System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a question input from a communication terminal; means for analyzing the received question and classifying the question into a category corresponding to the question; means for generating an answer to the analyzed question; means for evaluating reliability of the generated answer; means for transmitting the answer to the communication terminal when the reliability exceeds a predetermined threshold value; and means for displaying the acquired support information on the communication terminal.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] Currently, there is a lack of systems that can quickly provide appropriate answers and information to the many people who have concerns and worries about pregnancy and child-rearing. As a result, there is a need for methods that provide reliable, quick, and accurate answers to questions. In particular, the lack of an information support system that can be easily accessed even at night or in an emergency is a problem. Furthermore, differences in the child-rearing support information provided by each local government have led to disparities in services between regions. [Means for solving the problem]

[0005] The present invention provides a means for receiving a question input from a communication terminal, analyzing the question, and classifying it into categories. It also includes a means for generating an appropriate answer based on the analysis results and evaluating its reliability. If it is determined that the reliability exceeds a predetermined threshold, the answer is transmitted to the communication terminal. The system also includes a means for searching for support information based on the question, acquiring the relevant information, and displaying it on the communication terminal. This allows for the provision of information and the generation of an answer in a specific category related to pregnancy and childcare. The system also includes a means for generating a message prompting the user to ask the question again and transmitting the message to the communication terminal if the reliability of the generated answer falls below a threshold.

[0006] A "communications terminal" is a device that a user uses to enter questions and display received answers and information.

[0007] A "question" is an anxieties or worries about pregnancy or child-rearing that a user inputs in text format from a communication terminal.

[0008] "Analysis" is the process of understanding the content of the question and classifying it into appropriate categories.

[0009] "Categories" are groups categorized based on the type and content of questions, and include, for example, childcare worries and pregnancy issues.

[0010] An "answer" is information or advice provided in response to a parsed question.

[0011] "Reliability" is a measure of whether the generated answers are accurate and trustworthy.

[0012] "Evaluation" is the process for determining the reliability of a generated answer.

[0013] A "predetermined threshold" is a minimum score or standard above which an answer on a criterion is considered reliable.

[0014] "Support information" refers to useful information about pregnancy and child-rearing, including official information from the national and local governments.

[0015] "Searching" is the process of locating relevant supporting information from a database based on a query.

[0016] "Display" means showing the acquired answers and support information on the screen of the communication terminal.

[0017] The term "system" refers to an entire mechanism or device that functions by integrating the means of the present invention.

[0018] A "message" is a notification or guidance that prompts the user to ask the question again. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention provides an information support system for resolving worries and questions about pregnancy and child-rearing. The system allows users to input questions via a communication terminal and provides appropriate answers and support information to those questions.

[0041] System configuration

[0042] server

[0043] The server has a means for receiving questions input from a communication terminal. It analyzes the content of the question and classifies it into a category appropriate to the question. It generates an appropriate answer to the analyzed question and evaluates its reliability. If the reliability of the generated answer exceeds a predetermined threshold, it transmits the answer and searches for and acquires support information based on the question.

[0044] Terminal

[0045] A communication device that allows users to enter questions and view the received answers. The device provides a user interface using the LINE app or other messaging services. Users can enter questions and view answers through this interface.

[0046] User

[0047] The users of the system are individuals who have questions about pregnancy and childcare. Users input their questions through a communication terminal and receive answers and related information.

[0048] Processing Details

[0049] Server processing

[0050] 1. Receiving Questions

[0051] When a user sends a question using a communication terminal, the content of the question is sent to a server.

[0052] The server analyzes the question and categorizes it into the appropriate category.

[0053] 2. Answer Generation and Evaluation

[0054] The server generates an appropriate answer based on the analysis of the question, and the reliability of the generated answer is evaluated using a reliability evaluation model.

[0055] If the confidence score exceeds a predetermined threshold, an answer is sent to the user's communication terminal, and if the confidence score is below the threshold, a message prompting the user to ask the question again is generated.

[0056] 3. Search for support information

[0057] The system searches the database for support information related to the question and retrieves the relevant information. This information includes official child-rearing support information provided by the national and local governments.

[0058] Processing by the terminal

[0059] 1. Enter and submit your question

[0060] The user inputs a question using a communication device such as the LINE app, and the input question is sent to the server.

[0061] 2. Receiving and Displaying Responses

[0062] The answer and support information sent from the server are received and displayed on the screen of the communication terminal.

[0063] Specific examples

[0064] For example, suppose a user inputs a question such as, "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?"

[0065] 1. User Input

[0066] The user inputs a question into the communication terminal and presses the send button.

[0067] 2. Server Analysis

[0068] The server receives the questions and categorizes them into categories such as "night crying" and "childcare worries."

[0069] 3. Answer Generation

[0070] The server generates an answer such as, "Changing the environment and adjusting the sleep rhythm are effective in treating babies' nighttime crying."

[0071] 4. Reliability Assessment

[0072] A reliability assessment model verifies the reliability of the answer and obtains a score above a threshold.

[0073] 5. Submitting and Viewing Your Answers

[0074] The server sends a reliable response to the user's communication terminal, which then displays the received response on its screen so that the user can confirm it.

[0075] 6. Providing support information

[0076] In addition, the server searches for support information from relevant local governments and provides additional information such as "Try joining a local mom support community."

[0077] In this manner, the present invention provides a system that can provide pregnancy and parenting information quickly and reliably.

[0078] The processing flow will be explained below.

[0079] Step 1:

[0080] The user opens the LINE app on their communication device and types a question into the text box. For example, they might type, "My baby cries a lot at night. Is there anything I can do about it?"

[0081] Step 2:

[0082] The user presses the send button and the question entered in the text box is sent to the server.

[0083] Step 3:

[0084] The server receives the question and logs it. For example, it might log "Question received: My baby is crying a lot at night. Is there anything I can do about it?"

[0085] Step 4:

[0086] The server analyzes the received question using a natural language processing model. For example, it extracts keywords such as "night crying" or "baby" from the question and categorizes them into "childcare worries."

[0087] Step 5:

[0088] The server generates an appropriate answer based on the question category, for example, "To prevent a baby from crying at night, it is important to create a good sleeping environment. Baby massage and adjusting nap times are also effective."

[0089] Step 6:

[0090] The server evaluates the answer generated by the server using a reliability evaluation model. It determines whether the evaluation score exceeds a predetermined threshold. For example, if the reliability score is evaluated as 90 points and exceeds the threshold, the process proceeds.

[0091] Step 7:

[0092] The server verifies that the reliability score exceeds a predetermined threshold and transmits the generated answer to the user's communication terminal.

[0093] Step 8:

[0094] The device displays the answer received from the server to the user. For example, it might say, "To prevent your baby from crying at night, it's important to create a good bedroom environment. Baby massages and adjusting nap times can also be effective."

[0095] Step 9:

[0096] The server then searches the database for further related support information, such as "Try joining a local mom support community."

[0097] Step 10:

[0098] The device will display additional information to the user, for example, "Try joining a local mom support community."

[0099] Step 11:

[0100] The user reviews this information and, if necessary, enters further questions or decides next steps based on the information provided.

[0101] In this way, the entire system achieves a process that quickly provides reliable answers and relevant information to users' questions.

[0102] Example 1

[0103] 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."

[0104] Currently, many people with concerns or questions about pregnancy and child-rearing find it difficult to quickly obtain reliable information. While a great deal of information exists on the Internet, its reliability and accuracy cannot be guaranteed. Furthermore, there are limited means of centrally obtaining support information provided by local governments and specialist institutions, which requires users to go to the trouble of searching multiple sources of information. There is a need to solve these problems and enable users to quickly and accurately obtain the information they need.

[0105] 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.

[0106] In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question using natural language processing technology and classifying the question into a category corresponding to the question, means for generating an answer to the analyzed question using a generative AI model, means for evaluating the reliability of the generated answer using a reliability evaluation model, means for transmitting the answer to the communication terminal if the reliability is determined to exceed a predetermined threshold, means for generating and transmitting a message prompting the user to ask the question again if the reliability is below the predetermined threshold, means for searching a database for related information based on the question and acquiring the relevant information, means for displaying the acquired related information on the communication terminal, and means for providing a user interface for inputting a question from the communication terminal. This enables users to quickly and centrally acquire reliable answers and support information to their concerns and questions.

[0107] A "communication terminal" is a device that allows a user to input and send questions, and includes smartphones, tablets, PCs, etc.

[0108] "Natural language processing technology" is a technology for analyzing text data and understanding linguistic meaning, and includes morphological analysis and contextual analysis.

[0109] A "generative AI model" is an algorithm or program for generating natural language responses based on input prompts, including, for example, large-scale language models.

[0110] A "trust assessment model" is an algorithm or program for assessing the usefulness and accuracy of generated answers, including polarity classifiers and label prediction models.

[0111] The "trust threshold" is a reference value for evaluating the reliability of a generated answer, and indicates that an answer will be officially sent only if it exceeds this value.

[0112] A "database" is a collection of data for efficiently searching and retrieving relevant information based on a question, and includes relational and non-relational databases.

[0113] A "user interface" is an operating environment in which a user can input questions through a communication terminal and check the results, and includes applications and websites.

[0114] The present invention describes an information support system for resolving worries and questions about pregnancy and child-rearing. This system provides appropriate answers and support information to questions entered by users through a communication terminal. Specifically, the system is configured as follows.

[0115] Server configuration and processing contents

[0116] 1. Receiving Questions

[0117] When a user inputs and sends a question using a communication terminal, the question reaches the server. The server receives the question through an API. For example, a RESTful API is used as this API.

[0118] 2. Question Analysis

[0119] After receiving the question, the server analyzes it using natural language processing technology. Specifically, it uses a "natural language processing library" to extract the question's subject and keywords and classify them into appropriate categories (e.g., night crying, breastfeeding, parenting worries, etc.). Libraries used include spaCy and NLTK.

[0120] 3. Answer Generation

[0121] Based on the analyzed question, the server uses a "generative AI model" to generate an appropriate answer. One example of a model used for generation is OpenAI's GPT-3. A prompt sentence tailored to the question is input into the model to generate an answer. For example, a prompt sentence such as "My baby's crying at night is terrible. Is there anything I can do about it?" can be used.

[0122] 4. Reliability Assessment

[0123] The generated answers are then evaluated for their trustworthiness using a trustworthiness assessment model, such as a polarity classifier or label prediction model, which evaluates whether the answer is accurate and useful and outputs a trustworthiness score.

[0124] 5. Submit your response

[0125] If the reliability score exceeds a predetermined threshold (e.g., 80%), the server sends the generated answer to the user's communication terminal. If the reliability score is below the threshold, the server generates and sends a message prompting the user to ask a more detailed question.

[0126] 6. Searching for support information

[0127] The server searches and retrieves relevant support information from a database based on the query, including official childcare support information from the national and local governments. PostgreSQL and MongoDB are used for the database.

[0128] Terminal configuration and processing contents

[0129] 1. Providing a user interface

[0130] Users use communication devices such as smartphones or tablets to input and send questions through messaging services such as the LINE app or WhatsApp. The app provides a user interface, creating an environment where users can easily input questions.

[0131] 2. Receiving and displaying responses and support information

[0132] The response and support information sent from the server is received by the communication device, which then displays it on the LINE app or WhatsApp screen. The user can check the received response and support information on the screen and take the necessary action.

[0133] Specific examples

[0134] For example, consider the case where a user uses the LINE app on a communication device to send a question such as, "My baby's night crying is so bad I'm worried. Is there anything I can do about it?" The server receives the question and analyzes it using the spaCy library. Next, it uses a GPT-3 model to generate an answer: "To combat night crying, it's effective to create a good environment and regulate the baby's sleep rhythm." The reliability evaluation model assigns a reliability score of 85% to this answer, and because this score exceeds the threshold, the answer is sent to the user's communication device. At the same time, support information such as "local mom support communities" is retrieved from the database and provided to the user.

[0135] The above is an embodiment of the present invention. This system enables users to quickly obtain reliable information about pregnancy and childcare.

[0136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0137] Step 1:

[0138] A user inputs and sends a question using a communication terminal.

[0139] Specifically, a user opens a messaging app such as LINE or WhatsApp, types a question into the text box, for example, "My baby's crying at night is so bad I'm worried. Is there anything I can do about it?", and presses the send button. This operation sends the question data from the communication device to the server.

[0140] Input: A question entered by the user into a communication device (e.g., "My baby cries a lot at night. Is there anything I can do about it?")

[0141] Output: Question data is sent to the server

[0142] Step 2:

[0143] The server receives the question and analyzes it using natural language processing techniques.

[0144] After receiving the question via the RESTful API, the server analyzes it using a natural language processing library (e.g., spaCy). The analysis extracts the question's subject and keywords (e.g., baby, night crying, measures), and then categorizes it into categories (e.g., night crying, parenting worries).

[0145] Input: Question data sent from the communication terminal

[0146] Output: Parsed question topics, keywords, and categories

[0147] Step 3:

[0148] The server generates an answer using a generative AI model based on the analysis results.

[0149] Based on the analysis results, a generative AI model (e.g., OpenAI GPT-3) is used as the prompt. The prompt is generated based on the analysis results, and a question such as, "My baby's nighttime crying is so bad I'm worried. Is there anything I can do about it?" is entered. The generative AI model then generates an answer, such as, "To combat nighttime crying, it is effective to improve the baby's environment and sleep rhythm."

[0150] Input: Parsed question subject, keywords, categories, and prompt sentence

[0151] Output: Generated answer text

[0152] Step 4:

[0153] The server evaluates the trustworthiness of the generated answer using a trustworthiness evaluation model.

[0154] The generated answer is evaluated for reliability through a reliability assessment model (e.g., polarity classifier, label prediction model). A reliability score is generated, and a score of, say, 85% is assigned. It is then determined whether this score exceeds a predetermined threshold (e.g., 80%).

[0155] Input: Generated answer

[0156] Output: Confidence score for the generated answer

[0157] Step 5:

[0158] If the reliability exceeds a predetermined threshold, the server sends a response to the communication terminal.

[0159] If the reliability score exceeds the threshold, the server transmits the generated answer to the communication terminal, whereas if the reliability score falls below the threshold, the server generates and transmits a message prompting further questioning.

[0160] Input: Confidence score for generated answers

[0161] Output: A reliable answer or re-question message is sent to the communication device.

[0162] Step 6:

[0163] The server searches and retrieves relevant information based on the question from a database.

[0164] The server searches a database (e.g., PostgreSQL, MongoDB) based on the question and retrieves relevant support information (e.g., official childcare support information from the national or local government).

[0165] Input: Question content and analysis results

[0166] Output: Related information search results

[0167] Step 7:

[0168] The terminal receives and displays the response and related information.

[0169] The communication device receives the response and related information sent from the server, and the received information is displayed on the LINE app or WhatsApp screen for the user to check.

[0170] Input: Submitted answers and related information

[0171] Output: Answers and related information displayed on the communication device

[0172] (Application example 1)

[0173] 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."

[0174] The present invention relates to a system that provides appropriate and prompt information support to users who have concerns or questions about pregnancy and childcare. In particular, in situations where services such as childcare products are provided in physical stores, there is a need to provide optimal support based on the user's location information. However, current information support systems lack real-time support within the store, which makes it difficult for users to quickly obtain appropriate information and services.

[0175] 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.

[0176] In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question and classifying it into a category corresponding to the question, means for generating an answer to the analyzed question, means for evaluating the reliability of the generated answer, means for transmitting the answer to the communication terminal if it is determined that the reliability exceeds a predetermined threshold, means for searching for support information based on the question and acquiring corresponding information, means for displaying the acquired support information on the communication terminal, and means for providing information on related products and services of nearby stores based on the user's location information. This enables the user to not only receive highly reliable information about pregnancy and childcare, but also to quickly receive guidance on optimal products and services based on their location.

[0177] A "communication terminal" is an electronic device that allows a user to input information and exchange information with a server. Examples of this include smartphones and tablets.

[0178] "Analyzing a question" is the process of analyzing the content of a question entered by a user and understanding its meaning and intent.

[0179] "Categorizing" refers to grouping the analyzed questions according to specific themes or topics.

[0180] "Answer generation" is the process of creating an appropriate response to the parsed question.

[0181] "Assessing credibility" is the process of determining whether the generated answer is accurate and useful.

[0182] "Sending an answer to a communication terminal" means sending the evaluated answer to the communication terminal used by the user.

[0183] "Searching for help" is the process of searching a database for additional information or advice related to the user's question.

[0184] "Displaying the acquired support information" means displaying the related information acquired by the search on the user's communication terminal.

[0185] "Providing information about related products and services based on the user's location information" means providing information about products and services near the user's current location.

[0186] As an embodiment of the present invention, we will specifically describe an information support system for resolving concerns and questions about pregnancy and child-rearing. This system receives questions entered from a communication terminal and provides appropriate answers and support information.

[0187] Hardware and software used

[0188] Communication terminals: Includes electronic devices such as smartphones and tablets that allow users to input and receive information.

[0189] Server: The back-end system used to analyze and process data. This server is equipped with the following software:

[0190] Query processing system: Receives questions, analyzes them, categorizes them, generates answers, and assesses their reliability.

[0191] Generative AI models: Use AI models such as OpenAI's ChatGPT to generate appropriate answers.

[0192] Database system: A database for storing and retrieving support information based on a question.

[0193] GPS function: Obtains the user's location information and uses it to provide information on the most relevant products and services.

[0194] Program processing

[0195] The server receives questions entered from the communication terminal. The received questions are first analyzed and classified into categories according to their content. An appropriate answer is then generated for the analyzed question using a generative AI model. The reliability of the generated answer is then evaluated, and if the reliability score exceeds a predetermined threshold, the answer is sent to the communication terminal.

[0196] Furthermore, based on the user's question, the system searches for relevant support information from a database and acquires the relevant information. The acquired support information is displayed on the communication terminal. Additionally, based on the user's location information, the system also provides information on related products and services from nearby stores.

[0197] Specific examples

[0198] For example, consider the case where a user inputs a question such as "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?"

[0199] 1. The user enters a question into the communication terminal and presses the send button.

[0200] 2. The server receives the questions and categorizes them into categories such as "night crying" or "parenting worries."

[0201] 3. The server uses a generative AI model (e.g., OpenAI's ChatGPT) to generate an answer such as, "To prevent babies from crying at night, it is effective to improve their environment and sleep rhythm."

[0202] 4. The reliability of the answer is evaluated using a reliability evaluation model, and if it exceeds a predetermined threshold, the answer is sent to the user's communication terminal.

[0203] 5. Furthermore, the server searches the database for relevant support information and provides additional information such as "Try joining a local mom support community."

[0204] 6. Based on the user's location, information about related products and services available in nearby stores will also be provided.

[0205] In this way, the present invention can provide users with prompt and reliable answers and support information to their questions and concerns about pregnancy and child-rearing.

[0206] Example of input prompt sentence:

[0207] User Question: My baby cries a lot at night. Is there anything I can do about it?

[0208] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0209] Step 1:

[0210] The user uses a communication terminal (for example, a smartphone) to input a question and presses the send button.

[0211] Input: A question typed by the user (e.g., "My baby cries a lot at night. Is there anything I can do about it?").

[0212] Output: The question is sent to the server.

[0213] Step 2:

[0214] The server receives the query sent from the communication terminal.

[0215] Input: Question sent from communications terminal.

[0216] Output: The received query data.

[0217] Step 3:

[0218] The server analyzes the received questions and categorizes them based on their content.

[0219] Input: The received query data.

[0220] Data processing: The question content is analyzed using natural language processing technology to extract key keywords and phrases.

[0221] Output: Question categorization (e.g., "Crying at night" or "Parenting worries").

[0222] Step 4:

[0223] The server generates appropriate answers for categorized questions using a generative AI model (e.g., OpenAI's ChatGPT).

[0224] Input: Categorized questions.

[0225] Data computation: Generative AI models are used to generate answers that correspond to categories.

[0226] Output: The generated answer (e.g., "Changing the environment and adjusting sleep routines can help with babies' night crying").

[0227] Step 5:

[0228] The server evaluates the trustworthiness of the generated answer.

[0229] Input: The generated answer.

[0230] Data calculation: Use the reliability assessment model to calculate the reliability score of the answer.

[0231] Output: A confidence score.

[0232] Step 6:

[0233] The server determines whether the reliability score exceeds a predetermined threshold, and if so, transmits a response to the communication terminal.

[0234] Input: Confidence score.

[0235] Data calculation: Compare the confidence score to a threshold.

[0236] Output: Answer data that is judged to be reliable. If the reliability is low, a prompt to ask the question again is generated.

[0237] Step 7:

[0238] The server searches the database for relevant support information based on the query and acquires the relevant information.

[0239] Input: Question content and category information.

[0240] Data calculation: Using database search algorithms to retrieve relevant supporting information.

[0241] Output: Support information data (e.g., "Information about local support communities for mothers").

[0242] Step 8:

[0243] The server obtains the user's location information and provides information on related products and services at nearby stores based on that information.

[0244] Input: User's location, question.

[0245] Data calculation: Search and obtain information about nearby stores and related products and services based on location information.

[0246] Output: Information about nearby stores (e.g., "A store near you sells nighttime baby products").

[0247] Step 9:

[0248] The server transmits the acquired support information and nearby store information to the communication terminal, which then displays this information to the user.

[0249] Input: reliable answers, assistance, store information.

[0250] Output: Information displayed on the communication device.

[0251] Step 10:

[0252] The user checks the answers and support information received on the communication terminal and takes the necessary action.

[0253] Input: Information displayed on the communication terminal.

[0254] Output: User behavior (e.g., joining a mom support community, purchasing related products).

[0255] 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.

[0256] The present invention provides an information support system for resolving worries and questions about pregnancy and child-rearing. This system receives user questions, classifies them, generates answers, evaluates their reliability, and combines them with an emotion engine that recognizes the user's emotions. Specific embodiments of the system are described below.

[0257] System configuration

[0258] server

[0259] The server has a means for receiving questions input from a communication terminal, a means for analyzing the content of the question and classifying it into a category corresponding to the question, a means for generating an appropriate answer to the analyzed question and evaluating its reliability, and a means for transmitting the answer to the communication terminal if it is determined that the reliability exceeds a predetermined threshold. The server also has a means for searching for support information based on the question and acquiring the relevant information.

[0260] Emotion Engine

[0261] The emotion engine recognizes the user's emotion when receiving a question and adjusts the tone and content of the response based on the user's emotional state. For example, if the user is feeling anxious or stressed, the emotion engine may provide additional information about relaxation techniques or support services. It also generates and sends encouraging or congratulatory messages if the user's emotion is positive.

[0262] Terminal

[0263] A communication device that allows users to enter questions and view the received answers. The device provides a user interface using the LINE app or other messaging services. Users can enter questions and view answers through this interface.

[0264] User

[0265] The users of the system are individuals who have questions about pregnancy and childcare. Users input their questions through a communication terminal and receive answers and related information.

[0266] Processing Details

[0267] Server processing

[0268] 1. Receiving Questions

[0269] When a user sends a question using a communication terminal, the question content is sent to the server, which analyzes the question content and classifies it into categories.

[0270] 2. Answer Generation and Evaluation

[0271] The server generates an appropriate answer based on the analysis of the question, evaluates it using a trust evaluation model, and if the evaluation score exceeds a predetermined threshold, sends the answer to the user's communication terminal.

[0272] 3. Search for support information

[0273] The server searches the database for support information related to the question and retrieves the relevant information, including official child-rearing support information provided by the national and local governments.

[0274] 4. Emotional Recognition

[0275] The server uses an emotion engine to recognize the user's emotion when submitting a question, and this emotion data is used to generate and tailor answers.

[0276] 5. Adjust your responses based on emotions

[0277] The server adjusts the tone and content of the response based on the user's emotional state, as determined by the emotion engine. For example, if the server determines that the user is feeling stressed, it adds information about relaxation techniques and mental support.

[0278] 6. Submitting the final response

[0279] After the adjusted final answer passes the reliability evaluation, it is sent to the user's communication terminal.

[0280] Processing by the terminal

[0281] 1. Enter and submit your question

[0282] The user inputs a question using a communication device such as the LINE app, and the input question is sent to the server.

[0283] 2. Receiving and Displaying Responses

[0284] The answer and support information sent from the server are received and displayed on the screen of the communication terminal.

[0285] Specific examples

[0286] For example, if a user inputs a question such as "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?", the detailed flow is as follows:

[0287] 1. User Input

[0288] The user inputs a question into the communication terminal and presses the send button.

[0289] 2. Server Analysis

[0290] The server receives the questions and categorizes them into categories such as "night crying" and "childcare worries."

[0291] 3. Answer Generation

[0292] The server generates an answer such as, "Changing the environment and adjusting the sleep rhythm are effective in treating babies' nighttime crying."

[0293] 4. Reliability Assessment

[0294] A reliability assessment model verifies the reliability of the answer and obtains a score above a threshold.

[0295] 5. Emotional awareness and regulation

[0296] The emotion engine recognizes the user's anxiety and adds information about relaxation techniques and local support communities.

[0297] 6. Submitting and Viewing Final Answers

[0298] The server sends a reliable response to the user's communication terminal, which then displays the received response and additional information on its screen for the user to review.

[0299] In this way, the present invention realizes a system that quickly provides reliable answers to user questions and information that takes into consideration the user's feelings.

[0300] The processing flow will be explained below.

[0301] Processing Details

[0302] Step 1:

[0303] The user opens the LINE app on their communication device and types a question into the text box: "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?"

[0304] Step 2:

[0305] The user presses the send button and the question entered in the text box is sent to the server.

[0306] Step 3:

[0307] The server receives the question and logs it, for example, "Question received: My baby is crying a lot at night. Is there anything I can do about it?"

[0308] Step 4:

[0309] The server analyzes the question using a natural language processing model, extracts keywords such as "night crying" and "baby," and classifies them into the category of "childcare concerns."

[0310] Step 5:

[0311] When a user submits a question, the server analyzes the user's emotions using an emotion engine. The emotion engine reads anxiety and stress from the user's text and generates emotion data. For example, it records "User emotion: Anxiety (score 75)."

[0312] Step 6:

[0313] The server generates an appropriate answer based on the question category, for example, "To prevent a baby from crying at night, it is important to create a good sleeping environment. Baby massage and adjusting nap times are also effective."

[0314] Step 7:

[0315] The server evaluates the generated answer using a reliability evaluation model. It determines whether the evaluation score exceeds a predetermined threshold (e.g., 80 or more), and the score is evaluated as 90.

[0316] Step 8:

[0317] Based on the results of the emotion engine, the server adds information on relaxation techniques and mental support to ease the user's anxiety. For example, it adds information such as, "Deep breathing and light stretching are recommended to help you relax. Try joining a local mom support community."

[0318] Step 9:

[0319] The server sends a final response to the user's communication terminal.

[0320] Step 10:

[0321] The device displays the answer it receives from the server to the user. For example, it might say, "To prevent your baby from crying at night, it's important to create a good bedroom environment. Baby massages and adjusting nap times can also be effective. Deep breathing and light stretching are recommended for relaxation. Try joining a local support community for mothers."

[0322] Step 11:

[0323] The user reviews this information and, if necessary, enters further questions or decides next steps based on the information provided.

[0324] In this way, the entire system achieves a process of quickly providing reliable answers and emotionally sensitive information to users' questions.

[0325] Example 2

[0326] 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."

[0327] In modern society, an increasing number of individuals have concerns and questions about pregnancy and child-rearing, but it is difficult to provide reliable information quickly and obtain answers that take into consideration the user's feelings.In addition, there are insufficient systems that provide appropriate support information according to emotions, so it is necessary to ensure that users can use the system with peace of mind.

[0328] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question and classifying it into a category corresponding to the question, means for generating an answer to the analyzed question, means for evaluating the reliability of the generated answer, means for recognizing the user's emotions when the question was sent, means for adjusting the tone and content of the answer based on the user's emotional state, means for sending the answer to the communication terminal if it is determined that the reliability exceeds a predetermined threshold, means for searching for support information based on the question and acquiring corresponding information, and means for displaying the acquired support information on the communication terminal. This allows the user to quickly obtain a reliable answer and is also provided with appropriate support information corresponding to the user's emotions, allowing the user to use the system with peace of mind.

[0329] A "communication terminal" is a device that allows a user to input questions and display the received answers, such as a smartphone or a personal computer.

[0330] A "question" refers to a question or concern about pregnancy and child-rearing that a user inputs using a communication terminal and sends to the server.

[0331] "Analysis" refers to the process in which the server uses natural language processing technology to interpret the content of the question received and classify it into categories.

[0332] "Categories" are themes or topics classified based on the content of the question, and include, for example, "night crying" and "childcare worries."

[0333] "Answer" refers to information that includes solutions or advice to the user's questions or concerns, which the server generates based on the analyzed question.

[0334] "Evaluation" refers to the process by which the server verifies the quality and reliability of the generated answers, using a reliability evaluation model.

[0335] "Emotion" refers to the psychological state the user is in when submitting the question, and includes anxiety, stress, joy, etc.

[0336] An "emotion engine" refers to a system that allows the server to recognize the user's emotions and adjust the tone and content of the response based on that data.

[0337] "Support information" refers to information about specific support and resources obtained from external databases related to the question.

[0338] "Credibility" is one of the evaluation criteria that indicates whether the generated answer is useful to the user, accurate, and appropriate.

[0339] The "threshold" refers to a reference point for determining whether or not the reliability evaluation score will provide an answer to a user.

[0340] MODE FOR CARRYING OUT THE INVENTION

[0341] The present invention provides an information support system for resolving worries and questions about pregnancy and child-rearing. Specific embodiments of the system will be described in detail below.

[0342] Hardware and software used

[0343] server

[0344] The server is responsible for receiving questions, analyzing them, generating answers, evaluating trustworthiness, recognizing emotions, searching for support information, and sending answers. A typical server computer is used for the hardware. The software uses the following technologies:

[0345] Natural language processing libraries: NLTK, spaCy

[0346] Learning model: Machine learning algorithm, reliability evaluation model

[0347] Sentiment Engine: Sentiment Analysis Algorithm

[0348] communication terminal

[0349] The communication terminal is a device where the user can input questions and receive answers. It can be a smartphone or a PC. The user interface is the LINE app or other messaging services.

[0350] User

[0351] Users use this system to input questions and receive answers, primarily individuals with questions or concerns about pregnancy and child-rearing.

[0352] Specific processing flow

[0353] 1. Enter and submit your question

[0354] The user opens the LINE app on their communication device, types a question, for example, "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?" and presses the send button.

[0355] 2. Receiving and analyzing questions

[0356] The server analyzes the received questions and uses natural language processing libraries (NLTK or spaCy) to classify them into categories such as "night crying" or "parenting worries."

[0357] 3. Answer Generation

[0358] Based on the analysis results, the server generates an answer to the question such as, "Changing the environment and adjusting the sleep rhythm are effective in treating babies' nighttime crying."

[0359] 4. Reliability Assessment

[0360] The server calculates a reputation score for the generated answer using a reliability evaluation model, and proceeds to the next step only if the reputation score exceeds a predetermined threshold.

[0361] 5. Searching for support information

[0362] The server searches national and local government databases for support information related to the question and retrieves the relevant information. For example, it provides additional information on "local child-rearing support communities."

[0363] 6. Emotional awareness and regulation

[0364] The server uses an emotion engine to recognize emotions such as anxiety or stress from the user's question text, and adjusts the tone and content of the answer based on this emotion data. For example, it adds information about relaxation techniques to the answer.

[0365] 7. Submitting the final response

[0366] After the final adjusted answer passes the reliability evaluation, the server sends the final answer to the device. For example, it might say, "To combat your baby's nighttime crying, it's effective to improve the environment and regulate their sleep rhythm. Also, why not try joining a local parenting support community?"

[0367] 8. Receiving and Displaying Responses

[0368] The user's device receives the final answer sent from the server and displays it on the LINE app screen. The user can check the displayed answer and re-enter the question if necessary.

[0369] Example prompt sentences

[0370] Examples of prompts:

[0371] Example user question: My baby cries a lot at night. Is there anything I can do about it?

[0372] Emotion recognition: The user is determined to be feeling anxious.

[0373] Answer generation: To prevent babies from crying at night, it is effective to improve the environment and adjust their sleep rhythm.

[0374] Trustworthiness rating: The rating score exceeds a predetermined threshold.

[0375] Adjustments: Add information about relaxation techniques and local support communities.

[0376] Final answer: To combat nighttime crying, it is effective to improve the environment and establish a regular sleep routine. Also, why not join a local parenting support community?

[0377] As described above, the present invention realizes a system that quickly provides highly reliable answers to user questions and information that takes into consideration the user's feelings.

[0378] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0379] Step 1: Enter and submit your question

[0380] Input: The user's question or concern (e.g., "My baby cries a lot at night. Is there anything I can do about it?").

[0381] How it works: The user opens the LINE app on their device, enters the question as shown above, and presses the send button.

[0382] Output: The question text is sent to the server.

[0383] Step 2: Receiving and parsing the question

[0384] Input: The question text sent from the terminal.

[0385] How it works: The server receives the question text and uses natural language processing libraries (NLTK or spaCy) to analyze the question and classify it into categories such as "night crying" or "parenting worries."

[0386] Output: Question category information.

[0387] Step 3: Generate an answer

[0388] Input: Question category information.

[0389] How it works: The server searches a database of pre-prepared answers for the appropriate answer corresponding to the category, and generates an answer such as, "To treat a baby's night crying, it is effective to improve the environment and adjust the baby's sleep rhythm."

[0390] Output: The generated answer text.

[0391] Step 4: Assess reliability

[0392] Input: The generated answer text.

[0393] Operation: The server inputs the generated answer into the reliability evaluation model and calculates the evaluation score. If the evaluation score exceeds a predetermined threshold, it proceeds to the next step.

[0394] Output: A reliability assessment score.

[0395] Step 5: Finding support

[0396] Input: Confidence assessment score and question category information.

[0397] Operation: The server searches national and local government databases for support information related to the question and retrieves relevant information (e.g., information on local child-rearing support communities).

[0398] Output: Supporting information.

[0399] Step 6: Recognize and regulate your emotions

[0400] Input: Question text and generated answer text.

[0401] How it works: The server uses an emotion engine to recognize the user's emotions (e.g., anxiety or stress) from the question text. It then adjusts the generated answer based on the recognized emotion data, for example, adding information about relaxation techniques.

[0402] Output: The adjusted answer text.

[0403] Step 7: Submit your final response

[0404] Input: The adjusted answer text.

[0405] Operation: The server clears the trust evaluation and sends the adjusted final answer to the user's communication device.

[0406] Output: The final answer is sent to the terminal.

[0407] Step 8: Receive and view responses

[0408] Input: The final answer sent by the server.

[0409] Operation: The communication device receives the final response and displays it on the LINE app screen, allowing the user to check the displayed response.

[0410] Output: The final answer text that is displayed on the user's communication device.

[0411] Through the above processing steps, users can quickly obtain reliable answers and emotionally sensitive information.

[0412] (Application example 2)

[0413] 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."

[0414] There is a need to provide an information support system that can provide fast and reliable information to users who have concerns or questions about pregnancy and childcare, as well as to improve user satisfaction by providing appropriate support and answers according to the user's emotional state. In addition, there is a need to strengthen on-site support in physical stores, such as by providing information on related products and recommending products.

[0415] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question and classifying it into a category corresponding to the question, means for generating an answer to the analyzed question, means for evaluating the reliability of the generated answer, means for transmitting the answer to the communication terminal if the reliability is determined to exceed a predetermined threshold, means for searching for support information based on the question and acquiring the relevant information, means for recognizing the user's emotion and adjusting the tone and content of the answer based on the user's emotional state, means for displaying the acquired support information on the communication terminal, means for guiding the user to the location of related products and recommended products in a physical store, and means for generating a message prompting the user to ask the question again and transmitting the message to the communication terminal if the generated answer falls below the reliability evaluation threshold. This enables the provision of reliable information about pregnancy and childcare, the creation of appropriate support tailored to the user's emotional state, and user support in a physical store.

[0416] A "communication terminal" is a device that allows a user to input a question and send it to a server.

[0417] The "means for receiving a question" is a function that enables the server to receive a question sent from a communication terminal.

[0418] The "means for analyzing questions" is a function that understands the received questions and classifies them into appropriate categories according to their contents.

[0419] The "means for generating an answer" is a function that creates an appropriate answer based on the analyzed question.

[0420] "Means for assessing reliability" is a function for checking the accuracy and reliability of the generated answers.

[0421] The "means for sending a response" is a function for sending back a response whose reliability has been confirmed to the communication terminal.

[0422] "Means for searching for support information" is a function that finds information related to a question from a database or the like.

[0423] The "means for acquiring support information" is a function that allows the server to acquire the searched support information.

[0424] "Means for recognizing emotions" is a function for analyzing and understanding the emotional state of the user when entering a question.

[0425] "Means to adjust the tone and content of responses" refers to a function that appropriately changes the wording and content of generated responses based on the recognized user sentiment.

[0426] The "means for displaying support information" is a function for displaying acquired support information on the user's communication terminal.

[0427] "Means for guiding users to the location of related products and recommended products" refers to a function that allows users to navigate to the location of related products and recommended products within a physical store.

[0428] The "means for generating a message prompting the user to ask again" is a function for creating and sending a message prompting the user to ask the question again when the reliability of the answer is low.

[0429] The present invention is an information support system for resolving worries and questions about pregnancy and child-rearing, and is designed to provide answers and support information in accordance with the user's emotional state in a physical store. This embodiment will be described in detail below.

[0430] System configuration

[0431] server

[0432] Server Role:

[0433] The server plays a central role in analyzing questions sent from communication terminals, generating and evaluating appropriate answers, and providing the final answer to the user. The server has the following functions:

[0434] 1. Receiving Questions

[0435] A question input from a communication terminal is received.

[0436] 2. Question Analysis

[0437] Analyze the incoming question and classify it into a category that corresponds to the question, for example, using a natural language processing (NLP) model.

[0438] 3. Answer Generation

[0439] Generate answers to questions, using generative AI models to create relevant answers.

[0440] 4. Reliability Assessment

[0441] Evaluate the reliability of the generated answers. Check the accuracy of the answers using a reliability evaluation model.

[0442] 5. Submitting the final response

[0443] If it is determined that the reliability exceeds a predetermined threshold, a response is transmitted to the communication terminal.

[0444] 6. Searching for and obtaining support information

[0445] Search databases for support based on your question and retrieve relevant information, including data from official sources.

[0446] 7. Emotional awareness and regulation

[0447] Recognizing the user's emotions and adjusting the tone and content of responses based on their emotional state, for example by using a sentiment analysis engine (such as IBM Watson Tone Analyzer).

[0448] 8. Display of support information

[0449] The acquired support information is displayed on the communication terminal.

[0450] 9. Generate a message prompting you to ask again

[0451] If the generated answer falls below the reliability evaluation threshold, a message prompting the user to ask the question again is generated and transmitted to the communication terminal.

[0452] communication terminal

[0453] The role of the communication terminal:

[0454] A communication terminal is a device that allows users to input questions and receive answers and assistance information. It has the following functions:

[0455] 1. Enter and submit your question

[0456] A question entry form is provided where users can enter and submit their questions.

[0457] 2. Receiving and displaying responses and support information

[0458] Answers and support information sent from the server are received and displayed on the screen.

[0459] Physical store

[0460] In-store applications:

[0461] The system has the following features to enhance customer support in physical stores:

[0462] 1. Product Information

[0463] It guides users to the location of relevant products and recommends products in physical stores.

[0464] Specific examples

[0465] For example, if a user enters "I don't know how to choose diapers for my baby. Which ones are good?" in a physical store, the processing details are as follows:

[0466] 1. Enter and submit your question

[0467] The user enters a question into the communication terminal and presses the send button.

[0468] 2. Question Analysis

[0469] The server receives the questions and categorizes them into categories such as "How to choose diapers."

[0470] 3. Answer Generation

[0471] The server generates answers such as, "When choosing diapers, the baby's size, absorbency, and material are important. There are multiple options available in stores."

[0472] 4. Emotional awareness and regulation

[0473] The emotion engine recognizes the user's anxiety and tailors responses with a warm, reassuring tone, adding relaxation techniques and information about local support communities.

[0474] 5. Information on related products

[0475] The location of related products and recommended products within the physical store are displayed on the user's communication device.

[0476] Prompt sentences to input to the generative AI model

[0477] Prompt to generate an answer for the user:

[0478] "A customer asks, 'I don't know how to choose diapers for my baby in a physical store. Which ones are good?' Generate a reliable answer based on the question and provide additional information as needed."

[0479] Sentiment analysis prompt:

[0480] "Generate data that can be used to analyze sentiment from user questions and respond with the appropriate tone."

[0481] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0482] Step 1: Enter and submit your question

[0483] User action: The user opens the application on the communication terminal, enters "I don't know how to choose diapers for my baby. Which one is best?" into the question input form, and presses the send button.

[0484] Input: The question entered by the user.

[0485] Output: Question data sent from the communication terminal to the server.

[0486] Specific operation: The communication terminal sends the question data to the server as an HTTP POST request.

[0487] Step 2: Receiving and parsing the question

[0488] Server operation: The server receives the question sent from the communication terminal and analyzes the question using natural language processing (NLP).

[0489] Input: Query data sent from the communication terminal.

[0490] Output: Analysis results, specifically category information (e.g., "How to choose diapers").

[0491] Specific operation: The server uses an NLP tool (e.g., Google Cloud Natural Language API) to analyze the question and classify it into the appropriate category.

[0492] Step 3: Generate an answer

[0493] Server operation: The server uses a generative AI model to generate an appropriate answer based on the analysis results.

[0494] Input: Parsed category information.

[0495] Output: Generated answer (e.g., "When choosing a diaper, the baby's size, absorbency, and material are important. There are multiple options available in stores.").

[0496] Specific operation: The server uses a generative AI model (e.g., OpenAI GPT-3) to generate an appropriate answer based on the category information.

[0497] Step 4: Assess reliability

[0498] Server operation: The reliability of the generated answer is evaluated using a reliability evaluation model.

[0499] Input: The generated answer.

[0500] Output: A reliability assessment score.

[0501] How it works: The server uses a machine learning model (e.g., Scikit-learn or TensorFlow) to evaluate the reliability of the generated answer and calculate a score.

[0502] Step 5: Authenticity check and submit your answer

[0503] Server operation: If the reliability evaluation score exceeds a predetermined threshold, the server transmits an answer to the user's communication terminal.

[0504] Inputs: Confidence assessment score, generated answer.

[0505] Output: The answer sent to the user's communication device.

[0506] Specific operation: Check whether the reliability evaluation score exceeds the threshold, and if so, send the answer to the user's communication device in JSON format.

[0507] Step 6: Search and obtain support information

[0508] Server operation: Based on the content of the question, related support information is searched and acquired from the database.

[0509] Input: Question content, analysis results.

[0510] Output: Relevant supporting information.

[0511] Specific operation: The server queries the database and retrieves relevant data, such as official childcare support information from the government or local government.

[0512] Step 7: Recognize your emotions and adjust your response

[0513] Server Action: Uses an emotion engine to analyze the user's emotions and adjusts the tone and content of responses accordingly.

[0514] Input: User question data.

[0515] Output: A tailored response (e.g., a reassuring tone).

[0516] Specific operation: The server uses an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions and adjust the response text as necessary.

[0517] Step 8: Submit your final response and supporting information

[0518] Server operation: The server sends the final answer that has passed the reliability evaluation and the acquired support information to the user's communication terminal.

[0519] Input: Adjusted final answer, obtained supporting information.

[0520] Output: The final answer and supporting information sent to the user's communication terminal.

[0521] Specific operation: Reliable answers and assistance information are integrated and sent to the user's communication device in JSON format.

[0522] Step 9: Displaying answers and product information

[0523] Communication terminal operation: The received answers and support information are displayed on the screen, and the location of related products and recommended products are shown in the physical store.

[0524] Input: The final answer and supporting information sent from the server.

[0525] Output: Answers and support information displayed on the communication device screen, and information on related products in physical stores.

[0526] Specific operation: The communication terminal analyzes the received data and displays it on the user interface, while also using GPS and beacons to guide the user to the location of the product within the physical store.

[0527] This will enable the provision of reliable information about pregnancy and childcare, appropriate support tailored to the user's emotions, and user support in physical stores.

[0528] 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.

[0529] 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.

[0530] 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.

[0531] [Second embodiment]

[0532] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0533] 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.

[0534] 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).

[0535] 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.

[0536] 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.

[0537] 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).

[0538] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0539] 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.

[0540] 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.

[0541] 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.

[0542] 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.

[0543] 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."

[0544] The present invention provides an information support system for resolving worries and questions about pregnancy and child-rearing. The system allows users to input questions via a communication terminal and provides appropriate answers and support information to those questions.

[0545] System configuration

[0546] server

[0547] The server has a means for receiving questions input from a communication terminal. It analyzes the content of the question and classifies it into a category appropriate to the question. It generates an appropriate answer to the analyzed question and evaluates its reliability. If the reliability of the generated answer exceeds a predetermined threshold, it transmits the answer and searches for and acquires support information based on the question.

[0548] Terminal

[0549] A communication device that allows users to enter questions and view the received answers. The device provides a user interface using the LINE app or other messaging services. Users can enter questions and view answers through this interface.

[0550] User

[0551] The users of the system are individuals who have questions about pregnancy and childcare. Users input their questions through a communication terminal and receive answers and related information.

[0552] Processing Details

[0553] Server processing

[0554] 1. Receiving Questions

[0555] When a user sends a question using a communication terminal, the content of the question is sent to a server.

[0556] The server analyzes the question and categorizes it into the appropriate category.

[0557] 2. Answer Generation and Evaluation

[0558] The server generates an appropriate answer based on the analysis of the question, and the reliability of the generated answer is evaluated using a reliability evaluation model.

[0559] If the confidence score exceeds a predetermined threshold, an answer is sent to the user's communication terminal, and if the confidence score is below the threshold, a message prompting the user to ask the question again is generated.

[0560] 3. Search for support information

[0561] The system searches the database for support information related to the question and retrieves the relevant information. This information includes official child-rearing support information provided by the national and local governments.

[0562] Processing by the terminal

[0563] 1. Enter and submit your question

[0564] The user inputs a question using a communication device such as the LINE app, and the input question is sent to the server.

[0565] 2. Receiving and Displaying Responses

[0566] The answer and support information sent from the server are received and displayed on the screen of the communication terminal.

[0567] Specific examples

[0568] For example, suppose a user inputs a question such as, "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?"

[0569] 1. User Input

[0570] The user inputs a question into the communication terminal and presses the send button.

[0571] 2. Server Analysis

[0572] The server receives the questions and categorizes them into categories such as "night crying" and "childcare worries."

[0573] 3. Answer Generation

[0574] The server generates an answer such as, "Changing the environment and adjusting the sleep rhythm are effective in treating babies' nighttime crying."

[0575] 4. Reliability Assessment

[0576] A reliability assessment model verifies the reliability of the answer and obtains a score above a threshold.

[0577] 5. Submitting and Viewing Your Answers

[0578] The server sends a reliable response to the user's communication terminal, which then displays the received response on its screen so that the user can confirm it.

[0579] 6. Providing support information

[0580] In addition, the server searches for support information from relevant local governments and provides additional information such as "Try joining a local mom support community."

[0581] In this manner, the present invention provides a system that can provide pregnancy and parenting information quickly and reliably.

[0582] The processing flow will be explained below.

[0583] Step 1:

[0584] The user opens the LINE app on their communication device and types a question into the text box. For example, they might type, "My baby cries a lot at night. Is there anything I can do about it?"

[0585] Step 2:

[0586] The user presses the send button and the question entered in the text box is sent to the server.

[0587] Step 3:

[0588] The server receives the question and logs it. For example, it might log "Question received: My baby is crying a lot at night. Is there anything I can do about it?"

[0589] Step 4:

[0590] The server analyzes the received question using a natural language processing model. For example, it extracts keywords such as "night crying" or "baby" from the question and categorizes them into "childcare worries."

[0591] Step 5:

[0592] The server generates an appropriate answer based on the question category, for example, "To prevent a baby from crying at night, it is important to create a good sleeping environment. Baby massage and adjusting nap times are also effective."

[0593] Step 6:

[0594] The server evaluates the answer generated by the server using a reliability evaluation model. It determines whether the evaluation score exceeds a predetermined threshold. For example, if the reliability score is evaluated as 90 points and exceeds the threshold, the process proceeds.

[0595] Step 7:

[0596] The server verifies that the reliability score exceeds a predetermined threshold and transmits the generated answer to the user's communication terminal.

[0597] Step 8:

[0598] The device displays the answer received from the server to the user. For example, it might say, "To prevent your baby from crying at night, it's important to create a good bedroom environment. Baby massages and adjusting nap times can also be effective."

[0599] Step 9:

[0600] The server then searches the database for further related support information, such as "Try joining a local mom support community."

[0601] Step 10:

[0602] The device will display additional information to the user, for example, "Try joining a local mom support community."

[0603] Step 11:

[0604] The user reviews this information and, if necessary, enters further questions or decides next steps based on the information provided.

[0605] In this way, the entire system achieves a process that quickly provides reliable answers and relevant information to users' questions.

[0606] Example 1

[0607] 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."

[0608] Currently, many people with concerns or questions about pregnancy and child-rearing find it difficult to quickly obtain reliable information. While a great deal of information exists on the Internet, its reliability and accuracy cannot be guaranteed. Furthermore, there are limited means of centrally obtaining support information provided by local governments and specialist institutions, which requires users to go to the trouble of searching multiple sources of information. There is a need to solve these problems and enable users to quickly and accurately obtain the information they need.

[0609] 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.

[0610] In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question using natural language processing technology and classifying the question into a category corresponding to the question, means for generating an answer to the analyzed question using a generative AI model, means for evaluating the reliability of the generated answer using a reliability evaluation model, means for transmitting the answer to the communication terminal if the reliability is determined to exceed a predetermined threshold, means for generating and transmitting a message prompting the user to ask the question again if the reliability is below the predetermined threshold, means for searching a database for related information based on the question and acquiring the relevant information, means for displaying the acquired related information on the communication terminal, and means for providing a user interface for inputting a question from the communication terminal. This enables users to quickly and centrally acquire reliable answers and support information to their concerns and questions.

[0611] A "communication terminal" is a device that allows a user to input and send questions, and includes smartphones, tablets, PCs, etc.

[0612] "Natural language processing technology" is a technology for analyzing text data and understanding linguistic meaning, and includes morphological analysis and contextual analysis.

[0613] A "generative AI model" is an algorithm or program for generating natural language responses based on input prompts, including, for example, large-scale language models.

[0614] A "trust assessment model" is an algorithm or program for assessing the usefulness and accuracy of generated answers, including polarity classifiers and label prediction models.

[0615] The "trust threshold" is a reference value for evaluating the reliability of a generated answer, and indicates that an answer will be officially sent only if it exceeds this value.

[0616] A "database" is a collection of data for efficiently searching and retrieving relevant information based on a question, and includes relational and non-relational databases.

[0617] A "user interface" is an operating environment in which a user can input questions through a communication terminal and check the results, and includes applications and websites.

[0618] The present invention describes an information support system for resolving worries and questions about pregnancy and child-rearing. This system provides appropriate answers and support information to questions entered by users through a communication terminal. Specifically, the system is configured as follows.

[0619] Server configuration and processing contents

[0620] 1. Receiving Questions

[0621] When a user inputs and sends a question using a communication terminal, the question reaches the server. The server receives the question through an API. For example, a RESTful API is used as this API.

[0622] 2. Question Analysis

[0623] After receiving the question, the server analyzes it using natural language processing technology. Specifically, it uses a "natural language processing library" to extract the question's subject and keywords and classify them into appropriate categories (e.g., night crying, breastfeeding, parenting worries, etc.). Libraries used include spaCy and NLTK.

[0624] 3. Answer Generation

[0625] Based on the analyzed question, the server uses a "generative AI model" to generate an appropriate answer. One example of a model used for generation is OpenAI's GPT-3. A prompt sentence tailored to the question is input into the model to generate an answer. For example, a prompt sentence such as "My baby's crying at night is terrible. Is there anything I can do about it?" can be used.

[0626] 4. Reliability Assessment

[0627] The generated answers are then evaluated for their trustworthiness using a trustworthiness assessment model, such as a polarity classifier or label prediction model, which evaluates whether the answer is accurate and useful and outputs a trustworthiness score.

[0628] 5. Submit your response

[0629] If the reliability score exceeds a predetermined threshold (e.g., 80%), the server sends the generated answer to the user's communication terminal. If the reliability score is below the threshold, the server generates and sends a message prompting the user to ask a more detailed question.

[0630] 6. Searching for support information

[0631] The server searches and retrieves relevant support information from a database based on the query, including official childcare support information from the national and local governments. PostgreSQL and MongoDB are used for the database.

[0632] Terminal configuration and processing contents

[0633] 1. Providing a user interface

[0634] Users use communication devices such as smartphones or tablets to input and send questions through messaging services such as the LINE app or WhatsApp. The app provides a user interface, creating an environment where users can easily input questions.

[0635] 2. Receiving and displaying responses and support information

[0636] The response and support information sent from the server is received by the communication device, which then displays it on the LINE app or WhatsApp screen. The user can check the received response and support information on the screen and take the necessary action.

[0637] Specific examples

[0638] For example, consider the case where a user uses the LINE app on a communication device to send a question such as, "My baby's night crying is so bad I'm worried. Is there anything I can do about it?" The server receives the question and analyzes it using the spaCy library. Next, it uses a GPT-3 model to generate an answer: "To combat night crying, it's effective to create a good environment and regulate the baby's sleep rhythm." The reliability evaluation model assigns a reliability score of 85% to this answer, and because this score exceeds the threshold, the answer is sent to the user's communication device. At the same time, support information such as "local mom support communities" is retrieved from the database and provided to the user.

[0639] The above is an embodiment of the present invention. This system enables users to quickly obtain reliable information about pregnancy and childcare.

[0640] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0641] Step 1:

[0642] A user inputs and sends a question using a communication terminal.

[0643] Specifically, a user opens a messaging app such as LINE or WhatsApp, types a question into the text box, for example, "My baby's crying at night is so bad I'm worried. Is there anything I can do about it?", and presses the send button. This operation sends the question data from the communication device to the server.

[0644] Input: A question entered by the user into a communication device (e.g., "My baby cries a lot at night. Is there anything I can do about it?")

[0645] Output: Question data is sent to the server

[0646] Step 2:

[0647] The server receives the question and analyzes it using natural language processing techniques.

[0648] After receiving the question via the RESTful API, the server analyzes it using a natural language processing library (e.g., spaCy). The analysis extracts the question's subject and keywords (e.g., baby, night crying, measures), and then categorizes it into categories (e.g., night crying, parenting worries).

[0649] Input: Question data sent from the communication terminal

[0650] Output: Parsed question topics, keywords, and categories

[0651] Step 3:

[0652] The server generates an answer using a generative AI model based on the analysis results.

[0653] Based on the analysis results, a generative AI model (e.g., OpenAI GPT-3) is used as the prompt. The prompt is generated based on the analysis results, and a question such as, "My baby's nighttime crying is so bad I'm worried. Is there anything I can do about it?" is entered. The generative AI model then generates an answer, such as, "To combat nighttime crying, it is effective to improve the baby's environment and sleep rhythm."

[0654] Input: Parsed question subject, keywords, categories, and prompt sentence

[0655] Output: Generated answer text

[0656] Step 4:

[0657] The server evaluates the trustworthiness of the generated answer using a trustworthiness evaluation model.

[0658] The generated answer is evaluated for reliability through a reliability assessment model (e.g., polarity classifier, label prediction model). A reliability score is generated, and a score of, say, 85% is assigned. It is then determined whether this score exceeds a predetermined threshold (e.g., 80%).

[0659] Input: Generated answer

[0660] Output: Confidence score for the generated answer

[0661] Step 5:

[0662] If the reliability exceeds a predetermined threshold, the server sends a response to the communication terminal.

[0663] If the reliability score exceeds the threshold, the server transmits the generated answer to the communication terminal, whereas if the reliability score falls below the threshold, the server generates and transmits a message prompting further questioning.

[0664] Input: Confidence score for generated answers

[0665] Output: A reliable answer or re-question message is sent to the communication device.

[0666] Step 6:

[0667] The server searches and retrieves relevant information based on the question from a database.

[0668] The server searches a database (e.g., PostgreSQL, MongoDB) based on the question and retrieves relevant support information (e.g., official childcare support information from the national or local government).

[0669] Input: Question content and analysis results

[0670] Output: Related information search results

[0671] Step 7:

[0672] The terminal receives and displays the response and related information.

[0673] The communication device receives the response and related information sent from the server, and the received information is displayed on the LINE app or WhatsApp screen for the user to check.

[0674] Input: Submitted answers and related information

[0675] Output: Answers and related information displayed on the communication device

[0676] (Application example 1)

[0677] 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."

[0678] The present invention relates to a system that provides appropriate and prompt information support to users who have concerns or questions about pregnancy and childcare. In particular, in situations where services such as childcare products are provided in physical stores, there is a need to provide optimal support based on the user's location information. However, current information support systems lack real-time support within the store, which makes it difficult for users to quickly obtain appropriate information and services.

[0679] 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.

[0680] In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question and classifying it into a category corresponding to the question, means for generating an answer to the analyzed question, means for evaluating the reliability of the generated answer, means for transmitting the answer to the communication terminal if it is determined that the reliability exceeds a predetermined threshold, means for searching for support information based on the question and acquiring corresponding information, means for displaying the acquired support information on the communication terminal, and means for providing information on related products and services of nearby stores based on the user's location information. This enables the user to not only receive highly reliable information about pregnancy and childcare, but also to quickly receive guidance on optimal products and services based on their location.

[0681] A "communication terminal" is an electronic device that allows a user to input information and exchange information with a server. Examples of this include smartphones and tablets.

[0682] "Analyzing a question" is the process of analyzing the content of a question entered by a user and understanding its meaning and intent.

[0683] "Categorizing" refers to grouping the analyzed questions according to specific themes or topics.

[0684] "Answer generation" is the process of creating an appropriate response to the parsed question.

[0685] "Assessing credibility" is the process of determining whether the generated answer is accurate and useful.

[0686] "Sending an answer to a communication terminal" means sending the evaluated answer to the communication terminal used by the user.

[0687] "Searching for help" is the process of searching a database for additional information or advice related to the user's question.

[0688] "Displaying the acquired support information" means displaying the related information acquired by the search on the user's communication terminal.

[0689] "Providing information about related products and services based on the user's location information" means providing information about products and services near the user's current location.

[0690] As an embodiment of the present invention, we will specifically describe an information support system for resolving concerns and questions about pregnancy and child-rearing. This system receives questions entered from a communication terminal and provides appropriate answers and support information.

[0691] Hardware and software used

[0692] Communication terminals: Includes electronic devices such as smartphones and tablets that allow users to input and receive information.

[0693] Server: The back-end system used to analyze and process data. This server is equipped with the following software:

[0694] Query processing system: Receives questions, analyzes them, categorizes them, generates answers, and assesses their reliability.

[0695] Generative AI models: Use AI models such as OpenAI's ChatGPT to generate appropriate answers.

[0696] Database system: A database for storing and retrieving support information based on a question.

[0697] GPS function: Obtains the user's location information and uses it to provide information on the most relevant products and services.

[0698] Program processing

[0699] The server receives questions entered from the communication terminal. The received questions are first analyzed and classified into categories according to their content. An appropriate answer is then generated for the analyzed question using a generative AI model. The reliability of the generated answer is then evaluated, and if the reliability score exceeds a predetermined threshold, the answer is sent to the communication terminal.

[0700] Furthermore, based on the user's question, the system searches for relevant support information from a database and acquires the relevant information. The acquired support information is displayed on the communication terminal. Additionally, based on the user's location information, the system also provides information on related products and services from nearby stores.

[0701] Specific examples

[0702] For example, consider the case where a user inputs a question such as "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?"

[0703] 1. The user enters a question into the communication terminal and presses the send button.

[0704] 2. The server receives the questions and categorizes them into categories such as "night crying" or "parenting worries."

[0705] 3. The server uses a generative AI model (e.g., OpenAI's ChatGPT) to generate an answer such as, "To prevent babies from crying at night, it is effective to improve their environment and sleep rhythm."

[0706] 4. The reliability of the answer is evaluated using a reliability evaluation model, and if it exceeds a predetermined threshold, the answer is sent to the user's communication terminal.

[0707] 5. Furthermore, the server searches the database for relevant support information and provides additional information such as "Try joining a local mom support community."

[0708] 6. Based on the user's location, information about related products and services available in nearby stores will also be provided.

[0709] In this way, the present invention can provide users with prompt and reliable answers and support information to their questions and concerns about pregnancy and child-rearing.

[0710] Example of input prompt sentence:

[0711] User Question: My baby cries a lot at night. Is there anything I can do about it?

[0712] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0713] Step 1:

[0714] The user uses a communication terminal (for example, a smartphone) to input a question and presses the send button.

[0715] Input: A question typed by the user (e.g., "My baby cries a lot at night. Is there anything I can do about it?").

[0716] Output: The question is sent to the server.

[0717] Step 2:

[0718] The server receives the query sent from the communication terminal.

[0719] Input: Question sent from communications terminal.

[0720] Output: The received query data.

[0721] Step 3:

[0722] The server analyzes the received questions and categorizes them based on their content.

[0723] Input: The received query data.

[0724] Data processing: The question content is analyzed using natural language processing technology to extract key keywords and phrases.

[0725] Output: Question categorization (e.g., "Crying at night" or "Parenting worries").

[0726] Step 4:

[0727] The server generates appropriate answers for categorized questions using a generative AI model (e.g., OpenAI's ChatGPT).

[0728] Input: Categorized questions.

[0729] Data computation: Generative AI models are used to generate answers that correspond to categories.

[0730] Output: The generated answer (e.g., "Changing the environment and adjusting sleep routines can help with babies' night crying").

[0731] Step 5:

[0732] The server evaluates the trustworthiness of the generated answer.

[0733] Input: The generated answer.

[0734] Data calculation: Use the reliability assessment model to calculate the reliability score of the answer.

[0735] Output: A confidence score.

[0736] Step 6:

[0737] The server determines whether the reliability score exceeds a predetermined threshold, and if so, transmits a response to the communication terminal.

[0738] Input: Confidence score.

[0739] Data calculation: Compare the confidence score to a threshold.

[0740] Output: Answer data that is judged to be reliable. If the reliability is low, a prompt to ask the question again is generated.

[0741] Step 7:

[0742] The server searches the database for relevant support information based on the query and acquires the relevant information.

[0743] Input: Question content and category information.

[0744] Data calculation: Using database search algorithms to retrieve relevant supporting information.

[0745] Output: Support information data (e.g., "Information about local support communities for mothers").

[0746] Step 8:

[0747] The server obtains the user's location information and provides information on related products and services at nearby stores based on that information.

[0748] Input: User's location, question.

[0749] Data calculation: Search and obtain information about nearby stores and related products and services based on location information.

[0750] Output: Information about nearby stores (e.g., "A store near you sells nighttime baby products").

[0751] Step 9:

[0752] The server transmits the acquired support information and nearby store information to the communication terminal, which then displays this information to the user.

[0753] Input: reliable answers, assistance, store information.

[0754] Output: Information displayed on the communication device.

[0755] Step 10:

[0756] The user checks the answers and support information received on the communication terminal and takes the necessary action.

[0757] Input: Information displayed on the communication terminal.

[0758] Output: User behavior (e.g., joining a mom support community, purchasing related products).

[0759] 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.

[0760] The present invention provides an information support system for resolving worries and questions about pregnancy and child-rearing. This system receives user questions, classifies them, generates answers, evaluates their reliability, and combines them with an emotion engine that recognizes the user's emotions. Specific embodiments of the system are described below.

[0761] System configuration

[0762] server

[0763] The server has a means for receiving questions input from a communication terminal, a means for analyzing the content of the question and classifying it into a category corresponding to the question, a means for generating an appropriate answer to the analyzed question and evaluating its reliability, and a means for transmitting the answer to the communication terminal if it is determined that the reliability exceeds a predetermined threshold. The server also has a means for searching for support information based on the question and acquiring the relevant information.

[0764] Emotion Engine

[0765] The emotion engine recognizes the user's emotion when receiving a question and adjusts the tone and content of the response based on the user's emotional state. For example, if the user is feeling anxious or stressed, the emotion engine may provide additional information about relaxation techniques or support services. It also generates and sends encouraging or congratulatory messages if the user's emotion is positive.

[0766] Terminal

[0767] A communication device that allows users to enter questions and view the received answers. The device provides a user interface using the LINE app or other messaging services. Users can enter questions and view answers through this interface.

[0768] User

[0769] The users of the system are individuals who have questions about pregnancy and childcare. Users input their questions through a communication terminal and receive answers and related information.

[0770] Processing Details

[0771] Server processing

[0772] 1. Receiving Questions

[0773] When a user sends a question using a communication terminal, the question content is sent to the server, which analyzes the question content and classifies it into categories.

[0774] 2. Answer Generation and Evaluation

[0775] The server generates an appropriate answer based on the analysis of the question, evaluates it using a trust evaluation model, and if the evaluation score exceeds a predetermined threshold, sends the answer to the user's communication terminal.

[0776] 3. Search for support information

[0777] The server searches the database for support information related to the question and retrieves the relevant information, including official child-rearing support information provided by the national and local governments.

[0778] 4. Emotional Recognition

[0779] The server uses an emotion engine to recognize the user's emotion when submitting a question, and this emotion data is used to generate and tailor answers.

[0780] 5. Adjust your responses based on emotions

[0781] The server adjusts the tone and content of the response based on the user's emotional state, as determined by the emotion engine. For example, if the server determines that the user is feeling stressed, it adds information about relaxation techniques and mental support.

[0782] 6. Submitting the final response

[0783] After the adjusted final answer passes the reliability evaluation, it is sent to the user's communication terminal.

[0784] Processing by the terminal

[0785] 1. Enter and submit your question

[0786] The user inputs a question using a communication device such as the LINE app, and the input question is sent to the server.

[0787] 2. Receiving and Displaying Responses

[0788] The answer and support information sent from the server are received and displayed on the screen of the communication terminal.

[0789] Specific examples

[0790] For example, if a user inputs a question such as "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?", the detailed flow is as follows:

[0791] 1. User Input

[0792] The user inputs a question into the communication terminal and presses the send button.

[0793] 2. Server Analysis

[0794] The server receives the questions and categorizes them into categories such as "night crying" and "childcare worries."

[0795] 3. Answer Generation

[0796] The server generates an answer such as, "Changing the environment and adjusting the sleep rhythm are effective in treating babies' nighttime crying."

[0797] 4. Reliability Assessment

[0798] A reliability assessment model verifies the reliability of the answer and obtains a score above a threshold.

[0799] 5. Emotional awareness and regulation

[0800] The emotion engine recognizes the user's anxiety and adds information about relaxation techniques and local support communities.

[0801] 6. Submitting and Viewing Final Answers

[0802] The server sends a reliable response to the user's communication terminal, which then displays the received response and additional information on its screen for the user to review.

[0803] In this way, the present invention realizes a system that quickly provides reliable answers to user questions and information that takes into consideration the user's feelings.

[0804] The processing flow will be explained below.

[0805] Processing Details

[0806] Step 1:

[0807] The user opens the LINE app on their communication device and types a question into the text box: "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?"

[0808] Step 2:

[0809] The user presses the send button and the question entered in the text box is sent to the server.

[0810] Step 3:

[0811] The server receives the question and logs it, for example, "Question received: My baby is crying a lot at night. Is there anything I can do about it?"

[0812] Step 4:

[0813] The server analyzes the question using a natural language processing model, extracts keywords such as "night crying" and "baby," and classifies them into the category of "childcare concerns."

[0814] Step 5:

[0815] When a user submits a question, the server analyzes the user's emotions using an emotion engine. The emotion engine reads anxiety and stress from the user's text and generates emotion data. For example, it records "User emotion: Anxiety (score 75)."

[0816] Step 6:

[0817] The server generates an appropriate answer based on the question category, for example, "To prevent a baby from crying at night, it is important to create a good sleeping environment. Baby massage and adjusting nap times are also effective."

[0818] Step 7:

[0819] The server evaluates the generated answer using a reliability evaluation model. It determines whether the evaluation score exceeds a predetermined threshold (e.g., 80 or more), and the score is evaluated as 90.

[0820] Step 8:

[0821] Based on the results of the emotion engine, the server adds information on relaxation techniques and mental support to ease the user's anxiety. For example, it adds information such as, "Deep breathing and light stretching are recommended to help you relax. Try joining a local mom support community."

[0822] Step 9:

[0823] The server sends a final response to the user's communication terminal.

[0824] Step 10:

[0825] The device displays the answer it receives from the server to the user. For example, it might say, "To prevent your baby from crying at night, it's important to create a good bedroom environment. Baby massages and adjusting nap times can also be effective. Deep breathing and light stretching are recommended for relaxation. Try joining a local support community for mothers."

[0826] Step 11:

[0827] The user reviews this information and, if necessary, enters further questions or decides next steps based on the information provided.

[0828] In this way, the entire system achieves a process of quickly providing reliable answers and emotionally sensitive information to users' questions.

[0829] Example 2

[0830] 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."

[0831] In modern society, an increasing number of individuals have concerns and questions about pregnancy and child-rearing, but it is difficult to provide reliable information quickly and obtain answers that take into consideration the user's feelings.In addition, there are insufficient systems that provide appropriate support information according to emotions, so it is necessary to ensure that users can use the system with peace of mind.

[0832] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question and classifying it into a category corresponding to the question, means for generating an answer to the analyzed question, means for evaluating the reliability of the generated answer, means for recognizing the user's emotions when the question was sent, means for adjusting the tone and content of the answer based on the user's emotional state, means for sending the answer to the communication terminal if it is determined that the reliability exceeds a predetermined threshold, means for searching for support information based on the question and acquiring corresponding information, and means for displaying the acquired support information on the communication terminal. This allows the user to quickly obtain a reliable answer and is also provided with appropriate support information corresponding to the user's emotions, allowing the user to use the system with peace of mind.

[0833] A "communication terminal" is a device that allows a user to input questions and display the received answers, such as a smartphone or a personal computer.

[0834] A "question" refers to a question or concern about pregnancy and child-rearing that a user inputs using a communication terminal and sends to the server.

[0835] "Analysis" refers to the process in which the server uses natural language processing technology to interpret the content of the question received and classify it into categories.

[0836] "Categories" are themes or topics classified based on the content of the question, and include, for example, "night crying" and "childcare worries."

[0837] "Answer" refers to information that includes solutions or advice to the user's questions or concerns, which the server generates based on the analyzed question.

[0838] "Evaluation" refers to the process by which the server verifies the quality and reliability of the generated answers, using a reliability evaluation model.

[0839] "Emotion" refers to the psychological state the user is in when submitting the question, and includes anxiety, stress, joy, etc.

[0840] An "emotion engine" refers to a system that allows the server to recognize the user's emotions and adjust the tone and content of the response based on that data.

[0841] "Support information" refers to information about specific support and resources obtained from external databases related to the question.

[0842] "Credibility" is one of the evaluation criteria that indicates whether the generated answer is useful to the user, accurate, and appropriate.

[0843] The "threshold" refers to a reference point for determining whether or not the reliability evaluation score will provide an answer to a user.

[0844] MODE FOR CARRYING OUT THE INVENTION

[0845] The present invention provides an information support system for resolving worries and questions about pregnancy and child-rearing. Specific embodiments of the system will be described in detail below.

[0846] Hardware and software used

[0847] server

[0848] The server is responsible for receiving questions, analyzing them, generating answers, evaluating trustworthiness, recognizing emotions, searching for support information, and sending answers. A typical server computer is used for the hardware. The software uses the following technologies:

[0849] Natural language processing libraries: NLTK, spaCy

[0850] Learning model: Machine learning algorithm, reliability evaluation model

[0851] Sentiment Engine: Sentiment Analysis Algorithm

[0852] communication terminal

[0853] The communication terminal is a device where the user can input questions and receive answers. It can be a smartphone or a PC. The user interface is the LINE app or other messaging services.

[0854] User

[0855] Users use this system to input questions and receive answers, primarily individuals with questions or concerns about pregnancy and child-rearing.

[0856] Specific processing flow

[0857] 1. Enter and submit your question

[0858] The user opens the LINE app on their communication device, types a question, for example, "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?" and presses the send button.

[0859] 2. Receiving and analyzing questions

[0860] The server analyzes the received questions and uses natural language processing libraries (NLTK or spaCy) to classify them into categories such as "night crying" or "parenting worries."

[0861] 3. Answer Generation

[0862] Based on the analysis results, the server generates an answer to the question such as, "Changing the environment and adjusting the sleep rhythm are effective in treating babies' nighttime crying."

[0863] 4. Reliability Assessment

[0864] The server calculates a reputation score for the generated answer using a reliability evaluation model, and proceeds to the next step only if the reputation score exceeds a predetermined threshold.

[0865] 5. Searching for support information

[0866] The server searches national and local government databases for support information related to the question and retrieves the relevant information. For example, it provides additional information on "local child-rearing support communities."

[0867] 6. Emotional awareness and regulation

[0868] The server uses an emotion engine to recognize emotions such as anxiety or stress from the user's question text, and adjusts the tone and content of the answer based on this emotion data. For example, it adds information about relaxation techniques to the answer.

[0869] 7. Submitting the final response

[0870] After the final adjusted answer passes the reliability evaluation, the server sends the final answer to the device. For example, it might say, "To combat your baby's nighttime crying, it's effective to improve the environment and regulate their sleep rhythm. Also, why not try joining a local parenting support community?"

[0871] 8. Receiving and Displaying Responses

[0872] The user's device receives the final answer sent from the server and displays it on the LINE app screen. The user can check the displayed answer and re-enter the question if necessary.

[0873] Example prompt sentences

[0874] Examples of prompts:

[0875] Example user question: My baby cries a lot at night. Is there anything I can do about it?

[0876] Emotion recognition: The user is determined to be feeling anxious.

[0877] Answer generation: To prevent babies from crying at night, it is effective to improve the environment and adjust their sleep rhythm.

[0878] Trustworthiness rating: The rating score exceeds a predetermined threshold.

[0879] Adjustments: Add information about relaxation techniques and local support communities.

[0880] Final answer: To combat nighttime crying, it is effective to improve the environment and establish a regular sleep routine. Also, why not join a local parenting support community?

[0881] As described above, the present invention realizes a system that quickly provides highly reliable answers to user questions and information that takes into consideration the user's feelings.

[0882] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0883] Step 1: Enter and submit your question

[0884] Input: The user's question or concern (e.g., "My baby cries a lot at night. Is there anything I can do about it?").

[0885] How it works: The user opens the LINE app on their device, enters the question as shown above, and presses the send button.

[0886] Output: The question text is sent to the server.

[0887] Step 2: Receiving and parsing the question

[0888] Input: The question text sent from the terminal.

[0889] How it works: The server receives the question text and uses natural language processing libraries (NLTK or spaCy) to analyze the question and classify it into categories such as "night crying" or "parenting worries."

[0890] Output: Question category information.

[0891] Step 3: Generate an answer

[0892] Input: Question category information.

[0893] How it works: The server searches a database of pre-prepared answers for the appropriate answer corresponding to the category, and generates an answer such as, "To treat a baby's night crying, it is effective to improve the environment and adjust the baby's sleep rhythm."

[0894] Output: The generated answer text.

[0895] Step 4: Assess reliability

[0896] Input: The generated answer text.

[0897] Operation: The server inputs the generated answer into the reliability evaluation model and calculates the evaluation score. If the evaluation score exceeds a predetermined threshold, it proceeds to the next step.

[0898] Output: A reliability assessment score.

[0899] Step 5: Finding support

[0900] Input: Confidence assessment score and question category information.

[0901] Operation: The server searches national and local government databases for support information related to the question and retrieves relevant information (e.g., information on local child-rearing support communities).

[0902] Output: Supporting information.

[0903] Step 6: Recognize and regulate your emotions

[0904] Input: Question text and generated answer text.

[0905] How it works: The server uses an emotion engine to recognize the user's emotions (e.g., anxiety or stress) from the question text. It then adjusts the generated answer based on the recognized emotion data, for example, adding information about relaxation techniques.

[0906] Output: The adjusted answer text.

[0907] Step 7: Submit your final response

[0908] Input: The adjusted answer text.

[0909] Operation: The server clears the trust evaluation and sends the adjusted final answer to the user's communication device.

[0910] Output: The final answer is sent to the terminal.

[0911] Step 8: Receive and view responses

[0912] Input: The final answer sent by the server.

[0913] Operation: The communication device receives the final response and displays it on the LINE app screen, allowing the user to check the displayed response.

[0914] Output: The final answer text that is displayed on the user's communication device.

[0915] Through the above processing steps, users can quickly obtain reliable answers and emotionally sensitive information.

[0916] (Application example 2)

[0917] 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."

[0918] There is a need to provide an information support system that can provide fast and reliable information to users who have concerns or questions about pregnancy and childcare, as well as to improve user satisfaction by providing appropriate support and answers according to the user's emotional state. In addition, there is a need to strengthen on-site support in physical stores, such as by providing information on related products and recommending products.

[0919] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question and classifying it into a category corresponding to the question, means for generating an answer to the analyzed question, means for evaluating the reliability of the generated answer, means for transmitting the answer to the communication terminal if the reliability is determined to exceed a predetermined threshold, means for searching for support information based on the question and acquiring the relevant information, means for recognizing the user's emotion and adjusting the tone and content of the answer based on the user's emotional state, means for displaying the acquired support information on the communication terminal, means for guiding the user to the location of related products and recommended products in a physical store, and means for generating a message prompting the user to ask the question again and transmitting the message to the communication terminal if the generated answer falls below the reliability evaluation threshold. This enables the provision of reliable information about pregnancy and childcare, the creation of appropriate support tailored to the user's emotional state, and user support in a physical store.

[0920] A "communication terminal" is a device that allows a user to input a question and send it to a server.

[0921] The "means for receiving a question" is a function that enables the server to receive a question sent from a communication terminal.

[0922] The "means for analyzing questions" is a function that understands the received questions and classifies them into appropriate categories according to their contents.

[0923] The "means for generating an answer" is a function that creates an appropriate answer based on the analyzed question.

[0924] "Means for assessing reliability" is a function for checking the accuracy and reliability of the generated answers.

[0925] The "means for sending a response" is a function for sending back a response whose reliability has been confirmed to the communication terminal.

[0926] "Means for searching for support information" is a function that finds information related to a question from a database or the like.

[0927] The "means for acquiring support information" is a function that allows the server to acquire the searched support information.

[0928] "Means for recognizing emotions" is a function for analyzing and understanding the emotional state of the user when entering a question.

[0929] "Means to adjust the tone and content of responses" refers to a function that appropriately changes the wording and content of generated responses based on the recognized user sentiment.

[0930] The "means for displaying support information" is a function for displaying acquired support information on the user's communication terminal.

[0931] "Means for guiding users to the location of related products and recommended products" refers to a function that allows users to navigate to the location of related products and recommended products within a physical store.

[0932] The "means for generating a message prompting the user to ask again" is a function for creating and sending a message prompting the user to ask the question again when the reliability of the answer is low.

[0933] The present invention is an information support system for resolving worries and questions about pregnancy and child-rearing, and is designed to provide answers and support information in accordance with the user's emotional state in a physical store. This embodiment will be described in detail below.

[0934] System configuration

[0935] server

[0936] Server Role:

[0937] The server plays a central role in analyzing questions sent from communication terminals, generating and evaluating appropriate answers, and providing the final answer to the user. The server has the following functions:

[0938] 1. Receiving Questions

[0939] A question input from a communication terminal is received.

[0940] 2. Question Analysis

[0941] Analyze the incoming question and classify it into a category that corresponds to the question, for example, using a natural language processing (NLP) model.

[0942] 3. Answer Generation

[0943] Generate answers to questions, using generative AI models to create relevant answers.

[0944] 4. Reliability Assessment

[0945] Evaluate the reliability of the generated answers. Check the accuracy of the answers using a reliability evaluation model.

[0946] 5. Submitting the final response

[0947] If it is determined that the reliability exceeds a predetermined threshold, a response is transmitted to the communication terminal.

[0948] 6. Searching for and obtaining support information

[0949] Search databases for support based on your question and retrieve relevant information, including data from official sources.

[0950] 7. Emotional awareness and regulation

[0951] Recognizing the user's emotions and adjusting the tone and content of responses based on their emotional state, for example by using a sentiment analysis engine (such as IBM Watson Tone Analyzer).

[0952] 8. Display of support information

[0953] The acquired support information is displayed on the communication terminal.

[0954] 9. Generate a message prompting you to ask again

[0955] If the generated answer falls below the reliability evaluation threshold, a message prompting the user to ask the question again is generated and transmitted to the communication terminal.

[0956] communication terminal

[0957] The role of the communication terminal:

[0958] A communication terminal is a device that allows users to input questions and receive answers and assistance information. It has the following functions:

[0959] 1. Enter and submit your question

[0960] A question entry form is provided where users can enter and submit their questions.

[0961] 2. Receiving and displaying responses and support information

[0962] Answers and support information sent from the server are received and displayed on the screen.

[0963] Physical store

[0964] In-store applications:

[0965] The system has the following features to enhance customer support in physical stores:

[0966] 1. Product Information

[0967] It guides users to the location of relevant products and recommends products in physical stores.

[0968] Specific examples

[0969] For example, if a user enters "I don't know how to choose diapers for my baby. Which ones are good?" in a physical store, the processing details are as follows:

[0970] 1. Enter and submit your question

[0971] The user enters a question into the communication terminal and presses the send button.

[0972] 2. Question Analysis

[0973] The server receives the questions and categorizes them into categories such as "How to choose diapers."

[0974] 3. Answer Generation

[0975] The server generates answers such as, "When choosing diapers, the baby's size, absorbency, and material are important. There are multiple options available in stores."

[0976] 4. Emotional awareness and regulation

[0977] The emotion engine recognizes the user's anxiety and tailors responses with a warm, reassuring tone, adding relaxation techniques and information about local support communities.

[0978] 5. Information on related products

[0979] The location of related products and recommended products within the physical store are displayed on the user's communication device.

[0980] Prompt sentences to input to the generative AI model

[0981] Prompt to generate an answer for the user:

[0982] "A customer asks, 'I don't know how to choose diapers for my baby in a physical store. Which ones are good?' Generate a reliable answer based on the question and provide additional information as needed."

[0983] Sentiment analysis prompt:

[0984] "Generate data that can be used to analyze sentiment from user questions and respond with the appropriate tone."

[0985] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0986] Step 1: Enter and submit your question

[0987] User action: The user opens the application on the communication terminal, enters "I don't know how to choose diapers for my baby. Which one is best?" into the question input form, and presses the send button.

[0988] Input: The question entered by the user.

[0989] Output: Question data sent from the communication terminal to the server.

[0990] Specific operation: The communication terminal sends the question data to the server as an HTTP POST request.

[0991] Step 2: Receiving and parsing the question

[0992] Server operation: The server receives the question sent from the communication terminal and analyzes the question using natural language processing (NLP).

[0993] Input: Query data sent from the communication terminal.

[0994] Output: Analysis results, specifically category information (e.g., "How to choose diapers").

[0995] Specific operation: The server uses an NLP tool (e.g., Google Cloud Natural Language API) to analyze the question and classify it into the appropriate category.

[0996] Step 3: Generate an answer

[0997] Server operation: The server uses a generative AI model to generate an appropriate answer based on the analysis results.

[0998] Input: Parsed category information.

[0999] Output: Generated answer (e.g., "When choosing a diaper, the baby's size, absorbency, and material are important. There are multiple options available in stores.").

[1000] Specific operation: The server uses a generative AI model (e.g., OpenAI GPT-3) to generate an appropriate answer based on the category information.

[1001] Step 4: Assess reliability

[1002] Server operation: The reliability of the generated answer is evaluated using a reliability evaluation model.

[1003] Input: The generated answer.

[1004] Output: A reliability assessment score.

[1005] How it works: The server uses a machine learning model (e.g., Scikit-learn or TensorFlow) to evaluate the reliability of the generated answer and calculate a score.

[1006] Step 5: Authenticity check and submit your answer

[1007] Server operation: If the reliability evaluation score exceeds a predetermined threshold, the server transmits an answer to the user's communication terminal.

[1008] Inputs: Confidence assessment score, generated answer.

[1009] Output: The answer sent to the user's communication device.

[1010] Specific operation: Check whether the reliability evaluation score exceeds the threshold, and if so, send the answer to the user's communication device in JSON format.

[1011] Step 6: Search and obtain support information

[1012] Server operation: Based on the content of the question, related support information is searched and acquired from the database.

[1013] Input: Question content, analysis results.

[1014] Output: Relevant supporting information.

[1015] Specific operation: The server queries the database and retrieves relevant data, such as official childcare support information from the government or local government.

[1016] Step 7: Recognize your emotions and adjust your response

[1017] Server Action: Uses an emotion engine to analyze the user's emotions and adjusts the tone and content of responses accordingly.

[1018] Input: User question data.

[1019] Output: A tailored response (e.g., a reassuring tone).

[1020] Specific operation: The server uses an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions and adjust the response text as necessary.

[1021] Step 8: Submit your final response and supporting information

[1022] Server operation: The server sends the final answer that has passed the reliability evaluation and the acquired support information to the user's communication terminal.

[1023] Input: Adjusted final answer, obtained supporting information.

[1024] Output: The final answer and supporting information sent to the user's communication terminal.

[1025] Specific operation: Reliable answers and assistance information are integrated and sent to the user's communication device in JSON format.

[1026] Step 9: Displaying answers and product information

[1027] Communication terminal operation: The received answers and support information are displayed on the screen, and the location of related products and recommended products are shown in the physical store.

[1028] Input: The final answer and supporting information sent from the server.

[1029] Output: Answers and support information displayed on the communication device screen, and information on related products in physical stores.

[1030] Specific operation: The communication terminal analyzes the received data and displays it on the user interface, while also using GPS and beacons to guide the user to the location of the product within the physical store.

[1031] This will enable the provision of reliable information about pregnancy and childcare, appropriate support tailored to the user's emotions, and user support in physical stores.

[1032] 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.

[1033] 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.

[1034] 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.

[1035] [Third embodiment]

[1036] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1037] 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.

[1038] 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).

[1039] 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.

[1040] 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.

[1041] 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).

[1042] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1043] 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.

[1044] 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.

[1045] 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.

[1046] 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.

[1047] 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."

[1048] The present invention provides an information support system for resolving worries and questions about pregnancy and child-rearing. The system allows users to input questions via a communication terminal and provides appropriate answers and support information to those questions.

[1049] System configuration

[1050] server

[1051] The server has a means for receiving questions input from a communication terminal. It analyzes the content of the question and classifies it into a category appropriate to the question. It generates an appropriate answer to the analyzed question and evaluates its reliability. If the reliability of the generated answer exceeds a predetermined threshold, it transmits the answer and searches for and acquires support information based on the question.

[1052] Terminal

[1053] A communication device that allows users to enter questions and view the received answers. The device provides a user interface using the LINE app or other messaging services. Users can enter questions and view answers through this interface.

[1054] User

[1055] The users of the system are individuals who have questions about pregnancy and childcare. Users input their questions through a communication terminal and receive answers and related information.

[1056] Processing Details

[1057] Server processing

[1058] 1. Receiving Questions

[1059] When a user sends a question using a communication terminal, the content of the question is sent to a server.

[1060] The server analyzes the question and categorizes it into the appropriate category.

[1061] 2. Answer Generation and Evaluation

[1062] The server generates an appropriate answer based on the analysis of the question, and the reliability of the generated answer is evaluated using a reliability evaluation model.

[1063] If the confidence score exceeds a predetermined threshold, an answer is sent to the user's communication terminal, and if the confidence score is below the threshold, a message prompting the user to ask the question again is generated.

[1064] 3. Search for support information

[1065] The system searches the database for support information related to the question and retrieves the relevant information. This information includes official child-rearing support information provided by the national and local governments.

[1066] Processing by the terminal

[1067] 1. Enter and submit your question

[1068] The user inputs a question using a communication device such as the LINE app, and the input question is sent to the server.

[1069] 2. Receiving and Displaying Responses

[1070] The answer and support information sent from the server are received and displayed on the screen of the communication terminal.

[1071] Specific examples

[1072] For example, suppose a user inputs a question such as, "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?"

[1073] 1. User Input

[1074] The user inputs a question into the communication terminal and presses the send button.

[1075] 2. Server Analysis

[1076] The server receives the questions and categorizes them into categories such as "night crying" and "childcare worries."

[1077] 3. Answer Generation

[1078] The server generates an answer such as, "Changing the environment and adjusting the sleep rhythm are effective in treating babies' nighttime crying."

[1079] 4. Reliability Assessment

[1080] A reliability assessment model verifies the reliability of the answer and obtains a score above a threshold.

[1081] 5. Submitting and Viewing Your Answers

[1082] The server sends a reliable response to the user's communication terminal, which then displays the received response on its screen so that the user can confirm it.

[1083] 6. Providing support information

[1084] In addition, the server searches for support information from relevant local governments and provides additional information such as "Try joining a local mom support community."

[1085] In this manner, the present invention provides a system that can provide pregnancy and parenting information quickly and reliably.

[1086] The processing flow will be explained below.

[1087] Step 1:

[1088] The user opens the LINE app on their communication device and types a question into the text box. For example, they might type, "My baby cries a lot at night. Is there anything I can do about it?"

[1089] Step 2:

[1090] The user presses the send button and the question entered in the text box is sent to the server.

[1091] Step 3:

[1092] The server receives the question and logs it. For example, it might log "Question received: My baby is crying a lot at night. Is there anything I can do about it?"

[1093] Step 4:

[1094] The server analyzes the received question using a natural language processing model. For example, it extracts keywords such as "night crying" or "baby" from the question and categorizes them into "childcare worries."

[1095] Step 5:

[1096] The server generates an appropriate answer based on the question category, for example, "To prevent a baby from crying at night, it is important to create a good sleeping environment. Baby massage and adjusting nap times are also effective."

[1097] Step 6:

[1098] The server evaluates the answer generated by the server using a reliability evaluation model. It determines whether the evaluation score exceeds a predetermined threshold. For example, if the reliability score is evaluated as 90 points and exceeds the threshold, the process proceeds.

[1099] Step 7:

[1100] The server verifies that the reliability score exceeds a predetermined threshold and transmits the generated answer to the user's communication terminal.

[1101] Step 8:

[1102] The device displays the answer received from the server to the user. For example, it might say, "To prevent your baby from crying at night, it's important to create a good bedroom environment. Baby massages and adjusting nap times can also be effective."

[1103] Step 9:

[1104] The server then searches the database for further related support information, such as "Try joining a local mom support community."

[1105] Step 10:

[1106] The device will display additional information to the user, for example, "Try joining a local mom support community."

[1107] Step 11:

[1108] The user reviews this information and, if necessary, enters further questions or decides next steps based on the information provided.

[1109] In this way, the entire system achieves a process that quickly provides reliable answers and relevant information to users' questions.

[1110] Example 1

[1111] 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."

[1112] Currently, many people with concerns or questions about pregnancy and child-rearing find it difficult to quickly obtain reliable information. While a great deal of information exists on the Internet, its reliability and accuracy cannot be guaranteed. Furthermore, there are limited means of centrally obtaining support information provided by local governments and specialist institutions, which requires users to go to the trouble of searching multiple sources of information. There is a need to solve these problems and enable users to quickly and accurately obtain the information they need.

[1113] 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.

[1114] In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question using natural language processing technology and classifying the question into a category corresponding to the question, means for generating an answer to the analyzed question using a generative AI model, means for evaluating the reliability of the generated answer using a reliability evaluation model, means for transmitting the answer to the communication terminal if the reliability is determined to exceed a predetermined threshold, means for generating and transmitting a message prompting the user to ask the question again if the reliability is below the predetermined threshold, means for searching a database for related information based on the question and acquiring the relevant information, means for displaying the acquired related information on the communication terminal, and means for providing a user interface for inputting a question from the communication terminal. This enables users to quickly and centrally acquire reliable answers and support information to their concerns and questions.

[1115] A "communication terminal" is a device that allows a user to input and send questions, and includes smartphones, tablets, PCs, etc.

[1116] "Natural language processing technology" is a technology for analyzing text data and understanding linguistic meaning, and includes morphological analysis and contextual analysis.

[1117] A "generative AI model" is an algorithm or program for generating natural language responses based on input prompts, including, for example, large-scale language models.

[1118] A "trust assessment model" is an algorithm or program for assessing the usefulness and accuracy of generated answers, including polarity classifiers and label prediction models.

[1119] The "trust threshold" is a reference value for evaluating the reliability of a generated answer, and indicates that an answer will be officially sent only if it exceeds this value.

[1120] A "database" is a collection of data for efficiently searching and retrieving relevant information based on a question, and includes relational and non-relational databases.

[1121] A "user interface" is an operating environment in which a user can input questions through a communication terminal and check the results, and includes applications and websites.

[1122] The present invention describes an information support system for resolving worries and questions about pregnancy and child-rearing. This system provides appropriate answers and support information to questions entered by users through a communication terminal. Specifically, the system is configured as follows.

[1123] Server configuration and processing contents

[1124] 1. Receiving Questions

[1125] When a user inputs and sends a question using a communication terminal, the question reaches the server. The server receives the question through an API. For example, a RESTful API is used as this API.

[1126] 2. Question Analysis

[1127] After receiving the question, the server analyzes it using natural language processing technology. Specifically, it uses a "natural language processing library" to extract the question's subject and keywords and classify them into appropriate categories (e.g., night crying, breastfeeding, parenting worries, etc.). Libraries used include spaCy and NLTK.

[1128] 3. Answer Generation

[1129] Based on the analyzed question, the server uses a "generative AI model" to generate an appropriate answer. One example of a model used for generation is OpenAI's GPT-3. A prompt sentence tailored to the question is input into the model to generate an answer. For example, a prompt sentence such as "My baby's crying at night is terrible. Is there anything I can do about it?" can be used.

[1130] 4. Reliability Assessment

[1131] The generated answers are then evaluated for their trustworthiness using a trustworthiness assessment model, such as a polarity classifier or label prediction model, which evaluates whether the answer is accurate and useful and outputs a trustworthiness score.

[1132] 5. Submit your response

[1133] If the reliability score exceeds a predetermined threshold (e.g., 80%), the server sends the generated answer to the user's communication terminal. If the reliability score is below the threshold, the server generates and sends a message prompting the user to ask a more detailed question.

[1134] 6. Searching for support information

[1135] The server searches and retrieves relevant support information from a database based on the query, including official childcare support information from the national and local governments. PostgreSQL and MongoDB are used for the database.

[1136] Terminal configuration and processing contents

[1137] 1. Providing a user interface

[1138] Users use communication devices such as smartphones or tablets to input and send questions through messaging services such as the LINE app or WhatsApp. The app provides a user interface, creating an environment where users can easily input questions.

[1139] 2. Receiving and displaying responses and support information

[1140] The response and support information sent from the server is received by the communication device, which then displays it on the LINE app or WhatsApp screen. The user can check the received response and support information on the screen and take the necessary action.

[1141] Specific examples

[1142] For example, consider the case where a user uses the LINE app on a communication device to send a question such as, "My baby's night crying is so bad I'm worried. Is there anything I can do about it?" The server receives the question and analyzes it using the spaCy library. Next, it uses a GPT-3 model to generate an answer: "To combat night crying, it's effective to create a good environment and regulate the baby's sleep rhythm." The reliability evaluation model assigns a reliability score of 85% to this answer, and because this score exceeds the threshold, the answer is sent to the user's communication device. At the same time, support information such as "local mom support communities" is retrieved from the database and provided to the user.

[1143] The above is an embodiment of the present invention. This system enables users to quickly obtain reliable information about pregnancy and childcare.

[1144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1145] Step 1:

[1146] A user inputs and sends a question using a communication terminal.

[1147] Specifically, a user opens a messaging app such as LINE or WhatsApp, types a question into the text box, for example, "My baby's crying at night is so bad I'm worried. Is there anything I can do about it?", and presses the send button. This operation sends the question data from the communication device to the server.

[1148] Input: A question entered by the user into a communication device (e.g., "My baby cries a lot at night. Is there anything I can do about it?")

[1149] Output: Question data is sent to the server

[1150] Step 2:

[1151] The server receives the question and analyzes it using natural language processing techniques.

[1152] After receiving the question via the RESTful API, the server analyzes it using a natural language processing library (e.g., spaCy). The analysis extracts the question's subject and keywords (e.g., baby, night crying, measures), and then categorizes it into categories (e.g., night crying, parenting worries).

[1153] Input: Question data sent from the communication terminal

[1154] Output: Parsed question topics, keywords, and categories

[1155] Step 3:

[1156] The server generates an answer using a generative AI model based on the analysis results.

[1157] Based on the analysis results, a generative AI model (e.g., OpenAI GPT-3) is used as the prompt. The prompt is generated based on the analysis results, and a question such as, "My baby's nighttime crying is so bad I'm worried. Is there anything I can do about it?" is entered. The generative AI model then generates an answer, such as, "To combat nighttime crying, it is effective to improve the baby's environment and sleep rhythm."

[1158] Input: Parsed question subject, keywords, categories, and prompt sentence

[1159] Output: Generated answer text

[1160] Step 4:

[1161] The server evaluates the trustworthiness of the generated answer using a trustworthiness evaluation model.

[1162] The generated answer is evaluated for reliability through a reliability assessment model (e.g., polarity classifier, label prediction model). A reliability score is generated, and a score of, say, 85% is assigned. It is then determined whether this score exceeds a predetermined threshold (e.g., 80%).

[1163] Input: Generated answer

[1164] Output: Confidence score for the generated answer

[1165] Step 5:

[1166] If the reliability exceeds a predetermined threshold, the server sends a response to the communication terminal.

[1167] If the reliability score exceeds the threshold, the server transmits the generated answer to the communication terminal, whereas if the reliability score falls below the threshold, the server generates and transmits a message prompting further questioning.

[1168] Input: Confidence score for generated answers

[1169] Output: A reliable answer or re-question message is sent to the communication device.

[1170] Step 6:

[1171] The server searches and retrieves relevant information based on the question from a database.

[1172] The server searches a database (e.g., PostgreSQL, MongoDB) based on the question and retrieves relevant support information (e.g., official childcare support information from the national or local government).

[1173] Input: Question content and analysis results

[1174] Output: Related information search results

[1175] Step 7:

[1176] The terminal receives and displays the response and related information.

[1177] The communication device receives the response and related information sent from the server, and the received information is displayed on the LINE app or WhatsApp screen for the user to check.

[1178] Input: Submitted answers and related information

[1179] Output: Answers and related information displayed on the communication device

[1180] (Application example 1)

[1181] 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."

[1182] The present invention relates to a system that provides appropriate and prompt information support to users who have concerns or questions about pregnancy and childcare. In particular, in situations where services such as childcare products are provided in physical stores, there is a need to provide optimal support based on the user's location information. However, current information support systems lack real-time support within the store, which makes it difficult for users to quickly obtain appropriate information and services.

[1183] 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.

[1184] In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question and classifying it into a category corresponding to the question, means for generating an answer to the analyzed question, means for evaluating the reliability of the generated answer, means for transmitting the answer to the communication terminal if it is determined that the reliability exceeds a predetermined threshold, means for searching for support information based on the question and acquiring corresponding information, means for displaying the acquired support information on the communication terminal, and means for providing information on related products and services of nearby stores based on the user's location information. This enables the user to not only receive highly reliable information about pregnancy and childcare, but also to quickly receive guidance on optimal products and services based on their location.

[1185] A "communication terminal" is an electronic device that allows a user to input information and exchange information with a server. Examples of this include smartphones and tablets.

[1186] "Analyzing a question" is the process of analyzing the content of a question entered by a user and understanding its meaning and intent.

[1187] "Categorizing" refers to grouping the analyzed questions according to specific themes or topics.

[1188] "Answer generation" is the process of creating an appropriate response to the parsed question.

[1189] "Assessing credibility" is the process of determining whether the generated answer is accurate and useful.

[1190] "Sending an answer to a communication terminal" means sending the evaluated answer to the communication terminal used by the user.

[1191] "Searching for help" is the process of searching a database for additional information or advice related to the user's question.

[1192] "Displaying the acquired support information" means displaying the related information acquired by the search on the user's communication terminal.

[1193] "Providing information about related products and services based on the user's location information" means providing information about products and services near the user's current location.

[1194] As an embodiment of the present invention, we will specifically describe an information support system for resolving concerns and questions about pregnancy and child-rearing. This system receives questions entered from a communication terminal and provides appropriate answers and support information.

[1195] Hardware and software used

[1196] Communication terminals: Includes electronic devices such as smartphones and tablets that allow users to input and receive information.

[1197] Server: The back-end system used to analyze and process data. This server is equipped with the following software:

[1198] Query processing system: Receives questions, analyzes them, categorizes them, generates answers, and assesses their reliability.

[1199] Generative AI models: Use AI models such as OpenAI's ChatGPT to generate appropriate answers.

[1200] Database system: A database for storing and retrieving support information based on a question.

[1201] GPS function: Obtains the user's location information and uses it to provide information on the most relevant products and services.

[1202] Program processing

[1203] The server receives questions entered from the communication terminal. The received questions are first analyzed and classified into categories according to their content. An appropriate answer is then generated for the analyzed question using a generative AI model. The reliability of the generated answer is then evaluated, and if the reliability score exceeds a predetermined threshold, the answer is sent to the communication terminal.

[1204] Furthermore, based on the user's question, the system searches for relevant support information from a database and acquires the relevant information. The acquired support information is displayed on the communication terminal. Additionally, based on the user's location information, the system also provides information on related products and services from nearby stores.

[1205] Specific examples

[1206] For example, consider the case where a user inputs a question such as "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?"

[1207] 1. The user enters a question into the communication terminal and presses the send button.

[1208] 2. The server receives the questions and categorizes them into categories such as "night crying" or "parenting worries."

[1209] 3. The server uses a generative AI model (e.g., OpenAI's ChatGPT) to generate an answer such as, "To prevent babies from crying at night, it is effective to improve their environment and sleep rhythm."

[1210] 4. The reliability of the answer is evaluated using a reliability evaluation model, and if it exceeds a predetermined threshold, the answer is sent to the user's communication terminal.

[1211] 5. Furthermore, the server searches the database for relevant support information and provides additional information such as "Try joining a local mom support community."

[1212] 6. Based on the user's location, information about related products and services available in nearby stores will also be provided.

[1213] In this way, the present invention can provide users with prompt and reliable answers and support information to their questions and concerns about pregnancy and child-rearing.

[1214] Example of input prompt sentence:

[1215] User Question: My baby cries a lot at night. Is there anything I can do about it?

[1216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1217] Step 1:

[1218] The user uses a communication terminal (for example, a smartphone) to input a question and presses the send button.

[1219] Input: A question typed by the user (e.g., "My baby cries a lot at night. Is there anything I can do about it?").

[1220] Output: The question is sent to the server.

[1221] Step 2:

[1222] The server receives the query sent from the communication terminal.

[1223] Input: Question sent from communications terminal.

[1224] Output: The received query data.

[1225] Step 3:

[1226] The server analyzes the received questions and categorizes them based on their content.

[1227] Input: The received query data.

[1228] Data processing: The question content is analyzed using natural language processing technology to extract key keywords and phrases.

[1229] Output: Question categorization (e.g., "Crying at night" or "Parenting worries").

[1230] Step 4:

[1231] The server generates appropriate answers for categorized questions using a generative AI model (e.g., OpenAI's ChatGPT).

[1232] Input: Categorized questions.

[1233] Data computation: Generative AI models are used to generate answers that correspond to categories.

[1234] Output: The generated answer (e.g., "Changing the environment and adjusting sleep routines can help with babies' night crying").

[1235] Step 5:

[1236] The server evaluates the trustworthiness of the generated answer.

[1237] Input: The generated answer.

[1238] Data calculation: Use the reliability assessment model to calculate the reliability score of the answer.

[1239] Output: A confidence score.

[1240] Step 6:

[1241] The server determines whether the reliability score exceeds a predetermined threshold, and if so, transmits a response to the communication terminal.

[1242] Input: Confidence score.

[1243] Data calculation: Compare the confidence score to a threshold.

[1244] Output: Answer data that is judged to be reliable. If the reliability is low, a prompt to ask the question again is generated.

[1245] Step 7:

[1246] The server searches the database for relevant support information based on the query and acquires the relevant information.

[1247] Input: Question content and category information.

[1248] Data calculation: Using database search algorithms to retrieve relevant supporting information.

[1249] Output: Support information data (e.g., "Information about local support communities for mothers").

[1250] Step 8:

[1251] The server obtains the user's location information and provides information on related products and services at nearby stores based on that information.

[1252] Input: User's location, question.

[1253] Data calculation: Search and obtain information about nearby stores and related products and services based on location information.

[1254] Output: Information about nearby stores (e.g., "A store near you sells nighttime baby products").

[1255] Step 9:

[1256] The server transmits the acquired support information and nearby store information to the communication terminal, which then displays this information to the user.

[1257] Input: reliable answers, assistance, store information.

[1258] Output: Information displayed on the communication device.

[1259] Step 10:

[1260] The user checks the answers and support information received on the communication terminal and takes the necessary action.

[1261] Input: Information displayed on the communication terminal.

[1262] Output: User behavior (e.g., joining a mom support community, purchasing related products).

[1263] 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.

[1264] The present invention provides an information support system for resolving worries and questions about pregnancy and child-rearing. This system receives user questions, classifies them, generates answers, evaluates their reliability, and combines them with an emotion engine that recognizes the user's emotions. Specific embodiments of the system are described below.

[1265] System configuration

[1266] server

[1267] The server has a means for receiving questions input from a communication terminal, a means for analyzing the content of the question and classifying it into a category corresponding to the question, a means for generating an appropriate answer to the analyzed question and evaluating its reliability, and a means for transmitting the answer to the communication terminal if it is determined that the reliability exceeds a predetermined threshold. The server also has a means for searching for support information based on the question and acquiring the relevant information.

[1268] Emotion Engine

[1269] The emotion engine recognizes the user's emotion when receiving a question and adjusts the tone and content of the response based on the user's emotional state. For example, if the user is feeling anxious or stressed, the emotion engine may provide additional information about relaxation techniques or support services. It also generates and sends encouraging or congratulatory messages if the user's emotion is positive.

[1270] Terminal

[1271] A communication device that allows users to enter questions and view the received answers. The device provides a user interface using the LINE app or other messaging services. Users can enter questions and view answers through this interface.

[1272] User

[1273] The users of the system are individuals who have questions about pregnancy and childcare. Users input their questions through a communication terminal and receive answers and related information.

[1274] Processing Details

[1275] Server processing

[1276] 1. Receiving Questions

[1277] When a user sends a question using a communication terminal, the question content is sent to the server, which analyzes the question content and classifies it into categories.

[1278] 2. Answer Generation and Evaluation

[1279] The server generates an appropriate answer based on the analysis of the question, evaluates it using a trust evaluation model, and if the evaluation score exceeds a predetermined threshold, sends the answer to the user's communication terminal.

[1280] 3. Search for support information

[1281] The server searches the database for support information related to the question and retrieves the relevant information, including official child-rearing support information provided by the national and local governments.

[1282] 4. Emotional Recognition

[1283] The server uses an emotion engine to recognize the user's emotion when submitting a question, and this emotion data is used to generate and tailor answers.

[1284] 5. Adjust your responses based on emotions

[1285] The server adjusts the tone and content of the response based on the user's emotional state, as determined by the emotion engine. For example, if the server determines that the user is feeling stressed, it adds information about relaxation techniques and mental support.

[1286] 6. Submitting the final response

[1287] After the adjusted final answer passes the reliability evaluation, it is sent to the user's communication terminal.

[1288] Processing by the terminal

[1289] 1. Enter and submit your question

[1290] The user inputs a question using a communication device such as the LINE app, and the input question is sent to the server.

[1291] 2. Receiving and Displaying Responses

[1292] The answer and support information sent from the server are received and displayed on the screen of the communication terminal.

[1293] Specific examples

[1294] For example, if a user inputs a question such as "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?", the detailed flow is as follows:

[1295] 1. User Input

[1296] The user inputs a question into the communication terminal and presses the send button.

[1297] 2. Server Analysis

[1298] The server receives the questions and categorizes them into categories such as "night crying" and "childcare worries."

[1299] 3. Answer Generation

[1300] The server generates an answer such as, "Changing the environment and adjusting the sleep rhythm are effective in treating babies' nighttime crying."

[1301] 4. Reliability Assessment

[1302] A reliability assessment model verifies the reliability of the answer and obtains a score above a threshold.

[1303] 5. Emotional awareness and regulation

[1304] The emotion engine recognizes the user's anxiety and adds information about relaxation techniques and local support communities.

[1305] 6. Submitting and Viewing Final Answers

[1306] The server sends a reliable response to the user's communication terminal, which then displays the received response and additional information on its screen for the user to review.

[1307] In this way, the present invention realizes a system that quickly provides reliable answers to user questions and information that takes into consideration the user's feelings.

[1308] The processing flow will be explained below.

[1309] Processing Details

[1310] Step 1:

[1311] The user opens the LINE app on their communication device and types a question into the text box: "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?"

[1312] Step 2:

[1313] The user presses the send button and the question entered in the text box is sent to the server.

[1314] Step 3:

[1315] The server receives the question and logs it, for example, "Question received: My baby is crying a lot at night. Is there anything I can do about it?"

[1316] Step 4:

[1317] The server analyzes the question using a natural language processing model, extracts keywords such as "night crying" and "baby," and classifies them into the category of "childcare concerns."

[1318] Step 5:

[1319] When a user submits a question, the server analyzes the user's emotions using an emotion engine. The emotion engine reads anxiety and stress from the user's text and generates emotion data. For example, it records "User emotion: Anxiety (score 75)."

[1320] Step 6:

[1321] The server generates an appropriate answer based on the question category, for example, "To prevent a baby from crying at night, it is important to create a good sleeping environment. Baby massage and adjusting nap times are also effective."

[1322] Step 7:

[1323] The server evaluates the generated answer using a reliability evaluation model. It determines whether the evaluation score exceeds a predetermined threshold (e.g., 80 or more), and the score is evaluated as 90.

[1324] Step 8:

[1325] Based on the results of the emotion engine, the server adds information on relaxation techniques and mental support to ease the user's anxiety. For example, it adds information such as, "Deep breathing and light stretching are recommended to help you relax. Try joining a local mom support community."

[1326] Step 9:

[1327] The server sends a final response to the user's communication terminal.

[1328] Step 10:

[1329] The device displays the answer it receives from the server to the user. For example, it might say, "To prevent your baby from crying at night, it's important to create a good bedroom environment. Baby massages and adjusting nap times can also be effective. Deep breathing and light stretching are recommended for relaxation. Try joining a local support community for mothers."

[1330] Step 11:

[1331] The user reviews this information and, if necessary, enters further questions or decides next steps based on the information provided.

[1332] In this way, the entire system achieves a process of quickly providing reliable answers and emotionally sensitive information to users' questions.

[1333] Example 2

[1334] 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."

[1335] In modern society, an increasing number of individuals have concerns and questions about pregnancy and child-rearing, but it is difficult to provide reliable information quickly and obtain answers that take into consideration the user's feelings.In addition, there are insufficient systems that provide appropriate support information according to emotions, so it is necessary to ensure that users can use the system with peace of mind.

[1336] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question and classifying it into a category corresponding to the question, means for generating an answer to the analyzed question, means for evaluating the reliability of the generated answer, means for recognizing the user's emotions when the question was sent, means for adjusting the tone and content of the answer based on the user's emotional state, means for sending the answer to the communication terminal if it is determined that the reliability exceeds a predetermined threshold, means for searching for support information based on the question and acquiring corresponding information, and means for displaying the acquired support information on the communication terminal. This allows the user to quickly obtain a reliable answer and is also provided with appropriate support information corresponding to the user's emotions, allowing the user to use the system with peace of mind.

[1337] A "communication terminal" is a device that allows a user to input questions and display the received answers, such as a smartphone or a personal computer.

[1338] A "question" refers to a question or concern about pregnancy and child-rearing that a user inputs using a communication terminal and sends to the server.

[1339] "Analysis" refers to the process in which the server uses natural language processing technology to interpret the content of the question received and classify it into categories.

[1340] "Categories" are themes or topics classified based on the content of the question, and include, for example, "night crying" and "childcare worries."

[1341] "Answer" refers to information that includes solutions or advice to the user's questions or concerns, which the server generates based on the analyzed question.

[1342] "Evaluation" refers to the process by which the server verifies the quality and reliability of the generated answers, using a reliability evaluation model.

[1343] "Emotion" refers to the psychological state the user is in when submitting the question, and includes anxiety, stress, joy, etc.

[1344] An "emotion engine" refers to a system that allows the server to recognize the user's emotions and adjust the tone and content of the response based on that data.

[1345] "Support information" refers to information about specific support and resources obtained from external databases related to the question.

[1346] "Credibility" is one of the evaluation criteria that indicates whether the generated answer is useful to the user, accurate, and appropriate.

[1347] The "threshold" refers to a reference point for determining whether or not the reliability evaluation score will provide an answer to a user.

[1348] MODE FOR CARRYING OUT THE INVENTION

[1349] The present invention provides an information support system for resolving worries and questions about pregnancy and child-rearing. Specific embodiments of the system will be described in detail below.

[1350] Hardware and software used

[1351] server

[1352] The server is responsible for receiving questions, analyzing them, generating answers, evaluating trustworthiness, recognizing emotions, searching for support information, and sending answers. A typical server computer is used for the hardware. The software uses the following technologies:

[1353] Natural language processing libraries: NLTK, spaCy

[1354] Learning model: Machine learning algorithm, reliability evaluation model

[1355] Sentiment Engine: Sentiment Analysis Algorithm

[1356] communication terminal

[1357] The communication terminal is a device where the user can input questions and receive answers. It can be a smartphone or a PC. The user interface is the LINE app or other messaging services.

[1358] User

[1359] Users use this system to input questions and receive answers, primarily individuals with questions or concerns about pregnancy and child-rearing.

[1360] Specific processing flow

[1361] 1. Enter and submit your question

[1362] The user opens the LINE app on their communication device, types a question, for example, "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?" and presses the send button.

[1363] 2. Receiving and analyzing questions

[1364] The server analyzes the received questions and uses natural language processing libraries (NLTK or spaCy) to classify them into categories such as "night crying" or "parenting worries."

[1365] 3. Answer Generation

[1366] Based on the analysis results, the server generates an answer to the question such as, "Changing the environment and adjusting the sleep rhythm are effective in treating babies' nighttime crying."

[1367] 4. Reliability Assessment

[1368] The server calculates a reputation score for the generated answer using a reliability evaluation model, and proceeds to the next step only if the reputation score exceeds a predetermined threshold.

[1369] 5. Searching for support information

[1370] The server searches national and local government databases for support information related to the question and retrieves the relevant information. For example, it provides additional information on "local child-rearing support communities."

[1371] 6. Emotional awareness and regulation

[1372] The server uses an emotion engine to recognize emotions such as anxiety or stress from the user's question text, and adjusts the tone and content of the answer based on this emotion data. For example, it adds information about relaxation techniques to the answer.

[1373] 7. Submitting the final response

[1374] After the final adjusted answer passes the reliability evaluation, the server sends the final answer to the device. For example, it might say, "To combat your baby's nighttime crying, it's effective to improve the environment and regulate their sleep rhythm. Also, why not try joining a local parenting support community?"

[1375] 8. Receiving and Displaying Responses

[1376] The user's device receives the final answer sent from the server and displays it on the LINE app screen. The user can check the displayed answer and re-enter the question if necessary.

[1377] Example prompt sentences

[1378] Examples of prompts:

[1379] Example user question: My baby cries a lot at night. Is there anything I can do about it?

[1380] Emotion recognition: The user is determined to be feeling anxious.

[1381] Answer generation: To prevent babies from crying at night, it is effective to improve the environment and adjust their sleep rhythm.

[1382] Trustworthiness rating: The rating score exceeds a predetermined threshold.

[1383] Adjustments: Add information about relaxation techniques and local support communities.

[1384] Final answer: To combat nighttime crying, it is effective to improve the environment and establish a regular sleep routine. Also, why not join a local parenting support community?

[1385] As described above, the present invention realizes a system that quickly provides highly reliable answers to user questions and information that takes into consideration the user's feelings.

[1386] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1387] Step 1: Enter and submit your question

[1388] Input: The user's question or concern (e.g., "My baby cries a lot at night. Is there anything I can do about it?").

[1389] How it works: The user opens the LINE app on their device, enters the question as shown above, and presses the send button.

[1390] Output: The question text is sent to the server.

[1391] Step 2: Receiving and parsing the question

[1392] Input: The question text sent from the terminal.

[1393] How it works: The server receives the question text and uses natural language processing libraries (NLTK or spaCy) to analyze the question and classify it into categories such as "night crying" or "parenting worries."

[1394] Output: Question category information.

[1395] Step 3: Generate an answer

[1396] Input: Question category information.

[1397] How it works: The server searches a database of pre-prepared answers for the appropriate answer corresponding to the category, and generates an answer such as, "To treat a baby's night crying, it is effective to improve the environment and adjust the baby's sleep rhythm."

[1398] Output: The generated answer text.

[1399] Step 4: Assess reliability

[1400] Input: The generated answer text.

[1401] Operation: The server inputs the generated answer into the reliability evaluation model and calculates the evaluation score. If the evaluation score exceeds a predetermined threshold, it proceeds to the next step.

[1402] Output: A reliability assessment score.

[1403] Step 5: Finding support

[1404] Input: Confidence assessment score and question category information.

[1405] Operation: The server searches national and local government databases for support information related to the question and retrieves relevant information (e.g., information on local child-rearing support communities).

[1406] Output: Supporting information.

[1407] Step 6: Recognize and regulate your emotions

[1408] Input: Question text and generated answer text.

[1409] How it works: The server uses an emotion engine to recognize the user's emotions (e.g., anxiety or stress) from the question text. It then adjusts the generated answer based on the recognized emotion data, for example, adding information about relaxation techniques.

[1410] Output: The adjusted answer text.

[1411] Step 7: Submit your final response

[1412] Input: The adjusted answer text.

[1413] Operation: The server clears the trust evaluation and sends the adjusted final answer to the user's communication device.

[1414] Output: The final answer is sent to the terminal.

[1415] Step 8: Receive and view responses

[1416] Input: The final answer sent by the server.

[1417] Operation: The communication device receives the final response and displays it on the LINE app screen, allowing the user to check the displayed response.

[1418] Output: The final answer text that is displayed on the user's communication device.

[1419] Through the above processing steps, users can quickly obtain reliable answers and emotionally sensitive information.

[1420] (Application example 2)

[1421] 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."

[1422] There is a need to provide an information support system that can provide fast and reliable information to users who have concerns or questions about pregnancy and childcare, as well as to improve user satisfaction by providing appropriate support and answers according to the user's emotional state. In addition, there is a need to strengthen on-site support in physical stores, such as by providing information on related products and recommending products.

[1423] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question and classifying it into a category corresponding to the question, means for generating an answer to the analyzed question, means for evaluating the reliability of the generated answer, means for transmitting the answer to the communication terminal if the reliability is determined to exceed a predetermined threshold, means for searching for support information based on the question and acquiring the relevant information, means for recognizing the user's emotion and adjusting the tone and content of the answer based on the user's emotional state, means for displaying the acquired support information on the communication terminal, means for guiding the user to the location of related products and recommended products in a physical store, and means for generating a message prompting the user to ask the question again and transmitting the message to the communication terminal if the generated answer falls below the reliability evaluation threshold. This enables the provision of reliable information about pregnancy and childcare, the creation of appropriate support tailored to the user's emotional state, and user support in a physical store.

[1424] A "communication terminal" is a device that allows a user to input a question and send it to a server.

[1425] The "means for receiving a question" is a function that enables the server to receive a question sent from a communication terminal.

[1426] The "means for analyzing questions" is a function that understands the received questions and classifies them into appropriate categories according to their contents.

[1427] The "means for generating an answer" is a function that creates an appropriate answer based on the analyzed question.

[1428] "Means for assessing reliability" is a function for checking the accuracy and reliability of the generated answers.

[1429] The "means for sending a response" is a function for sending back a response whose reliability has been confirmed to the communication terminal.

[1430] "Means for searching for support information" is a function that finds information related to a question from a database or the like.

[1431] The "means for acquiring support information" is a function that allows the server to acquire the searched support information.

[1432] "Means for recognizing emotions" is a function for analyzing and understanding the emotional state of the user when entering a question.

[1433] "Means to adjust the tone and content of responses" refers to a function that appropriately changes the wording and content of generated responses based on the recognized user sentiment.

[1434] The "means for displaying support information" is a function for displaying acquired support information on the user's communication terminal.

[1435] "Means for guiding users to the location of related products and recommended products" refers to a function that allows users to navigate to the location of related products and recommended products within a physical store.

[1436] The "means for generating a message prompting the user to ask again" is a function for creating and sending a message prompting the user to ask the question again when the reliability of the answer is low.

[1437] The present invention is an information support system for resolving worries and questions about pregnancy and child-rearing, and is designed to provide answers and support information in accordance with the user's emotional state in a physical store. This embodiment will be described in detail below.

[1438] System configuration

[1439] server

[1440] Server Role:

[1441] The server plays a central role in analyzing questions sent from communication terminals, generating and evaluating appropriate answers, and providing the final answer to the user. The server has the following functions:

[1442] 1. Receiving Questions

[1443] A question input from a communication terminal is received.

[1444] 2. Question Analysis

[1445] Analyze the incoming question and classify it into a category that corresponds to the question, for example, using a natural language processing (NLP) model.

[1446] 3. Answer Generation

[1447] Generate answers to questions, using generative AI models to create relevant answers.

[1448] 4. Reliability Assessment

[1449] Evaluate the reliability of the generated answers. Check the accuracy of the answers using a reliability evaluation model.

[1450] 5. Submitting the final response

[1451] If it is determined that the reliability exceeds a predetermined threshold, a response is transmitted to the communication terminal.

[1452] 6. Searching for and obtaining support information

[1453] Search databases for support based on your question and retrieve relevant information, including data from official sources.

[1454] 7. Emotional awareness and regulation

[1455] Recognizing the user's emotions and adjusting the tone and content of responses based on their emotional state, for example by using a sentiment analysis engine (such as IBM Watson Tone Analyzer).

[1456] 8. Display of support information

[1457] The acquired support information is displayed on the communication terminal.

[1458] 9. Generate a message prompting you to ask again

[1459] If the generated answer falls below the reliability evaluation threshold, a message prompting the user to ask the question again is generated and transmitted to the communication terminal.

[1460] communication terminal

[1461] The role of the communication terminal:

[1462] A communication terminal is a device that allows users to input questions and receive answers and assistance information. It has the following functions:

[1463] 1. Enter and submit your question

[1464] A question entry form is provided where users can enter and submit their questions.

[1465] 2. Receiving and displaying responses and support information

[1466] Answers and support information sent from the server are received and displayed on the screen.

[1467] Physical store

[1468] In-store applications:

[1469] The system has the following features to enhance customer support in physical stores:

[1470] 1. Product Information

[1471] It guides users to the location of relevant products and recommends products in physical stores.

[1472] Specific examples

[1473] For example, if a user enters "I don't know how to choose diapers for my baby. Which ones are good?" in a physical store, the processing details are as follows:

[1474] 1. Enter and submit your question

[1475] The user enters a question into the communication terminal and presses the send button.

[1476] 2. Question Analysis

[1477] The server receives the questions and categorizes them into categories such as "How to choose diapers."

[1478] 3. Answer Generation

[1479] The server generates answers such as, "When choosing diapers, the baby's size, absorbency, and material are important. There are multiple options available in stores."

[1480] 4. Emotional awareness and regulation

[1481] The emotion engine recognizes the user's anxiety and tailors responses with a warm, reassuring tone, adding relaxation techniques and information about local support communities.

[1482] 5. Information on related products

[1483] The location of related products and recommended products within the physical store are displayed on the user's communication device.

[1484] Prompt sentences to input to the generative AI model

[1485] Prompt to generate an answer for the user:

[1486] "A customer asks, 'I don't know how to choose diapers for my baby in a physical store. Which ones are good?' Generate a reliable answer based on the question and provide additional information as needed."

[1487] Sentiment analysis prompt:

[1488] "Generate data that can be used to analyze sentiment from user questions and respond with the appropriate tone."

[1489] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1490] Step 1: Enter and submit your question

[1491] User action: The user opens the application on the communication terminal, enters "I don't know how to choose diapers for my baby. Which one is best?" into the question input form, and presses the send button.

[1492] Input: The question entered by the user.

[1493] Output: Question data sent from the communication terminal to the server.

[1494] Specific operation: The communication terminal sends the question data to the server as an HTTP POST request.

[1495] Step 2: Receiving and parsing the question

[1496] Server operation: The server receives the question sent from the communication terminal and analyzes the question using natural language processing (NLP).

[1497] Input: Query data sent from the communication terminal.

[1498] Output: Analysis results, specifically category information (e.g., "How to choose diapers").

[1499] Specific operation: The server uses an NLP tool (e.g., Google Cloud Natural Language API) to analyze the question and classify it into the appropriate category.

[1500] Step 3: Generate an answer

[1501] Server operation: The server uses a generative AI model to generate an appropriate answer based on the analysis results.

[1502] Input: Parsed category information.

[1503] Output: Generated answer (e.g., "When choosing a diaper, the baby's size, absorbency, and material are important. There are multiple options available in stores.").

[1504] Specific operation: The server uses a generative AI model (e.g., OpenAI GPT-3) to generate an appropriate answer based on the category information.

[1505] Step 4: Assess reliability

[1506] Server operation: The reliability of the generated answer is evaluated using a reliability evaluation model.

[1507] Input: The generated answer.

[1508] Output: A reliability assessment score.

[1509] How it works: The server uses a machine learning model (e.g., Scikit-learn or TensorFlow) to evaluate the reliability of the generated answer and calculate a score.

[1510] Step 5: Authenticity check and submit your answer

[1511] Server operation: If the reliability evaluation score exceeds a predetermined threshold, the server transmits an answer to the user's communication terminal.

[1512] Inputs: Confidence assessment score, generated answer.

[1513] Output: The answer sent to the user's communication device.

[1514] Specific operation: Check whether the reliability evaluation score exceeds the threshold, and if so, send the answer to the user's communication device in JSON format.

[1515] Step 6: Search and obtain support information

[1516] Server operation: Based on the content of the question, related support information is searched and acquired from the database.

[1517] Input: Question content, analysis results.

[1518] Output: Relevant supporting information.

[1519] Specific operation: The server queries the database and retrieves relevant data, such as official childcare support information from the government or local government.

[1520] Step 7: Recognize your emotions and adjust your response

[1521] Server Action: Uses an emotion engine to analyze the user's emotions and adjusts the tone and content of responses accordingly.

[1522] Input: User question data.

[1523] Output: A tailored response (e.g., a reassuring tone).

[1524] Specific operation: The server uses an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions and adjust the response text as necessary.

[1525] Step 8: Submit your final response and supporting information

[1526] Server operation: The server sends the final answer that has passed the reliability evaluation and the acquired support information to the user's communication terminal.

[1527] Input: Adjusted final answer, obtained supporting information.

[1528] Output: The final answer and supporting information sent to the user's communication terminal.

[1529] Specific operation: Reliable answers and assistance information are integrated and sent to the user's communication device in JSON format.

[1530] Step 9: Displaying answers and product information

[1531] Communication terminal operation: The received answers and support information are displayed on the screen, and the location of related products and recommended products are shown in the physical store.

[1532] Input: The final answer and supporting information sent from the server.

[1533] Output: Answers and support information displayed on the communication device screen, and information on related products in physical stores.

[1534] Specific operation: The communication terminal analyzes the received data and displays it on the user interface, while also using GPS and beacons to guide the user to the location of the product within the physical store.

[1535] This will enable the provision of reliable information about pregnancy and childcare, appropriate support tailored to the user's emotions, and user support in physical stores.

[1536] 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.

[1537] 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.

[1538] 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.

[1539] [Fourth embodiment]

[1540] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1541] 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.

[1542] 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).

[1543] 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.

[1544] 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.

[1545] 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).

[1546] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1547] 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.

[1548] 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.

[1549] 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.

[1550] 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.

[1551] 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.

[1552] 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."

[1553] The present invention provides an information support system for resolving worries and questions about pregnancy and child-rearing. The system allows users to input questions via a communication terminal and provides appropriate answers and support information to those questions.

[1554] System configuration

[1555] server

[1556] The server has a means for receiving questions input from a communication terminal. It analyzes the content of the question and classifies it into a category appropriate to the question. It generates an appropriate answer to the analyzed question and evaluates its reliability. If the reliability of the generated answer exceeds a predetermined threshold, it transmits the answer and searches for and acquires support information based on the question.

[1557] Terminal

[1558] A communication device that allows users to enter questions and view the received answers. The device provides a user interface using the LINE app or other messaging services. Users can enter questions and view answers through this interface.

[1559] User

[1560] The users of the system are individuals who have questions about pregnancy and childcare. Users input their questions through a communication terminal and receive answers and related information.

[1561] Processing Details

[1562] Server processing

[1563] 1. Receiving Questions

[1564] When a user sends a question using a communication terminal, the content of the question is sent to a server.

[1565] The server analyzes the question and categorizes it into the appropriate category.

[1566] 2. Answer Generation and Evaluation

[1567] The server generates an appropriate answer based on the analysis of the question, and the reliability of the generated answer is evaluated using a reliability evaluation model.

[1568] If the confidence score exceeds a predetermined threshold, an answer is sent to the user's communication terminal, and if the confidence score is below the threshold, a message prompting the user to ask the question again is generated.

[1569] 3. Search for support information

[1570] The system searches the database for support information related to the question and retrieves the relevant information. This information includes official child-rearing support information provided by the national and local governments.

[1571] Processing by the terminal

[1572] 1. Enter and submit your question

[1573] The user inputs a question using a communication device such as the LINE app, and the input question is sent to the server.

[1574] 2. Receiving and Displaying Responses

[1575] The answer and support information sent from the server are received and displayed on the screen of the communication terminal.

[1576] Specific examples

[1577] For example, suppose a user inputs a question such as, "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?"

[1578] 1. User Input

[1579] The user inputs a question into the communication terminal and presses the send button.

[1580] 2. Server Analysis

[1581] The server receives the questions and categorizes them into categories such as "night crying" and "childcare worries."

[1582] 3. Answer Generation

[1583] The server generates an answer such as, "Changing the environment and adjusting the sleep rhythm are effective in treating babies' nighttime crying."

[1584] 4. Reliability Assessment

[1585] A reliability assessment model verifies the reliability of the answer and obtains a score above a threshold.

[1586] 5. Submitting and Viewing Your Answers

[1587] The server sends a reliable response to the user's communication terminal, which then displays the received response on its screen so that the user can confirm it.

[1588] 6. Providing support information

[1589] In addition, the server searches for support information from relevant local governments and provides additional information such as "Try joining a local mom support community."

[1590] In this manner, the present invention provides a system that can provide pregnancy and parenting information quickly and reliably.

[1591] The processing flow will be explained below.

[1592] Step 1:

[1593] The user opens the LINE app on their communication device and types a question into the text box. For example, they might type, "My baby cries a lot at night. Is there anything I can do about it?"

[1594] Step 2:

[1595] The user presses the send button and the question entered in the text box is sent to the server.

[1596] Step 3:

[1597] The server receives the question and logs it. For example, it might log "Question received: My baby is crying a lot at night. Is there anything I can do about it?"

[1598] Step 4:

[1599] The server analyzes the received question using a natural language processing model. For example, it extracts keywords such as "night crying" or "baby" from the question and categorizes them into "childcare worries."

[1600] Step 5:

[1601] The server generates an appropriate answer based on the question category, for example, "To prevent a baby from crying at night, it is important to create a good sleeping environment. Baby massage and adjusting nap times are also effective."

[1602] Step 6:

[1603] The server evaluates the answer generated by the server using a reliability evaluation model. It determines whether the evaluation score exceeds a predetermined threshold. For example, if the reliability score is evaluated as 90 points and exceeds the threshold, the process proceeds.

[1604] Step 7:

[1605] The server verifies that the reliability score exceeds a predetermined threshold and transmits the generated answer to the user's communication terminal.

[1606] Step 8:

[1607] The device displays the answer received from the server to the user. For example, it might say, "To prevent your baby from crying at night, it's important to create a good bedroom environment. Baby massages and adjusting nap times can also be effective."

[1608] Step 9:

[1609] The server then searches the database for further related support information, such as "Try joining a local mom support community."

[1610] Step 10:

[1611] The device will display additional information to the user, for example, "Try joining a local mom support community."

[1612] Step 11:

[1613] The user reviews this information and, if necessary, enters further questions or decides next steps based on the information provided.

[1614] In this way, the entire system achieves a process that quickly provides reliable answers and relevant information to users' questions.

[1615] Example 1

[1616] 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."

[1617] Currently, many people with concerns or questions about pregnancy and child-rearing find it difficult to quickly obtain reliable information. While a great deal of information exists on the Internet, its reliability and accuracy cannot be guaranteed. Furthermore, there are limited means of centrally obtaining support information provided by local governments and specialist institutions, which requires users to go to the trouble of searching multiple sources of information. There is a need to solve these problems and enable users to quickly and accurately obtain the information they need.

[1618] 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.

[1619] In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question using natural language processing technology and classifying the question into a category corresponding to the question, means for generating an answer to the analyzed question using a generative AI model, means for evaluating the reliability of the generated answer using a reliability evaluation model, means for transmitting the answer to the communication terminal if the reliability is determined to exceed a predetermined threshold, means for generating and transmitting a message prompting the user to ask the question again if the reliability is below the predetermined threshold, means for searching a database for related information based on the question and acquiring the relevant information, means for displaying the acquired related information on the communication terminal, and means for providing a user interface for inputting a question from the communication terminal. This enables users to quickly and centrally acquire reliable answers and support information to their concerns and questions.

[1620] A "communication terminal" is a device that allows a user to input and send questions, and includes smartphones, tablets, PCs, etc.

[1621] "Natural language processing technology" is a technology for analyzing text data and understanding linguistic meaning, and includes morphological analysis and contextual analysis.

[1622] A "generative AI model" is an algorithm or program for generating natural language responses based on input prompts, including, for example, large-scale language models.

[1623] A "trust assessment model" is an algorithm or program for assessing the usefulness and accuracy of generated answers, including polarity classifiers and label prediction models.

[1624] The "trust threshold" is a reference value for evaluating the reliability of a generated answer, and indicates that an answer will be officially sent only if it exceeds this value.

[1625] A "database" is a collection of data for efficiently searching and retrieving relevant information based on a question, and includes relational and non-relational databases.

[1626] A "user interface" is an operating environment in which a user can input questions through a communication terminal and check the results, and includes applications and websites.

[1627] The present invention describes an information support system for resolving worries and questions about pregnancy and child-rearing. This system provides appropriate answers and support information to questions entered by users through a communication terminal. Specifically, the system is configured as follows.

[1628] Server configuration and processing contents

[1629] 1. Receiving Questions

[1630] When a user inputs and sends a question using a communication terminal, the question reaches the server. The server receives the question through an API. For example, a RESTful API is used as this API.

[1631] 2. Question Analysis

[1632] After receiving the question, the server analyzes it using natural language processing technology. Specifically, it uses a "natural language processing library" to extract the question's subject and keywords and classify them into appropriate categories (e.g., night crying, breastfeeding, parenting worries, etc.). Libraries used include spaCy and NLTK.

[1633] 3. Answer Generation

[1634] Based on the analyzed question, the server uses a "generative AI model" to generate an appropriate answer. One example of a model used for generation is OpenAI's GPT-3. A prompt sentence tailored to the question is input into the model to generate an answer. For example, a prompt sentence such as "My baby's crying at night is terrible. Is there anything I can do about it?" can be used.

[1635] 4. Reliability Assessment

[1636] The generated answers are then evaluated for their trustworthiness using a trustworthiness assessment model, such as a polarity classifier or label prediction model, which evaluates whether the answer is accurate and useful and outputs a trustworthiness score.

[1637] 5. Submit your response

[1638] If the reliability score exceeds a predetermined threshold (e.g., 80%), the server sends the generated answer to the user's communication terminal. If the reliability score is below the threshold, the server generates and sends a message prompting the user to ask a more detailed question.

[1639] 6. Searching for support information

[1640] The server searches and retrieves relevant support information from a database based on the query, including official childcare support information from the national and local governments. PostgreSQL and MongoDB are used for the database.

[1641] Terminal configuration and processing contents

[1642] 1. Providing a user interface

[1643] Users use communication devices such as smartphones or tablets to input and send questions through messaging services such as the LINE app or WhatsApp. The app provides a user interface, creating an environment where users can easily input questions.

[1644] 2. Receiving and displaying responses and support information

[1645] The response and support information sent from the server is received by the communication device, which then displays it on the LINE app or WhatsApp screen. The user can check the received response and support information on the screen and take the necessary action.

[1646] Specific examples

[1647] For example, consider the case where a user uses the LINE app on a communication device to send a question such as, "My baby's night crying is so bad I'm worried. Is there anything I can do about it?" The server receives the question and analyzes it using the spaCy library. Next, it uses a GPT-3 model to generate an answer: "To combat night crying, it's effective to create a good environment and regulate the baby's sleep rhythm." The reliability evaluation model assigns a reliability score of 85% to this answer, and because this score exceeds the threshold, the answer is sent to the user's communication device. At the same time, support information such as "local mom support communities" is retrieved from the database and provided to the user.

[1648] The above is an embodiment of the present invention. This system enables users to quickly obtain reliable information about pregnancy and childcare.

[1649] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1650] Step 1:

[1651] A user inputs and sends a question using a communication terminal.

[1652] Specifically, a user opens a messaging app such as LINE or WhatsApp, types a question into the text box, for example, "My baby's crying at night is so bad I'm worried. Is there anything I can do about it?", and presses the send button. This operation sends the question data from the communication device to the server.

[1653] Input: A question entered by the user into a communication device (e.g., "My baby cries a lot at night. Is there anything I can do about it?")

[1654] Output: Question data is sent to the server

[1655] Step 2:

[1656] The server receives the question and analyzes it using natural language processing techniques.

[1657] After receiving the question via the RESTful API, the server analyzes it using a natural language processing library (e.g., spaCy). The analysis extracts the question's subject and keywords (e.g., baby, night crying, measures), and then categorizes it into categories (e.g., night crying, parenting worries).

[1658] Input: Question data sent from the communication terminal

[1659] Output: Parsed question topics, keywords, and categories

[1660] Step 3:

[1661] The server generates an answer using a generative AI model based on the analysis results.

[1662] Based on the analysis results, a generative AI model (e.g., OpenAI GPT-3) is used as the prompt. The prompt is generated based on the analysis results, and a question such as, "My baby's nighttime crying is so bad I'm worried. Is there anything I can do about it?" is entered. The generative AI model then generates an answer, such as, "To combat nighttime crying, it is effective to improve the baby's environment and sleep rhythm."

[1663] Input: Parsed question subject, keywords, categories, and prompt sentence

[1664] Output: Generated answer text

[1665] Step 4:

[1666] The server evaluates the trustworthiness of the generated answer using a trustworthiness evaluation model.

[1667] The generated answer is evaluated for reliability through a reliability assessment model (e.g., polarity classifier, label prediction model). A reliability score is generated, and a score of, say, 85% is assigned. It is then determined whether this score exceeds a predetermined threshold (e.g., 80%).

[1668] Input: Generated answer

[1669] Output: Confidence score for the generated answer

[1670] Step 5:

[1671] If the reliability exceeds a predetermined threshold, the server sends a response to the communication terminal.

[1672] If the reliability score exceeds the threshold, the server transmits the generated answer to the communication terminal, whereas if the reliability score falls below the threshold, the server generates and transmits a message prompting further questioning.

[1673] Input: Confidence score for generated answers

[1674] Output: A reliable answer or re-question message is sent to the communication device.

[1675] Step 6:

[1676] The server searches and retrieves relevant information based on the question from a database.

[1677] The server searches a database (e.g., PostgreSQL, MongoDB) based on the question and retrieves relevant support information (e.g., official childcare support information from the national or local government).

[1678] Input: Question content and analysis results

[1679] Output: Related information search results

[1680] Step 7:

[1681] The terminal receives and displays the response and related information.

[1682] The communication device receives the response and related information sent from the server, and the received information is displayed on the LINE app or WhatsApp screen for the user to check.

[1683] Input: Submitted answers and related information

[1684] Output: Answers and related information displayed on the communication device

[1685] (Application example 1)

[1686] 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."

[1687] The present invention relates to a system that provides appropriate and prompt information support to users who have concerns or questions about pregnancy and childcare. In particular, in situations where services such as childcare products are provided in physical stores, there is a need to provide optimal support based on the user's location information. However, current information support systems lack real-time support within the store, which makes it difficult for users to quickly obtain appropriate information and services.

[1688] 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.

[1689] In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question and classifying it into a category corresponding to the question, means for generating an answer to the analyzed question, means for evaluating the reliability of the generated answer, means for transmitting the answer to the communication terminal if it is determined that the reliability exceeds a predetermined threshold, means for searching for support information based on the question and acquiring corresponding information, means for displaying the acquired support information on the communication terminal, and means for providing information on related products and services of nearby stores based on the user's location information. This enables the user to not only receive highly reliable information about pregnancy and childcare, but also to quickly receive guidance on optimal products and services based on their location.

[1690] A "communication terminal" is an electronic device that allows a user to input information and exchange information with a server. Examples of this include smartphones and tablets.

[1691] "Analyzing a question" is the process of analyzing the content of a question entered by a user and understanding its meaning and intent.

[1692] "Categorizing" refers to grouping the analyzed questions according to specific themes or topics.

[1693] "Answer generation" is the process of creating an appropriate response to the parsed question.

[1694] "Assessing credibility" is the process of determining whether the generated answer is accurate and useful.

[1695] "Sending an answer to a communication terminal" means sending the evaluated answer to the communication terminal used by the user.

[1696] "Searching for help" is the process of searching a database for additional information or advice related to the user's question.

[1697] "Displaying the acquired support information" means displaying the related information acquired by the search on the user's communication terminal.

[1698] "Providing information about related products and services based on the user's location information" means providing information about products and services near the user's current location.

[1699] As an embodiment of the present invention, we will specifically describe an information support system for resolving concerns and questions about pregnancy and child-rearing. This system receives questions entered from a communication terminal and provides appropriate answers and support information.

[1700] Hardware and software used

[1701] Communication terminals: Includes electronic devices such as smartphones and tablets that allow users to input and receive information.

[1702] Server: The back-end system used to analyze and process data. This server is equipped with the following software:

[1703] Query processing system: Receives questions, analyzes them, categorizes them, generates answers, and assesses their reliability.

[1704] Generative AI models: Use AI models such as OpenAI's ChatGPT to generate appropriate answers.

[1705] Database system: A database for storing and retrieving support information based on a question.

[1706] GPS function: Obtains the user's location information and uses it to provide information on the most relevant products and services.

[1707] Program processing

[1708] The server receives questions entered from the communication terminal. The received questions are first analyzed and classified into categories according to their content. An appropriate answer is then generated for the analyzed question using a generative AI model. The reliability of the generated answer is then evaluated, and if the reliability score exceeds a predetermined threshold, the answer is sent to the communication terminal.

[1709] Furthermore, based on the user's question, the system searches for relevant support information from a database and acquires the relevant information. The acquired support information is displayed on the communication terminal. Additionally, based on the user's location information, the system also provides information on related products and services from nearby stores.

[1710] Specific examples

[1711] For example, consider the case where a user inputs a question such as "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?"

[1712] 1. The user enters a question into the communication terminal and presses the send button.

[1713] 2. The server receives the questions and categorizes them into categories such as "night crying" or "parenting worries."

[1714] 3. The server uses a generative AI model (e.g., OpenAI's ChatGPT) to generate an answer such as, "To prevent babies from crying at night, it is effective to improve their environment and sleep rhythm."

[1715] 4. The reliability of the answer is evaluated using a reliability evaluation model, and if it exceeds a predetermined threshold, the answer is sent to the user's communication terminal.

[1716] 5. Furthermore, the server searches the database for relevant support information and provides additional information such as "Try joining a local mom support community."

[1717] 6. Based on the user's location, information about related products and services available in nearby stores will also be provided.

[1718] In this way, the present invention can provide users with prompt and reliable answers and support information to their questions and concerns about pregnancy and child-rearing.

[1719] Example of input prompt sentence:

[1720] User Question: My baby cries a lot at night. Is there anything I can do about it?

[1721] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1722] Step 1:

[1723] The user uses a communication terminal (for example, a smartphone) to input a question and presses the send button.

[1724] Input: A question typed by the user (e.g., "My baby cries a lot at night. Is there anything I can do about it?").

[1725] Output: The question is sent to the server.

[1726] Step 2:

[1727] The server receives the query sent from the communication terminal.

[1728] Input: Question sent from communications terminal.

[1729] Output: The received query data.

[1730] Step 3:

[1731] The server analyzes the received questions and categorizes them based on their content.

[1732] Input: The received query data.

[1733] Data processing: The question content is analyzed using natural language processing technology to extract key keywords and phrases.

[1734] Output: Question categorization (e.g., "Crying at night" or "Parenting worries").

[1735] Step 4:

[1736] The server generates appropriate answers for categorized questions using a generative AI model (e.g., OpenAI's ChatGPT).

[1737] Input: Categorized questions.

[1738] Data computation: Generative AI models are used to generate answers that correspond to categories.

[1739] Output: The generated answer (e.g., "Changing the environment and adjusting sleep routines can help with babies' night crying").

[1740] Step 5:

[1741] The server evaluates the trustworthiness of the generated answer.

[1742] Input: The generated answer.

[1743] Data calculation: Use the reliability assessment model to calculate the reliability score of the answer.

[1744] Output: A confidence score.

[1745] Step 6:

[1746] The server determines whether the reliability score exceeds a predetermined threshold, and if so, transmits a response to the communication terminal.

[1747] Input: Confidence score.

[1748] Data calculation: Compare the confidence score to a threshold.

[1749] Output: Answer data that is judged to be reliable. If the reliability is low, a prompt to ask the question again is generated.

[1750] Step 7:

[1751] The server searches the database for relevant support information based on the query and acquires the relevant information.

[1752] Input: Question content and category information.

[1753] Data calculation: Using database search algorithms to retrieve relevant supporting information.

[1754] Output: Support information data (e.g., "Information about local support communities for mothers").

[1755] Step 8:

[1756] The server obtains the user's location information and provides information on related products and services at nearby stores based on that information.

[1757] Input: User's location, question.

[1758] Data calculation: Search and obtain information about nearby stores and related products and services based on location information.

[1759] Output: Information about nearby stores (e.g., "A store near you sells nighttime baby products").

[1760] Step 9:

[1761] The server transmits the acquired support information and nearby store information to the communication terminal, which then displays this information to the user.

[1762] Input: reliable answers, assistance, store information.

[1763] Output: Information displayed on the communication device.

[1764] Step 10:

[1765] The user checks the answers and support information received on the communication terminal and takes the necessary action.

[1766] Input: Information displayed on the communication terminal.

[1767] Output: User behavior (e.g., joining a mom support community, purchasing related products).

[1768] 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.

[1769] The present invention provides an information support system for resolving worries and questions about pregnancy and child-rearing. This system receives user questions, classifies them, generates answers, evaluates their reliability, and combines them with an emotion engine that recognizes the user's emotions. Specific embodiments of the system are described below.

[1770] System configuration

[1771] server

[1772] The server has a means for receiving questions input from a communication terminal, a means for analyzing the content of the question and classifying it into a category corresponding to the question, a means for generating an appropriate answer to the analyzed question and evaluating its reliability, and a means for transmitting the answer to the communication terminal if it is determined that the reliability exceeds a predetermined threshold. The server also has a means for searching for support information based on the question and acquiring the relevant information.

[1773] Emotion Engine

[1774] The emotion engine recognizes the user's emotion when receiving a question and adjusts the tone and content of the response based on the user's emotional state. For example, if the user is feeling anxious or stressed, the emotion engine may provide additional information about relaxation techniques or support services. It also generates and sends encouraging or congratulatory messages if the user's emotion is positive.

[1775] Terminal

[1776] A communication device that allows users to enter questions and view the received answers. The device provides a user interface using the LINE app or other messaging services. Users can enter questions and view answers through this interface.

[1777] User

[1778] The users of the system are individuals who have questions about pregnancy and childcare. Users input their questions through a communication terminal and receive answers and related information.

[1779] Processing Details

[1780] Server processing

[1781] 1. Receiving Questions

[1782] When a user sends a question using a communication terminal, the question content is sent to the server, which analyzes the question content and classifies it into categories.

[1783] 2. Answer Generation and Evaluation

[1784] The server generates an appropriate answer based on the analysis of the question, evaluates it using a trust evaluation model, and if the evaluation score exceeds a predetermined threshold, sends the answer to the user's communication terminal.

[1785] 3. Search for support information

[1786] The server searches the database for support information related to the question and retrieves the relevant information, including official child-rearing support information provided by the national and local governments.

[1787] 4. Emotional Recognition

[1788] The server uses an emotion engine to recognize the user's emotion when submitting a question, and this emotion data is used to generate and tailor answers.

[1789] 5. Adjust your responses based on emotions

[1790] The server adjusts the tone and content of the response based on the user's emotional state, as determined by the emotion engine. For example, if the server determines that the user is feeling stressed, it adds information about relaxation techniques and mental support.

[1791] 6. Submitting the final response

[1792] After the adjusted final answer passes the reliability evaluation, it is sent to the user's communication terminal.

[1793] Processing by the terminal

[1794] 1. Enter and submit your question

[1795] The user inputs a question using a communication device such as the LINE app, and the input question is sent to the server.

[1796] 2. Receiving and Displaying Responses

[1797] The answer and support information sent from the server are received and displayed on the screen of the communication terminal.

[1798] Specific examples

[1799] For example, if a user inputs a question such as "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?", the detailed flow is as follows:

[1800] 1. User Input

[1801] The user inputs a question into the communication terminal and presses the send button.

[1802] 2. Server Analysis

[1803] The server receives the questions and categorizes them into categories such as "night crying" and "childcare worries."

[1804] 3. Answer Generation

[1805] The server generates an answer such as, "Changing the environment and adjusting the sleep rhythm are effective in treating babies' nighttime crying."

[1806] 4. Reliability Assessment

[1807] A reliability assessment model verifies the reliability of the answer and obtains a score above a threshold.

[1808] 5. Emotional awareness and regulation

[1809] The emotion engine recognizes the user's anxiety and adds information about relaxation techniques and local support communities.

[1810] 6. Submitting and Viewing Final Answers

[1811] The server sends a reliable response to the user's communication terminal, which then displays the received response and additional information on its screen for the user to review.

[1812] In this way, the present invention realizes a system that quickly provides reliable answers to user questions and information that takes into consideration the user's feelings.

[1813] The processing flow will be explained below.

[1814] Processing Details

[1815] Step 1:

[1816] The user opens the LINE app on their communication device and types a question into the text box: "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?"

[1817] Step 2:

[1818] The user presses the send button and the question entered in the text box is sent to the server.

[1819] Step 3:

[1820] The server receives the question and logs it, for example, "Question received: My baby is crying a lot at night. Is there anything I can do about it?"

[1821] Step 4:

[1822] The server analyzes the question using a natural language processing model, extracts keywords such as "night crying" and "baby," and classifies them into the category of "childcare concerns."

[1823] Step 5:

[1824] When a user submits a question, the server analyzes the user's emotions using an emotion engine. The emotion engine reads anxiety and stress from the user's text and generates emotion data. For example, it records "User emotion: Anxiety (score 75)."

[1825] Step 6:

[1826] The server generates an appropriate answer based on the question category, for example, "To prevent a baby from crying at night, it is important to create a good sleeping environment. Baby massage and adjusting nap times are also effective."

[1827] Step 7:

[1828] The server evaluates the generated answer using a reliability evaluation model. It determines whether the evaluation score exceeds a predetermined threshold (e.g., 80 or more), and the score is evaluated as 90.

[1829] Step 8:

[1830] Based on the results of the emotion engine, the server adds information on relaxation techniques and mental support to ease the user's anxiety. For example, it adds information such as, "Deep breathing and light stretching are recommended to help you relax. Try joining a local mom support community."

[1831] Step 9:

[1832] The server sends a final response to the user's communication terminal.

[1833] Step 10:

[1834] The device displays the answer it receives from the server to the user. For example, it might say, "To prevent your baby from crying at night, it's important to create a good bedroom environment. Baby massages and adjusting nap times can also be effective. Deep breathing and light stretching are recommended for relaxation. Try joining a local support community for mothers."

[1835] Step 11:

[1836] The user reviews this information and, if necessary, enters further questions or decides next steps based on the information provided.

[1837] In this way, the entire system achieves a process of quickly providing reliable answers and emotionally sensitive information to users' questions.

[1838] Example 2

[1839] 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."

[1840] In modern society, an increasing number of individuals have concerns and questions about pregnancy and child-rearing, but it is difficult to provide reliable information quickly and obtain answers that take into consideration the user's feelings.In addition, there are insufficient systems that provide appropriate support information according to emotions, so it is necessary to ensure that users can use the system with peace of mind.

[1841] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question and classifying it into a category corresponding to the question, means for generating an answer to the analyzed question, means for evaluating the reliability of the generated answer, means for recognizing the user's emotions when the question was sent, means for adjusting the tone and content of the answer based on the user's emotional state, means for sending the answer to the communication terminal if it is determined that the reliability exceeds a predetermined threshold, means for searching for support information based on the question and acquiring corresponding information, and means for displaying the acquired support information on the communication terminal. This allows the user to quickly obtain a reliable answer and is also provided with appropriate support information corresponding to the user's emotions, allowing the user to use the system with peace of mind.

[1842] A "communication terminal" is a device that allows a user to input questions and display the received answers, such as a smartphone or a personal computer.

[1843] A "question" refers to a question or concern about pregnancy and child-rearing that a user inputs using a communication terminal and sends to the server.

[1844] "Analysis" refers to the process in which the server uses natural language processing technology to interpret the content of the question received and classify it into categories.

[1845] "Categories" are themes or topics classified based on the content of the question, and include, for example, "night crying" and "childcare worries."

[1846] "Answer" refers to information that includes solutions or advice to the user's questions or concerns, which the server generates based on the analyzed question.

[1847] "Evaluation" refers to the process by which the server verifies the quality and reliability of the generated answers, using a reliability evaluation model.

[1848] "Emotion" refers to the psychological state the user is in when submitting the question, and includes anxiety, stress, joy, etc.

[1849] An "emotion engine" refers to a system that allows the server to recognize the user's emotions and adjust the tone and content of the response based on that data.

[1850] "Support information" refers to information about specific support and resources obtained from external databases related to the question.

[1851] "Credibility" is one of the evaluation criteria that indicates whether the generated answer is useful to the user, accurate, and appropriate.

[1852] The "threshold" refers to a reference point for determining whether or not the reliability evaluation score will provide an answer to a user.

[1853] MODE FOR CARRYING OUT THE INVENTION

[1854] The present invention provides an information support system for resolving worries and questions about pregnancy and child-rearing. Specific embodiments of the system will be described in detail below.

[1855] Hardware and software used

[1856] server

[1857] The server is responsible for receiving questions, analyzing them, generating answers, evaluating trustworthiness, recognizing emotions, searching for support information, and sending answers. A typical server computer is used for the hardware. The software uses the following technologies:

[1858] Natural language processing libraries: NLTK, spaCy

[1859] Learning model: Machine learning algorithm, reliability evaluation model

[1860] Sentiment Engine: Sentiment Analysis Algorithm

[1861] communication terminal

[1862] The communication terminal is a device where the user can input questions and receive answers. It can be a smartphone or a PC. The user interface is the LINE app or other messaging services.

[1863] User

[1864] Users use this system to input questions and receive answers, primarily individuals with questions or concerns about pregnancy and child-rearing.

[1865] Specific processing flow

[1866] 1. Enter and submit your question

[1867] The user opens the LINE app on their communication device, types a question, for example, "My baby cries a lot at night and it's bothering me. Is there anything I can do about it?" and presses the send button.

[1868] 2. Receiving and analyzing questions

[1869] The server analyzes the received questions and uses natural language processing libraries (NLTK or spaCy) to classify them into categories such as "night crying" or "parenting worries."

[1870] 3. Answer Generation

[1871] Based on the analysis results, the server generates an answer to the question such as, "Changing the environment and adjusting the sleep rhythm are effective in treating babies' nighttime crying."

[1872] 4. Reliability Assessment

[1873] The server calculates a reputation score for the generated answer using a reliability evaluation model, and proceeds to the next step only if the reputation score exceeds a predetermined threshold.

[1874] 5. Searching for support information

[1875] The server searches national and local government databases for support information related to the question and retrieves the relevant information. For example, it provides additional information on "local child-rearing support communities."

[1876] 6. Emotional awareness and regulation

[1877] The server uses an emotion engine to recognize emotions such as anxiety or stress from the user's question text, and adjusts the tone and content of the answer based on this emotion data. For example, it adds information about relaxation techniques to the answer.

[1878] 7. Submitting the final response

[1879] After the final adjusted answer passes the reliability evaluation, the server sends the final answer to the device. For example, it might say, "To combat your baby's nighttime crying, it's effective to improve the environment and regulate their sleep rhythm. Also, why not try joining a local parenting support community?"

[1880] 8. Receiving and Displaying Responses

[1881] The user's device receives the final answer sent from the server and displays it on the LINE app screen. The user can check the displayed answer and re-enter the question if necessary.

[1882] Example prompt sentences

[1883] Examples of prompts:

[1884] Example user question: My baby cries a lot at night. Is there anything I can do about it?

[1885] Emotion recognition: The user is determined to be feeling anxious.

[1886] Answer generation: To prevent babies from crying at night, it is effective to improve the environment and adjust their sleep rhythm.

[1887] Trustworthiness rating: The rating score exceeds a predetermined threshold.

[1888] Adjustments: Add information about relaxation techniques and local support communities.

[1889] Final answer: To combat nighttime crying, it is effective to improve the environment and establish a regular sleep routine. Also, why not join a local parenting support community?

[1890] As described above, the present invention realizes a system that quickly provides highly reliable answers to user questions and information that takes into consideration the user's feelings.

[1891] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1892] Step 1: Enter and submit your question

[1893] Input: The user's question or concern (e.g., "My baby cries a lot at night. Is there anything I can do about it?").

[1894] How it works: The user opens the LINE app on their device, enters the question as shown above, and presses the send button.

[1895] Output: The question text is sent to the server.

[1896] Step 2: Receiving and parsing the question

[1897] Input: The question text sent from the terminal.

[1898] How it works: The server receives the question text and uses natural language processing libraries (NLTK or spaCy) to analyze the question and classify it into categories such as "night crying" or "parenting worries."

[1899] Output: Question category information.

[1900] Step 3: Generate an answer

[1901] Input: Question category information.

[1902] How it works: The server searches a database of pre-prepared answers for the appropriate answer corresponding to the category, and generates an answer such as, "To treat a baby's night crying, it is effective to improve the environment and adjust the baby's sleep rhythm."

[1903] Output: The generated answer text.

[1904] Step 4: Assess reliability

[1905] Input: The generated answer text.

[1906] Operation: The server inputs the generated answer into the reliability evaluation model and calculates the evaluation score. If the evaluation score exceeds a predetermined threshold, it proceeds to the next step.

[1907] Output: A reliability assessment score.

[1908] Step 5: Finding support

[1909] Input: Confidence assessment score and question category information.

[1910] Operation: The server searches national and local government databases for support information related to the question and retrieves relevant information (e.g., information on local child-rearing support communities).

[1911] Output: Supporting information.

[1912] Step 6: Recognize and regulate your emotions

[1913] Input: Question text and generated answer text.

[1914] How it works: The server uses an emotion engine to recognize the user's emotions (e.g., anxiety or stress) from the question text. It then adjusts the generated answer based on the recognized emotion data, for example, adding information about relaxation techniques.

[1915] Output: The adjusted answer text.

[1916] Step 7: Submit your final response

[1917] Input: The adjusted answer text.

[1918] Operation: The server clears the trust evaluation and sends the adjusted final answer to the user's communication device.

[1919] Output: The final answer is sent to the terminal.

[1920] Step 8: Receive and view responses

[1921] Input: The final answer sent by the server.

[1922] Operation: The communication device receives the final response and displays it on the LINE app screen, allowing the user to check the displayed response.

[1923] Output: The final answer text that is displayed on the user's communication device.

[1924] Through the above processing steps, users can quickly obtain reliable answers and emotionally sensitive information.

[1925] (Application example 2)

[1926] 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."

[1927] There is a need to provide an information support system that can provide fast and reliable information to users who have concerns or questions about pregnancy and childcare, as well as to improve user satisfaction by providing appropriate support and answers according to the user's emotional state. In addition, there is a need to strengthen on-site support in physical stores, such as by providing information on related products and recommending products.

[1928] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a question input from a communication terminal, means for analyzing the received question and classifying it into a category corresponding to the question, means for generating an answer to the analyzed question, means for evaluating the reliability of the generated answer, means for transmitting the answer to the communication terminal if the reliability is determined to exceed a predetermined threshold, means for searching for support information based on the question and acquiring the relevant information, means for recognizing the user's emotion and adjusting the tone and content of the answer based on the user's emotional state, means for displaying the acquired support information on the communication terminal, means for guiding the user to the location of related products and recommended products in a physical store, and means for generating a message prompting the user to ask the question again and transmitting the message to the communication terminal if the generated answer falls below the reliability evaluation threshold. This enables the provision of reliable information about pregnancy and childcare, the creation of appropriate support tailored to the user's emotional state, and user support in a physical store.

[1929] A "communication terminal" is a device that allows a user to input a question and send it to a server.

[1930] The "means for receiving a question" is a function that enables the server to receive a question sent from a communication terminal.

[1931] The "means for analyzing questions" is a function that understands the received questions and classifies them into appropriate categories according to their contents.

[1932] The "means for generating an answer" is a function that creates an appropriate answer based on the analyzed question.

[1933] "Means for assessing reliability" is a function for checking the accuracy and reliability of the generated answers.

[1934] The "means for sending a response" is a function for sending back a response whose reliability has been confirmed to the communication terminal.

[1935] "Means for searching for support information" is a function that finds information related to a question from a database or the like.

[1936] The "means for acquiring support information" is a function that allows the server to acquire the searched support information.

[1937] "Means for recognizing emotions" is a function for analyzing and understanding the emotional state of the user when entering a question.

[1938] "Means to adjust the tone and content of responses" refers to a function that appropriately changes the wording and content of generated responses based on the recognized user sentiment.

[1939] The "means for displaying support information" is a function for displaying acquired support information on the user's communication terminal.

[1940] "Means for guiding users to the location of related products and recommended products" refers to a function that allows users to navigate to the location of related products and recommended products within a physical store.

[1941] The "means for generating a message prompting the user to ask again" is a function for creating and sending a message prompting the user to ask the question again when the reliability of the answer is low.

[1942] The present invention is an information support system for resolving worries and questions about pregnancy and child-rearing, and is designed to provide answers and support information in accordance with the user's emotional state in a physical store. This embodiment will be described in detail below.

[1943] System configuration

[1944] server

[1945] Server Role:

[1946] The server plays a central role in analyzing questions sent from communication terminals, generating and evaluating appropriate answers, and providing the final answer to the user. The server has the following functions:

[1947] 1. Receiving Questions

[1948] A question input from a communication terminal is received.

[1949] 2. Question Analysis

[1950] Analyze the incoming question and classify it into a category that corresponds to the question, for example, using a natural language processing (NLP) model.

[1951] 3. Answer Generation

[1952] Generate answers to questions, using generative AI models to create relevant answers.

[1953] 4. Reliability Assessment

[1954] Evaluate the reliability of the generated answers. Check the accuracy of the answers using a reliability evaluation model.

[1955] 5. Submitting the final response

[1956] If it is determined that the reliability exceeds a predetermined threshold, a response is transmitted to the communication terminal.

[1957] 6. Searching for and obtaining support information

[1958] Search databases for support based on your question and retrieve relevant information, including data from official sources.

[1959] 7. Emotional awareness and regulation

[1960] Recognizing the user's emotions and adjusting the tone and content of responses based on their emotional state, for example by using a sentiment analysis engine (such as IBM Watson Tone Analyzer).

[1961] 8. Display of support information

[1962] The acquired support information is displayed on the communication terminal.

[1963] 9. Generate a message prompting you to ask again

[1964] If the generated answer falls below the reliability evaluation threshold, a message prompting the user to ask the question again is generated and transmitted to the communication terminal.

[1965] communication terminal

[1966] The role of the communication terminal:

[1967] A communication terminal is a device that allows users to input questions and receive answers and assistance information. It has the following functions:

[1968] 1. Enter and submit your question

[1969] A question entry form is provided where users can enter and submit their questions.

[1970] 2. Receiving and displaying responses and support information

[1971] Answers and support information sent from the server are received and displayed on the screen.

[1972] Physical store

[1973] In-store applications:

[1974] The system has the following features to enhance customer support in physical stores:

[1975] 1. Product Information

[1976] It guides users to the location of relevant products and recommends products in physical stores.

[1977] Specific examples

[1978] For example, if a user enters "I don't know how to choose diapers for my baby. Which ones are good?" in a physical store, the processing details are as follows:

[1979] 1. Enter and submit your question

[1980] The user enters a question into the communication terminal and presses the send button.

[1981] 2. Question Analysis

[1982] The server receives the questions and categorizes them into categories such as "How to choose diapers."

[1983] 3. Answer Generation

[1984] The server generates answers such as, "When choosing diapers, the baby's size, absorbency, and material are important. There are multiple options available in stores."

[1985] 4. Emotional awareness and regulation

[1986] The emotion engine recognizes the user's anxiety and tailors responses with a warm, reassuring tone, adding relaxation techniques and information about local support communities.

[1987] 5. Information on related products

[1988] The location of related products and recommended products within the physical store are displayed on the user's communication device.

[1989] Prompt sentences to input to the generative AI model

[1990] Prompt to generate an answer for the user:

[1991] "A customer asks, 'I don't know how to choose diapers for my baby in a physical store. Which ones are good?' Generate a reliable answer based on the question and provide additional information as needed."

[1992] Sentiment analysis prompt:

[1993] "Generate data that can be used to analyze sentiment from user questions and respond with the appropriate tone."

[1994] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1995] Step 1: Enter and submit your question

[1996] User action: The user opens the application on the communication terminal, enters "I don't know how to choose diapers for my baby. Which one is best?" into the question input form, and presses the send button.

[1997] Input: The question entered by the user.

[1998] Output: Question data sent from the communication terminal to the server.

[1999] Specific operation: The communication terminal sends the question data to the server as an HTTP POST request.

[2000] Step 2: Receiving and parsing the question

[2001] Server operation: The server receives the question sent from the communication terminal and analyzes the question using natural language processing (NLP).

[2002] Input: Query data sent from the communication terminal.

[2003] Output: Analysis results, specifically category information (e.g., "How to choose diapers").

[2004] Specific operation: The server uses an NLP tool (e.g., Google Cloud Natural Language API) to analyze the question and classify it into the appropriate category.

[2005] Step 3: Generate an answer

[2006] Server operation: The server uses a generative AI model to generate an appropriate answer based on the analysis results.

[2007] Input: Parsed category information.

[2008] Output: Generated answer (e.g., "When choosing a diaper, the baby's size, absorbency, and material are important. There are multiple options available in stores.").

[2009] Specific operation: The server uses a generative AI model (e.g., OpenAI GPT-3) to generate an appropriate answer based on the category information.

[2010] Step 4: Assess reliability

[2011] Server operation: The reliability of the generated answer is evaluated using a reliability evaluation model.

[2012] Input: The generated answer.

[2013] Output: A reliability assessment score.

[2014] How it works: The server uses a machine learning model (e.g., Scikit-learn or TensorFlow) to evaluate the reliability of the generated answer and calculate a score.

[2015] Step 5: Authenticity check and submit your answer

[2016] Server operation: If the reliability evaluation score exceeds a predetermined threshold, the server transmits an answer to the user's communication terminal.

[2017] Inputs: Confidence assessment score, generated answer.

[2018] Output: The answer sent to the user's communication device.

[2019] Specific operation: Check whether the reliability evaluation score exceeds the threshold, and if so, send the answer to the user's communication device in JSON format.

[2020] Step 6: Search and obtain support information

[2021] Server operation: Based on the content of the question, related support information is searched and acquired from the database.

[2022] Input: Question content, analysis results.

[2023] Output: Relevant supporting information.

[2024] Specific operation: The server queries the database and retrieves relevant data, such as official childcare support information from the government or local government.

[2025] Step 7: Recognize your emotions and adjust your response

[2026] Server Action: Uses an emotion engine to analyze the user's emotions and adjusts the tone and content of responses accordingly.

[2027] Input: User question data.

[2028] Output: A tailored response (e.g., a reassuring tone).

[2029] Specific operation: The server uses an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions and adjust the response text as necessary.

[2030] Step 8: Submit your final response and supporting information

[2031] Server operation: The server sends the final answer that has passed the reliability evaluation and the acquired support information to the user's communication terminal.

[2032] Input: Adjusted final answer, obtained supporting information.

[2033] Output: The final answer and supporting information sent to the user's communication terminal.

[2034] Specific operation: Reliable answers and assistance information are integrated and sent to the user's communication device in JSON format.

[2035] Step 9: Displaying answers and product information

[2036] Communication terminal operation: The received answers and support information are displayed on the screen, and the location of related products and recommended products are shown in the physical store.

[2037] Input: The final answer and supporting information sent from the server.

[2038] Output: Answers and support information displayed on the communication device screen, and information on related products in physical stores.

[2039] Specific operation: The communication terminal analyzes the received data and displays it on the user interface, while also using GPS and beacons to guide the user to the location of the product within the physical store.

[2040] This will enable the provision of reliable information about pregnancy and childcare, appropriate support tailored to the user's emotions, and user support in physical stores.

[2041] 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.

[2042] 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.

[2043] 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.

[2044] 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.

[2045] 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.

[2046] 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.

[2047] 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).

[2048] 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.

[2049] 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."

[2050] 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.

[2051] 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).

[2052] 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.

[2053] 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.

[2054] 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.

[2055] 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.

[2056] 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.

[2057] 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.

[2058] 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 fun...

Claims

1. means for receiving a question input from a communication terminal; means for analyzing the received questions and classifying them into categories according to the questions; means for generating answers to the parsed questions; a means of assessing the reliability of the generated answers; means for transmitting a response to the communication terminal when it is determined that the reliability exceeds a predetermined threshold; A means for searching for support information based on a question and acquiring the relevant information; a means for displaying the acquired support information on a communication terminal; A system including:

2. 10. The system of claim 1, further comprising means for providing information and generating answers regarding specific categories related to pregnancy and parenting.

3. 2. The system according to claim 1, further comprising means for generating a message prompting the user to ask the question again and transmitting the message to the communication terminal if the generated answer falls below a reliability evaluation threshold.

Images