes and analyzes the emotions contained in users' questions.

[0277] "Category" refers to various classifications based on the content of the user's question (e.g., health, education, childcare, etc.).

[0278] A "database" refers to a collection of related information that is stored, managed, and provided in a searchable format.

[0279] An "external API" refers to a program interface for obtaining information in collaboration with other systems or services.

[0280] "Answer" refers to specific information or advice that the system generates in response to a user's question.

[0281] "Service arrangement" refers to the procedure for providing additional support or services based on the user's question and emotion recognition results.

[0282] "Tokenization" refers to the process in natural language processing of dividing input text into semantic units.

[0283] "Grammatical structure" refers to structural analysis that analyzes the relationships between subjects, predicates, objects, etc. in a sentence.

[0284] "Emotion" refers to the psychological state (e.g., urgency, impatience, worry, etc.) contained within the user's text.

[0285] "Tone" refers to the nuances and style of language used in responses.

[0286] "Relevant information" refers to data and knowledge necessary to generate an answer to a user's question.

[0287] "Childcare agency services" refer to external services that provide support such as temporary childcare and transportation.

[0288] The above are definitions of important terms included in the claims.

[0289] The present invention provides a system that quickly and accurately responds to childcare-related problems that users face on a daily basis. This system is characterized by incorporating an emotion engine that recognizes the user's emotions. Specific embodiments are described below.

[0290] A user inputs a question into the system using a terminal (a device such as a smartphone or PC). For example, a user might ask, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This input is sent to the server via the terminal.

[0291] The server receives a question from a user and analyzes it using a natural language processing engine (e.g., spaCy, NLTK). This analysis involves tokenizing the text, extracting subjects, predicates, and objects, and then using an emotion engine (e.g., IBM Watson® Tone Analyzer) to recognize emotions in the question, such as urgency, impatience, or worry, and adjusts the analysis results accordingly.

[0292] Based on the analysis and emotion recognition results, the server classifies the question into an appropriate category (e.g., health-related). The server then searches for information from databases or external APIs (e.g., Google Maps API) related to that category. If the question is health-related, the server searches for information about the nearest emergency clinic or emergency response advice. The search results are quickly retrieved and passed on to subsequent processing steps.

[0293] Based on the acquired information, the server generates a specific response for the user. This response can be based on a fixed template or a customized message. For example, the response might be, "The nearest emergency clinic is XX Hospital. If your symptoms worsen, please call an ambulance." The tone and content of the response are also adjusted appropriately based on the results of the emotion engine.

[0294] If necessary, the server arranges for additional services. If the emotion engine recognizes a high level of urgency, related services (for example, arranging for an ambulance) are given priority. If a user asks, "I'm going to be late to pick up my child from daycare due to an emergency. Can someone pick me up for me?", the server searches for related childcare services and proceeds with the arrangements.

[0295] Finally, the server sends the generated answer and the status of the service arrangement to the user's device. The device receives this and displays it to the user. The user can check the specific countermeasures and the services that have been arranged on the device. For example, if a user is feeling anxious and asks about childcare services, the device will display a list such as "Pick-up service is available. The available services are as follows," and notify the user in a reassuring tone.

[0296] The following are examples of prompt sentences:

[0297] "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?"

[0298] "I have a question about a child care issue that needs immediate attention. What steps should I take?"

[0299] The above is a specific embodiment of the present invention, and the system is capable of dealing with childcare-related issues quickly and accurately while taking into account the user's feelings.

[0300] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0301] Step 1:

[0302] A user uses a terminal to input a question into the system. The input is text data in natural language. For example, a question might be input like, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" The input question is sent to the server via the terminal. Specific actions on the terminal include entering text into a question input form and clicking the send button. Input: User's question text. Output: Sending question data to the server.

[0303] Step 2:

[0304] The server receives questions sent by users. The received question text is passed to a natural language processing engine for analysis. Specific analysis operations include tokenizing the text (breaking it down into words and phrases) and understanding the context (extracting the subject, predicate, and object). For example, information such as "child," "late night," "sudden fever," and "should an ambulance be called" is broken down and the meaning of each part is identified. Input: Received question text. Output: Tokenized text and context information.

[0305] Step 3:

[0306] The server uses an emotion engine to recognize the emotion contained in the question based on the analysis results obtained from the natural language processing engine. The emotion engine extracts emotional elements such as urgency, impatience, and worry, and adjusts the analysis results accordingly. Specifically, it uses an emotion analysis algorithm to evaluate text data and detect high levels of urgency or anxiety. Input: Tokenized text and contextual information. Output: Emotion recognition results.

[0307] Step 4:

[0308] The server classifies the question into an appropriate category based on the analysis and emotion recognition results. For example, the question is classified into the "health-related" category. The specific operation includes a process of matching the question with a predefined category list and selecting the category that best suits the question. Input: Analysis results and emotion recognition results. Output: Question category.

[0309] Step 5:

[0310] The server searches for information from relevant databases or external APIs depending on the question category. For example, if the question is health-related, it searches for information on the nearest emergency clinic after hours or advice on how to respond to an emergency. The specific operation involves sending a query to a database and retrieving the relevant information. Input: Question category. Output: Search results.

[0311] Step 6:

[0312] The server generates a specific answer based on the information obtained. This answer is based on a fixed template, but includes a customized message if necessary. The tone and content of the answer are adjusted appropriately based on the results of the emotion engine. For example, it generates a specific answer such as, "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance." Input: Search results and emotion recognition results. Output: Generated answer.

[0313] Step 7:

[0314] If necessary, the server will arrange for additional services. If the emotion engine recognizes a high level of urgency, it will prioritize related services (for example, arranging for an ambulance). For example, if a user asks, "I have an emergency and will be late to pick up my child from daycare. Can someone pick me up for me?", it will search for related childcare services and proceed with the arrangements. Input: Question and high-urgency emotion recognition result. Output: Arranged service.

[0315] Step 8:

[0316] Finally, the server sends the generated answer and the arrangement status to the user's terminal. The terminal receives this and displays it to the user. The user can check the specific countermeasures and the arranged services on the terminal. For example, in response to a user's question, a list such as "Pick-up service is available. Available services are as follows" can be displayed, providing a sense of security. Input: Generated answer and arrangement status. Output: Display of answer and arrangement status on the terminal.

[0317] (Application example 2)

[0318] 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."

[0319] Childcare issues are diverse, and it is necessary to respond promptly to users' anxieties and urgencies. Furthermore, it is necessary to provide appropriate services and information while taking into consideration the user's emotions. However, conventional systems are limited to simply providing information in response to users' questions, and it is difficult to provide comprehensive support that addresses the user's emotions or arranges specific services. This leads to delays in resolving childcare emergencies and everyday problems.

[0320] 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 recognizing the user's emotions and adjusting the analysis results, means for adjusting the tone and information of the proposal content based on the emotions, and means for extracting keywords, recognizing subjects, predicates, and objects, and analyzing emotions in question analysis and categorization. This makes it possible to provide appropriate answers and arrange services that are in line with the user's emotions.

[0321] The "means for receiving questions from the user" is a mechanism by which the system receives information and questions entered by the user.

[0322] "Means for analyzing questions using a natural language processing engine" refers to natural language processing technology used to handle text data received from users and understand their contents.

[0323] "Means for categorizing questions based on the analysis results" is a function that organizes the content of the analyzed questions into specific areas or categories.

[0324] "Means for searching related information from databases or external APIs according to question categories" refers to a method for collecting related information from internal and external data sources based on classified question categories.

[0325] "Means for generating an answer to the user based on the search results" refers to the process of creating an appropriate answer to the user based on the acquired information.

[0326] The "means for transmitting the generated answer to the user" refers to a means for transmitting the answer generated by the system to the user's terminal.

[0327] The "means for arranging related services as needed" is a function for executing additional services or arrangements according to the user's inquiries or circumstances.

[0328] "Means for recognizing the user's emotions and adjusting the analysis results" refers to a technology that analyzes the emotions contained in the user's question and adjusts the information provided or answer according to those emotions.

[0329] "Means for adjusting the tone and information of the proposed content based on the user's emotions" refers to a mechanism that appropriately changes the way the proposed content is expressed and the information provided to match the user's emotions.

[0330] "Keyword extraction" is a technique for extracting important words and phrases from a user's question.

[0331] "Subject-predicate-object recognition" is a technique for identifying and analyzing the components of a sentence: subject, predicate, and object.

[0332] "Sentiment analysis" is a technique for analyzing the type and intensity of emotions from text data.

[0333] A specific category such as "childcare support, education, health-related" is a classification that organizes the content of a user's question into a specific area, and includes areas related to childcare support, education, and health.

[0334] A system for carrying out the present invention accepts childcare consultations via a user's smartphone app and proposes appropriate childcare-related services and products. Detailed embodiments of this system are described below.

[0335] System Program

[0336] This system consists of a server and a user device (smartphone). When a user sends a question through a smartphone app, the data is sent to the server. The server analyzes the question and recognizes the user's emotions.

[0337] Hardware and software used

[0338] Server: The central computing unit that handles the backend of this system, primarily for data processing and analysis.

[0339] Smartphone: A device used by a user to enter questions and receive answers from the system.

[0340] Flask: A Python-based micro-web framework used to build server-side APIs.

[0341] Transformers: A natural language processing library provided by Hugging Face for sentiment analysis and question answering.

[0342] Data processing and calculation

[0343] 1. Receiving a question: The user enters a question into the smartphone app and sends it to the server.

[0344] 2. Natural Language Processing: The server uses the Transformers library to analyze the question, tokenize it, and extract the subject, predicate, and object.

[0345] 3. Emotion recognition: Extract the user's emotions from the analyzed questions and recognize the type of emotion (e.g., anxiety, impatience, etc.).

[0346] 4. Categorization and information retrieval: Based on the analysis results, the question is categorized appropriately and relevant information is retrieved from databases or external APIs. For example, if the question is about childcare support, information on appropriate childcare products and services is retrieved.

[0347] 5. Generate and send an answer: Based on the search results and emotion recognition results, an appropriate answer is generated and sent to the smartphone app.

[0348] Specific examples

[0349] Consider the case where a user asks the following question:

[0350] "My baby cries a lot at night. Are there any good products?"

[0351] The server receives this question, analyzes the question content and sentiment, and generates and sends the following answer as a result of the analysis:

[0352] "We will suggest products that will help you get your baby to sleep. You seem to be worried, but baby carriers and stuffed toys that help you get your baby to sleep are effective. You can check them out in store."

[0353] This system allows users to receive specific suggestions that are in line with their emotions, enabling them to quickly resolve their child-rearing concerns.

[0354] Prompt statement

[0355] Below are some example prompts to input to the generative AI model:

[0356] "I'm having trouble getting my baby to sleep. What products do I need?"

[0357] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0358] Step 1:

[0359] A user enters a question using a smartphone app. The entered question data is sent from the smartphone to a server. The input is the text that the user enters into the app, and the output is the text data sent to the server. The specific action performed at this stage is for the user to enter a question in the text box and tap the "Send" button.

[0360] Step 2:

[0361] The server passes the received question data to a natural language processing engine (Transformers library) and analyzes the question. Specifically, the process tokenizes the text and extracts the subject, predicate, and object. The input is the text data received from the user, and the output is the analyzed text structure.

[0362] Step 3:

[0363] The server passes the analysis results to an emotion recognition engine to recognize the user's emotions. The input is the analyzed text structure, and the output is the recognized emotion information (e.g., anxiety, impatience, etc.). The specific operation is that the emotion recognition engine analyzes the text data and generates an emotion score.

[0364] Step 4:

[0365] The server classifies questions into appropriate categories based on the analysis and emotion recognition results. The input is the analyzed text structure and emotion information, and the output is a category label (e.g., parenting support, health-related, etc.). Specifically, the classification algorithm determines the category based on the text data and emotion score.

[0366] Step 5:

[0367] The server searches for relevant information from a database or external API according to the question category. The input is a category label, and the output is related information data (e.g., product list, service information, etc.). The specific operation is to execute a database query or API call to obtain information.

[0368] Step 6:

[0369] The server generates a response for the user based on the search results and emotion recognition results. The input is related information data and emotion scores, and the output is a customized response text. The specific operation is that a template or customized message generation engine creates a response based on the information.

[0370] Step 7:

[0371] The server sends the generated answer to the user's smartphone app. The input is the generated answer text, and the output is the answer message displayed on the smartphone. The specific operation is data transmission from the server to the smartphone app. The user can check the sent answer on the app and take action based on the suggested product or service information.

[0372] 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.

[0373] 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.

[0374] 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.

[0375] [Second embodiment]

[0376] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0377] 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.

[0378] 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).

[0379] 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.

[0380] 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.

[0381] 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).

[0382] 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. 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.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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."

[0388] The system of the present invention is a system for quickly and accurately responding to childcare-related problems that users face on a daily basis. This system has the function of receiving and analyzing questions from users, and providing optimal answers and arranging services. Specific embodiments of the system are described below.

[0389] 1. Receiving questions from users

[0390] First, a user uses a terminal (a device such as a smartphone or PC) to input a question to the system. For example, a user might ask, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This question is sent to the server via the terminal.

[0391] 2. Question analysis and classification

[0392] The server receives the user's question and analyzes it using a natural language processing engine. This analysis involves tokenizing the text, extracting subjects, predicates, and objects, and analyzing sentiment. Based on this information, the server classifies the question into an appropriate category. For example, a question like "My child suddenly developed a fever in the middle of the night" would be classified as a health-related category.

[0393] 3. Information Search

[0394] After parsing and classification is complete, the server searches for information from databases or external APIs related to the relevant category. For health-related questions, it searches for information on the nearest emergency clinic or emergency response advice. The search results are quickly retrieved and passed on to subsequent processing steps.

[0395] 4. Answer Generation

[0396] Based on the information obtained, the server generates a specific answer for the user. This answer can be based on a fixed template or a customized message. For example, the server might generate an answer like, "The nearest emergency clinic is at XX Hospital. If your symptoms worsen, please call an ambulance."

[0397] 5. Arrangements for Service

[0398] If necessary, the server arranges for additional services. For example, if a user asks, "I have an emergency and will be late to pick up my child from daycare. Can someone pick me up?", the server searches for relevant childcare services and proceeds with the arrangements.

[0399] 6. Sending the response to the user

[0400] Finally, the server sends the generated response and the status of the service arrangement to the user's device, which receives it and displays it to the user. The user can then check the specific countermeasures and the arranged services on the device.

[0401] For example, if a user asks about childcare services, the terminal displays a list such as "Pick-up services are available. Available services are listed below."

[0402] ---

[0403] The components of this system work together to enable quick and accurate responses to user questions. This invention enables effective responses to everyday childcare problems and emergencies.

[0404] The processing flow will be explained below.

[0405] Step 1: User enters question

[0406] A user uses a terminal to input and send a question, for example, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?"

[0407] Step 2: The device sends a question

[0408] The terminal transmits the input question data to the server.

[0409] Step 3: The server receives the query

[0410] The server receives the query data from the terminal.

[0411] Step 4: The server parses the question

[0412] The server analyzes the received question using a natural language processing engine to extract important keywords (e.g., "child," "fever," "ambulance") and contextual information.

[0413] Step 5: The server categorizes the question

[0414] The server classifies the question into an appropriate category (e.g., "health-related") based on the analysis results.

[0415] Step 6: The server searches for relevant information

[0416] Depending on the question category, the server searches for relevant information from internal databases or external APIs, such as the nearest emergency clinic or emergency response guidelines.

[0417] Step 7: The server aggregates the search results

[0418] The server aggregates the search results it has obtained and organizes them into a series of information to provide to the user.

[0419] Step 8: Server Generates Answer

[0420] The server generates an answer to provide to the user based on the organized information. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0421] Step 9: The server considers arranging for service.

[0422] The server determines the need for additional services (e.g., dispatching an ambulance) based on the user's question.

[0423] Step 10: The server arranges for related services

[0424] If necessary, the server may request an ambulance from a service provider that it works with.

[0425] Step 11: Server sends response

[0426] The server sends the generated response and the arranged service information to the user's terminal.

[0427] Step 12: The device notifies the user of the answer

[0428] The device notifies the user of the received response and service information and displays it on the screen. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0429] Example 1

[0430] 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."

[0431] In childcare, users often face many problems and emergencies on a daily basis. Accessing information and services that allow them to quickly and appropriately respond to these issues is important to users, and effective methods are needed to improve the quality of childcare support. However, current systems have issues with difficulty responding promptly to user questions, and the efficiency of information retrieval and answer generation is low. Furthermore, they often fail to properly assess the specificity and urgency of questions and respond accordingly.

[0432] 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.

[0433] In this invention, the server includes means for receiving questions from users, means for analyzing the questions with a natural language processing engine, means for categorizing the questions based on the analysis results, means for searching for related information from a database or an external API according to the question category, means for generating answers to the users based on the search results, means for sending the generated answers to the users, means for arranging related services as needed, and means for tokenization, extracting subjects, predicates, and objects, and performing sentiment analysis. This enables a system that can respond quickly and accurately to user questions.

[0434] The "means for receiving questions from users" refers to the technical means by which the server receives questions from users sent from terminals.

[0435] "Means for analyzing questions using a natural language processing engine" refers to technical means for performing tokenization, grammar analysis, sentiment analysis, etc. on questions received by the server using natural language processing technology.

[0436] "Means for categorizing questions based on analysis results" refers to technical means for categorizing questions into predefined categories (e.g., health, childcare, education, etc.) based on analysis results obtained through natural language processing.

[0437] "Means for searching for relevant information from databases or external APIs according to question categories" refers to technical means for searching for relevant information from internal databases or external APIs based on the category into which a question is classified.

[0438] "Means for generating answers to users based on search results" refers to technical means for automatically generating specific answers based on information obtained from searches.

[0439] The "means for transmitting the generated answer to the user" refers to the technical means for transmitting the answer generated by the server to the user's terminal and displaying it.

[0440] The "means for arranging related services as needed" refers to a technical means for searching for and arranging additional related services based on the content of the user's inquiry.

[0441] "Tokenization" is a natural language processing process that breaks up the text of a question into words and phrases.

[0442] "Means for extracting subjects, predicates, and objects" refers to technical means for analyzing the grammatical structure of a question and identifying the subject, predicate, and object therefrom.

[0443] "Means for performing sentiment analysis" refers to technical means for assessing the user's sentiment and urgency from the question text.

[0444] The system of the present invention is designed to quickly and accurately respond to childcare-related problems that users face on a daily basis. This system uses various technical means to receive and analyze questions from users and provide optimal answers and service arrangements. Specific embodiments of the system are described below.

[0445] First, a user inputs a question into the system using a device such as a smartphone or PC. The input question is sent to the server via the device. For example, a user might input a question such as, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This question is sent to the server.

[0446] The server then uses a natural language processing engine (e.g., SpaCy, NLTK) to parse the received question. This involves tokenizing the text, extracting subjects, predicates, and objects, and performing sentiment analysis. This process helps understand the content and urgency of the question and categorize it into the appropriate category (e.g., health, parenting, education, etc.).

[0447] For each classified question, the server searches for relevant information from databases or external APIs (e.g., Google Maps API, medical data API). For example, if the user's question is about health, it will search for information on the nearest emergency clinics and emergency response guidelines. Based on the information obtained, the server generates a specific answer. This answer can be based on a fixed template or a customized message format.

[0448] The generated answer is sent from the server to the user's device, where the user receives it and checks it. For example, it displays specific countermeasures such as, "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0449] If necessary, the server can also arrange for related services. For example, if a user asks, "I have an emergency and will be late to pick up my child from daycare. Can someone pick me up for me?", the server will search for related childcare services and proceed with the arrangements.

[0450] The system's components work together to provide users with fast and accurate responses, allowing them to effectively respond to everyday parenting issues and emergencies.

[0451] For example, if a user asks "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?", the server analyzes the question and classifies it into a health category. The server then searches for information on night-time emergency clinics and generates a response such as "The nearest night-time emergency clinic is XX Hospital. If the symptoms worsen, please call an ambulance." and sends it to the user's device.

[0452] Example prompt sentence:

[0453] What is the appropriate response when a user asks, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" Please generate an answer that includes information about night clinics and emergency procedures.

[0454] This system allows users to deal with childcare-related issues quickly and accurately, thereby improving the quality of childcare support.

[0455] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0456] Step 1: User enters question

[0457] The user uses a device (smartphone or PC) to input a question into the system. For example, they might input a question like, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" The device then sends the user's input data to the server.

[0458] Input: Question text from user

[0459] Output: Sending the query data to the server

[0460] Specific operation: The user enters a question into the terminal application or web interface and presses the send button.

[0461] Step 2: The server receives and analyzes the query

[0462] The server receives the question sent from the device and analyzes it using a natural language processing engine (e.g., SpaCy, NLTK). The analysis involves tokenizing the text, extracting subjects, predicates, and objects, and analyzing sentiment.

[0463] Input: Question data sent from the terminal

[0464] Output: Analysis data (tokenization, subject, predicate, object, sentiment analysis results)

[0465] Specific operation: The server receives the question data and passes it to the natural language processing engine for analysis.

[0466] Step 3: Server classifies the question

[0467] Based on the analysis results, the server classifies the question into an appropriate category (e.g., health, childcare, education, etc.) and prepares to search for appropriate information according to the category.

[0468] Input: Analysis data

[0469] Output: Question category

[0470] Specific operation: The server classifies questions into categories such as "health" or "childcare" based on the results of subject, predicate, object, and sentiment analysis.

[0471] Step 4: Server Looks Up Information

[0472] Based on the question category, the server searches for relevant information from internal databases or external APIs (e.g., Google Maps API, medical data API). For example, for the health category, the server searches for information on the nearest emergency clinics.

[0473] Input: Question Category

[0474] Output: Related information (e.g., a list of emergency clinics open overnight)

[0475] Specific operation: The server sends a query to a database or external API to obtain the necessary information.

[0476] Step 5: Server Generates Answer

[0477] The server uses the information obtained from the search to generate specific answers for the user, which can be in the form of fixed templates or customized messages.

[0478] Input: Related Information

[0479] Output: Specific answer

[0480] Specific operation: The server uses the template to generate a response such as, "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0481] Step 6: Arranging for service by the server

[0482] If necessary, the server arranges for additional services, for example, if the user wants to use childcare services, it searches for and arranges for relevant service providers.

[0483] Input: Add user request

[0484] Output: Arranged service information

[0485] Specific operation: The server searches for information on relevant service providers and makes reservations and arrangements for services on behalf of the user.

[0486] Step 7: Server sends response to user

[0487] The server sends the generated response and the status of the arranged service to the user's terminal, where the user receives and checks it.

[0488] Input: Generated answers, arranged service information

[0489] Output: Notification to user terminal

[0490] Specific operation: The server sends the answer to the user's device, which displays it. For example, it displays a list such as "Pick-up service is available. Available services are listed below."

[0491] This system allows users to respond quickly and accurately to child-rearing-related issues, enabling them to receive smooth child-rearing support.

[0492] (Application example 1)

[0493] 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."

[0494] When users encounter childcare-related issues, there is still no system in place to quickly and accurately respond to those issues. In particular, there is a lack of systems to assist users in selecting childcare products and arranging appropriate services in physical stores. As a result, users have to spend a lot of time and effort searching for information and finding the best products and services themselves.

[0495] 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.

[0496] In this invention, the server includes means for receiving questions from users, means for analyzing the questions with a natural language processing engine, means for categorizing the questions based on the analysis results, means for searching for related information from a database or external API according to the question category, means for generating an answer to the user based on the search results, means for sending the generated answer to the user, means for arranging related services as needed, and means for searching for products and services based on the user's question and providing information on corresponding products in physical stores. This enables even busy parents to respond quickly and accurately to child-rearing-related issues.

[0497] The "means for receiving questions from users" is a function for sending questions input by users via their terminals to the server.

[0498] "Means for analyzing questions using a natural language processing engine" refers to a function that analyzes input questions using natural language processing technology and converts them into structured information.

[0499] The "means for classifying questions into categories based on the analysis results" is a function for classifying the analyzed question content into predetermined categories and associating them with specific domains.

[0500] "Means of searching for relevant information from databases or external APIs according to question categories" refers to a function that retrieves relevant information from an internal database or external API service based on classified categories.

[0501] The "means for generating a response to the user based on the search results" is a function for generating a specific response to be provided to the user based on the acquired information.

[0502] The "means for transmitting the generated answer to the user" is a function for transferring the generated answer to the user's terminal and displaying it.

[0503] The "means for arranging related services as needed" is a function for arranging additional services (for example, childcare support or emergency response) based on the user's request and managing the status of the arrangement.

[0504] "A means for searching for products and services based on a user's question and providing relevant product information in physical stores" is a function that searches for related products and services in physical stores based on the question entered by the user and provides the user with relevant information.

[0505] The present invention is a system for quickly and accurately dealing with childcare-related problems. Detailed embodiments of the present invention will be described below.

[0506] 1. System Configuration

[0507] This system consists of user terminals, a server, a database, and an external API. User terminals include mobile devices such as smartphones and tablets. The server plays a central role in performing advanced data processing and calculations.

[0508] 2. Hardware and Software

[0509] Hardware: Smartphones (iOS / Android devices), tablets, servers

[0510] software:

[0511] Natural language processing libraries (Google Cloud Natural Language API, spaCy, NLTK, etc.)

[0512] Product information database (Firebase, MySQL, etc.)

[0513] Push notification service (Firebase Cloud Messaging)

[0514] User Interface (React Native)

[0515] 3. System Implementation

[0516] 1. Receiving questions from users

[0517] A user uses a smartphone or tablet to voice or text a question into the application.

[0518] 2. Question Analysis

[0519] The server analyzes the input question using a natural language processing engine (e.g., Google Cloud Natural Language API), performing tokenization, part-of-speech tagging, and sentiment analysis.

[0520] 3. Question Classification

[0521] Based on the analysis, the server categorizes the questions into specific categories, such as health-related, childcare support-related, education-related, etc.

[0522] 4. Information Search

[0523] The server searches for related information from databases or external APIs according to the category. For example, if the question is about childcare products, it searches for the relevant product from a product information database.

[0524] 5. Answer Generation

[0525] Based on the search results, the server generates specific answers for the user, including standard phrases and customized messages.

[0526] 6. Submit your response

[0527] The generated answer is sent from the server to the user's terminal and displayed on the user's terminal.

[0528] 7. Arrangement of related services

[0529] If necessary, the server arranges for additional services (e.g., childcare or emergency response), and this information is sent to the user's device.

[0530] 4. Specific Examples

[0531] When a user asks the app, "What is the appropriate size of diaper?", the system analyzes the question and provides the most appropriate product information (e.g., for newborns, medium-sized diapers, etc.) along with the location of the item in the store. It also provides advice on how to choose the right size based on the baby's weight and age.

[0532] 5. Examples of prompts

[0533] What is the correct size of diaper?

[0534] As described above, the system of the present invention quickly and accurately analyzes user questions about child-rearing and provides optimal information and service arrangements, thereby reducing the burden on users even in physical stores and realizing efficient child-rearing support.

[0535] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0536] Step 1:

[0537] The user inputs a question into the terminal.

[0538] Input: The user uses a smartphone or tablet to enter a question using text or voice.

[0539] What happens: The application receives user input and sends that data to the server for analysis.

[0540] Step 2:

[0541] The server analyzes the entered question.

[0542] Input: User question text data sent from the terminal.

[0543] What it does: The server uses a natural language processing engine (e.g., Google Cloud Natural Language API) to tokenize the question and perform part-of-speech tagging, subject-predicate-object recognition, and sentiment analysis.

[0544] Output: Parsed structured data of the question.

[0545] Step 3:

[0546] The server categorizes the questions based on the analysis results.

[0547] Input: Parsed question structured data.

[0548] What it does: The server uses the analysis results to apply an algorithm that categorizes the question into the appropriate category (e.g., childcare support, health-related, education, etc.).

[0549] Output: Categorized question data.

[0550] Step 4:

[0551] The server searches for information according to the question category.

[0552] Input: Categorized question data.

[0553] What it does: The server uses internal databases (e.g., Firebase, MySQL) and external APIs (e.g., Google Places API) to find the information most relevant to the question.

[0554] Output: Search result data.

[0555] Step 5:

[0556] The server generates an answer for the user based on the search results.

[0557] Input: Search result data.

[0558] Specific Action: The server generates a specific response using a template-based approach or an algorithm that generates customized messages.

[0559] Output: The generated response data.

[0560] Step 6:

[0561] The server generates a response and sends it to the user.

[0562] Input: The generated response data.

[0563] Specific operation: The server sends the generated answer to the user's device and notifies them via push notification or in-app message.

[0564] Output: The answer displayed on the user's terminal.

[0565] Step 7:

[0566] The server arranges for related services as needed.

[0567] Input: User request or additional information.

[0568] Specific operation: The server arranges related services and manages the arrangement status. Service arrangement includes API calls and staff notifications.

[0569] Output: Notification of order status and feedback of service execution status.

[0570] Through the above steps, the system can quickly and accurately provide childcare-related information and arrange services based on questions entered by the user.

[0571] 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.

[0572] The system of the present invention is a system for quickly and accurately responding to childcare-related problems that users face on a daily basis, and is characterized by incorporating an emotion engine that recognizes the user's emotions. This system has the function of receiving and analyzing questions from users, recognizing their emotions, and providing optimal answers and arranging services. Specific embodiments of the system are described below.

[0573] 1. Receiving questions from users

[0574] First, a user uses a terminal (a device such as a smartphone or PC) to input a question to the system. For example, a user might ask, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This question is sent to the server via the terminal.

[0575] 2. Question Analysis and Emotion Recognition

[0576] The server receives the user's question and analyzes it using a natural language processing engine. This analysis involves tokenizing the text, extracting subjects, predicates, and objects, and then using an emotion engine to recognize emotions contained in the question (e.g., urgency, impatience, worry, etc.) and adjust the analysis results accordingly.

[0577] 3. Question classification and information search

[0578] Based on the emotion recognition and analysis results, the server classifies the question into an appropriate category (e.g., health-related). The server then searches for information from databases or external APIs related to that category. If the question is health-related, it searches for information on the nearest emergency clinic or emergency response advice. The search results are quickly retrieved and passed on to subsequent processing steps.

[0579] 4. Answer generation and emotion-based adjustment

[0580] Based on the acquired information, the server generates a specific response for the user. This response can be based on a fixed template or a customized message. For example, the response might be, "The nearest emergency clinic is XX Hospital. If your symptoms worsen, please call an ambulance." The tone and content of the response are also adjusted appropriately based on the results of the emotion engine.

[0581] 5. Arranging for service and determining the level of urgency

[0582] If necessary, the server arranges for additional services. If the emotion engine recognizes a high level of urgency, related services (for example, arranging for an ambulance) are given priority. If a user asks, "I'm going to be late to pick up my child from daycare due to an emergency. Can someone pick me up for me?", the server searches for related childcare services and proceeds with the arrangements.

[0583] 6. Sending the response to the user

[0584] Finally, the server sends the generated response and the status of the service arrangement to the user's device, which receives it and displays it to the user. The user can then check the specific countermeasures and the arranged services on the device.

[0585] For example, if a user becomes anxious and asks about childcare services, the device will display a list such as, "Pick-up services are available. Available services are listed below," and notify the user in a reassuring tone.

[0586] ---

[0587] Each component of this system also includes an emotion engine, which enables it to respond quickly and accurately to user questions and provide appropriate services that take emotions into consideration. This invention enables effective responses to everyday childcare troubles and emergencies while recognizing the user's emotions.

[0588] The processing flow will be explained below.

[0589] Step 1: User enters question

[0590] A user uses a terminal to input and send a question, for example, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?"

[0591] Step 2: The device sends a question

[0592] The terminal transmits the input question data to the server.

[0593] Step 3: The server receives the query

[0594] The server receives the query data from the terminal.

[0595] Step 4: The server parses the question

[0596] The server analyzes the received question using a natural language processing engine to extract important keywords (e.g., "child," "fever," "ambulance") and contextual information.

[0597] Step 5: The server recognizes the user's emotion

[0598] The server uses an emotion engine to recognize the emotion (e.g., "worry" or "urgency") contained in the question.

[0599] Step 6: The server categorizes the question

[0600] The server classifies the question into an appropriate category (e.g., "health-related") based on the analysis and emotion recognition results.

[0601] Step 7: The server searches for relevant information

[0602] Depending on the question category, the server searches for relevant information from internal databases or external APIs, for example, the nearest emergency clinic or emergency response guidelines.

[0603] Step 8: The server aggregates the search results

[0604] The server aggregates the search results it has obtained and organizes them into a series of information to provide to the user.

[0605] Step 9: Server Generates Answer

[0606] The server generates an answer to provide to the user based on the organized information. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0607] Step 10: The server adjusts the answer based on the sentiment

[0608] The server then adjusts the tone and content of the generated response appropriately based on the emotion recognition results. For example, if the emotion is strong, it may include additional advice such as, "Don't worry, here's how to deal with it first."

[0609] Step 11: The server considers arranging for service

[0610] The server determines the need for additional services (e.g., dispatching an ambulance) based on the user's question and the emotion recognition results.

[0611] Step 12: The server arranges for related services

[0612] If necessary, the server may request an ambulance from a service provider that it works with.

[0613] Step 13: The server sends the response and the dispatch result.

[0614] The server sends the generated response and the arranged service information to the user's terminal.

[0615] Step 14: The device notifies the user of the answer

[0616] The device notifies the user of the received response and service information and displays it on the screen. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0617] Example 2

[0618] 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."

[0619] In today's childcare environment, parents face a variety of problems. Many of these problems are highly urgent and involve emotional stress. However, conventional systems have had difficulty accurately capturing users' emotions and responding quickly and appropriately. In particular, there is a demand for systems that can recognize emotions and respond to childcare-related worries and emergencies. Therefore, the challenge is to provide a childcare support system that can take users' emotions into consideration and provide optimal services.

[0620] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0621] In this invention, the server includes means for receiving questions from users, means for analyzing the questions with a natural language processing engine, means for categorizing the questions based on the analysis results, means for searching for related information from a database or an external API according to the question category, means for generating answers to the users based on the search results, means for sending the generated answers to the users, means for arranging related services as needed, means for recognizing emotions contained in the questions using an emotion engine, and means for adjusting the tone and content of the answers based on the recognized emotions. This makes it possible to respond to child-rearing issues quickly and accurately while taking the user's emotions into consideration.

[0622] "User" refers to an individual who uses this system to enter questions and receive answers and services.

[0623] "Terminal" refers to the device (smartphone, PC, etc.) that a user uses to enter a question.

[0624] "Server" refers to a computer system that receives questions from users and performs processes such as analysis, classification, answer generation, and service arrangement.

[0625] A "natural language processing engine" refers to software that analyzes questions entered by users and performs tasks such as understanding grammatical structures and tokenizing them.

[0626] An "emotion engine" refers to software that recognizes and analyzes the emotions contained in users' questions.

[0627] "Category" refers to various classifications based on the content of the user's question (e.g., health, education, childcare, etc.).

[0628] A "database" refers to a collection of related information that is stored, managed, and provided in a searchable format.

[0629] An "external API" refers to a program interface for obtaining information in collaboration with other systems or services.

[0630] "Answer" refers to specific information or advice that the system generates in response to a user's question.

[0631] "Service arrangement" refers to the procedure for providing additional support or services based on the user's question and emotion recognition results.

[0632] "Tokenization" refers to the process in natural language processing of dividing input text into semantic units.

[0633] "Grammatical structure" refers to structural analysis that analyzes the relationships between subjects, predicates, objects, etc. in a sentence.

[0634] "Emotion" refers to the psychological state (e.g., urgency, impatience, worry, etc.) contained within the user's text.

[0635] "Tone" refers to the nuances and style of language used in responses.

[0636] "Relevant information" refers to data and knowledge necessary to generate an answer to a user's question.

[0637] "Childcare agency services" refer to external services that provide support such as temporary childcare and transportation.

[0638] The above are definitions of important terms included in the claims.

[0639] The present invention provides a system that quickly and accurately responds to childcare-related problems that users face on a daily basis. This system is characterized by incorporating an emotion engine that recognizes the user's emotions. Specific embodiments are described below.

[0640] A user inputs a question into the system using a terminal (a device such as a smartphone or PC). For example, a user might ask, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This input is sent to the server via the terminal.

[0641] The server receives a user's question and analyzes it using a natural language processing engine (e.g., spaCy, NLTK). This analysis involves tokenizing the text, extracting subjects, predicates, and objects, and then using an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions in the question, such as urgency, impatience, or worry, and adjusts the analysis results accordingly.

[0642] Based on the analysis and emotion recognition results, the server classifies the question into an appropriate category (e.g., health-related). The server then searches for information from databases or external APIs (e.g., Google Maps API) related to that category. If the question is health-related, the server searches for information about the nearest emergency clinic or emergency response advice. The search results are quickly retrieved and passed on to subsequent processing steps.

[0643] Based on the acquired information, the server generates a specific response for the user. This response can be based on a fixed template or a customized message. For example, the response might be, "The nearest emergency clinic is XX Hospital. If your symptoms worsen, please call an ambulance." The tone and content of the response are also adjusted appropriately based on the results of the emotion engine.

[0644] If necessary, the server arranges for additional services. If the emotion engine recognizes a high level of urgency, related services (for example, arranging for an ambulance) are given priority. If a user asks, "I'm going to be late to pick up my child from daycare due to an emergency. Can someone pick me up for me?", the server searches for related childcare services and proceeds with the arrangements.

[0645] Finally, the server sends the generated answer and the status of the service arrangement to the user's device. The device receives this and displays it to the user. The user can check the specific countermeasures and the services that have been arranged on the device. For example, if a user is feeling anxious and asks about childcare services, the device will display a list such as "Pick-up service is available. The available services are as follows," and notify the user in a reassuring tone.

[0646] The following are examples of prompt sentences:

[0647] "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?"

[0648] "I have a question about a child care issue that needs immediate attention. What steps should I take?"

[0649] The above is a specific embodiment of the present invention, and the system is capable of dealing with childcare-related issues quickly and accurately while taking into account the user's feelings.

[0650] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0651] Step 1:

[0652] A user uses a terminal to input a question into the system. The input is text data in natural language. For example, a question might be input like, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" The input question is sent to the server via the terminal. Specific actions on the terminal include entering text into a question input form and clicking the send button. Input: User's question text. Output: Sending question data to the server.

[0653] Step 2:

[0654] The server receives questions sent by users. The received question text is passed to a natural language processing engine for analysis. Specific analysis operations include tokenizing the text (breaking it down into words and phrases) and understanding the context (extracting the subject, predicate, and object). For example, information such as "child," "late night," "sudden fever," and "should an ambulance be called" is broken down and the meaning of each part is identified. Input: Received question text. Output: Tokenized text and context information.

[0655] Step 3:

[0656] The server uses an emotion engine to recognize the emotion contained in the question based on the analysis results obtained from the natural language processing engine. The emotion engine extracts emotional elements such as urgency, impatience, and worry, and adjusts the analysis results accordingly. Specifically, it uses an emotion analysis algorithm to evaluate text data and detect high levels of urgency or anxiety. Input: Tokenized text and contextual information. Output: Emotion recognition results.

[0657] Step 4:

[0658] The server classifies the question into an appropriate category based on the analysis and emotion recognition results. For example, the question is classified into the "health-related" category. The specific operation includes a process of matching the question with a predefined category list and selecting the category that best suits the question. Input: Analysis results and emotion recognition results. Output: Question category.

[0659] Step 5:

[0660] The server searches for information from relevant databases or external APIs depending on the question category. For example, if the question is health-related, it searches for information on the nearest emergency clinic after hours or advice on how to respond to an emergency. The specific operation involves sending a query to a database and retrieving the relevant information. Input: Question category. Output: Search results.

[0661] Step 6:

[0662] The server generates a specific answer based on the information obtained. This answer is based on a fixed template, but includes a customized message if necessary. The tone and content of the answer are adjusted appropriately based on the results of the emotion engine. For example, it generates a specific answer such as, "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance." Input: Search results and emotion recognition results. Output: Generated answer.

[0663] Step 7:

[0664] If necessary, the server will arrange for additional services. If the emotion engine recognizes a high level of urgency, it will prioritize related services (for example, arranging for an ambulance). For example, if a user asks, "I have an emergency and will be late to pick up my child from daycare. Can someone pick me up for me?", it will search for related childcare services and proceed with the arrangements. Input: Question and high-urgency emotion recognition result. Output: Arranged service.

[0665] Step 8:

[0666] Finally, the server sends the generated answer and the arrangement status to the user's terminal. The terminal receives this and displays it to the user. The user can check the specific countermeasures and the arranged services on the terminal. For example, in response to a user's question, a list such as "Pick-up service is available. Available services are as follows" can be displayed, providing a sense of security. Input: Generated answer and arrangement status. Output: Display of answer and arrangement status on the terminal.

[0667] (Application example 2)

[0668] 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."

[0669] Childcare issues are diverse, and it is necessary to respond promptly to users' anxieties and urgencies. Furthermore, it is necessary to provide appropriate services and information while taking into consideration the user's emotions. However, conventional systems are limited to simply providing information in response to users' questions, and it is difficult to provide comprehensive support that addresses the user's emotions or arranges specific services. This leads to delays in resolving childcare emergencies and everyday problems.

[0670] 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 recognizing the user's emotions and adjusting the analysis results, means for adjusting the tone and information of the proposal content based on the emotions, and means for extracting keywords, recognizing subjects, predicates, and objects, and analyzing emotions in question analysis and categorization. This makes it possible to provide appropriate answers and arrange services that are in line with the user's emotions.

[0671] The "means for receiving questions from the user" is a mechanism by which the system receives information and questions entered by the user.

[0672] "Means for analyzing questions using a natural language processing engine" refers to natural language processing technology used to handle text data received from users and understand their contents.

[0673] "Means for categorizing questions based on the analysis results" is a function that organizes the content of the analyzed questions into specific areas or categories.

[0674] "Means for searching related information from databases or external APIs according to question categories" refers to a method for collecting related information from internal and external data sources based on classified question categories.

[0675] "Means for generating an answer to the user based on the search results" refers to the process of creating an appropriate answer to the user based on the acquired information.

[0676] The "means for transmitting the generated answer to the user" refers to a means for transmitting the answer generated by the system to the user's terminal.

[0677] The "means for arranging related services as needed" is a function for executing additional services or arrangements according to the user's inquiries or circumstances.

[0678] "Means for recognizing the user's emotions and adjusting the analysis results" refers to a technology that analyzes the emotions contained in the user's question and adjusts the information provided or answer according to those emotions.

[0679] "Means for adjusting the tone and information of the proposed content based on the user's emotions" refers to a mechanism that appropriately changes the way the proposed content is expressed and the information provided to match the user's emotions.

[0680] "Keyword extraction" is a technique for extracting important words and phrases from a user's question.

[0681] "Subject-predicate-object recognition" is a technique for identifying and analyzing the components of a sentence: subject, predicate, and object.

[0682] "Sentiment analysis" is a technique for analyzing the type and intensity of emotions from text data.

[0683] A specific category such as "childcare support, education, health-related" is a classification that organizes the content of a user's question into a specific area, and includes areas related to childcare support, education, and health.

[0684] A system for carrying out the present invention accepts childcare consultations via a user's smartphone app and proposes appropriate childcare-related services and products. Detailed embodiments of this system are described below.

[0685] System Program

[0686] This system consists of a server and a user device (smartphone). When a user sends a question through a smartphone app, the data is sent to the server. The server analyzes the question and recognizes the user's emotions.

[0687] Hardware and software used

[0688] Server: The central computing unit that handles the backend of this system, primarily for data processing and analysis.

[0689] Smartphone: A device used by a user to enter questions and receive answers from the system.

[0690] Flask: A Python-based micro-web framework used to build server-side APIs.

[0691] Transformers: A natural language processing library provided by Hugging Face for sentiment analysis and question answering.

[0692] Data processing and calculation

[0693] 1. Receiving a question: The user enters a question into the smartphone app and sends it to the server.

[0694] 2. Natural Language Processing: The server uses the Transformers library to analyze the question, tokenize it, and extract the subject, predicate, and object.

[0695] 3. Emotion recognition: Extract the user's emotions from the analyzed questions and recognize the type of emotion (e.g., anxiety, impatience, etc.).

[0696] 4. Categorization and information retrieval: Based on the analysis results, the question is categorized appropriately and relevant information is retrieved from databases or external APIs. For example, if the question is about childcare support, information on appropriate childcare products and services is retrieved.

[0697] 5. Generate and send an answer: Based on the search results and emotion recognition results, an appropriate answer is generated and sent to the smartphone app.

[0698] Specific examples

[0699] Consider the case where a user asks the following question:

[0700] "My baby cries a lot at night. Are there any good products?"

[0701] The server receives this question, analyzes the question content and sentiment, and generates and sends the following answer as a result of the analysis:

[0702] "We will suggest products that will help you get your baby to sleep. You seem to be worried, but baby carriers and stuffed toys that help you get your baby to sleep are effective. You can check them out in store."

[0703] This system allows users to receive specific suggestions that are in line with their emotions, enabling them to quickly resolve their child-rearing concerns.

[0704] Prompt statement

[0705] Below are some example prompts to input to the generative AI model:

[0706] "I'm having trouble getting my baby to sleep. What products do I need?"

[0707] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0708] Step 1:

[0709] A user enters a question using a smartphone app. The entered question data is sent from the smartphone to a server. The input is the text that the user enters into the app, and the output is the text data sent to the server. The specific action performed at this stage is for the user to enter a question in the text box and tap the "Send" button.

[0710] Step 2:

[0711] The server passes the received question data to a natural language processing engine (Transformers library) and analyzes the question. Specifically, the process tokenizes the text and extracts the subject, predicate, and object. The input is the text data received from the user, and the output is the analyzed text structure.

[0712] Step 3:

[0713] The server passes the analysis results to an emotion recognition engine to recognize the user's emotions. The input is the analyzed text structure, and the output is the recognized emotion information (e.g., anxiety, impatience, etc.). The specific operation is that the emotion recognition engine analyzes the text data and generates an emotion score.

[0714] Step 4:

[0715] The server classifies questions into appropriate categories based on the analysis and emotion recognition results. The input is the analyzed text structure and emotion information, and the output is a category label (e.g., parenting support, health-related, etc.). Specifically, the classification algorithm determines the category based on the text data and emotion score.

[0716] Step 5:

[0717] The server searches for relevant information from a database or external API according to the question category. The input is a category label, and the output is related information data (e.g., product list, service information, etc.). The specific operation is to execute a database query or API call to obtain information.

[0718] Step 6:

[0719] The server generates a response for the user based on the search results and emotion recognition results. The input is related information data and emotion scores, and the output is a customized response text. The specific operation is that a template or customized message generation engine creates a response based on the information.

[0720] Step 7:

[0721] The server sends the generated answer to the user's smartphone app. The input is the generated answer text, and the output is the answer message displayed on the smartphone. The specific operation is data transmission from the server to the smartphone app. The user can check the sent answer on the app and take action based on the suggested product or service information.

[0722] 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.

[0723] 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.

[0724] 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.

[0725] [Third embodiment]

[0726] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0727] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0728] 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).

[0729] 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.

[0730] 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.

[0731] 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).

[0732] 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. 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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."

[0738] The system of the present invention is a system for quickly and accurately responding to childcare-related problems that users face on a daily basis. This system has the function of receiving and analyzing questions from users, and providing optimal answers and arranging services. Specific embodiments of the system are described below.

[0739] 1. Receiving questions from users

[0740] First, a user uses a terminal (a device such as a smartphone or PC) to input a question to the system. For example, a user might ask, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This question is sent to the server via the terminal.

[0741] 2. Question analysis and classification

[0742] The server receives the user's question and analyzes it using a natural language processing engine. This analysis involves tokenizing the text, extracting subjects, predicates, and objects, and analyzing sentiment. Based on this information, the server classifies the question into an appropriate category. For example, a question like "My child suddenly developed a fever in the middle of the night" would be classified as a health-related category.

[0743] 3. Information Search

[0744] After parsing and classification is complete, the server searches for information from databases or external APIs related to the relevant category. For health-related questions, it searches for information on the nearest emergency clinic or emergency response advice. The search results are quickly retrieved and passed on to subsequent processing steps.

[0745] 4. Answer Generation

[0746] Based on the information obtained, the server generates a specific answer for the user. This answer can be based on a fixed template or a customized message. For example, the server might generate an answer like, "The nearest emergency clinic is at XX Hospital. If your symptoms worsen, please call an ambulance."

[0747] 5. Arrangements for Service

[0748] If necessary, the server arranges for additional services. For example, if a user asks, "I have an emergency and will be late to pick up my child from daycare. Can someone pick me up?", the server searches for relevant childcare services and proceeds with the arrangements.

[0749] 6. Sending the response to the user

[0750] Finally, the server sends the generated response and the status of the service arrangement to the user's device, which receives it and displays it to the user. The user can then check the specific countermeasures and the arranged services on the device.

[0751] For example, if a user asks about childcare services, the terminal displays a list such as "Pick-up services are available. Available services are listed below."

[0752] ---

[0753] The components of this system work together to enable quick and accurate responses to user questions. This invention enables effective responses to everyday childcare problems and emergencies.

[0754] The processing flow will be explained below.

[0755] Step 1: User enters question

[0756] A user uses a terminal to input and send a question, for example, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?"

[0757] Step 2: The device sends a question

[0758] The terminal transmits the input question data to the server.

[0759] Step 3: The server receives the query

[0760] The server receives the query data from the terminal.

[0761] Step 4: The server parses the question

[0762] The server analyzes the received question using a natural language processing engine to extract important keywords (e.g., "child," "fever," "ambulance") and contextual information.

[0763] Step 5: The server categorizes the question

[0764] The server classifies the question into an appropriate category (e.g., "health-related") based on the analysis results.

[0765] Step 6: The server searches for relevant information

[0766] Depending on the question category, the server searches for relevant information from internal databases or external APIs, such as the nearest emergency clinic or emergency response guidelines.

[0767] Step 7: The server aggregates the search results

[0768] The server aggregates the search results it has obtained and organizes them into a series of information to provide to the user.

[0769] Step 8: Server Generates Answer

[0770] The server generates an answer to provide to the user based on the organized information. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0771] Step 9: The server considers arranging for service.

[0772] The server determines the need for additional services (e.g., dispatching an ambulance) based on the user's question.

[0773] Step 10: The server arranges for related services

[0774] If necessary, the server may request an ambulance from a service provider that it works with.

[0775] Step 11: Server sends response

[0776] The server sends the generated response and the arranged service information to the user's terminal.

[0777] Step 12: The device notifies the user of the answer

[0778] The device notifies the user of the received response and service information and displays it on the screen. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0779] Example 1

[0780] 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."

[0781] In childcare, users often face many problems and emergencies on a daily basis. Accessing information and services that allow them to quickly and appropriately respond to these issues is important to users, and effective methods are needed to improve the quality of childcare support. However, current systems have issues with difficulty responding promptly to user questions, and the efficiency of information retrieval and answer generation is low. Furthermore, they often fail to properly assess the specificity and urgency of questions and respond accordingly.

[0782] 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.

[0783] In this invention, the server includes means for receiving questions from users, means for analyzing the questions with a natural language processing engine, means for categorizing the questions based on the analysis results, means for searching for related information from a database or an external API according to the question category, means for generating answers to the users based on the search results, means for sending the generated answers to the users, means for arranging related services as needed, and means for tokenization, extracting subjects, predicates, and objects, and performing sentiment analysis. This enables a system that can respond quickly and accurately to user questions.

[0784] The "means for receiving questions from users" refers to the technical means by which the server receives questions from users sent from terminals.

[0785] "Means for analyzing questions using a natural language processing engine" refers to technical means for performing tokenization, grammar analysis, sentiment analysis, etc. on questions received by the server using natural language processing technology.

[0786] "Means for categorizing questions based on analysis results" refers to technical means for categorizing questions into predefined categories (e.g., health, childcare, education, etc.) based on analysis results obtained through natural language processing.

[0787] "Means for searching for relevant information from databases or external APIs according to question categories" refers to technical means for searching for relevant information from internal databases or external APIs based on the category into which a question is classified.

[0788] "Means for generating answers to users based on search results" refers to technical means for automatically generating specific answers based on information obtained from searches.

[0789] The "means for transmitting the generated answer to the user" refers to the technical means for transmitting the answer generated by the server to the user's terminal and displaying it.

[0790] The "means for arranging related services as needed" refers to a technical means for searching for and arranging additional related services based on the content of the user's inquiry.

[0791] "Tokenization" is a natural language processing process that breaks up the text of a question into words and phrases.

[0792] "Means for extracting subjects, predicates, and objects" refers to technical means for analyzing the grammatical structure of a question and identifying the subject, predicate, and object therefrom.

[0793] "Means for performing sentiment analysis" refers to technical means for assessing the user's sentiment and urgency from the question text.

[0794] The system of the present invention is designed to quickly and accurately respond to childcare-related problems that users face on a daily basis. This system uses various technical means to receive and analyze questions from users and provide optimal answers and service arrangements. Specific embodiments of the system are described below.

[0795] First, a user inputs a question into the system using a device such as a smartphone or PC. The input question is sent to the server via the device. For example, a user might input a question such as, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This question is sent to the server.

[0796] The server then uses a natural language processing engine (e.g., SpaCy, NLTK) to parse the received question. This involves tokenizing the text, extracting subjects, predicates, and objects, and performing sentiment analysis. This process helps understand the content and urgency of the question and categorize it into the appropriate category (e.g., health, parenting, education, etc.).

[0797] For each classified question, the server searches for relevant information from databases or external APIs (e.g., Google Maps API, medical data API). For example, if the user's question is about health, it will search for information on the nearest emergency clinics and emergency response guidelines. Based on the information obtained, the server generates a specific answer. This answer can be based on a fixed template or a customized message format.

[0798] The generated answer is sent from the server to the user's device, where the user receives it and checks it. For example, it displays specific countermeasures such as, "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0799] If necessary, the server can also arrange for related services. For example, if a user asks, "I have an emergency and will be late to pick up my child from daycare. Can someone pick me up for me?", the server will search for related childcare services and proceed with the arrangements.

[0800] The system's components work together to provide users with fast and accurate responses, allowing them to effectively respond to everyday parenting issues and emergencies.

[0801] For example, if a user asks "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?", the server analyzes the question and classifies it into a health category. The server then searches for information on night-time emergency clinics and generates a response such as "The nearest night-time emergency clinic is XX Hospital. If the symptoms worsen, please call an ambulance." and sends it to the user's device.

[0802] Example prompt sentence:

[0803] What is the appropriate response when a user asks, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" Please generate an answer that includes information about night clinics and emergency procedures.

[0804] This system allows users to deal with childcare-related issues quickly and accurately, thereby improving the quality of childcare support.

[0805] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0806] Step 1: User enters question

[0807] The user uses a device (smartphone or PC) to input a question into the system. For example, they might input a question like, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" The device then sends the user's input data to the server.

[0808] Input: Question text from user

[0809] Output: Sending the query data to the server

[0810] Specific operation: The user enters a question into the terminal application or web interface and presses the send button.

[0811] Step 2: The server receives and analyzes the query

[0812] The server receives the question sent from the device and analyzes it using a natural language processing engine (e.g., SpaCy, NLTK). The analysis involves tokenizing the text, extracting subjects, predicates, and objects, and analyzing sentiment.

[0813] Input: Question data sent from the terminal

[0814] Output: Analysis data (tokenization, subject, predicate, object, sentiment analysis results)

[0815] Specific operation: The server receives the question data and passes it to the natural language processing engine for analysis.

[0816] Step 3: Server classifies the question

[0817] Based on the analysis results, the server classifies the question into an appropriate category (e.g., health, childcare, education, etc.) and prepares to search for appropriate information according to the category.

[0818] Input: Analysis data

[0819] Output: Question category

[0820] Specific operation: The server classifies questions into categories such as "health" or "childcare" based on the results of subject, predicate, object, and sentiment analysis.

[0821] Step 4: Server Looks Up Information

[0822] Based on the question category, the server searches for relevant information from internal databases or external APIs (e.g., Google Maps API, medical data API). For example, for the health category, the server searches for information on the nearest emergency clinics.

[0823] Input: Question Category

[0824] Output: Related information (e.g., a list of emergency clinics open overnight)

[0825] Specific operation: The server sends a query to a database or external API to obtain the necessary information.

[0826] Step 5: Server Generates Answer

[0827] The server uses the information obtained from the search to generate specific answers for the user, which can be in the form of fixed templates or customized messages.

[0828] Input: Related Information

[0829] Output: Specific answer

[0830] Specific operation: The server uses the template to generate a response such as, "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0831] Step 6: Arranging for service by the server

[0832] If necessary, the server arranges for additional services, for example, if the user wants to use childcare services, it searches for and arranges for relevant service providers.

[0833] Input: Add user request

[0834] Output: Arranged service information

[0835] Specific operation: The server searches for information on relevant service providers and makes reservations and arrangements for services on behalf of the user.

[0836] Step 7: Server sends response to user

[0837] The server sends the generated response and the status of the arranged service to the user's terminal, where the user receives and checks it.

[0838] Input: Generated answers, arranged service information

[0839] Output: Notification to user terminal

[0840] Specific operation: The server sends the answer to the user's device, which displays it. For example, it displays a list such as "Pick-up service is available. Available services are listed below."

[0841] This system allows users to respond quickly and accurately to child-rearing-related issues, enabling them to receive smooth child-rearing support.

[0842] (Application example 1)

[0843] 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."

[0844] When users encounter childcare-related issues, there is still no system in place to quickly and accurately respond to those issues. In particular, there is a lack of systems to assist users in selecting childcare products and arranging appropriate services in physical stores. As a result, users have to spend a lot of time and effort searching for information and finding the best products and services themselves.

[0845] 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.

[0846] In this invention, the server includes means for receiving questions from users, means for analyzing the questions with a natural language processing engine, means for categorizing the questions based on the analysis results, means for searching for related information from a database or external API according to the question category, means for generating an answer to the user based on the search results, means for sending the generated answer to the user, means for arranging related services as needed, and means for searching for products and services based on the user's question and providing information on corresponding products in physical stores. This enables even busy parents to respond quickly and accurately to child-rearing-related issues.

[0847] The "means for receiving questions from users" is a function for sending questions input by users via their terminals to the server.

[0848] "Means for analyzing questions using a natural language processing engine" refers to a function that analyzes input questions using natural language processing technology and converts them into structured information.

[0849] The "means for classifying questions into categories based on the analysis results" is a function for classifying the analyzed question content into predetermined categories and associating them with specific domains.

[0850] "Means of searching for relevant information from databases or external APIs according to question categories" refers to a function that retrieves relevant information from an internal database or external API service based on classified categories.

[0851] The "means for generating a response to the user based on the search results" is a function for generating a specific response to be provided to the user based on the acquired information.

[0852] The "means for transmitting the generated answer to the user" is a function for transferring the generated answer to the user's terminal and displaying it.

[0853] The "means for arranging related services as needed" is a function for arranging additional services (for example, childcare support or emergency response) based on the user's request and managing the status of the arrangement.

[0854] "A means for searching for products and services based on a user's question and providing relevant product information in physical stores" is a function that searches for related products and services in physical stores based on the question entered by the user and provides the user with relevant information.

[0855] The present invention is a system for quickly and accurately dealing with childcare-related problems. Detailed embodiments of the present invention will be described below.

[0856] 1. System Configuration

[0857] This system consists of user terminals, a server, a database, and an external API. User terminals include mobile devices such as smartphones and tablets. The server plays a central role in performing advanced data processing and calculations.

[0858] 2. Hardware and Software

[0859] Hardware: Smartphones (iOS / Android devices), tablets, servers

[0860] software:

[0861] Natural language processing libraries (Google Cloud Natural Language API, spaCy, NLTK, etc.)

[0862] Product information database (Firebase, MySQL, etc.)

[0863] Push notification service (Firebase Cloud Messaging)

[0864] User Interface (React Native)

[0865] 3. System Implementation

[0866] 1. Receiving questions from users

[0867] A user uses a smartphone or tablet to voice or text a question into the application.

[0868] 2. Question Analysis

[0869] The server analyzes the input question using a natural language processing engine (e.g., Google Cloud Natural Language API), performing tokenization, part-of-speech tagging, and sentiment analysis.

[0870] 3. Question Classification

[0871] Based on the analysis, the server categorizes the questions into specific categories, such as health-related, childcare support-related, education-related, etc.

[0872] 4. Information Search

[0873] The server searches for related information from databases or external APIs according to the category. For example, if the question is about childcare products, it searches for the relevant product from a product information database.

[0874] 5. Answer Generation

[0875] Based on the search results, the server generates specific answers for the user, including standard phrases and customized messages.

[0876] 6. Submit your response

[0877] The generated answer is sent from the server to the user's terminal and displayed on the user's terminal.

[0878] 7. Arrangement of related services

[0879] If necessary, the server arranges for additional services (e.g., childcare or emergency response), and this information is sent to the user's device.

[0880] 4. Specific Examples

[0881] When a user asks the app, "What is the appropriate size of diaper?", the system analyzes the question and provides the most appropriate product information (e.g., for newborns, medium-sized diapers, etc.) along with the location of the item in the store. It also provides advice on how to choose the right size based on the baby's weight and age.

[0882] 5. Examples of prompts

[0883] What is the correct size of diaper?

[0884] As described above, the system of the present invention quickly and accurately analyzes user questions about child-rearing and provides optimal information and service arrangements, thereby reducing the burden on users even in physical stores and realizing efficient child-rearing support.

[0885] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0886] Step 1:

[0887] The user inputs a question into the terminal.

[0888] Input: The user uses a smartphone or tablet to enter a question using text or voice.

[0889] What happens: The application receives user input and sends that data to the server for analysis.

[0890] Step 2:

[0891] The server analyzes the entered question.

[0892] Input: User question text data sent from the terminal.

[0893] What it does: The server uses a natural language processing engine (e.g., Google Cloud Natural Language API) to tokenize the question and perform part-of-speech tagging, subject-predicate-object recognition, and sentiment analysis.

[0894] Output: Parsed structured data of the question.

[0895] Step 3:

[0896] The server categorizes the questions based on the analysis results.

[0897] Input: Parsed question structured data.

[0898] What it does: The server uses the analysis results to apply an algorithm that categorizes the question into the appropriate category (e.g., childcare support, health-related, education, etc.).

[0899] Output: Categorized question data.

[0900] Step 4:

[0901] The server searches for information according to the question category.

[0902] Input: Categorized question data.

[0903] What it does: The server uses internal databases (e.g., Firebase, MySQL) and external APIs (e.g., Google Places API) to find the information most relevant to the question.

[0904] Output: Search result data.

[0905] Step 5:

[0906] The server generates an answer for the user based on the search results.

[0907] Input: Search result data.

[0908] Specific Action: The server generates a specific response using a template-based approach or an algorithm that generates customized messages.

[0909] Output: The generated response data.

[0910] Step 6:

[0911] The server generates a response and sends it to the user.

[0912] Input: The generated response data.

[0913] Specific operation: The server sends the generated answer to the user's device and notifies them via push notification or in-app message.

[0914] Output: The answer displayed on the user's terminal.

[0915] Step 7:

[0916] The server arranges for related services as needed.

[0917] Input: User request or additional information.

[0918] Specific operation: The server arranges related services and manages the arrangement status. Service arrangement includes API calls and staff notifications.

[0919] Output: Notification of order status and feedback of service execution status.

[0920] Through the above steps, the system can quickly and accurately provide childcare-related information and arrange services based on questions entered by the user.

[0921] 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.

[0922] The system of the present invention is a system for quickly and accurately responding to childcare-related problems that users face on a daily basis, and is characterized by incorporating an emotion engine that recognizes the user's emotions. This system has the function of receiving and analyzing questions from users, recognizing their emotions, and providing optimal answers and arranging services. Specific embodiments of the system are described below.

[0923] 1. Receiving questions from users

[0924] First, a user uses a terminal (a device such as a smartphone or PC) to input a question to the system. For example, a user might ask, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This question is sent to the server via the terminal.

[0925] 2. Question Analysis and Emotion Recognition

[0926] The server receives the user's question and analyzes it using a natural language processing engine. This analysis involves tokenizing the text, extracting subjects, predicates, and objects, and then using an emotion engine to recognize emotions contained in the question (e.g., urgency, impatience, worry, etc.) and adjust the analysis results accordingly.

[0927] 3. Question classification and information search

[0928] Based on the emotion recognition and analysis results, the server classifies the question into an appropriate category (e.g., health-related). The server then searches for information from databases or external APIs related to that category. If the question is health-related, it searches for information on the nearest emergency clinic or emergency response advice. The search results are quickly retrieved and passed on to subsequent processing steps.

[0929] 4. Answer generation and emotion-based adjustment

[0930] Based on the acquired information, the server generates a specific response for the user. This response can be based on a fixed template or a customized message. For example, the response might be, "The nearest emergency clinic is XX Hospital. If your symptoms worsen, please call an ambulance." The tone and content of the response are also adjusted appropriately based on the results of the emotion engine.

[0931] 5. Arranging for service and determining the level of urgency

[0932] If necessary, the server arranges for additional services. If the emotion engine recognizes a high level of urgency, related services (for example, arranging for an ambulance) are given priority. If a user asks, "I'm going to be late to pick up my child from daycare due to an emergency. Can someone pick me up for me?", the server searches for related childcare services and proceeds with the arrangements.

[0933] 6. Sending the response to the user

[0934] Finally, the server sends the generated response and the status of the service arrangement to the user's device, which receives it and displays it to the user. The user can then check the specific countermeasures and the arranged services on the device.

[0935] For example, if a user becomes anxious and asks about childcare services, the device will display a list such as, "Pick-up services are available. Available services are listed below," and notify the user in a reassuring tone.

[0936] ---

[0937] Each component of this system also includes an emotion engine, which enables it to respond quickly and accurately to user questions and provide appropriate services that take emotions into consideration. This invention enables effective responses to everyday childcare troubles and emergencies while recognizing the user's emotions.

[0938] The processing flow will be explained below.

[0939] Step 1: User enters question

[0940] A user uses a terminal to input and send a question, for example, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?"

[0941] Step 2: The device sends a question

[0942] The terminal transmits the input question data to the server.

[0943] Step 3: The server receives the query

[0944] The server receives the query data from the terminal.

[0945] Step 4: The server parses the question

[0946] The server analyzes the received question using a natural language processing engine to extract important keywords (e.g., "child," "fever," "ambulance") and contextual information.

[0947] Step 5: The server recognizes the user's emotion

[0948] The server uses an emotion engine to recognize the emotion (e.g., "worry" or "urgency") contained in the question.

[0949] Step 6: The server categorizes the question

[0950] The server classifies the question into an appropriate category (e.g., "health-related") based on the analysis and emotion recognition results.

[0951] Step 7: The server searches for relevant information

[0952] Depending on the question category, the server searches for relevant information from internal databases or external APIs, for example, the nearest emergency clinic or emergency response guidelines.

[0953] Step 8: The server aggregates the search results

[0954] The server aggregates the search results it has obtained and organizes them into a series of information to provide to the user.

[0955] Step 9: Server Generates Answer

[0956] The server generates an answer to provide to the user based on the organized information. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0957] Step 10: The server adjusts the answer based on the sentiment

[0958] The server then adjusts the tone and content of the generated response appropriately based on the emotion recognition results. For example, if the emotion is strong, it may include additional advice such as, "Don't worry, here's how to deal with it first."

[0959] Step 11: The server considers arranging for service

[0960] The server determines the need for additional services (e.g., dispatching an ambulance) based on the user's question and the emotion recognition results.

[0961] Step 12: The server arranges for related services

[0962] If necessary, the server may request an ambulance from a service provider that it works with.

[0963] Step 13: The server sends the response and the dispatch result.

[0964] The server sends the generated response and the arranged service information to the user's terminal.

[0965] Step 14: The device notifies the user of the answer

[0966] The device notifies the user of the received response and service information and displays it on the screen. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[0967] Example 2

[0968] 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."

[0969] In today's childcare environment, parents face a variety of problems. Many of these problems are highly urgent and involve emotional stress. However, conventional systems have had difficulty accurately capturing users' emotions and responding quickly and appropriately. In particular, there is a demand for systems that can recognize emotions and respond to childcare-related worries and emergencies. Therefore, the challenge is to provide a childcare support system that can take users' emotions into consideration and provide optimal services.

[0970] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0971] In this invention, the server includes means for receiving questions from users, means for analyzing the questions with a natural language processing engine, means for categorizing the questions based on the analysis results, means for searching for related information from a database or an external API according to the question category, means for generating answers to the users based on the search results, means for sending the generated answers to the users, means for arranging related services as needed, means for recognizing emotions contained in the questions using an emotion engine, and means for adjusting the tone and content of the answers based on the recognized emotions. This makes it possible to respond to child-rearing issues quickly and accurately while taking the user's emotions into consideration.

[0972] "User" refers to an individual who uses this system to enter questions and receive answers and services.

[0973] "Terminal" refers to the device (smartphone, PC, etc.) that a user uses to enter a question.

[0974] "Server" refers to a computer system that receives questions from users and performs processes such as analysis, classification, answer generation, and service arrangement.

[0975] A "natural language processing engine" refers to software that analyzes questions entered by users and performs tasks such as understanding grammatical structures and tokenizing them.

[0976] An "emotion engine" refers to software that recognizes and analyzes the emotions contained in users' questions.

[0977] "Category" refers to various classifications based on the content of the user's question (e.g., health, education, childcare, etc.).

[0978] A "database" refers to a collection of related information that is stored, managed, and provided in a searchable format.

[0979] An "external API" refers to a program interface for obtaining information in collaboration with other systems or services.

[0980] "Answer" refers to specific information or advice that the system generates in response to a user's question.

[0981] "Service arrangement" refers to the procedure for providing additional support or services based on the user's question and emotion recognition results.

[0982] "Tokenization" refers to the process in natural language processing of dividing input text into semantic units.

[0983] "Grammatical structure" refers to structural analysis that analyzes the relationships between subjects, predicates, objects, etc. in a sentence.

[0984] "Emotion" refers to the psychological state (e.g., urgency, impatience, worry, etc.) contained within the user's text.

[0985] "Tone" refers to the nuances and style of language used in responses.

[0986] "Relevant information" refers to data and knowledge necessary to generate an answer to a user's question.

[0987] "Childcare agency services" refer to external services that provide support such as temporary childcare and transportation.

[0988] The above are definitions of important terms included in the claims.

[0989] The present invention provides a system that quickly and accurately responds to childcare-related problems that users face on a daily basis. This system is characterized by incorporating an emotion engine that recognizes the user's emotions. Specific embodiments are described below.

[0990] A user inputs a question into the system using a terminal (a device such as a smartphone or PC). For example, a user might ask, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This input is sent to the server via the terminal.

[0991] The server receives a user's question and analyzes it using a natural language processing engine (e.g., spaCy, NLTK). This analysis involves tokenizing the text, extracting subjects, predicates, and objects, and then using an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions in the question, such as urgency, impatience, or worry, and adjusts the analysis results accordingly.

[0992] Based on the analysis and emotion recognition results, the server classifies the question into an appropriate category (e.g., health-related). The server then searches for information from databases or external APIs (e.g., Google Maps API) related to that category. If the question is health-related, the server searches for information about the nearest emergency clinic or emergency response advice. The search results are quickly retrieved and passed on to subsequent processing steps.

[0993] Based on the acquired information, the server generates a specific response for the user. This response can be based on a fixed template or a customized message. For example, the response might be, "The nearest emergency clinic is XX Hospital. If your symptoms worsen, please call an ambulance." The tone and content of the response are also adjusted appropriately based on the results of the emotion engine.

[0994] If necessary, the server arranges for additional services. If the emotion engine recognizes a high level of urgency, related services (for example, arranging for an ambulance) are given priority. If a user asks, "I'm going to be late to pick up my child from daycare due to an emergency. Can someone pick me up for me?", the server searches for related childcare services and proceeds with the arrangements.

[0995] Finally, the server sends the generated answer and the status of the service arrangement to the user's device. The device receives this and displays it to the user. The user can check the specific countermeasures and the services that have been arranged on the device. For example, if a user is feeling anxious and asks about childcare services, the device will display a list such as "Pick-up service is available. The available services are as follows," and notify the user in a reassuring tone.

[0996] The following are examples of prompt sentences:

[0997] "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?"

[0998] "I have a question about a child care issue that needs immediate attention. What steps should I take?"

[0999] The above is a specific embodiment of the present invention, and the system is capable of dealing with childcare-related issues quickly and accurately while taking into account the user's feelings.

[1000] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1001] Step 1:

[1002] A user uses a terminal to input a question into the system. The input is text data in natural language. For example, a question might be input like, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" The input question is sent to the server via the terminal. Specific actions on the terminal include entering text into a question input form and clicking the send button. Input: User's question text. Output: Sending question data to the server.

[1003] Step 2:

[1004] The server receives questions sent by users. The received question text is passed to a natural language processing engine for analysis. Specific analysis operations include tokenizing the text (breaking it down into words and phrases) and understanding the context (extracting the subject, predicate, and object). For example, information such as "child," "late night," "sudden fever," and "should an ambulance be called" is broken down and the meaning of each part is identified. Input: Received question text. Output: Tokenized text and context information.

[1005] Step 3:

[1006] The server uses an emotion engine to recognize the emotion contained in the question based on the analysis results obtained from the natural language processing engine. The emotion engine extracts emotional elements such as urgency, impatience, and worry, and adjusts the analysis results accordingly. Specifically, it uses an emotion analysis algorithm to evaluate text data and detect high levels of urgency or anxiety. Input: Tokenized text and contextual information. Output: Emotion recognition results.

[1007] Step 4:

[1008] The server classifies the question into an appropriate category based on the analysis and emotion recognition results. For example, the question is classified into the "health-related" category. The specific operation includes a process of matching the question with a predefined category list and selecting the category that best suits the question. Input: Analysis results and emotion recognition results. Output: Question category.

[1009] Step 5:

[1010] The server searches for information from relevant databases or external APIs depending on the question category. For example, if the question is health-related, it searches for information on the nearest emergency clinic after hours or advice on how to respond to an emergency. The specific operation involves sending a query to a database and retrieving the relevant information. Input: Question category. Output: Search results.

[1011] Step 6:

[1012] The server generates a specific answer based on the information obtained. This answer is based on a fixed template, but includes a customized message if necessary. The tone and content of the answer are adjusted appropriately based on the results of the emotion engine. For example, it generates a specific answer such as, "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance." Input: Search results and emotion recognition results. Output: Generated answer.

[1013] Step 7:

[1014] If necessary, the server will arrange for additional services. If the emotion engine recognizes a high level of urgency, it will prioritize related services (for example, arranging for an ambulance). For example, if a user asks, "I have an emergency and will be late to pick up my child from daycare. Can someone pick me up for me?", it will search for related childcare services and proceed with the arrangements. Input: Question and high-urgency emotion recognition result. Output: Arranged service.

[1015] Step 8:

[1016] Finally, the server sends the generated answer and the arrangement status to the user's terminal. The terminal receives this and displays it to the user. The user can check the specific countermeasures and the arranged services on the terminal. For example, in response to a user's question, a list such as "Pick-up service is available. Available services are as follows" can be displayed, providing a sense of security. Input: Generated answer and arrangement status. Output: Display of answer and arrangement status on the terminal.

[1017] (Application example 2)

[1018] 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."

[1019] Childcare issues are diverse, and it is necessary to respond promptly to users' anxieties and urgencies. Furthermore, it is necessary to provide appropriate services and information while taking into consideration the user's emotions. However, conventional systems are limited to simply providing information in response to users' questions, and it is difficult to provide comprehensive support that addresses the user's emotions or arranges specific services. This leads to delays in resolving childcare emergencies and everyday problems.

[1020] 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 recognizing the user's emotions and adjusting the analysis results, means for adjusting the tone and information of the proposal content based on the emotions, and means for extracting keywords, recognizing subjects, predicates, and objects, and analyzing emotions in question analysis and categorization. This makes it possible to provide appropriate answers and arrange services that are in line with the user's emotions.

[1021] The "means for receiving questions from the user" is a mechanism by which the system receives information and questions entered by the user.

[1022] "Means for analyzing questions using a natural language processing engine" refers to natural language processing technology used to handle text data received from users and understand their contents.

[1023] "Means for categorizing questions based on the analysis results" is a function that organizes the content of the analyzed questions into specific areas or categories.

[1024] "Means for searching related information from databases or external APIs according to question categories" refers to a method for collecting related information from internal and external data sources based on classified question categories.

[1025] "Means for generating an answer to the user based on the search results" refers to the process of creating an appropriate answer to the user based on the acquired information.

[1026] The "means for transmitting the generated answer to the user" refers to a means for transmitting the answer generated by the system to the user's terminal.

[1027] The "means for arranging related services as needed" is a function for executing additional services or arrangements according to the user's inquiries or circumstances.

[1028] "Means for recognizing the user's emotions and adjusting the analysis results" refers to a technology that analyzes the emotions contained in the user's question and adjusts the information provided or answer according to those emotions.

[1029] "Means for adjusting the tone and information of the proposed content based on the user's emotions" refers to a mechanism that appropriately changes the way the proposed content is expressed and the information provided to match the user's emotions.

[1030] "Keyword extraction" is a technique for extracting important words and phrases from a user's question.

[1031] "Subject-predicate-object recognition" is a technique for identifying and analyzing the components of a sentence: subject, predicate, and object.

[1032] "Sentiment analysis" is a technique for analyzing the type and intensity of emotions from text data.

[1033] A specific category such as "childcare support, education, health-related" is a classification that organizes the content of a user's question into a specific area, and includes areas related to childcare support, education, and health.

[1034] A system for carrying out the present invention accepts childcare consultations via a user's smartphone app and proposes appropriate childcare-related services and products. Detailed embodiments of this system are described below.

[1035] System Program

[1036] This system consists of a server and a user device (smartphone). When a user sends a question through a smartphone app, the data is sent to the server. The server analyzes the question and recognizes the user's emotions.

[1037] Hardware and software used

[1038] Server: The central computing unit that handles the backend of this system, primarily for data processing and analysis.

[1039] Smartphone: A device used by a user to enter questions and receive answers from the system.

[1040] Flask: A Python-based micro-web framework used to build server-side APIs.

[1041] Transformers: A natural language processing library provided by Hugging Face for sentiment analysis and question answering.

[1042] Data processing and calculation

[1043] 1. Receiving a question: The user enters a question into the smartphone app and sends it to the server.

[1044] 2. Natural Language Processing: The server uses the Transformers library to analyze the question, tokenize it, and extract the subject, predicate, and object.

[1045] 3. Emotion recognition: Extract the user's emotions from the analyzed questions and recognize the type of emotion (e.g., anxiety, impatience, etc.).

[1046] 4. Categorization and information retrieval: Based on the analysis results, the question is categorized appropriately and relevant information is retrieved from databases or external APIs. For example, if the question is about childcare support, information on appropriate childcare products and services is retrieved.

[1047] 5. Generate and send an answer: Based on the search results and emotion recognition results, an appropriate answer is generated and sent to the smartphone app.

[1048] Specific examples

[1049] Consider the case where a user asks the following question:

[1050] "My baby cries a lot at night. Are there any good products?"

[1051] The server receives this question, analyzes the question content and sentiment, and generates and sends the following answer as a result of the analysis:

[1052] "We will suggest products that will help you get your baby to sleep. You seem to be worried, but baby carriers and stuffed toys that help you get your baby to sleep are effective. You can check them out in store."

[1053] This system allows users to receive specific suggestions that are in line with their emotions, enabling them to quickly resolve their child-rearing concerns.

[1054] Prompt statement

[1055] Below are some example prompts to input to the generative AI model:

[1056] "I'm having trouble getting my baby to sleep. What products do I need?"

[1057] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1058] Step 1:

[1059] A user enters a question using a smartphone app. The entered question data is sent from the smartphone to a server. The input is the text that the user enters into the app, and the output is the text data sent to the server. The specific action performed at this stage is for the user to enter a question in the text box and tap the "Send" button.

[1060] Step 2:

[1061] The server passes the received question data to a natural language processing engine (Transformers library) and analyzes the question. Specifically, the process tokenizes the text and extracts the subject, predicate, and object. The input is the text data received from the user, and the output is the analyzed text structure.

[1062] Step 3:

[1063] The server passes the analysis results to an emotion recognition engine to recognize the user's emotions. The input is the analyzed text structure, and the output is the recognized emotion information (e.g., anxiety, impatience, etc.). The specific operation is that the emotion recognition engine analyzes the text data and generates an emotion score.

[1064] Step 4:

[1065] The server classifies questions into appropriate categories based on the analysis and emotion recognition results. The input is the analyzed text structure and emotion information, and the output is a category label (e.g., parenting support, health-related, etc.). Specifically, the classification algorithm determines the category based on the text data and emotion score.

[1066] Step 5:

[1067] The server searches for relevant information from a database or external API according to the question category. The input is a category label, and the output is related information data (e.g., product list, service information, etc.). The specific operation is to execute a database query or API call to obtain information.

[1068] Step 6:

[1069] The server generates a response for the user based on the search results and emotion recognition results. The input is related information data and emotion scores, and the output is a customized response text. The specific operation is that a template or customized message generation engine creates a response based on the information.

[1070] Step 7:

[1071] The server sends the generated answer to the user's smartphone app. The input is the generated answer text, and the output is the answer message displayed on the smartphone. The specific operation is data transmission from the server to the smartphone app. The user can check the sent answer on the app and take action based on the suggested product or service information.

[1072] 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.

[1073] 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.

[1074] 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.

[1075] [Fourth embodiment]

[1076] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1077] 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.

[1078] 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).

[1079] 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.

[1080] 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.

[1081] 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).

[1082] 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. 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.

[1083] 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.

[1084] 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.

[1085] 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.

[1086] 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.

[1087] 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.

[1088] 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."

[1089] The system of the present invention is a system for quickly and accurately responding to childcare-related problems that users face on a daily basis. This system has the function of receiving and analyzing questions from users, and providing optimal answers and arranging services. Specific embodiments of the system are described below.

[1090] 1. Receiving questions from users

[1091] First, a user uses a terminal (a device such as a smartphone or PC) to input a question to the system. For example, a user might ask, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This question is sent to the server via the terminal.

[1092] 2. Question analysis and classification

[1093] The server receives the user's question and analyzes it using a natural language processing engine. This analysis involves tokenizing the text, extracting subjects, predicates, and objects, and analyzing sentiment. Based on this information, the server classifies the question into an appropriate category. For example, a question like "My child suddenly developed a fever in the middle of the night" would be classified as a health-related category.

[1094] 3. Information Search

[1095] After parsing and classification is complete, the server searches for information from databases or external APIs related to the relevant category. For health-related questions, it searches for information on the nearest emergency clinic or emergency response advice. The search results are quickly retrieved and passed on to subsequent processing steps.

[1096] 4. Answer Generation

[1097] Based on the information obtained, the server generates a specific answer for the user. This answer can be based on a fixed template or a customized message. For example, the server might generate an answer like, "The nearest emergency clinic is at XX Hospital. If your symptoms worsen, please call an ambulance."

[1098] 5. Arrangements for Service

[1099] If necessary, the server arranges for additional services. For example, if a user asks, "I have an emergency and will be late to pick up my child from daycare. Can someone pick me up?", the server searches for relevant childcare services and proceeds with the arrangements.

[1100] 6. Sending the response to the user

[1101] Finally, the server sends the generated response and the status of the service arrangement to the user's device, which receives it and displays it to the user. The user can then check the specific countermeasures and the arranged services on the device.

[1102] For example, if a user asks about childcare services, the terminal displays a list such as "Pick-up services are available. Available services are listed below."

[1103] ---

[1104] The components of this system work together to enable quick and accurate responses to user questions. This invention enables effective responses to everyday childcare problems and emergencies.

[1105] The processing flow will be explained below.

[1106] Step 1: User enters question

[1107] A user uses a terminal to input and send a question, for example, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?"

[1108] Step 2: The device sends a question

[1109] The terminal transmits the input question data to the server.

[1110] Step 3: The server receives the query

[1111] The server receives the query data from the terminal.

[1112] Step 4: The server parses the question

[1113] The server analyzes the received question using a natural language processing engine to extract important keywords (e.g., "child," "fever," "ambulance") and contextual information.

[1114] Step 5: The server categorizes the question

[1115] The server classifies the question into an appropriate category (e.g., "health-related") based on the analysis results.

[1116] Step 6: The server searches for relevant information

[1117] Depending on the question category, the server searches for relevant information from internal databases or external APIs, such as the nearest emergency clinic or emergency response guidelines.

[1118] Step 7: The server aggregates the search results

[1119] The server aggregates the search results it has obtained and organizes them into a series of information to provide to the user.

[1120] Step 8: Server Generates Answer

[1121] The server generates an answer to provide to the user based on the organized information. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[1122] Step 9: The server considers arranging for service.

[1123] The server determines the need for additional services (e.g., dispatching an ambulance) based on the user's question.

[1124] Step 10: The server arranges for related services

[1125] If necessary, the server may request an ambulance from a service provider that it works with.

[1126] Step 11: Server sends response

[1127] The server sends the generated response and the arranged service information to the user's terminal.

[1128] Step 12: The device notifies the user of the answer

[1129] The device notifies the user of the received response and service information and displays it on the screen. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[1130] Example 1

[1131] 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."

[1132] In childcare, users often face many problems and emergencies on a daily basis. Accessing information and services that allow them to quickly and appropriately respond to these issues is important to users, and effective methods are needed to improve the quality of childcare support. However, current systems have issues with difficulty responding promptly to user questions, and the efficiency of information retrieval and answer generation is low. Furthermore, they often fail to properly assess the specificity and urgency of questions and respond accordingly.

[1133] 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.

[1134] In this invention, the server includes means for receiving questions from users, means for analyzing the questions with a natural language processing engine, means for categorizing the questions based on the analysis results, means for searching for related information from a database or an external API according to the question category, means for generating answers to the users based on the search results, means for sending the generated answers to the users, means for arranging related services as needed, and means for tokenization, extracting subjects, predicates, and objects, and performing sentiment analysis. This enables a system that can respond quickly and accurately to user questions.

[1135] The "means for receiving questions from users" refers to the technical means by which the server receives questions from users sent from terminals.

[1136] "Means for analyzing questions using a natural language processing engine" refers to technical means for performing tokenization, grammar analysis, sentiment analysis, etc. on questions received by the server using natural language processing technology.

[1137] "Means for categorizing questions based on analysis results" refers to technical means for categorizing questions into predefined categories (e.g., health, childcare, education, etc.) based on analysis results obtained through natural language processing.

[1138] "Means for searching for relevant information from databases or external APIs according to question categories" refers to technical means for searching for relevant information from internal databases or external APIs based on the category into which a question is classified.

[1139] "Means for generating answers to users based on search results" refers to technical means for automatically generating specific answers based on information obtained from searches.

[1140] The "means for transmitting the generated answer to the user" refers to the technical means for transmitting the answer generated by the server to the user's terminal and displaying it.

[1141] The "means for arranging related services as needed" refers to a technical means for searching for and arranging additional related services based on the content of the user's inquiry.

[1142] "Tokenization" is a natural language processing process that breaks up the text of a question into words and phrases.

[1143] "Means for extracting subjects, predicates, and objects" refers to technical means for analyzing the grammatical structure of a question and identifying the subject, predicate, and object therefrom.

[1144] "Means for performing sentiment analysis" refers to technical means for assessing the user's sentiment and urgency from the question text.

[1145] The system of the present invention is designed to quickly and accurately respond to childcare-related problems that users face on a daily basis. This system uses various technical means to receive and analyze questions from users and provide optimal answers and service arrangements. Specific embodiments of the system are described below.

[1146] First, a user inputs a question into the system using a device such as a smartphone or PC. The input question is sent to the server via the device. For example, a user might input a question such as, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This question is sent to the server.

[1147] The server then uses a natural language processing engine (e.g., SpaCy, NLTK) to parse the received question. This involves tokenizing the text, extracting subjects, predicates, and objects, and performing sentiment analysis. This process helps understand the content and urgency of the question and categorize it into the appropriate category (e.g., health, parenting, education, etc.).

[1148] For each classified question, the server searches for relevant information from databases or external APIs (e.g., Google Maps API, medical data API). For example, if the user's question is about health, it will search for information on the nearest emergency clinics and emergency response guidelines. Based on the information obtained, the server generates a specific answer. This answer can be based on a fixed template or a customized message format.

[1149] The generated answer is sent from the server to the user's device, where the user receives it and checks it. For example, it displays specific countermeasures such as, "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[1150] If necessary, the server can also arrange for related services. For example, if a user asks, "I have an emergency and will be late to pick up my child from daycare. Can someone pick me up for me?", the server will search for related childcare services and proceed with the arrangements.

[1151] The system's components work together to provide users with fast and accurate responses, allowing them to effectively respond to everyday parenting issues and emergencies.

[1152] For example, if a user asks "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?", the server analyzes the question and classifies it into a health category. The server then searches for information on night-time emergency clinics and generates a response such as "The nearest night-time emergency clinic is XX Hospital. If the symptoms worsen, please call an ambulance." and sends it to the user's device.

[1153] Example prompt sentence:

[1154] What is the appropriate response when a user asks, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" Please generate an answer that includes information about night clinics and emergency procedures.

[1155] This system allows users to deal with childcare-related issues quickly and accurately, thereby improving the quality of childcare support.

[1156] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1157] Step 1: User enters question

[1158] The user uses a device (smartphone or PC) to input a question into the system. For example, they might input a question like, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" The device then sends the user's input data to the server.

[1159] Input: Question text from user

[1160] Output: Sending the query data to the server

[1161] Specific operation: The user enters a question into the terminal application or web interface and presses the send button.

[1162] Step 2: The server receives and analyzes the query

[1163] The server receives the question sent from the device and analyzes it using a natural language processing engine (e.g., SpaCy, NLTK). The analysis involves tokenizing the text, extracting subjects, predicates, and objects, and analyzing sentiment.

[1164] Input: Question data sent from the terminal

[1165] Output: Analysis data (tokenization, subject, predicate, object, sentiment analysis results)

[1166] Specific operation: The server receives the question data and passes it to the natural language processing engine for analysis.

[1167] Step 3: Server classifies the question

[1168] Based on the analysis results, the server classifies the question into an appropriate category (e.g., health, childcare, education, etc.) and prepares to search for appropriate information according to the category.

[1169] Input: Analysis data

[1170] Output: Question category

[1171] Specific operation: The server classifies questions into categories such as "health" or "childcare" based on the results of subject, predicate, object, and sentiment analysis.

[1172] Step 4: Server Looks Up Information

[1173] Based on the question category, the server searches for relevant information from internal databases or external APIs (e.g., Google Maps API, medical data API). For example, for the health category, the server searches for information on the nearest emergency clinics.

[1174] Input: Question Category

[1175] Output: Related information (e.g., a list of emergency clinics open overnight)

[1176] Specific operation: The server sends a query to a database or external API to obtain the necessary information.

[1177] Step 5: Server Generates Answer

[1178] The server uses the information obtained from the search to generate specific answers for the user, which can be in the form of fixed templates or customized messages.

[1179] Input: Related Information

[1180] Output: Specific answer

[1181] Specific operation: The server uses the template to generate a response such as, "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[1182] Step 6: Arranging for service by the server

[1183] If necessary, the server arranges for additional services, for example, if the user wants to use childcare services, it searches for and arranges for relevant service providers.

[1184] Input: Add user request

[1185] Output: Arranged service information

[1186] Specific operation: The server searches for information on relevant service providers and makes reservations and arrangements for services on behalf of the user.

[1187] Step 7: Server sends response to user

[1188] The server sends the generated response and the status of the arranged service to the user's terminal, where the user receives and checks it.

[1189] Input: Generated answers, arranged service information

[1190] Output: Notification to user terminal

[1191] Specific operation: The server sends the answer to the user's device, which displays it. For example, it displays a list such as "Pick-up service is available. Available services are listed below."

[1192] This system allows users to respond quickly and accurately to child-rearing-related issues, enabling them to receive smooth child-rearing support.

[1193] (Application example 1)

[1194] 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."

[1195] When users encounter childcare-related issues, there is still no system in place to quickly and accurately respond to those issues. In particular, there is a lack of systems to assist users in selecting childcare products and arranging appropriate services in physical stores. As a result, users have to spend a lot of time and effort searching for information and finding the best products and services themselves.

[1196] 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.

[1197] In this invention, the server includes means for receiving questions from users, means for analyzing the questions with a natural language processing engine, means for categorizing the questions based on the analysis results, means for searching for related information from a database or external API according to the question category, means for generating an answer to the user based on the search results, means for sending the generated answer to the user, means for arranging related services as needed, and means for searching for products and services based on the user's question and providing information on corresponding products in physical stores. This enables even busy parents to respond quickly and accurately to child-rearing-related issues.

[1198] The "means for receiving questions from users" is a function for sending questions input by users via their terminals to the server.

[1199] "Means for analyzing questions using a natural language processing engine" refers to a function that analyzes input questions using natural language processing technology and converts them into structured information.

[1200] The "means for classifying questions into categories based on the analysis results" is a function for classifying the analyzed question content into predetermined categories and associating them with specific domains.

[1201] "Means of searching for relevant information from databases or external APIs according to question categories" refers to a function that retrieves relevant information from an internal database or external API service based on classified categories.

[1202] The "means for generating a response to the user based on the search results" is a function for generating a specific response to be provided to the user based on the acquired information.

[1203] The "means for transmitting the generated answer to the user" is a function for transferring the generated answer to the user's terminal and displaying it.

[1204] The "means for arranging related services as needed" is a function for arranging additional services (for example, childcare support or emergency response) based on the user's request and managing the status of the arrangement.

[1205] "A means for searching for products and services based on a user's question and providing relevant product information in physical stores" is a function that searches for related products and services in physical stores based on the question entered by the user and provides the user with relevant information.

[1206] The present invention is a system for quickly and accurately dealing with childcare-related problems. Detailed embodiments of the present invention will be described below.

[1207] 1. System Configuration

[1208] This system consists of user terminals, a server, a database, and an external API. User terminals include mobile devices such as smartphones and tablets. The server plays a central role in performing advanced data processing and calculations.

[1209] 2. Hardware and Software

[1210] Hardware: Smartphones (iOS / Android devices), tablets, servers

[1211] software:

[1212] Natural language processing libraries (Google Cloud Natural Language API, spaCy, NLTK, etc.)

[1213] Product information database (Firebase, MySQL, etc.)

[1214] Push notification service (Firebase Cloud Messaging)

[1215] User Interface (React Native)

[1216] 3. System Implementation

[1217] 1. Receiving questions from users

[1218] A user uses a smartphone or tablet to voice or text a question into the application.

[1219] 2. Question Analysis

[1220] The server analyzes the input question using a natural language processing engine (e.g., Google Cloud Natural Language API), performing tokenization, part-of-speech tagging, and sentiment analysis.

[1221] 3. Question Classification

[1222] Based on the analysis, the server categorizes the questions into specific categories, such as health-related, childcare support-related, education-related, etc.

[1223] 4. Information Search

[1224] The server searches for related information from databases or external APIs according to the category. For example, if the question is about childcare products, it searches for the relevant product from a product information database.

[1225] 5. Answer Generation

[1226] Based on the search results, the server generates specific answers for the user, including standard phrases and customized messages.

[1227] 6. Submit your response

[1228] The generated answer is sent from the server to the user's terminal and displayed on the user's terminal.

[1229] 7. Arrangement of related services

[1230] If necessary, the server arranges for additional services (e.g., childcare or emergency response), and this information is sent to the user's device.

[1231] 4. Specific Examples

[1232] When a user asks the app, "What is the appropriate size of diaper?", the system analyzes the question and provides the most appropriate product information (e.g., for newborns, medium-sized diapers, etc.) along with the location of the item in the store. It also provides advice on how to choose the right size based on the baby's weight and age.

[1233] 5. Examples of prompts

[1234] What is the correct size of diaper?

[1235] As described above, the system of the present invention quickly and accurately analyzes user questions about child-rearing and provides optimal information and service arrangements, thereby reducing the burden on users even in physical stores and realizing efficient child-rearing support.

[1236] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1237] Step 1:

[1238] The user inputs a question into the terminal.

[1239] Input: The user uses a smartphone or tablet to enter a question using text or voice.

[1240] What happens: The application receives user input and sends that data to the server for analysis.

[1241] Step 2:

[1242] The server analyzes the entered question.

[1243] Input: User question text data sent from the terminal.

[1244] What it does: The server uses a natural language processing engine (e.g., Google Cloud Natural Language API) to tokenize the question and perform part-of-speech tagging, subject-predicate-object recognition, and sentiment analysis.

[1245] Output: Parsed structured data of the question.

[1246] Step 3:

[1247] The server categorizes the questions based on the analysis results.

[1248] Input: Parsed question structured data.

[1249] What it does: The server uses the analysis results to apply an algorithm that categorizes the question into the appropriate category (e.g., childcare support, health-related, education, etc.).

[1250] Output: Categorized question data.

[1251] Step 4:

[1252] The server searches for information according to the question category.

[1253] Input: Categorized question data.

[1254] What it does: The server uses internal databases (e.g., Firebase, MySQL) and external APIs (e.g., Google Places API) to find the information most relevant to the question.

[1255] Output: Search result data.

[1256] Step 5:

[1257] The server generates an answer for the user based on the search results.

[1258] Input: Search result data.

[1259] Specific Action: The server generates a specific response using a template-based approach or an algorithm that generates customized messages.

[1260] Output: The generated response data.

[1261] Step 6:

[1262] The server generates a response and sends it to the user.

[1263] Input: The generated response data.

[1264] Specific operation: The server sends the generated answer to the user's device and notifies them via push notification or in-app message.

[1265] Output: The answer displayed on the user's terminal.

[1266] Step 7:

[1267] The server arranges for related services as needed.

[1268] Input: User request or additional information.

[1269] Specific operation: The server arranges related services and manages the arrangement status. Service arrangement includes API calls and staff notifications.

[1270] Output: Notification of order status and feedback of service execution status.

[1271] Through the above steps, the system can quickly and accurately provide childcare-related information and arrange services based on questions entered by the user.

[1272] 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.

[1273] The system of the present invention is a system for quickly and accurately responding to childcare-related problems that users face on a daily basis, and is characterized by incorporating an emotion engine that recognizes the user's emotions. This system has the function of receiving and analyzing questions from users, recognizing their emotions, and providing optimal answers and arranging services. Specific embodiments of the system are described below.

[1274] 1. Receiving questions from users

[1275] First, a user uses a terminal (a device such as a smartphone or PC) to input a question to the system. For example, a user might ask, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This question is sent to the server via the terminal.

[1276] 2. Question Analysis and Emotion Recognition

[1277] The server receives the user's question and analyzes it using a natural language processing engine. This analysis involves tokenizing the text, extracting subjects, predicates, and objects, and then using an emotion engine to recognize emotions contained in the question (e.g., urgency, impatience, worry, etc.) and adjust the analysis results accordingly.

[1278] 3. Question classification and information search

[1279] Based on the emotion recognition and analysis results, the server classifies the question into an appropriate category (e.g., health-related). The server then searches for information from databases or external APIs related to that category. If the question is health-related, it searches for information on the nearest emergency clinic or emergency response advice. The search results are quickly retrieved and passed on to subsequent processing steps.

[1280] 4. Answer generation and emotion-based adjustment

[1281] Based on the acquired information, the server generates a specific response for the user. This response can be based on a fixed template or a customized message. For example, the response might be, "The nearest emergency clinic is XX Hospital. If your symptoms worsen, please call an ambulance." The tone and content of the response are also adjusted appropriately based on the results of the emotion engine.

[1282] 5. Arranging for service and determining the level of urgency

[1283] If necessary, the server arranges for additional services. If the emotion engine recognizes a high level of urgency, related services (for example, arranging for an ambulance) are given priority. If a user asks, "I'm going to be late to pick up my child from daycare due to an emergency. Can someone pick me up for me?", the server searches for related childcare services and proceeds with the arrangements.

[1284] 6. Sending the response to the user

[1285] Finally, the server sends the generated response and the status of the service arrangement to the user's device, which receives it and displays it to the user. The user can then check the specific countermeasures and the arranged services on the device.

[1286] For example, if a user becomes anxious and asks about childcare services, the device will display a list such as, "Pick-up services are available. Available services are listed below," and notify the user in a reassuring tone.

[1287] ---

[1288] Each component of this system also includes an emotion engine, which enables it to respond quickly and accurately to user questions and provide appropriate services that take emotions into consideration. This invention enables effective responses to everyday childcare troubles and emergencies while recognizing the user's emotions.

[1289] The processing flow will be explained below.

[1290] Step 1: User enters question

[1291] A user uses a terminal to input and send a question, for example, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?"

[1292] Step 2: The device sends a question

[1293] The terminal transmits the input question data to the server.

[1294] Step 3: The server receives the query

[1295] The server receives the query data from the terminal.

[1296] Step 4: The server parses the question

[1297] The server analyzes the received question using a natural language processing engine to extract important keywords (e.g., "child," "fever," "ambulance") and contextual information.

[1298] Step 5: The server recognizes the user's emotion

[1299] The server uses an emotion engine to recognize the emotion (e.g., "worry" or "urgency") contained in the question.

[1300] Step 6: The server categorizes the question

[1301] The server classifies the question into an appropriate category (e.g., "health-related") based on the analysis and emotion recognition results.

[1302] Step 7: The server searches for relevant information

[1303] Depending on the question category, the server searches for relevant information from internal databases or external APIs, for example, the nearest emergency clinic or emergency response guidelines.

[1304] Step 8: The server aggregates the search results

[1305] The server aggregates the search results it has obtained and organizes them into a series of information to provide to the user.

[1306] Step 9: Server Generates Answer

[1307] The server generates an answer to provide to the user based on the organized information. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[1308] Step 10: The server adjusts the answer based on the sentiment

[1309] The server then adjusts the tone and content of the generated response appropriately based on the emotion recognition results. For example, if the emotion is strong, it may include additional advice such as, "Don't worry, here's how to deal with it first."

[1310] Step 11: The server considers arranging for service

[1311] The server determines the need for additional services (e.g., dispatching an ambulance) based on the user's question and the emotion recognition results.

[1312] Step 12: The server arranges for related services

[1313] If necessary, the server may request an ambulance from a service provider that it works with.

[1314] Step 13: The server sends the response and the dispatch result.

[1315] The server sends the generated response and the arranged service information to the user's terminal.

[1316] Step 14: The device notifies the user of the answer

[1317] The device notifies the user of the received response and service information and displays it on the screen. Example: "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance."

[1318] Example 2

[1319] 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."

[1320] In today's childcare environment, parents face a variety of problems. Many of these problems are highly urgent and involve emotional stress. However, conventional systems have had difficulty accurately capturing users' emotions and responding quickly and appropriately. In particular, there is a demand for systems that can recognize emotions and respond to childcare-related worries and emergencies. Therefore, the challenge is to provide a childcare support system that can take users' emotions into consideration and provide optimal services.

[1321] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1322] In this invention, the server includes means for receiving questions from users, means for analyzing the questions with a natural language processing engine, means for categorizing the questions based on the analysis results, means for searching for related information from a database or an external API according to the question category, means for generating answers to the users based on the search results, means for sending the generated answers to the users, means for arranging related services as needed, means for recognizing emotions contained in the questions using an emotion engine, and means for adjusting the tone and content of the answers based on the recognized emotions. This makes it possible to respond to child-rearing issues quickly and accurately while taking the user's emotions into consideration.

[1323] "User" refers to an individual who uses this system to enter questions and receive answers and services.

[1324] "Terminal" refers to the device (smartphone, PC, etc.) that a user uses to enter a question.

[1325] "Server" refers to a computer system that receives questions from users and performs processes such as analysis, classification, answer generation, and service arrangement.

[1326] A "natural language processing engine" refers to software that analyzes questions entered by users and performs tasks such as understanding grammatical structures and tokenizing them.

[1327] An "emotion engine" refers to software that recognizes and analyzes the emotions contained in users' questions.

[1328] "Category" refers to various classifications based on the content of the user's question (e.g., health, education, childcare, etc.).

[1329] A "database" refers to a collection of related information that is stored, managed, and provided in a searchable format.

[1330] An "external API" refers to a program interface for obtaining information in collaboration with other systems or services.

[1331] "Answer" refers to specific information or advice that the system generates in response to a user's question.

[1332] "Service arrangement" refers to the procedure for providing additional support or services based on the user's question and emotion recognition results.

[1333] "Tokenization" refers to the process in natural language processing of dividing input text into semantic units.

[1334] "Grammatical structure" refers to structural analysis that analyzes the relationships between subjects, predicates, objects, etc. in a sentence.

[1335] "Emotion" refers to the psychological state (e.g., urgency, impatience, worry, etc.) contained within the user's text.

[1336] "Tone" refers to the nuances and style of language used in responses.

[1337] "Relevant information" refers to data and knowledge necessary to generate an answer to a user's question.

[1338] "Childcare agency services" refer to external services that provide support such as temporary childcare and transportation.

[1339] The above are definitions of important terms included in the claims.

[1340] The present invention provides a system that quickly and accurately responds to childcare-related problems that users face on a daily basis. This system is characterized by incorporating an emotion engine that recognizes the user's emotions. Specific embodiments are described below.

[1341] A user inputs a question into the system using a terminal (a device such as a smartphone or PC). For example, a user might ask, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" This input is sent to the server via the terminal.

[1342] The server receives a user's question and analyzes it using a natural language processing engine (e.g., spaCy, NLTK). This analysis involves tokenizing the text, extracting subjects, predicates, and objects, and then using an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions in the question, such as urgency, impatience, or worry, and adjusts the analysis results accordingly.

[1343] Based on the analysis and emotion recognition results, the server classifies the question into an appropriate category (e.g., health-related). The server then searches for information from databases or external APIs (e.g., Google Maps API) related to that category. If the question is health-related, the server searches for information about the nearest emergency clinic or emergency response advice. The search results are quickly retrieved and passed on to subsequent processing steps.

[1344] Based on the acquired information, the server generates a specific response for the user. This response can be based on a fixed template or a customized message. For example, the response might be, "The nearest emergency clinic is XX Hospital. If your symptoms worsen, please call an ambulance." The tone and content of the response are also adjusted appropriately based on the results of the emotion engine.

[1345] If necessary, the server arranges for additional services. If the emotion engine recognizes a high level of urgency, related services (for example, arranging for an ambulance) are given priority. If a user asks, "I'm going to be late to pick up my child from daycare due to an emergency. Can someone pick me up for me?", the server searches for related childcare services and proceeds with the arrangements.

[1346] Finally, the server sends the generated answer and the status of the service arrangement to the user's device. The device receives this and displays it to the user. The user can check the specific countermeasures and the services that have been arranged on the device. For example, if a user is feeling anxious and asks about childcare services, the device will display a list such as "Pick-up service is available. The available services are as follows," and notify the user in a reassuring tone.

[1347] The following are examples of prompt sentences:

[1348] "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?"

[1349] "I have a question about a child care issue that needs immediate attention. What steps should I take?"

[1350] The above is a specific embodiment of the present invention, and the system is capable of dealing with childcare-related issues quickly and accurately while taking into account the user's feelings.

[1351] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1352] Step 1:

[1353] A user uses a terminal to input a question into the system. The input is text data in natural language. For example, a question might be input like, "My child suddenly developed a fever in the middle of the night. Should I call an ambulance?" The input question is sent to the server via the terminal. Specific actions on the terminal include entering text into a question input form and clicking the send button. Input: User's question text. Output: Sending question data to the server.

[1354] Step 2:

[1355] The server receives questions sent by users. The received question text is passed to a natural language processing engine for analysis. Specific analysis operations include tokenizing the text (breaking it down into words and phrases) and understanding the context (extracting the subject, predicate, and object). For example, information such as "child," "late night," "sudden fever," and "should an ambulance be called" is broken down and the meaning of each part is identified. Input: Received question text. Output: Tokenized text and context information.

[1356] Step 3:

[1357] The server uses an emotion engine to recognize the emotion contained in the question based on the analysis results obtained from the natural language processing engine. The emotion engine extracts emotional elements such as urgency, impatience, and worry, and adjusts the analysis results accordingly. Specifically, it uses an emotion analysis algorithm to evaluate text data and detect high levels of urgency or anxiety. Input: Tokenized text and contextual information. Output: Emotion recognition results.

[1358] Step 4:

[1359] The server classifies the question into an appropriate category based on the analysis and emotion recognition results. For example, the question is classified into the "health-related" category. The specific operation includes a process of matching the question with a predefined category list and selecting the category that best suits the question. Input: Analysis results and emotion recognition results. Output: Question category.

[1360] Step 5:

[1361] The server searches for information from relevant databases or external APIs depending on the question category. For example, if the question is health-related, it searches for information on the nearest emergency clinic after hours or advice on how to respond to an emergency. The specific operation involves sending a query to a database and retrieving the relevant information. Input: Question category. Output: Search results.

[1362] Step 6:

[1363] The server generates a specific answer based on the information obtained. This answer is based on a fixed template, but includes a customized message if necessary. The tone and content of the answer are adjusted appropriately based on the results of the emotion engine. For example, it generates a specific answer such as, "The nearest emergency clinic at night is XX Hospital. If your symptoms worsen, please call an ambulance." Input: Search results and emotion recognition results. Output: Generated answer.

[1364] Step 7:

[1365] If necessary, the server will arrange for additional services. If the emotion engine recognizes a high level of urgency, it will prioritize related services (for example, arranging for an ambulance). For example, if a user asks, "I have an emergency and will be late to pick up my child from daycare. Can someone pick me up for me?", it will search for related childcare services and proceed with the arrangements. Input: Question and high-urgency emotion recognition result. Output: Arranged service.

[1366] Step 8:

[1367] Finally, the server sends the generated answer and the arrangement status to the user's terminal. The terminal receives this and displays it to the user. The user can check the specific countermeasures and the arranged services on the terminal. For example, in response to a user's question, a list such as "Pick-up service is available. Available services are as follows" can be displayed, providing a sense of security. Input: Generated answer and arrangement status. Output: Display of answer and arrangement status on the terminal.

[1368] (Application example 2)

[1369] 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."

[1370] Childcare issues are diverse, and it is necessary to respond promptly to users' anxieties and urgencies. Furthermore, it is necessary to provide appropriate services and information while taking into consideration the user's emotions. However, conventional systems are limited to simply providing information in response to users' questions, and it is difficult to provide comprehensive support that addresses the user's emotions or arranges specific services. This leads to delays in resolving childcare emergencies and everyday problems.

[1371] 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 recognizing the user's emotions and adjusting the analysis results, means for adjusting the tone and information of the proposal content based on the emotions, and means for extracting keywords, recognizing subjects, predicates, and objects, and analyzing emotions in question analysis and categorization. This makes it possible to provide appropriate answers and arrange services that are in line with the user's emotions.

[1372] The "means for receiving questions from the user" is a mechanism by which the system receives information and questions entered by the user.

[1373] "Means for analyzing questions using a natural language processing engine" refers to natural language processing technology used to handle text data received from users and understand their contents.

[1374] "Means for categorizing questions based on the analysis results" is a function that organizes the content of the analyzed questions into specific areas or categories.

[1375] "Means for searching related information from databases or external APIs according to question categories" refers to a method for collecting related information from internal and external data sources based on classified question categories.

[1376] "Means for generating an answer to the user based on the search results" refers to the process of creating an appropriate answer to the user based on the acquired information.

[1377] The "means for transmitting the generated answer to the user" refers to a means for transmitting the answer generated by the system to the user's terminal.

[1378] The "means for arranging related services as needed" is a function for executing additional services or arrangements according to the user's inquiries or circumstances.

[1379] "Means for recognizing the user's emotions and adjusting the analysis results" refers to a technology that analyzes the emotions contained in the user's question and adjusts the information provided or answer according to those emotions.

[1380] "Means for adjusting the tone and information of the proposed content based on the user's emotions" refers to a mechanism that appropriately changes the way the proposed content is expressed and the information provided to match the user's emotions.

[1381] "Keyword extraction" is a technique for extracting important words and phrases from a user's question.

[1382] "Subject-predicate-object recognition" is a technique for identifying and analyzing the components of a sentence: subject, predicate, and object.

[1383] "Sentiment analysis" is a technique for analyzing the type and intensity of emotions from text data.

[1384] A specific category such as "childcare support, education, health-related" is a classification that organizes the content of a user's question into a specific area, and includes areas related to childcare support, education, and health.

[1385] A system for carrying out the present invention accepts childcare consultations via a user's smartphone app and proposes appropriate childcare-related services and products. Detailed embodiments of this system are described below.

[1386] System Program

[1387] This system consists of a server and a user device (smartphone). When a user sends a question through a smartphone app, the data is sent to the server. The server analyzes the question and recognizes the user's emotions.

[1388] Hardware and software used

[1389] Server: The central computing unit that handles the backend of this system, primarily for data processing and analysis.

[1390] Smartphone: A device used by a user to enter questions and receive answers from the system.

[1391] Flask: A Python-based micro-web framework used to build server-side APIs.

[1392] Transformers: A natural language processing library provided by Hugging Face for sentiment analysis and question answering.

[1393] Data processing and calculation

[1394] 1. Receiving a question: The user enters a question into the smartphone app and sends it to the server.

[1395] 2. Natural Language Processing: The server uses the Transformers library to analyze the question, tokenize it, and extract the subject, predicate, and object.

[1396] 3. Emotion recognition: Extract the user's emotions from the analyzed questions and recognize the type of emotion (e.g., anxiety, impatience, etc.).

[1397] 4. Categorization and information retrieval: Based on the analysis results, the question is categorized appropriately and relevant information is retrieved from databases or external APIs. For example, if the question is about childcare support, information on appropriate childcare products and services is retrieved.

[1398] 5. Generate and send an answer: Based on the search results and emotion recognition results, an appropriate answer is generated and sent to the smartphone app.

[1399] Specific examples

[1400] Consider the case where a user asks the following question:

[1401] "My baby cries a lot at night. Are there any good products?"

[1402] The server receives this question, analyzes the question content and sentiment, and generates and sends the following answer as a result of the analysis:

[1403] "We will suggest products that will help you get your baby to sleep. You seem to be worried, but baby carriers and stuffed toys that help you get your baby to sleep are effective. You can check them out in store."

[1404] This system allows users to receive specific suggestions that are in line with their emotions, enabling them to quickly resolve their child-rearing concerns.

[1405] Prompt statement

[1406] Below are some example prompts to input to the generative AI model:

[1407] "I'm having trouble getting my baby to sleep. What products do I need?"

[1408] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1409] Step 1:

[1410] A user enters a question using a smartphone app. The entered question data is sent from the smartphone to a server. The input is the text that the user enters into the app, and the output is the text data sent to the server. The specific action performed at this stage is for the user to enter a question in the text box and tap the "Send" button.

[1411] Step 2:

[1412] The server passes the received question data to a natural language processing engine (Transformers library) and analyzes the question. Specifically, the process tokenizes the text and extracts the subject, predicate, and object. The input is the text data received from the user, and the output is the analyzed text structure.

[1413] Step 3:

[1414] The server passes the analysis results to an emotion recognition engine to recognize the user's emotions. The input is the analyzed text structure, and the output is the recognized emotion information (e.g., anxiety, impatience, etc.). The specific operation is that the emotion recognition engine analyzes the text data and generates an emotion score.

[1415] Step 4:

[1416] The server classifies questions into appropriate categories based on the analysis and emotion recognition results. The input is the analyzed text structure and emotion information, and the output is a category label (e.g., parenting support, health-related, etc.). Specifically, the classification algorithm determines the category based on the text data and emotion score.

[1417] Step 5:

[1418] The server searches for relevant information from a database or external API according to the question category. The input is a category label, and the output is related information data (e.g., product list, service information, etc.). The specific operation is to execute a database query or API call to obtain information.

[1419] Step 6:

[1420] The server generates a response for the user based on the search results and emotion recognition results. The input is related information data and emotion scores, and the output is a customized response text. The specific operation is that a template or customized message generation engine creates a response based on the information.

[1421] Step 7:

[1422] The server sends the generated answer to the user's smartphone app. The input is the generated answer text, and the output is the answer message displayed on the smartphone. The specific operation is data transmission from the server to the smartphone app. The user can check the sent answer on the app and take action based on the suggested product or service information.

[1423] 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.

[1424] 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.

[1425] 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.

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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).

[1430] 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.

[1431] 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."

[1432] 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.

[1433] 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).

[1434] 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.

[1435] 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.

[1436] 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.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] The following is further disclosed regarding the above embodiment.

[1445] (Claim 1)

[1446] means for receiving questions from users;

[1447] A means of analyzing questions using a natural language processing engine;

[1448] A means of categorizing questions based on the analysis results;

[1449] A means to search for related information from databases and external APIs according to question categories, and

[1450] means for generating an answer for the user based on the search results;

[1451] means for transmitting the generated answer to the user;

[1452] the means to arrange related services as needed;

[1453] A system including:

[1454] (Claim 2)

[1455] 2. The system according to claim 1, further comprising means for performing keyword extraction, subject-predicate-object recognition, and sentiment analysis in question analysis and category classification.

[1456] (Claim 3)

[1457] 2. The system of claim 1, further comprising means for classifying user questions into specific categories such as childcare support, education, and health-related, based on the content of the user's questions.

[1458] "Example 1"

[1459] (Claim 1)

[1460] means for receiving questions from users;

[1461] A means of analyzing questions using a natural language processing engine;

[1462] A means of categorizing questions based on the analysis results;

[1463] A means to search for related information from databases and external APIs according to question categories, and

[1464] means for generating an answer for the user based on the search results;

[1465] means for transmitting the generated answer to the user;

[1466] the means to arrange related services as needed;

[1467] A means for tokenization, subject, predicate, and object extraction, and sentiment analysis;

[1468] A system including:

[1469] (Claim 2)

[1470] 10. The system of claim 1, further comprising means for performing tokenization, subject-predicate-object recognition, and sentiment analysis in question parsing and categorization.

[1471] (Claim 3)

[1472] 2. The system according to claim 1, further comprising means for classifying the user's questions into specific categories such as childcare, education, and health based on the content of the user's questions.

[1473] "Application Example 1"

[1474] (Claim 1)

[1475] means for receiving questions from users;

[1476] A means of analyzing questions using a natural language processing engine;

[1477] A means of categorizing questions based on the analysis results;

[1478] A means to search for related information from databases and external APIs according to question categories, and

[1479] means for generating an answer for the user based on the search results;

[1480] means for transmitting the generated answer to the user;

[1481] the means to arrange related services as needed;

[1482] A means for searching for products and services based on a user's question and providing relevant product information in physical stores;

[1483] A system including:

[1484] (Claim 2)

[1485] 2. The system according to claim 1, further comprising means for performing keyword extraction, subject-predicate-object recognition, and sentiment analysis in question analysis and category classification.

[1486] (Claim 3)

[1487] 2. The system of claim 1, further comprising means for classifying a user's question into a specific category such as childcare support, education, or health-related, based on the content of the user's question.

[1488] "Example 2: Combining Emotion Engines"

[1489] (Claim 1)

[1490] means for receiving questions from users;

[1491] A means of analyzing questions using a natural language processing engine;

[1492] A means of categorizing questions based on the analysis results;

[1493] A means to search for related information from databases and external APIs according to question categories, and

[1494] means for generating an answer for the user based on the search results;

[1495] means for transmitting the generated answer to the user;

[1496] the means to arrange related services as needed;

[1497] means for recognizing emotions contained in a question using an emotion engine;

[1498] a means of adjusting the tone and content of responses based on perceived emotions;

[1499] A system including:

[1500] (Claim 2)

[1501] 2. The system according to claim 1, further comprising means for performing keyword extraction, subject-predicate-object recognition, and sentiment analysis in question analysis and category classification.

[1502] (Claim 3)

[1503] 2. The system of claim 1, further comprising means for classifying user questions into specific categories such as childcare support, education, and health-related, based on the content of the user's questions.

[1504] "Application example 2 when combining emotion engines"

[1505] (Claim 1)

[1506] means for receiving questions from users;

[1507] A means of analyzing questions using a natural language processing engine;

[1508] A means of categorizing questions based on the analysis results;

[1509] A means to search for related information from databases and external APIs according to question categories, and

[1510] means for generating an answer for the user based on the search results;

[1511] means for transmitting the generated answer to the user;

[1512] the means to arrange related services as needed;

[1513] a means for recognizing a user's emotions and adjusting the analysis results;

[1514] A means for adjusting the tone and information of the recommendations based on the user's emotions;

[1515] A system including:

[1516] (Claim 2)

[1517] 2. The system according to claim 1, further comprising means for performing keyword extraction, subject-predicate-object recognition, and sentiment analysis in question analysis and category classification.

[1518] (Claim 3)

[1519] 10. The system of claim 1, further comprising means for classifying the user's questions into specific categories such as childcare support, education, health-related, etc. based on the content of the user's questions and emotion recognition. [Explanation of symbols]

[1520] 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 questions from users; A means of analyzing questions using a natural language processing engine; A means of categorizing questions based on the analysis results; A means to search for related information from databases and external APIs according to question categories, and means for generating an answer for the user based on the search results; means for transmitting the generated answer to the user; the means to arrange related services as needed; A system including:

2. 2. The system according to claim 1, further comprising means for extracting keywords, recognizing subjects, predicates and objects, and performing sentiment analysis in the question analysis and categorization.

3. The system according to claim 1 , further comprising means for classifying the user's questions into specific categories such as childcare support, education, and health-related, based on the content of the user's questions.

Images