system

Abstract

Provide a system. 【Solution means】 Message receiving means, Message analysis means for analyzing the message using natural language processing technology, Means for obtaining the user's residential area information based on the content analyzed by the message analysis means, Information search means for searching for appropriate information from a database based on the analyzed content and the residential area information, Means for collating with the local government information providing the appropriate information, Message generation means for generating a response message based on the collated result, Message sending means for sending the response message to the user, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, the number of parents seeking information and support regarding child-rearing is increasing, but there is a shortage of systems that can provide services available 24 hours a day and timely provide appropriate information corresponding to the residential area of users. In particular, there is a need for a system that can respond quickly and accurately to a wide range of needs, such as guidance on appropriate medical institutions in case of emergencies such as sudden fever or injury, detailed information for nursery school enrollment, and leisure information that can be enjoyed with the family on holidays. It is necessary to provide a system that can efficiently solve such problems.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system including a message receiving means, a message analysis means for analyzing the message using natural language processing technology, a means for acquiring the user's residential area information based on the content of the analyzed message, an information retrieval means for searching for appropriate information from a database based on the analyzed content and the residential area information, a means for comparing the appropriate information with local government information, a message generation means for generating a response message based on the matching result, and a message transmission means for sending the response message to the user. With this system, users can consult about their worries and questions regarding childcare at any time, 24 hours a day, and receive timely and appropriate information corresponding to their residential area.

[0006] "Message receiving means" refers to a communication interface or software for receiving text messages sent by a user.

[0007] "Message analysis means" refers to a method for analyzing received messages using natural language processing technology to understand their intent and content.

[0008] "Means for obtaining user residential area information" refers to means that have the function of obtaining information about the user's residential area from a database or similar source.

[0009] "Information retrieval means" refers to a means for retrieving appropriate information from a database based on the information analyzed by the message analysis means and the user's residential area information.

[0010] "Means of cross-referencing with local government information" refers to means of obtaining the latest information provided by local governments and cross-referencing it with information retrieved using information retrieval tools.

[0011] "Message generation means" refers to means for generating an appropriate response message to provide to the user based on the matched results.

[0012] "Message transmission means" refers to the communication interface or software used to send the generated response message to the user. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0027] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The present invention will be described based on the following system overview and specific examples.

[0035] System Overview

[0036] This system allows users to send questions and consultations about childcare through an official LINE account. The server receives and analyzes these messages and provides appropriate information. The system is available 24 hours a day and can also provide information tailored to the user's residential area.

[0037] Program Processing Overview

[0038] Step 1: The user sends a message.

[0039] Users use the chat function of the official LINE account to send messages such as, "Please tell me how to enroll my child in daycare."

[0040] Step 2: The server receives the message.

[0041] The server receives messages sent by users via the LINE API.

[0042] The server converts the received message into a format that can be parsed.

[0043] Step 3: The server parses the message.

[0044] The server uses natural language processing techniques to analyze the message.

[0045] Example: Extract the keywords "nursery school" and "how to enroll," and determine the category to be "information on finding childcare."

[0046] Step 4: The server retrieves the user's residential area information.

[0047] The server retrieves residential area information (for example, Shinjuku Ward) from the user's profile.

[0048] If the profile does not contain information about the user's residential area, the server will generate a response message asking, "Please tell us where you live."

[0049] Step 5: The server searches for the appropriate information.

[0050] The server uses message analysis results and residential area information to search the database for information such as nursery school admission requirements, necessary documents, and application procedures.

[0051] Step 6: The server matches with the local government information.

[0052] The server retrieves the latest information from the local government's API and official website, and compares it with the searched information.

[0053] If the most recent information matches, select that information.

[0054] Step 7: The server generates a response message.

[0055] Based on the information acquired by the server, a response message is generated to be provided to the user.

[0056] Example: "Details regarding admission to a nursery school in Shinjuku Ward are as follows. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: You can apply online through the ward office website."

[0057] Step 8: The server sends the message

[0058] The server sends a response message to the user via the LINE API.

[0059] Specific example

[0060] Case 1: Inquiry about childcare application information (nursery school enrollment)

[0061] 1. User: "Please tell me how to enroll my child in daycare."

[0062] 2. The server receives and analyzes the message. Based on the keywords "nursery school" and "how to enroll," it determines the category to be "childcare information."

[0063] 3. The server retrieves the user's residential area information (Shinjuku Ward) from their profile.

[0064] 4. The server searches the database for the latest information regarding childcare applications in Shinjuku Ward (conditions, documents, and methods).

[0065] 5. The server retrieves the latest information from the local government's API and compares it with the search results.

[0066] 6. The server generates a message stating, "Here are the details for enrolling in a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website."

[0067] 7. The server sends the generated message to the user via LINE.

[0068] Case 2: Medical information for sudden fever or injury

[0069] 1. User: "My child has a fever. Where can I get them examined?"

[0070] 2. The server receives and analyzes the message. It determines whether it is an emergency medical event based on the keywords "fever" and "medical institution."

[0071] 3. The server retrieves residential area information (Kita Ward, Osaka City).

[0072] 4. The server searches its database for medical institutions in Kita Ward, Osaka City that can provide emergency medical care.

[0073] 5. The server retrieves the latest medical institution information from the local government API and compares it with the search results.

[0074] 6. The server generates the message: "Osaka City Kita Ward General Hospital is open 24 hours a day. The emergency center is also available. The address is ○○."

[0075] 7. The server sends the generated message to the user via LINE.

[0076] In this way, this system efficiently processes user inquiries, providing prompt responses and accurate information. This will enable it to address a wide range of needs related to childcare.

[0077] The following describes the processing flow.

[0078] Step 1:

[0079] A user sends a message to the official LINE account. This message might be something like, "Please tell me how to enroll my child in daycare."

[0080] Step 2:

[0081] The server receives messages sent by users via the LINE API. The received messages are then converted into an analyzable format.

[0082] Step 3:

[0083] The server invokes a natural language processing (NLP) engine to analyze the received message. This analysis extracts keywords such as "nursery school" and "how to enroll," and the question category is determined to be "childcare information."

[0084] Step 4:

[0085] The server retrieves residential area information from the user's profile information. For example, if the user has previously registered "Shinjuku Ward," that information will be used. If residential area information is not registered, the server will ask the user for their residential area in a subsequent process.

[0086] Step 5:

[0087] The server searches the database for relevant information based on the message analysis results and residential area information. For example, it extracts information about childcare activities in Shinjuku Ward (admission requirements, necessary documents, application methods, etc.).

[0088] Step 6:

[0089] The server retrieves the latest local government information from the local government's API and official website. This allows the server to compare the latest childcare information with the contents of the database, ensuring the consistency of the information.

[0090] Step 7:

[0091] The server generates a response message to the user based on the collected and verified information.

[0092] For example, the content might read: "Details regarding admission to a nursery school in Shinjuku Ward are as follows. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: You can apply online through the ward office website."

[0093] Step 8:

[0094] The server sends a generated response message to the user via the LINE API. The user can receive the message on the LINE chat screen and check the suggested solution.

[0095] Specific example (in the case of an inquiry about childcare information):

[0096] Step 1:

[0097] User: Sends a message saying, "Please tell me how to enroll my child in daycare."

[0098] Step 2:

[0099] The server receives this message using the LINE API.

[0100] Step 3:

[0101] The server analyzes the message using an NLP engine, extracts "nursery school" and "how to enroll" as keywords, and classifies them as "childcare information."

[0102] Step 4:

[0103] The server retrieves residential area information for "Shinjuku Ward" from the user's profile.

[0104] Step 5:

[0105] The server searches the database for nursery school enrollment information related to Shinjuku Ward.

[0106] Step 6:

[0107] The server retrieves the latest nursery school enrollment information from the Shinjuku Ward official website and compares it with the database.

[0108] Step 7:

[0109] The server generates a response message stating, "Details regarding admission to a nursery school in Shinjuku Ward are as follows. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: You can apply online through the ward office website."

[0110] Step 8:

[0111] The server sends this message to the user via LINE, and the user receives and confirms its contents.

[0112] (Example 1)

[0113] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0114] Conventional information systems struggled to respond quickly and accurately to user questions and inquiries. Furthermore, they often failed to adequately address users' residential areas, resulting in inconsistencies with the latest information from local governments. Additionally, the lack of message optimization meant users often received unclear and easily understandable responses.

[0115] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0116] In this invention, the server includes a message receiving means, a message analysis means for analyzing the message using natural language processing technology, a means for acquiring the user's residential area information based on the content analyzed by the message analysis means, an information retrieval means for searching for appropriate information from a database based on the analyzed content and residential area information, a means for comparing with administrative agency information that provides appropriate information, a message generation means for generating a response message based on the comparison result, a message sending means for sending the response message to the user, and a means for optimizing the generated message using a generation AI model. This enables the rapid and accurate provision of information in response to user questions and consultations, provides optimal information tailored to the residential area, ensures consistency with the latest information from administrative agencies, and provides a response message that is easy for the user to understand.

[0117] "Message receiving means" refers to a combination of a system and process that receives messages sent by users and converts those messages into a parseable format.

[0118] "Natural language processing technology" refers to the techniques that enable computers to understand, analyze, and generate human language, and includes methods for interpreting the meaning of text.

[0119] A "message analysis system" refers to a system that analyzes received messages and has the function of extracting and understanding keywords and context within those messages.

[0120] "User residential area information" refers to data related to the geographical area where the user resides, including address and region name.

[0121] "Information retrieval means" refers to a system that has the function of extracting highly relevant information from a database based on message analysis results and residential area information.

[0122] A "database" is a systematically organized collection of data, and refers to a system that allows for the fast and efficient searching, adding, updating, and deleting of specific information.

[0123] "Government agency information" refers to data and information officially provided by public institutions such as local governments.

[0124] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and generates an optimized response for a specific task.

[0125] "Message generation means" refers to a system that has the function of creating an appropriate response message based on the analyzed content and matching results.

[0126] "Message sending means" refers to a communication means for sending a generated response message to the user.

[0127] As an embodiment of the present invention, a system is described in which a user sends questions or requests for advice regarding childcare using an online messaging platform (e.g., LINE official account), a server receives and analyzes the message, and provides appropriate information.

[0128] The server first receives messages sent by users using a message receiving method. LINE's Messaging API is used for message reception. Next, the server analyzes the messages using natural language processing technology (for example, Google Cloud Natural Language API). This makes it possible to extract keywords and intent from the message content.

[0129] Based on the analyzed data, the server retrieves the user's residential area information. This includes a function to refer to the user's profile information, and if residential area information is missing, it generates a response message asking the user, "Please tell us where you live."

[0130] Next, the server uses the analysis results and residential area information to search for appropriate information from the database. The database can be a relational or non-relational database such as MySQL® or MongoDB. The retrieved information includes specific details such as nursery school admission requirements, necessary documents, and application procedures.

[0131] The server then retrieves the latest information from the local government's APIs and official websites and compares it with the previously retrieved database information. For example, it ensures the accuracy of the information provided by comparing it with the latest information obtained from Shinjuku Ward's open data API.

[0132] Next, the server generates a response message based on the matching results. Here, a generative AI model (e.g., GPT-4®) is used to optimize the response message. This allows the user to receive clear and relevant information.

[0133] Finally, the server uses a message sending method to send the generated response message to the user. The message is sent to the user's LINE account via LINE's Messaging API.

[0134] Specific example

[0135] Case 1: Inquiry about nursery school enrollment information

[0136] 1. User: "Please tell me how to enroll my child in daycare."

[0137] 2. The server receives the message and analyzes it using natural language processing technology. Based on the keywords "nursery school" and "how to enroll," it determines the category to be "childcare information."

[0138] 3. The server retrieves the user's residential area information (Shinjuku Ward).

[0139] 4. The server searches the database for the latest information regarding childcare applications in Shinjuku Ward (conditions, documents, and methods).

[0140] 5. The server retrieves the latest information from the local government's API and compares it with the search results.

[0141] 6. The server generates a message stating, "Here are the details for enrolling in a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website."

[0142] 7. The server sends the generated message to the user via LINE.

[0143] Case 2: Medical information for sudden fever or injury

[0144] 1. User: "My child has a fever. Where can I get them examined?"

[0145] 2. The server receives and analyzes the message. It determines whether it is an emergency medical event based on the keywords "fever" and "medical institution."

[0146] 3. The server retrieves residential area information (Kita Ward, Osaka City).

[0147] 4. The server searches its database for medical institutions in Kita Ward, Osaka City that can provide emergency medical care.

[0148] 5. The server retrieves the latest medical institution information from the local government API and compares it with the search results.

[0149] 6. The server generates the message: "Osaka City Kita Ward General Hospital is open 24 hours a day. The emergency center is also available. The address is ○○."

[0150] 7. The server sends the generated message to the user via LINE.

[0151] This invention allows users to obtain quick and accurate information, enabling them to address diverse childcare needs. The system is particularly useful as it is available 24 / 7 through messaging platforms like LINE, significantly improving user convenience.

[0152] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0153] Program processing flow

[0154] Step 1:

[0155] Users can use the chat function of the official LINE account to enter questions or requests for advice and send messages.

[0156] Input: Message from the user (e.g., "Please tell me how to enroll my child in daycare.")

[0157] Output: A message is sent to the LINE server.

[0158] Specific action: The user types a message on the LINE app on their smartphone or PC and presses the send button.

[0159] Step 2:

[0160] The server uses LINE's Messaging API to retrieve incoming messages.

[0161] Input: Message sent from LINE server

[0162] Output: The message arrives on the server in JSON format (Example: { "type": "text", "text": "Please tell me how to enroll my child in daycare"})

[0163] Specific operation: The server polls for new messages via the LINE Messaging API endpoint.

[0164] Step 3:

[0165] The server uses natural language processing techniques to analyze the message.

[0166] Input: Message in JSON format (Example: { "type": "text", "text": "Please tell me how to enroll my child in daycare"})

[0167] Output: Analysis results (Keywords: "nursery school", "how to enroll", Category: "childcare information")

[0168] Specific operation: The server uses an NLP engine such as the Google Cloud Natural Language API to extract keywords from the message text and classify the intent.

[0169] Step 4:

[0170] The server retrieves the user's residential area information.

[0171] Input: Analysis results (Category "Childcare Information")

[0172] Output: Residential area information (e.g., Shinjuku Ward)

[0173] Specific operation: The server searches for the user's residential area from their LINE profile information and retrieves the information. If residential area information is insufficient, it generates a message asking "Please tell us where you live" and sends it to the user.

[0174] Step 5:

[0175] The server uses the analysis results and residential area information to search for appropriate information from the database.

[0176] Input: Analysis results, residential area information

[0177] Output: Appropriate information (e.g., nursery school admission requirements, necessary documents, application procedures)

[0178] Specific operation: The server queries databases such as MySQL or MongoDB to retrieve analysis results and related data based on residential area information.

[0179] Step 6:

[0180] The server retrieves the latest information from local government APIs and official websites and compares it with search results.

[0181] Input: Appropriate information (search results from the database), up-to-date local government information (obtained from API or official website)

[0182] Output: Matching results (latest matching information)

[0183] Specific operation: The server retrieves the latest information from sources such as Shinjuku Ward's open data API, and verifies its consistency by comparing it with information obtained from the database.

[0184] Step 7:

[0185] The server generates a response message based on the matching results.

[0186] Input: Matching result

[0187] Output: Response message (Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website.")

[0188] Specific operation: The server uses a generated AI model (e.g., GPT-4) to create a response message that provides information to the user in an easily understandable format.

[0189] Step 8:

[0190] The server sends a response message to the user.

[0191] Input: Response message

[0192] Output: Message delivered to the user

[0193] Specific operation: The server sends the generated response message to the user's LINE account via LINE's Messaging API.

[0194] (Application Example 1)

[0195] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0196] In today's lifestyle, obtaining information about childcare quickly and accurately is crucial. Furthermore, there is a need for a means to quickly obtain appropriate information, even in situations requiring urgent action. To utilize such information services more diversely, convenience is needed not only for information provision but also for paid services and content purchases using electronic payments. However, current systems struggle to simultaneously meet all these requirements.

[0197] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0198] In this invention, the server includes a message receiving means, a message analysis means for analyzing the message using natural language processing technology, a means for acquiring the user's residential area information based on the content analyzed by the message analysis means, an information retrieval means for searching a database for appropriate information based on the analyzed content and the residential area information, a means for comparing the appropriate information with local government information, a message generation means for generating a response message based on the matching result, a message transmission means for sending the response message to the user, and an electronic payment means. This enables the user to receive information suitable for their residential area, receive emergency consultations, and even purchase paid consultations and childcare-related content using electronic payment.

[0199] A "message receiving means" is a means that has the function of receiving messages sent by a user.

[0200] A "message analysis tool" is a means of analyzing a received message using natural language processing technology to understand its content.

[0201] "Means for obtaining residential area information" refers to methods for extracting and obtaining information about a user's residential area from their profile information or inquiry messages.

[0202] An "information retrieval method" is a means of searching for appropriate information from a database based on the content of the analyzed message and the acquired residential area information.

[0203] "Means of cross-referencing with local government information" refers to methods for verifying and cross-referencing the searched information with the latest information from the local government.

[0204] A "message generation means" is a means for creating a response message to be provided to the user based on the verified information.

[0205] "Message sending means" refers to means for sending the generated response message to the user.

[0206] "Electronic payment methods" refer to means that have the functionality of electronic payment and can be used by users when purchasing paid services or content.

[0207] A "generative AI model" is an artificial intelligence model used to generate appropriate answers or response messages in response to user inquiries.

[0208] A "prompt sentence" is a sentence of instruction or question that is input to a generative AI model, and it is the input sentence that enables the model to generate an appropriate answer.

[0209] The system for carrying out the present invention is constructed using the following hardware and software.

[0210] hardware

[0211] Server: Used as a central processing unit for database management, communication processing, message analysis, and generation.

[0212] User terminal: A device, such as a smartphone, used by a user to send and receive messages.

[0213] Internet connection: A network infrastructure that facilitates communication between servers and user terminals.

[0214] software

[0215] LINE Messaging API: Used to receive messages from users and forward them to the server.

[0216] Natural language processing libraries (e.g., NLTK): Provide natural language processing techniques for message analysis.

[0217] SQLite: A database system that stores user information and childcare information by region.

[0218] Python: Used as the programming language to integrate all of the above parts.

[0219] Processing flow

[0220] 1. Message Reception: Users send questions and requests for advice regarding childcare using the LINE app on their device. For example, they might send a message such as, "Please tell me how to enroll my child in daycare."

[0221] 2. Message Analysis: After receiving a message via the LINE Messaging API, the server uses NLTK to analyze the message and extract keywords (e.g., "nursery school," "how to enroll").

[0222] 3. Obtaining residential area information: The server obtains residential area information (e.g., "Shinjuku Ward") from the user profile information.

[0223] 4. Information Retrieval: The server searches for appropriate information from the SQLite database based on the analyzed keywords and residential area information.

[0224] 5. Verification with local government information: The server retrieves the latest information from local government APIs and official websites and verifies it against the search results.

[0225] 6. Generating a response message: The server generates a response message based on the matching results (e.g., "Details regarding admission to a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website.").

[0226] 7. Message Sending: The generated response message is sent to the user via the LINE Messaging API.

[0227] 8. Electronic payment: Users utilize electronic payment functions to purchase paid consultations and childcare-related content.

[0228] This system allows users to quickly and accurately obtain childcare information tailored to their residential area. Furthermore, it enables prompt and appropriate responses to urgent inquiries and emergencies, and allows for paid consultations and content purchases using electronic payment.

[0229] Specific example

[0230] User: "My child has a fever. Where can I get them examined?"

[0231] server:

[0232] The message was analyzed, and the keywords "fever" and "medical institution" were extracted.

[0233] Retrieve residential area information (e.g., "Kita Ward, Osaka City").

[0234] Search the database for information on medical institutions in the relevant area.

[0235] Check against the latest local government information.

[0236] Generate a response message (e.g., "Osaka City Kita Ward General Hospital is open 24 hours. The emergency center is also available. The address is XX.").

[0237] Send a message to the user.

[0238] Examples of prompts for generative AI models

[0239] User: "Please tell me how to enroll my child in daycare."

[0240] AI: "I will now explain the specific procedures for enrolling your child in daycare. First, please prepare the necessary documents. Next, I will explain how to apply online."

[0241] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0242] Step 1:

[0243] Users send questions and requests for advice about childcare using the LINE app on their devices. The input is a text message, such as "Please tell me how to enroll my child in daycare." This message is then sent to the server.

[0244] Step 2:

[0245] The server receives messages from users via the LINE Messaging API. The received messages are converted into a parseable format. The input is the user's text message, and the output is text data for parsing.

[0246] Step 3:

[0247] The server parses incoming messages using a natural language processing library (such as NLTK). It extracts keywords from the messages (e.g., "nursery school," "how to enroll"). The input is text data for analysis, and the output is a list of keywords.

[0248] Step 4:

[0249] The server retrieves residential area information from the user's profile information. This ensures that the analyzed keywords and the user's residential area information are matched. The input is the user ID, and the output is the user's residential area information (e.g., "Shinjuku Ward").

[0250] Step 5:

[0251] The server searches for appropriate information from the SQLite database based on the analyzed keywords and acquired residential area information. The input is a list of keywords and residential area information, and the output is the initial search result.

[0252] Step 6:

[0253] The server retrieves the latest information from local government APIs and official websites and compares it with the initial search results. This verifies the timeliness of the information. The input is the initial search results, and the output is the final, verified information.

[0254] Step 7:

[0255] The server generates a response message based on the final information it has verified. The input is the final information, and the output is a text message sent to the user (e.g., "Here are the details for nursery school enrollment in Shinjuku Ward. Required documents: resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website.").

[0256] Step 8:

[0257] The server sends the generated response message to the user via the LINE Messaging API. The input is the response message, and the output is the message displayed on the user's device.

[0258] Step 9:

[0259] Users utilize in-app electronic payment methods to access paid consultations and childcare-related content. The input is the user's electronic payment information, and the output is a confirmation message upon completion of the payment.

[0260] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0261] The present invention will be described based on the following system overview and specific examples.

[0262] System Overview

[0263] This system allows users to send questions and consultations about childcare via a LINE official account. The server receives and analyzes these messages and provides appropriate information. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it can provide even more appropriate responses. The system is available 24 hours a day and can also provide information tailored to the user's residential area.

[0264] Program Processing Overview

[0265] Step 1: The user sends a message.

[0266] Users use the chat function of the official LINE account to send messages such as, "Please tell me how to enroll my child in daycare."

[0267] Step 2: The server receives the message.

[0268] The server receives messages sent by users via the LINE API. The received messages are converted into an analyzable format.

[0269] Step 3: The server parses the message.

[0270] The server invokes a natural language processing (NLP) engine to analyze the received message. This analysis extracts the keywords "nursery school" and "how to enroll," and the question category is determined to be "nursery school information."

[0271] Step 4: The server uses the emotion engine to recognize emotions.

[0272] The server uses an emotion engine to recognize emotions from the content of the user's message. For example, the emotion engine can detect emotions such as "anxiety" or "impatience" from the user's message.

[0273] Step 5: The server retrieves the user's residential area information.

[0274] The server retrieves residential area information from the user's profile information. For example, if the user has previously registered "Shinjuku Ward," that information will be used. If residential area information is not registered, the server will ask the user for their residential area in a subsequent process.

[0275] Step 6: The server searches for the appropriate information.

[0276] The server searches the database for relevant information based on the message analysis results and residential area information. For example, it extracts information about childcare activities in Shinjuku Ward (admission requirements, necessary documents, application methods, etc.).

[0277] Step 7: The server matches with the local government information.

[0278] The server retrieves the latest local government information from the local government's API and official website. This allows the server to compare the latest childcare information with the contents of the database, ensuring the consistency of the information.

[0279] Step 8: The server generates a response message.

[0280] The server generates a response message based on the emotions recognized by the emotion engine. The content and tone of the response message are adjusted to match the user's emotions. For example, if anxiety is detected, the message will include reassuring language.

[0281] Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. There's no need to worry unnecessarily. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[0282] Step 9: The server sends the message

[0283] The server sends a generated response message to the user via the LINE API. The user can receive the message on the LINE chat screen and check the suggested solution.

[0284] Specific Example (in the case of inquiry about child care information)

[0285] Case 1: Inquiry about child care (kindergarten enrollment) information

[0286] 1. The user sends a message saying, "Please tell me how to enroll in a kindergarten."

[0287] 2. The server receives this message using the LINE API.

[0288] 3. The server analyzes the message using the NLP engine, extracts "kindergarten" and "enrollment method" as keywords, and classifies it as "child care information."

[0289] 4. The server uses the emotion engine to recognize the emotion of "unease" from the user's message.

[0290] 5. The server obtains the residential area information of "Shinjuku Ward" from the user's profile.

[0291] 6. The server searches the database for kindergarten enrollment information related to Shinjuku Ward.

[0292] 7. The server obtains the latest kindergarten enrollment information from the official website of Shinjuku Ward and compares it with the database.

[0293] 8. The server generates a response message containing reassuring words such as "Here is the details of kindergarten enrollment in Shinjuku Ward. Don't worry. The required documents are family register,母子手帳 (maternity and child handbook), etc. The application method is available for online application from the ward office's website."

[0294] 9. The server sends this message to the user via LINE, and the user receives and checks the content.

[0295] In this way, this system efficiently processes inquiries from users, provides accurate information with a prompt response that empathizes with emotions. As a result, it becomes possible to respond considering the emotional aspects to various needs related to child-rearing.

[0296] The processing flow will be described below.

[0297] Step 1:

[0298] The user sends a message "Please teach me how to enroll in a nursery school" to the LINE official account.

[0299] Step 2:

[0300] The server receives this message through the LINE API. The received message is converted into an analyzable format.

[0301] Step 3:

[0302] The server calls a natural language processing (NLP) engine to analyze the message. Specific keywords (here, "nursery school" and "enrollment method") are extracted, and the category of the question is determined to be "childcare information".

[0303] Step 4:

[0304] The server calls an emotion engine to recognize the emotion from the user's message. For example, emotions such as "uneasiness" or "anxiety" are detected from the user's message.

[0305] Step 5:

[0306] The server refers to the user's profile information and obtains the residential area information (e.g., "Shinjuku Ward"). If the residential area information is not registered, a message asking the user for the residential area will be generated in subsequent processing.

[0307] Step 6:

[0308] The server searches the database for relevant information based on the message analysis results and acquired residential area information. For example, it might retrieve information such as admission requirements, necessary documents, and application procedures for daycare centers in Shinjuku Ward.

[0309] Step 7:

[0310] The server retrieves the latest information from the local government's API and official website. This latest information is then compared with the database information to verify consistency.

[0311] Step 8:

[0312] The server generates a response message based on the recognition results from the emotion engine. If the user is feeling anxious, a message designed to reassure them will be generated.

[0313] Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. Please rest assured. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[0314] Step 9:

[0315] The server sends a generated response message to the user via the LINE API. The user can receive the message on the LINE chat screen and check the suggested solution.

[0316] Specific example (in the case of an inquiry about childcare information):

[0317] Step 1:

[0318] User: Sends a message saying, "Please tell me how to enroll my child in daycare."

[0319] Step 2:

[0320] The server uses the LINE API to receive messages.

[0321] Step 3:

[0322] The server uses an NLP engine to analyze the message, extracts the keywords "nursery school" and "how to enroll," and classifies it as "information on finding childcare."

[0323] Step 4:

[0324] The server uses an emotion engine to recognize the emotion of "anxiety" from the user's message.

[0325] Step 5:

[0326] The server retrieves residential area information for "Shinjuku Ward" from the user's profile information.

[0327] Step 6:

[0328] The server searches the database for nursery school enrollment information related to Shinjuku Ward.

[0329] Step 7:

[0330] The server retrieves the latest nursery school enrollment information from the local government's API and compares it with the database.

[0331] Step 8:

[0332] The server, responding to the emotion of "anxiety," generates a response message that reads, "Here are the details for enrolling in a nursery school in Shinjuku Ward. Please rest assured. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[0333] Step 9:

[0334] The server sends this message to the user via the LINE API. The user can then view the received message.

[0335] (Example 2)

[0336] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0337] In modern society, providing timely and appropriate information about childcare is crucial. However, existing systems struggle to provide information that takes users' emotions into account, and there are challenges in adequately addressing the needs of users who require emotional support. Furthermore, the lack of up-to-date information specific to a particular residential area makes it difficult to provide appropriate advice for each region.

[0338] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0339] In this invention, the server includes message receiving means, message analysis means for analyzing the message using natural language processing technology, emotion recognition means for recognizing the user's emotions from the message, means for acquiring the user's residential area information based on the content analyzed by the message analysis means, information retrieval means for searching a database for appropriate information based on the analyzed content and the residential area information, means for comparing the information with local government information that provides the appropriate information, message generation means for generating a response message based on the emotions recognized by the emotion recognition means, and message transmission means for sending the response message to the user. This makes it possible to quickly provide the latest and most appropriate information for each residential area while being attentive to the user's emotions.

[0340] A "message receiving means" is a means for receiving messages sent by a user.

[0341] A "message analysis means" is a means for analyzing a received message using natural language processing technology.

[0342] "Emotion recognition means" refers to a method for recognizing a user's emotions from a received message.

[0343] "Means for obtaining user residential area information" refers to means for obtaining information about the user's place of residence.

[0344] An "information retrieval method" is a means of searching for appropriate information from a database based on the analyzed content and residential area information.

[0345] "Means of cross-referencing with local government information" refers to means of cross-referencing appropriate information with the latest information provided by local governments.

[0346] A "message generation means" is a means for generating a response message based on the emotion recognized by the emotion recognition means.

[0347] "Message sending means" refers to means for sending the generated response message to the user.

[0348] Modes for carrying out the invention

[0349] This invention relates to a system in which a server receives, analyzes, and provides appropriate information in response to questions and consultations about childcare sent by users through an online chat platform. A key feature of this system is its ability to provide responses that take the user's emotions into consideration, particularly through the integration of emotion recognition functionality. The embodiments of this system are described in detail below.

[0350] System Overview

[0351] This system consists of the following main hardware and software components:

[0352] server

[0353] User devices (smartphones, tablets, PCs)

[0354] LINE official accounts and their APIs

[0355] Natural language processing engines (e.g., SpaCy, NLTK)

[0356] Emotion recognition engine (e.g., IBM Watson® Tone Analyzer)

[0357] Databases (e.g., MySQL, MongoDB)

[0358] Local government API or official website

[0359] Specific operation of the system

[0360] 1. The user sends a message.

[0361] Users can send questions and inquiries through the chat window of the official LINE account. For example, specific questions such as "Please tell me how to enroll my child in daycare" are possible.

[0362] 2. The server receives the message.

[0363] The server receives messages from users via the LINE API. At this time, the message data is transferred to the server in JSON format.

[0364] 3. The server parses the message.

[0365] The server uses a natural language processing engine (e.g., SpaCy) to analyze the received message. This analysis extracts keywords such as "nursery school" and "how to enroll," and the question category is classified as "nursery school information."

[0366] 4. The server recognizes emotions.

[0367] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to detect the user's emotions from the message. For example, it can identify emotions such as "anxiety" or "restlessness."

[0368] 5. The server retrieves the user's residential area information.

[0369] The server queries the user's profile information to obtain information about their residential area. For example, if the user has previously registered "Shinjuku Ward," that information will be used. If the residential area is not registered, the system will prompt the user to enter the information.

[0370] 6. The server searches for the appropriate information.

[0371] The server searches for relevant information from databases (e.g., MySQL, MongoDB) based on the analysis results and residential area information. For example, it extracts information on nursery school enrollment in Shinjuku Ward (enrollment conditions, required documents, application methods, etc.).

[0372] 7. The server compares the information with that of the local government.

[0373] The server uses the latest information obtained from the local government's API and official website to compare it with the information in the database. This verifies the accuracy of the information provided.

[0374] 8. The server generates a response message.

[0375] The server generates a response message that takes the user's emotions into consideration, based on the results of the emotion recognition engine. If anxiety is detected, it will include reassuring phrases such as, "There's no need to worry unnecessarily."

[0376] 9. The server sends the message.

[0377] The server sends the generated response message to the user via the LINE API. The user can then view the response message in the LINE chat window.

[0378] Specific example

[0379] For example, if a user sends a message such as "Please tell me how to enroll my child in daycare," the server will process it in the following steps:

[0380] 1. The user sends a message through the LINE official account.

[0381] 2. The server receives the message via the LINE API.

[0382] 3. The server uses a natural language processing engine to parse the message.

[0383] 4. The server uses an emotion recognition engine to recognize emotions.

[0384] 5. The server retrieves the user's residential area information.

[0385] 6. The server searches the database for relevant information.

[0386] 7. The server compares the municipal information it has obtained with the contents of the database.

[0387] 8. The server generates a response message.

[0388] 9. The server sends a response message to the user via LINE.

[0389] Example of a prompt:

[0390] "Please tell me how to enroll my child in daycare."

[0391] "Please tell me about childhood vaccinations."

[0392] "I'm looking for a nearby childcare facility."

[0393] By following the above steps, this system can provide accurate and timely information while being sensitive to the user's emotions.

[0394] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0395] Program processing flow

[0396] Step 1:

[0397] Input: The user sends a message using the chat function of the LINE official account. Example: "Please tell me how to enroll my child in daycare."

[0398] Specific action: The user types a message in the chat window and presses the send button.

[0399] Output: The message is transferred to the server via the LINE API.

[0400] Step 2:

[0401] Input: The server receives message data from the LINE API.

[0402] Specific operation: The server waits for incoming requests and retrieves message data.

[0403] Output: The received message data is saved on the server and becomes ready for analysis.

[0404] Step 3:

[0405] Input: The server that receives the message data invokes a natural language processing engine (e.g., SpaCy).

[0406] Specific operation: The server instantiates an NLP engine and parses the incoming message.

[0407] Data processing / calculation: Extract keywords and phrases from messages and understand the context.

[0408] Output: Keywords such as "nursery school" and "how to enroll" are extracted, and the question category is classified as "childcare information."

[0409] Step 4:

[0410] Input: The server receives the results of the natural language processing engine's analysis.

[0411] Specific operation: The server calls an emotion recognition engine (e.g., IBM Watson Tone Analyzer) and sends the analysis results.

[0412] Data processing / calculation: Identify emotions (e.g., anxiety, impatience) from messages.

[0413] Output: The emotion analysis results in the detection of "anxiety."

[0414] Step 5:

[0415] Input: The server, having received the sentiment analysis results, retrieves the user's residential area information from the database.

[0416] Specific operation: The server executes a database query to extract the user's residential area from their profile information.

[0417] Data processing / calculation: Obtain residential area information in JSON format.

[0418] Output: Information about "Shinjuku Ward" that the user registered in advance is retrieved.

[0419] Step 6:

[0420] Input: Based on residential area information and analysis results, the server searches the database for relevant information.

[0421] Specific operation: The server executes a database query to extract childcare information related to Shinjuku Ward.

[0422] Data processing / calculation: Filter search results and organize relevant information.

[0423] Output: Information on childcare activities in Shinjuku Ward (e.g., admission requirements, necessary documents, application procedures) will be obtained.

[0424] Step 7:

[0425] Input: The server that retrieves the search results cross-references the latest information with the local government's API and official website.

[0426] Specific operation: The server sends an API request to retrieve the latest information from the local government.

[0427] Data processing / calculation: Compare and verify the contents of the database with the latest information obtained.

[0428] Output: Information matching and updates are confirmed, and the latest information is reflected in the database.

[0429] Step 8:

[0430] Input: Based on the latest information matched with the sentiment analysis results, the server generates a response message.

[0431] Specific operation: The server uses a template engine to construct emotionally sensitive response messages.

[0432] Data processing / calculation: Generate appropriate wording based on emotions and incorporate it into the message.

[0433] Output: Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. There's no need to worry unnecessarily. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[0434] Step 9:

[0435] Input: The server receives the generated response message.

[0436] Specific operation: The server uses the LINE API to send a response message.

[0437] Output: The user receives and confirms the response message in the LINE chat window.

[0438] The above outlines the specific processing steps of this system. This enables the provision of accurate information that resonates with the user's emotions.

[0439] (Application Example 2)

[0440] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0441] Current information processing systems are required to respond quickly and accurately to user inquiries and emergency reports. However, conventional systems struggle to adequately consider emotions and urgency in their responses, leaving challenges in ensuring user confidence and safety. Furthermore, there is a lack of mechanisms to acquire the latest information from local governments in real time and provide appropriate information immediately. As a result, users are prone to feeling anxious due to a lack of information and delayed responses, and a system that provides efficient information and a sense of security is needed.

[0442] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a message receiving means, a message analysis means for analyzing a message using natural language processing technology, a means for acquiring user residential area information based on the content analyzed by the message analysis means, an information retrieval means for searching for appropriate information from a database based on the analyzed content and residential area information, a means for comparing with local government information that provides appropriate information, a message generation means for generating a response message based on the matching result, a message transmission means for sending the response message to the user, a means for receiving reports of emergencies and suspicious person information from the user, recognizing the user's emotions using an emotion engine, and generating a message including highly urgent countermeasures, and a means for providing the latest information from the local government and presenting methods for ensuring safety. This enables the rapid and accurate provision of information that takes into account the user's emotions and urgency, thereby realizing a system that enhances the user's sense of security and contributes to ensuring safety.

[0443] "Message receiving means" refers to a device or software for receiving messages sent by a user.

[0444] A "message analysis means" is a device or software that analyzes a received message using natural language processing technology and extracts important information.

[0445] "Residential area information" refers to information about the region where the user lives, and is obtained from profile information.

[0446] "Information retrieval means" refers to a device or software that retrieves appropriate information from a database based on the analyzed message content and residential area information.

[0447] "Local government information" refers to official information provided by local administrative agencies, which is obtained from online APIs and official websites.

[0448] A "message generation means" is a device or software that generates a response message to send to the user based on analyzed information and sentiment data.

[0449] "Message transmission means" refers to a device or software for sending a generated response message to a user.

[0450] An "emotion engine" is a device or software that recognizes and analyzes emotions from a user's message.

[0451] "Reporting emergencies or suspicious person information" refers to the act of a user reporting an emergency situation or information about a suspicious person to the system.

[0452] "Appropriate information" refers to useful and accurate information in response to user inquiries or emergencies.

[0453] "Methods for ensuring safety" refer to specific means and advice for ensuring safety when a user feels anxious or in danger.

[0454] A security service system capable of ensuring safety and responding quickly to emergencies is described below as an embodiment of this invention.

[0455] The system consists of the following hardware and software:

[0456] Server: The server will use a cloud server (e.g., AWS®, Google Cloud, Microsoft® Azure®).

[0457] User device: A smartphone or tablet used to send messages.

[0458] The server includes the following software modules:

[0459] 1. Message receiving method: The server receives messages sent by the user via the LINE API.

[0460] 2. Message analysis method: The server analyzes the received message using a natural language processing (NLP) engine (e.g., NLTK, Google Cloud Natural Language API) and extracts keywords.

[0461] 3. Means for obtaining residential area information: The server obtains residential area information from the user's profile information.

[0462] 4. Information Retrieval Method: The server searches the database for relevant information based on the analyzed message content and residential area information. This database includes information such as police station contact information and emergency procedures.

[0463] 5. Local Government Information Verification Method: The server retrieves the latest local government information from the local government's online API or official website (e.g., local government API) and verifies it against the information in the database.

[0464] 6. Message generation means: The server generates a response message that takes into account the user's emotions and urgency, based on emotions recognized by an emotion engine (e.g., IBM Watson Sentiment Analysis API).

[0465] 7. Message sending method: The server sends the generated response message back to the user via the LINE API.

[0466] As an example, the following shows what happens when a user sends the message, "I saw a suspicious person in my neighborhood. What should I do?"

[0467] 1. The server receives the message using the message receiving means and analyzes it using the message analysis means.

[0468] 2. Obtain the user's residential area information and search the database for contact information for the local police station and emergency response information.

[0469] 3. Obtain the latest information from the local government's API and verify its accuracy by comparing it with the information provided.

[0470] 4. The emotion engine analyzes the user's emotions, and if it detects feelings of "anxiety" or "fear," it generates a reassuring response message that takes these feelings into account.

[0471] 5. Finally, send the generated response message to the user, informing them of the necessary actions to take.

[0472] In this way, this system can provide information quickly and accurately, taking into account the user's emotions and urgency, thereby enhancing the user's sense of security and contributing to safety.

[0473] Example of a prompt:

[0474] "I saw a suspicious person in my neighborhood. What should I do?"

[0475] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0476] Step 1:

[0477] The user's device sends a message using the chat function of the LINE official account or dedicated app. This message becomes the input. Example: "I saw a suspicious person in my neighborhood."

[0478] Step 2:

[0479] The server uses a message receiving mechanism to receive messages sent by users via the LINE API. The received messages become the input. This input data (messages) is converted into an analyzable format.

[0480] Step 3:

[0481] The server activates an NLP engine as a message analysis tool and analyzes the received message. This analysis extracts keywords. Example: "suspicious person," "neighborhood." The input is the received message, and the output is the extracted keywords.

[0482] Step 4:

[0483] The server retrieves the user's residential area information. It obtains this information from the user's profile; for example, "Minato-ku, Tokyo." The input is the user's profile data, and the output is the residential area information.

[0484] Step 5:

[0485] The server uses an information retrieval tool to search for relevant information from the database based on the analyzed keywords and residential area information. Example: Contact information for police stations and information on what to do. The input is keywords and residential area information, and the output is relevant information.

[0486] Step 6:

[0487] The server retrieves the latest municipal information from the municipality's API or official website. For example, it can retrieve the latest police station contact information and notices. The input is residential area information, and the output is the latest municipal information.

[0488] Step 7:

[0489] The server compares the municipality information it retrieves with existing database information to verify consistency. If the comparison does not result in a match, the database is updated. The input is the search results and the latest municipality information, and the output is the consistent information.

[0490] Step 8:

[0491] The server uses an emotion engine to recognize emotions from the content of the user's message. Example: Detecting the emotion "anxiety". The input is the received message, and the output is the recognized emotion.

[0492] Step 9:

[0493] The server uses a message generation mechanism to generate a response message based on the emotions recognized by the emotion engine. Example: "This is a report of a suspicious person in Minato Ward. First, please evacuate to a safe place. Please make a note of the suspicious person's characteristics in as much detail as possible and immediately contact the nearest police station (phone number: xxx-xxxx-xxxx)." The input is the consistent information and recognized emotions, and the output is the response message.

[0494] Step 10:

[0495] The server uses a message sending method to send the generated response message to the user via the LINE API. The user receives the message on the LINE chat screen on their smartphone or tablet and checks the solution. The input is the response message, and the output is the result of sending it to the user.

[0496] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0497] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0498] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0499] [Second Embodiment]

[0500] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0501] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0502] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0503] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0504] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0505] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0506] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0507] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0508] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0509] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0510] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0511] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0512] The present invention will be described based on the following system overview and specific examples.

[0513] System Overview

[0514] This system allows users to send questions and consultations about childcare through an official LINE account. The server receives and analyzes these messages and provides appropriate information. The system is available 24 hours a day and can also provide information tailored to the user's residential area.

[0515] Program Processing Overview

[0516] Step 1: The user sends a message.

[0517] Users use the chat function of the official LINE account to send messages such as, "Please tell me how to enroll my child in daycare."

[0518] Step 2: The server receives the message.

[0519] The server receives messages sent by users via the LINE API.

[0520] The server converts the received message into a format that can be parsed.

[0521] Step 3: The server parses the message.

[0522] The server uses natural language processing techniques to analyze the message.

[0523] Example: Extract the keywords "nursery school" and "how to enroll," and determine the category to be "information on finding childcare."

[0524] Step 4: The server retrieves the user's residential area information.

[0525] The server retrieves residential area information (for example, Shinjuku Ward) from the user's profile.

[0526] If the profile does not contain information about the user's residential area, the server will generate a response message asking, "Please tell us where you live."

[0527] Step 5: The server searches for the appropriate information.

[0528] The server uses message analysis results and residential area information to search the database for information such as nursery school admission requirements, necessary documents, and application procedures.

[0529] Step 6: The server matches with the local government information.

[0530] The server retrieves the latest information from the local government's API and official website, and compares it with the searched information.

[0531] If the most recent information matches, select that information.

[0532] Step 7: The server generates a response message.

[0533] Based on the information acquired by the server, a response message is generated to be provided to the user.

[0534] Example: "Details regarding admission to a nursery school in Shinjuku Ward are as follows. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: You can apply online through the ward office website."

[0535] Step 8: The server sends the message

[0536] The server sends a response message to the user via the LINE API.

[0537] Specific example

[0538] Case 1: Inquiry about childcare application information (nursery school enrollment)

[0539] 1. User: "Please tell me how to enroll my child in daycare."

[0540] 2. The server receives and analyzes the message. Based on the keywords "nursery school" and "how to enroll," it determines the category to be "childcare information."

[0541] 3. The server retrieves the user's residential area information (Shinjuku Ward) from their profile.

[0542] 4. The server searches the database for the latest information regarding childcare applications in Shinjuku Ward (conditions, documents, and methods).

[0543] 5. The server retrieves the latest information from the local government's API and compares it with the search results.

[0544] 6. The server generates a message stating, "Here are the details for enrolling in a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website."

[0545] 7. The server sends the generated message to the user via LINE.

[0546] Case 2: Medical information for sudden fever or injury

[0547] 1. User: "My child has a fever. Where can I get them examined?"

[0548] 2. The server receives and analyzes the message. It determines whether it is an emergency medical event based on the keywords "fever" and "medical institution."

[0549] 3. The server retrieves residential area information (Kita Ward, Osaka City).

[0550] 4. The server searches its database for medical institutions in Kita Ward, Osaka City that can provide emergency medical care.

[0551] 5. The server retrieves the latest medical institution information from the local government API and compares it with the search results.

[0552] 6. The server generates the message: "Osaka City Kita Ward General Hospital is open 24 hours a day. The emergency center is also available. The address is ○○."

[0553] 7. The server sends the generated message to the user via LINE.

[0554] In this way, this system efficiently processes user inquiries, providing prompt responses and accurate information. This will enable it to address a wide range of needs related to childcare.

[0555] The following describes the processing flow.

[0556] Step 1:

[0557] A user sends a message to the official LINE account. This message might be something like, "Please tell me how to enroll my child in daycare."

[0558] Step 2:

[0559] The server receives messages sent by users via the LINE API. The received messages are then converted into an analyzable format.

[0560] Step 3:

[0561] The server invokes a natural language processing (NLP) engine to analyze the received message. This analysis extracts keywords such as "nursery school" and "how to enroll," and the question category is determined to be "childcare information."

[0562] Step 4:

[0563] The server retrieves residential area information from the user's profile information. For example, if the user has previously registered "Shinjuku Ward," that information will be used. If residential area information is not registered, the server will ask the user for their residential area in a subsequent process.

[0564] Step 5:

[0565] The server searches the database for relevant information based on the message analysis results and residential area information. For example, it extracts information about childcare activities in Shinjuku Ward (admission requirements, necessary documents, application methods, etc.).

[0566] Step 6:

[0567] The server retrieves the latest local government information from the local government's API and official website. This allows the server to compare the latest childcare information with the contents of the database, ensuring the consistency of the information.

[0568] Step 7:

[0569] The server generates a response message to the user based on the collected and verified information.

[0570] For example, the content might read: "Details regarding admission to a nursery school in Shinjuku Ward are as follows. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: You can apply online through the ward office website."

[0571] Step 8:

[0572] The server sends a generated response message to the user via the LINE API. The user can receive the message on the LINE chat screen and check the suggested solution.

[0573] Specific example (in the case of an inquiry about childcare information):

[0574] Step 1:

[0575] User: Sends a message saying, "Please tell me how to enroll my child in daycare."

[0576] Step 2:

[0577] The server receives this message using the LINE API.

[0578] Step 3:

[0579] The server analyzes the message using an NLP engine, extracts "nursery school" and "how to enroll" as keywords, and classifies them as "childcare information."

[0580] Step 4:

[0581] The server retrieves residential area information for "Shinjuku Ward" from the user's profile.

[0582] Step 5:

[0583] The server searches the database for nursery school enrollment information related to Shinjuku Ward.

[0584] Step 6:

[0585] The server retrieves the latest nursery school enrollment information from the Shinjuku Ward official website and compares it with the database.

[0586] Step 7:

[0587] The server generates a response message stating, "Details regarding admission to a nursery school in Shinjuku Ward are as follows. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: You can apply online through the ward office website."

[0588] Step 8:

[0589] The server sends this message to the user via LINE, and the user receives and confirms its contents.

[0590] (Example 1)

[0591] Next, we will describe Example 1. 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".

[0592] Conventional information systems struggled to respond quickly and accurately to user questions and inquiries. Furthermore, they often failed to adequately address users' residential areas, resulting in inconsistencies with the latest information from local governments. Additionally, the lack of message optimization meant users often received unclear and easily understandable responses.

[0593] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0594] In this invention, the server includes a message receiving means, a message analysis means for analyzing the message using natural language processing technology, a means for acquiring the user's residential area information based on the content analyzed by the message analysis means, an information retrieval means for searching for appropriate information from a database based on the analyzed content and residential area information, a means for comparing with administrative agency information that provides appropriate information, a message generation means for generating a response message based on the comparison result, a message sending means for sending the response message to the user, and a means for optimizing the generated message using a generation AI model. This enables the rapid and accurate provision of information in response to user questions and consultations, provides optimal information tailored to the residential area, ensures consistency with the latest information from administrative agencies, and provides a response message that is easy for the user to understand.

[0595] "Message receiving means" refers to a combination of a system and process that receives messages sent by users and converts those messages into a parseable format.

[0596] "Natural language processing technology" refers to the techniques that enable computers to understand, analyze, and generate human language, and includes methods for interpreting the meaning of text.

[0597] A "message analysis system" refers to a system that analyzes received messages and has the function of extracting and understanding keywords and context within those messages.

[0598] "User residential area information" refers to data related to the geographical area where the user resides, including address and region name.

[0599] "Information retrieval means" refers to a system that has the function of extracting highly relevant information from a database based on message analysis results and residential area information.

[0600] A "database" is a systematically organized collection of data, and refers to a system that allows for the fast and efficient searching, adding, updating, and deleting of specific information.

[0601] "Government agency information" refers to data and information officially provided by public institutions such as local governments.

[0602] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and generates an optimized response for a specific task.

[0603] "Message generation means" refers to a system that has the function of creating an appropriate response message based on the analyzed content and matching results.

[0604] "Message sending means" refers to a communication means for sending a generated response message to the user.

[0605] As an embodiment of the present invention, a system is described in which a user sends questions or requests for advice regarding childcare using an online messaging platform (e.g., LINE official account), a server receives and analyzes the message, and provides appropriate information.

[0606] The server first receives messages sent by users using a message receiving method. LINE's Messaging API is used for message reception. Next, the server analyzes the messages using natural language processing technology (for example, Google Cloud Natural Language API). This makes it possible to extract keywords and intent from the message content.

[0607] Based on the analyzed data, the server retrieves the user's residential area information. This includes a function to refer to the user's profile information, and if residential area information is missing, it generates a response message asking the user, "Please tell us where you live."

[0608] Next, the server uses the analysis results and residential area information to search for appropriate information from the database. The database can be a relational or non-relational database such as MySQL or MongoDB. The retrieved information includes specific details such as nursery school admission requirements, necessary documents, and application procedures.

[0609] The server then retrieves the latest information from the local government's APIs and official websites and compares it with the previously retrieved database information. For example, it ensures the accuracy of the information provided by comparing it with the latest information obtained from Shinjuku Ward's open data API.

[0610] Next, the server generates a response message based on the matching results. Here, a generative AI model (e.g., GPT-4) is used to optimize the response message. This ensures that the user receives clear and relevant information.

[0611] Finally, the server uses a message sending method to send the generated response message to the user. The message is sent to the user's LINE account via LINE's Messaging API.

[0612] Specific example

[0613] Case 1: Inquiry about nursery school enrollment information

[0614] 1. User: "Please tell me how to enroll my child in daycare."

[0615] 2. The server receives the message and analyzes it using natural language processing technology. Based on the keywords "nursery school" and "how to enroll," it determines the category to be "childcare information."

[0616] 3. The server retrieves the user's residential area information (Shinjuku Ward).

[0617] 4. The server searches the database for the latest information regarding childcare applications in Shinjuku Ward (conditions, documents, and methods).

[0618] 5. The server retrieves the latest information from the local government's API and compares it with the search results.

[0619] 6. The server generates a message stating, "Here are the details for enrolling in a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website."

[0620] 7. The server sends the generated message to the user via LINE.

[0621] Case 2: Medical information for sudden fever or injury

[0622] 1. User: "My child has a fever. Where can I get them examined?"

[0623] 2. The server receives and analyzes the message. It determines whether it is an emergency medical event based on the keywords "fever" and "medical institution."

[0624] 3. The server retrieves residential area information (Kita Ward, Osaka City).

[0625] 4. The server searches its database for medical institutions in Kita Ward, Osaka City that can provide emergency medical care.

[0626] 5. The server retrieves the latest medical institution information from the local government API and compares it with the search results.

[0627] 6. The server generates the message: "Osaka City Kita Ward General Hospital is open 24 hours a day. The emergency center is also available. The address is ○○."

[0628] 7. The server sends the generated message to the user via LINE.

[0629] This invention allows users to obtain quick and accurate information, enabling them to address diverse childcare needs. The system is particularly useful as it is available 24 / 7 through messaging platforms like LINE, significantly improving user convenience.

[0630] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0631] Program processing flow

[0632] Step 1:

[0633] Users can use the chat function of the official LINE account to enter questions or requests for advice and send messages.

[0634] Input: Message from the user (e.g., "Please tell me how to enroll my child in daycare.")

[0635] Output: A message is sent to the LINE server.

[0636] Specific action: The user types a message on the LINE app on their smartphone or PC and presses the send button.

[0637] Step 2:

[0638] The server uses LINE's Messaging API to retrieve incoming messages.

[0639] Input: Message sent from LINE server

[0640] Output: The message arrives on the server in JSON format (Example: { "type": "text", "text": "Please tell me how to enroll my child in daycare"})

[0641] Specific operation: The server polls for new messages via the LINE Messaging API endpoint.

[0642] Step 3:

[0643] The server uses natural language processing techniques to analyze the message.

[0644] Input: Message in JSON format (Example: { "type": "text", "text": "Please tell me how to enroll my child in daycare"})

[0645] Output: Analysis results (Keywords: "nursery school", "how to enroll", Category: "childcare information")

[0646] Specific operation: The server uses an NLP engine such as the Google Cloud Natural Language API to extract keywords from the message text and classify the intent.

[0647] Step 4:

[0648] The server retrieves the user's residential area information.

[0649] Input: Analysis results (Category "Childcare Information")

[0650] Output: Residential area information (e.g., Shinjuku Ward)

[0651] Specific operation: The server searches for the user's residential area from their LINE profile information and retrieves the information. If residential area information is insufficient, it generates a message asking "Please tell us where you live" and sends it to the user.

[0652] Step 5:

[0653] The server uses the analysis results and residential area information to search for appropriate information from the database.

[0654] Input: Analysis results, residential area information

[0655] Output: Appropriate information (e.g., nursery school admission requirements, necessary documents, application procedures)

[0656] Specific operation: The server queries databases such as MySQL or MongoDB to retrieve analysis results and related data based on residential area information.

[0657] Step 6:

[0658] The server retrieves the latest information from local government APIs and official websites and compares it with search results.

[0659] Input: Appropriate information (search results from the database), up-to-date local government information (obtained from API or official website)

[0660] Output: Matching results (latest matching information)

[0661] Specific operation: The server retrieves the latest information from sources such as Shinjuku Ward's open data API, and verifies its consistency by comparing it with information obtained from the database.

[0662] Step 7:

[0663] The server generates a response message based on the matching results.

[0664] Input: Matching result

[0665] Output: Response message (Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website.")

[0666] Specific operation: The server uses a generated AI model (e.g., GPT-4) to create a response message that provides information to the user in an easily understandable format.

[0667] Step 8:

[0668] The server sends a response message to the user.

[0669] Input: Response message

[0670] Output: Message delivered to the user

[0671] Specific operation: The server sends the generated response message to the user's LINE account via LINE's Messaging API.

[0672] (Application Example 1)

[0673] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0674] In today's lifestyle, obtaining information about childcare quickly and accurately is crucial. Furthermore, there is a need for a means to quickly obtain appropriate information, even in situations requiring urgent action. To utilize such information services more diversely, convenience is needed not only for information provision but also for paid services and content purchases using electronic payments. However, current systems struggle to simultaneously meet all these requirements.

[0675] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0676] In this invention, the server includes a message receiving means, a message analysis means for analyzing the message using natural language processing technology, a means for acquiring the user's residential area information based on the content analyzed by the message analysis means, an information retrieval means for searching a database for appropriate information based on the analyzed content and the residential area information, a means for comparing the appropriate information with local government information, a message generation means for generating a response message based on the matching result, a message transmission means for sending the response message to the user, and an electronic payment means. This enables the user to receive information suitable for their residential area, receive emergency consultations, and even purchase paid consultations and childcare-related content using electronic payment.

[0677] A "message receiving means" is a means that has the function of receiving messages sent by a user.

[0678] A "message analysis tool" is a means of analyzing a received message using natural language processing technology to understand its content.

[0679] "Means for obtaining residential area information" refers to methods for extracting and obtaining information about a user's residential area from their profile information or inquiry messages.

[0680] An "information retrieval method" is a means of searching for appropriate information from a database based on the content of the analyzed message and the acquired residential area information.

[0681] "Means of cross-referencing with local government information" refers to methods for verifying and cross-referencing the searched information with the latest information from the local government.

[0682] A "message generation means" is a means for creating a response message to be provided to the user based on the verified information.

[0683] "Message sending means" refers to means for sending the generated response message to the user.

[0684] "Electronic payment methods" refer to means that have the functionality of electronic payment and can be used by users when purchasing paid services or content.

[0685] A "generative AI model" is an artificial intelligence model used to generate appropriate answers or response messages in response to user inquiries.

[0686] A "prompt sentence" is a sentence of instruction or question that is input to a generative AI model, and it is the input sentence that enables the model to generate an appropriate answer.

[0687] The system for carrying out the present invention is constructed using the following hardware and software.

[0688] hardware

[0689] Server: Used as a central processing unit for database management, communication processing, message analysis, and generation.

[0690] User terminal: A device, such as a smartphone, used by a user to send and receive messages.

[0691] Internet connection: A network infrastructure that facilitates communication between servers and user terminals.

[0692] software

[0693] LINE Messaging API: Used to receive messages from users and forward them to the server.

[0694] Natural language processing libraries (e.g., NLTK): Provide natural language processing techniques for message analysis.

[0695] SQLite: A database system that stores user information and childcare information by region.

[0696] Python: Used as the programming language to integrate all of the above parts.

[0697] Processing flow

[0698] 1. Message Reception: Users send questions and requests for advice regarding childcare using the LINE app on their device. For example, they might send a message such as, "Please tell me how to enroll my child in daycare."

[0699] 2. Message Analysis: After receiving a message via the LINE Messaging API, the server uses NLTK to analyze the message and extract keywords (e.g., "nursery school," "how to enroll").

[0700] 3. Obtaining residential area information: The server obtains residential area information (e.g., "Shinjuku Ward") from the user profile information.

[0701] 4. Information Retrieval: The server searches for appropriate information from the SQLite database based on the analyzed keywords and residential area information.

[0702] 5. Verification with local government information: The server retrieves the latest information from local government APIs and official websites and verifies it against the search results.

[0703] 6. Generating a response message: The server generates a response message based on the matching results (e.g., "Details regarding admission to a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website.").

[0704] 7. Message Sending: The generated response message is sent to the user via the LINE Messaging API.

[0705] 8. Electronic payment: Users utilize electronic payment functions to purchase paid consultations and childcare-related content.

[0706] This system allows users to quickly and accurately obtain childcare information tailored to their residential area. Furthermore, it enables prompt and appropriate responses to urgent inquiries and emergencies, and allows for paid consultations and content purchases using electronic payment.

[0707] Specific example

[0708] User: "My child has a fever. Where can I get them examined?"

[0709] server:

[0710] The message was analyzed, and the keywords "fever" and "medical institution" were extracted.

[0711] Retrieve residential area information (e.g., "Kita Ward, Osaka City").

[0712] Search the database for information on medical institutions in the relevant area.

[0713] Check against the latest local government information.

[0714] Generate a response message (e.g., "Osaka City Kita Ward General Hospital is open 24 hours. The emergency center is also available. The address is XX.").

[0715] Send a message to the user.

[0716] Examples of prompts for generative AI models

[0717] User: "Please tell me how to enroll my child in daycare."

[0718] AI: "I will now explain the specific procedures for enrolling your child in daycare. First, please prepare the necessary documents. Next, I will explain how to apply online."

[0719] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0720] Step 1:

[0721] Users send questions and requests for advice about childcare using the LINE app on their devices. The input is a text message, such as "Please tell me how to enroll my child in daycare." This message is then sent to the server.

[0722] Step 2:

[0723] The server receives messages from users via the LINE Messaging API. The received messages are converted into a parseable format. The input is the user's text message, and the output is text data for parsing.

[0724] Step 3:

[0725] The server parses incoming messages using a natural language processing library (such as NLTK). It extracts keywords from the messages (e.g., "nursery school," "how to enroll"). The input is text data for analysis, and the output is a list of keywords.

[0726] Step 4:

[0727] The server retrieves residential area information from the user's profile information. This ensures that the analyzed keywords and the user's residential area information are matched. The input is the user ID, and the output is the user's residential area information (e.g., "Shinjuku Ward").

[0728] Step 5:

[0729] The server searches for appropriate information from the SQLite database based on the analyzed keywords and acquired residential area information. The input is a list of keywords and residential area information, and the output is the initial search result.

[0730] Step 6:

[0731] The server retrieves the latest information from local government APIs and official websites and compares it with the initial search results. This verifies the timeliness of the information. The input is the initial search results, and the output is the final, verified information.

[0732] Step 7:

[0733] The server generates a response message based on the final information it has verified. The input is the final information, and the output is a text message sent to the user (e.g., "Here are the details for nursery school enrollment in Shinjuku Ward. Required documents: resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website.").

[0734] Step 8:

[0735] The server sends the generated response message to the user via the LINE Messaging API. The input is the response message, and the output is the message displayed on the user's device.

[0736] Step 9:

[0737] Users utilize in-app electronic payment methods to access paid consultations and childcare-related content. The input is the user's electronic payment information, and the output is a confirmation message upon completion of the payment.

[0738] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0739] The present invention will be described based on the following system overview and specific examples.

[0740] System Overview

[0741] This system allows users to send questions and consultations about childcare via a LINE official account. The server receives and analyzes these messages and provides appropriate information. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it can provide even more appropriate responses. The system is available 24 hours a day and can also provide information tailored to the user's residential area.

[0742] Program Processing Overview

[0743] Step 1: The user sends a message.

[0744] Users use the chat function of the official LINE account to send messages such as, "Please tell me how to enroll my child in daycare."

[0745] Step 2: The server receives the message.

[0746] The server receives messages sent by users via the LINE API. The received messages are converted into an analyzable format.

[0747] Step 3: The server parses the message.

[0748] The server invokes a natural language processing (NLP) engine to analyze the received message. This analysis extracts the keywords "nursery school" and "how to enroll," and the question category is determined to be "nursery school information."

[0749] Step 4: The server uses the emotion engine to recognize emotions.

[0750] The server uses an emotion engine to recognize emotions from the content of the user's message. For example, the emotion engine can detect emotions such as "anxiety" or "impatience" from the user's message.

[0751] Step 5: The server retrieves the user's residential area information.

[0752] The server retrieves residential area information from the user's profile information. For example, if the user has previously registered "Shinjuku Ward," that information will be used. If residential area information is not registered, the server will ask the user for their residential area in a subsequent process.

[0753] Step 6: The server searches for the appropriate information.

[0754] The server searches the database for relevant information based on the message analysis results and residential area information. For example, it extracts information about childcare activities in Shinjuku Ward (admission requirements, necessary documents, application methods, etc.).

[0755] Step 7: The server matches with the local government information.

[0756] The server retrieves the latest local government information from the local government's API and official website. This allows the server to compare the latest childcare information with the contents of the database, ensuring the consistency of the information.

[0757] Step 8: The server generates a response message.

[0758] The server generates a response message based on the emotions recognized by the emotion engine. The content and tone of the response message are adjusted to match the user's emotions. For example, if anxiety is detected, the message will include reassuring language.

[0759] Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. There's no need to worry unnecessarily. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[0760] Step 9: The server sends the message

[0761] The server sends a generated response message to the user via the LINE API. The user can receive the message on the LINE chat screen and check the suggested solution.

[0762] Specific example (in the case of an inquiry about childcare information):

[0763] Case 1: Inquiry about childcare application information (nursery school enrollment)

[0764] 1. User: Sends a message saying, "Please tell me how to enroll my child in daycare."

[0765] 2. The server receives this message using the LINE API.

[0766] 3. The server uses an NLP engine to analyze the message, extracts keywords such as "nursery school" and "how to enroll," and classifies it as "childcare information."

[0767] 4. The server uses an emotion engine to recognize the emotion of "anxiety" from the user's message.

[0768] 5. The server retrieves residential area information for "Shinjuku Ward" from the user's profile.

[0769] 6. The server searches the database for nursery school enrollment information related to Shinjuku Ward.

[0770] 7. The server retrieves the latest nursery school enrollment information from the Shinjuku Ward official website and compares it with the database.

[0771] 8. The server generates a response message that includes reassuring wording such as, "Here are the details for enrolling in a nursery school in Shinjuku Ward. There is no need to worry unnecessarily. Required documents include a resident registration certificate and a maternal and child health handbook. You can apply online through the ward office website."

[0772] 9. The server sends this message to the user via LINE, and the user receives and confirms its contents.

[0773] In this way, the system efficiently processes user inquiries and provides accurate information along with prompt, empathetic responses. This makes it possible to address diverse childcare needs while also considering their emotional aspects.

[0774] The following describes the processing flow.

[0775] Step 1:

[0776] A user sends a message to the official LINE account saying, "Please tell me how to enroll my child in daycare."

[0777] Step 2:

[0778] The server receives this message via the LINE API. The received message is converted into a parseable format.

[0779] Step 3:

[0780] The server invokes a natural language processing (NLP) engine to analyze the message. It extracts specific keywords (in this case, "nursery school" and "how to enroll") and determines that the question falls under the category of "nursery school information."

[0781] Step 4:

[0782] The server invokes an emotion engine to recognize emotions from the user's message. For example, it can detect emotions such as "anxiety" or "restlessness" from the user's message.

[0783] Step 5:

[0784] The server accesses the user's profile information and retrieves their residential area information (e.g., "Shinjuku Ward"). If the residential area information is not registered, a message is generated in the subsequent process asking the user to provide their residential area.

[0785] Step 6:

[0786] The server searches the database for relevant information based on the message analysis results and acquired residential area information. For example, it might retrieve information such as admission requirements, necessary documents, and application procedures for daycare centers in Shinjuku Ward.

[0787] Step 7:

[0788] The server retrieves the latest information from the local government's API and official website. This latest information is then compared with the database information to verify consistency.

[0789] Step 8:

[0790] The server generates a response message based on the recognition results from the emotion engine. If the user is feeling anxious, a message designed to reassure them will be generated.

[0791] Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. Please rest assured. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[0792] Step 9:

[0793] The server sends a generated response message to the user via the LINE API. The user can receive the message on the LINE chat screen and check the suggested solution.

[0794] Specific example (in the case of an inquiry about childcare information):

[0795] Step 1:

[0796] User: Sends a message saying, "Please tell me how to enroll my child in daycare."

[0797] Step 2:

[0798] The server uses the LINE API to receive messages.

[0799] Step 3:

[0800] The server uses an NLP engine to analyze the message, extracts the keywords "nursery school" and "how to enroll," and classifies it as "information on finding childcare."

[0801] Step 4:

[0802] The server uses an emotion engine to recognize the emotion of "anxiety" from the user's message.

[0803] Step 5:

[0804] The server retrieves residential area information for "Shinjuku Ward" from the user's profile information.

[0805] Step 6:

[0806] The server searches the database for nursery school enrollment information related to Shinjuku Ward.

[0807] Step 7:

[0808] The server retrieves the latest nursery school enrollment information from the local government's API and compares it with the database.

[0809] Step 8:

[0810] The server, responding to the emotion of "anxiety," generates a response message that reads, "Here are the details for enrolling in a nursery school in Shinjuku Ward. Please rest assured. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[0811] Step 9:

[0812] The server sends this message to the user via the LINE API. The user can then view the received message.

[0813] (Example 2)

[0814] Next, we will describe Example 2. 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".

[0815] In modern society, providing timely and appropriate information about childcare is crucial. However, existing systems struggle to provide information that takes users' emotions into account, and there are challenges in adequately addressing the needs of users who require emotional support. Furthermore, the lack of up-to-date information specific to a particular residential area makes it difficult to provide appropriate advice for each region.

[0816] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0817] In this invention, the server includes message receiving means, message analysis means for analyzing the message using natural language processing technology, emotion recognition means for recognizing the user's emotions from the message, means for acquiring the user's residential area information based on the content analyzed by the message analysis means, information retrieval means for searching a database for appropriate information based on the analyzed content and the residential area information, means for comparing the information with local government information that provides the appropriate information, message generation means for generating a response message based on the emotions recognized by the emotion recognition means, and message transmission means for sending the response message to the user. This makes it possible to quickly provide the latest and most appropriate information for each residential area while being attentive to the user's emotions.

[0818] A "message receiving means" is a means for receiving messages sent by a user.

[0819] A "message analysis means" is a means for analyzing a received message using natural language processing technology.

[0820] "Emotion recognition means" refers to a method for recognizing a user's emotions from a received message.

[0821] "Means for obtaining user residential area information" refers to means for obtaining information about the user's place of residence.

[0822] An "information retrieval method" is a means of searching for appropriate information from a database based on the analyzed content and residential area information.

[0823] "Means of cross-referencing with local government information" refers to means of cross-referencing appropriate information with the latest information provided by local governments.

[0824] A "message generation means" is a means for generating a response message based on the emotion recognized by the emotion recognition means.

[0825] "Message sending means" refers to means for sending the generated response message to the user.

[0826] Modes for carrying out the invention

[0827] This invention relates to a system in which a server receives, analyzes, and provides appropriate information in response to questions and consultations about childcare sent by users through an online chat platform. A key feature of this system is its ability to provide responses that take the user's emotions into consideration, particularly through the integration of emotion recognition functionality. The embodiments of this system are described in detail below.

[0828] System Overview

[0829] This system consists of the following main hardware and software components:

[0830] server

[0831] User devices (smartphones, tablets, PCs)

[0832] LINE official accounts and their APIs

[0833] Natural language processing engines (e.g., SpaCy, NLTK)

[0834] Emotion recognition engine (e.g., IBM Watson Tone Analyzer)

[0835] Databases (e.g., MySQL, MongoDB)

[0836] Local government API or official website

[0837] Specific operation of the system

[0838] 1. The user sends a message.

[0839] Users can send questions and inquiries through the chat window of the official LINE account. For example, specific questions such as "Please tell me how to enroll my child in daycare" are possible.

[0840] 2. The server receives the message.

[0841] The server receives messages from users via the LINE API. At this time, the message data is transferred to the server in JSON format.

[0842] 3. The server parses the message.

[0843] The server uses a natural language processing engine (e.g., SpaCy) to analyze the received message. This analysis extracts keywords such as "nursery school" and "how to enroll," and the question category is classified as "nursery school information."

[0844] 4. The server recognizes emotions.

[0845] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to detect the user's emotions from the message. For example, it can identify emotions such as "anxiety" or "restlessness."

[0846] 5. The server retrieves the user's residential area information.

[0847] The server queries the user's profile information to obtain information about their residential area. For example, if the user has previously registered "Shinjuku Ward," that information will be used. If the residential area is not registered, the system will prompt the user to enter the information.

[0848] 6. The server searches for the appropriate information.

[0849] The server searches for relevant information from databases (e.g., MySQL, MongoDB) based on the analysis results and residential area information. For example, it extracts information on nursery school enrollment in Shinjuku Ward (enrollment conditions, required documents, application methods, etc.).

[0850] 7. The server compares the information with that of the local government.

[0851] The server uses the latest information obtained from the local government's API and official website to compare it with the information in the database. This verifies the accuracy of the information provided.

[0852] 8. The server generates a response message.

[0853] The server generates a response message that takes the user's emotions into consideration, based on the results of the emotion recognition engine. If anxiety is detected, it will include reassuring phrases such as, "There's no need to worry unnecessarily."

[0854] 9. The server sends the message.

[0855] The server sends the generated response message to the user via the LINE API. The user can then view the response message in the LINE chat window.

[0856] Specific example

[0857] For example, if a user sends a message such as "Please tell me how to enroll my child in daycare," the server will process it in the following steps:

[0858] 1. The user sends a message through the LINE official account.

[0859] 2. The server receives the message via the LINE API.

[0860] 3. The server uses a natural language processing engine to parse the message.

[0861] 4. The server uses an emotion recognition engine to recognize emotions.

[0862] 5. The server retrieves the user's residential area information.

[0863] 6. The server searches the database for relevant information.

[0864] 7. The server compares the municipal information it has obtained with the contents of the database.

[0865] 8. The server generates a response message.

[0866] 9. The server sends a response message to the user via LINE.

[0867] Example of a prompt:

[0868] "Please tell me how to enroll my child in daycare."

[0869] "Please tell me about childhood vaccinations."

[0870] "I'm looking for a nearby childcare facility."

[0871] By following the above steps, this system can provide accurate and timely information while being sensitive to the user's emotions.

[0872] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0873] Program processing flow

[0874] Step 1:

[0875] Input: The user sends a message using the chat function of the LINE official account. Example: "Please tell me how to enroll my child in daycare."

[0876] Specific action: The user types a message in the chat window and presses the send button.

[0877] Output: The message is transferred to the server via the LINE API.

[0878] Step 2:

[0879] Input: The server receives message data from the LINE API.

[0880] Specific operation: The server waits for incoming requests and retrieves message data.

[0881] Output: The received message data is saved on the server and becomes ready for analysis.

[0882] Step 3:

[0883] Input: The server that receives the message data invokes a natural language processing engine (e.g., SpaCy).

[0884] Specific operation: The server instantiates an NLP engine and parses the incoming message.

[0885] Data processing / calculation: Extract keywords and phrases from messages and understand the context.

[0886] Output: Keywords such as "nursery school" and "how to enroll" are extracted, and the question category is classified as "childcare information."

[0887] Step 4:

[0888] Input: The server receives the results of the natural language processing engine's analysis.

[0889] Specific operation: The server calls an emotion recognition engine (e.g., IBM Watson Tone Analyzer) and sends the analysis results.

[0890] Data processing / calculation: Identify emotions (e.g., anxiety, impatience) from messages.

[0891] Output: The emotion analysis results in the detection of "anxiety."

[0892] Step 5:

[0893] Input: The server, having received the sentiment analysis results, retrieves the user's residential area information from the database.

[0894] Specific operation: The server executes a database query to extract the user's residential area from their profile information.

[0895] Data processing / calculation: Obtain residential area information in JSON format.

[0896] Output: Information about "Shinjuku Ward" that the user registered in advance is retrieved.

[0897] Step 6:

[0898] Input: Based on residential area information and analysis results, the server searches the database for relevant information.

[0899] Specific operation: The server executes a database query to extract childcare information related to Shinjuku Ward.

[0900] Data processing / calculation: Filter search results and organize relevant information.

[0901] Output: Information on childcare activities in Shinjuku Ward (e.g., admission requirements, necessary documents, application procedures) will be obtained.

[0902] Step 7:

[0903] Input: The server that retrieves the search results cross-references the latest information with the local government's API and official website.

[0904] Specific operation: The server sends an API request to retrieve the latest information from the local government.

[0905] Data processing / calculation: Compare and verify the contents of the database with the latest information obtained.

[0906] Output: Information matching and updates are confirmed, and the latest information is reflected in the database.

[0907] Step 8:

[0908] Input: Based on the latest information matched with the sentiment analysis results, the server generates a response message.

[0909] Specific operation: The server uses a template engine to construct emotionally sensitive response messages.

[0910] Data processing / calculation: Generate appropriate wording based on emotions and incorporate it into the message.

[0911] Output: Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. There's no need to worry unnecessarily. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[0912] Step 9:

[0913] Input: The server receives the generated response message.

[0914] Specific operation: The server uses the LINE API to send a response message.

[0915] Output: The user receives and confirms the response message in the LINE chat window.

[0916] The above outlines the specific processing steps of this system. This enables the provision of accurate information that resonates with the user's emotions.

[0917] (Application Example 2)

[0918] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0919] Current information processing systems are required to respond quickly and accurately to user inquiries and emergency reports. However, conventional systems struggle to adequately consider emotions and urgency in their responses, leaving challenges in ensuring user confidence and safety. Furthermore, there is a lack of mechanisms to acquire the latest information from local governments in real time and provide appropriate information immediately. As a result, users are prone to feeling anxious due to a lack of information and delayed responses, and a system that provides efficient information and a sense of security is needed.

[0920] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a message receiving means, a message analysis means for analyzing a message using natural language processing technology, a means for acquiring user residential area information based on the content analyzed by the message analysis means, an information retrieval means for searching for appropriate information from a database based on the analyzed content and residential area information, a means for comparing with local government information that provides appropriate information, a message generation means for generating a response message based on the matching result, a message transmission means for sending the response message to the user, a means for receiving reports of emergencies and suspicious person information from the user, recognizing the user's emotions using an emotion engine, and generating a message including highly urgent countermeasures, and a means for providing the latest information from the local government and presenting methods for ensuring safety. This enables the rapid and accurate provision of information that takes into account the user's emotions and urgency, thereby realizing a system that enhances the user's sense of security and contributes to ensuring safety.

[0921] "Message receiving means" refers to a device or software for receiving messages sent by a user.

[0922] A "message analysis means" is a device or software that analyzes a received message using natural language processing technology and extracts important information.

[0923] "Residential area information" refers to information about the region where the user lives, and is obtained from profile information.

[0924] "Information retrieval means" refers to a device or software that retrieves appropriate information from a database based on the analyzed message content and residential area information.

[0925] "Local government information" refers to official information provided by local administrative agencies, which is obtained from online APIs and official websites.

[0926] A "message generation means" is a device or software that generates a response message to send to the user based on analyzed information and sentiment data.

[0927] "Message transmission means" refers to a device or software for sending a generated response message to a user.

[0928] An "emotion engine" is a device or software that recognizes and analyzes emotions from a user's message.

[0929] "Reporting emergencies or suspicious person information" refers to the act of a user reporting an emergency situation or information about a suspicious person to the system.

[0930] "Appropriate information" refers to useful and accurate information in response to user inquiries or emergencies.

[0931] "Methods for ensuring safety" refer to specific means and advice for ensuring safety when a user feels anxious or in danger.

[0932] A security service system capable of ensuring safety and responding quickly to emergencies is described below as an embodiment of this invention.

[0933] The system consists of the following hardware and software:

[0934] Server: The server will use a cloud server (e.g., AWS, Google Cloud, Microsoft Azure).

[0935] User device: A smartphone or tablet used to send messages.

[0936] The server includes the following software modules:

[0937] 1. Message receiving method: The server receives messages sent by the user via the LINE API.

[0938] 2. Message analysis method: The server analyzes the received message using a natural language processing (NLP) engine (e.g., NLTK, Google Cloud Natural Language API) and extracts keywords.

[0939] 3. Means for obtaining residential area information: The server obtains residential area information from the user's profile information.

[0940] 4. Information Retrieval Method: The server searches the database for relevant information based on the analyzed message content and residential area information. This database includes information such as police station contact information and emergency procedures.

[0941] 5. Local Government Information Verification Method: The server retrieves the latest local government information from the local government's online API or official website (e.g., local government API) and verifies it against the information in the database.

[0942] 6. Message generation means: The server generates a response message that takes into account the user's emotions and urgency, based on emotions recognized by an emotion engine (e.g., IBM Watson Sentiment Analysis API).

[0943] 7. Message sending method: The server sends the generated response message back to the user via the LINE API.

[0944] As an example, the following shows what happens when a user sends the message, "I saw a suspicious person in my neighborhood. What should I do?"

[0945] 1. The server receives the message using the message receiving means and analyzes it using the message analysis means.

[0946] 2. Obtain the user's residential area information and search the database for contact information for the local police station and emergency response information.

[0947] 3. Obtain the latest information from the local government's API and verify its accuracy by comparing it with the information provided.

[0948] 4. The emotion engine analyzes the user's emotions, and if it detects feelings of "anxiety" or "fear," it generates a reassuring response message that takes these feelings into account.

[0949] 5. Finally, send the generated response message to the user, informing them of the necessary actions to take.

[0950] In this way, this system can provide information quickly and accurately, taking into account the user's emotions and urgency, thereby enhancing the user's sense of security and contributing to safety.

[0951] Example of a prompt:

[0952] "I saw a suspicious person in my neighborhood. What should I do?"

[0953] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0954] Step 1:

[0955] The user's device sends a message using the chat function of the LINE official account or dedicated app. This message becomes the input. Example: "I saw a suspicious person in my neighborhood."

[0956] Step 2:

[0957] The server uses a message receiving mechanism to receive messages sent by users via the LINE API. The received messages become the input. This input data (messages) is converted into an analyzable format.

[0958] Step 3:

[0959] The server activates an NLP engine as a message analysis tool and analyzes the received message. This analysis extracts keywords. Example: "suspicious person," "neighborhood." The input is the received message, and the output is the extracted keywords.

[0960] Step 4:

[0961] The server retrieves the user's residential area information. It obtains this information from the user's profile; for example, "Minato-ku, Tokyo." The input is the user's profile data, and the output is the residential area information.

[0962] Step 5:

[0963] The server uses an information retrieval tool to search for relevant information from the database based on the analyzed keywords and residential area information. Example: Contact information for police stations and information on what to do. The input is keywords and residential area information, and the output is relevant information.

[0964] Step 6:

[0965] The server retrieves the latest municipal information from the municipality's API or official website. For example, it can retrieve the latest police station contact information and notices. The input is residential area information, and the output is the latest municipal information.

[0966] Step 7:

[0967] The server compares the municipality information it retrieves with existing database information to verify consistency. If the comparison does not result in a match, the database is updated. The input is the search results and the latest municipality information, and the output is the consistent information.

[0968] Step 8:

[0969] The server uses an emotion engine to recognize emotions from the content of the user's message. Example: Detecting the emotion "anxiety". The input is the received message, and the output is the recognized emotion.

[0970] Step 9:

[0971] The server uses a message generation mechanism to generate a response message based on the emotions recognized by the emotion engine. Example: "This is a report of a suspicious person in Minato Ward. First, please evacuate to a safe place. Please make a note of the suspicious person's characteristics in as much detail as possible and immediately contact the nearest police station (phone number: xxx-xxxx-xxxx)." The input is the consistent information and recognized emotions, and the output is the response message.

[0972] Step 10:

[0973] The server uses a message sending method to send the generated response message to the user via the LINE API. The user receives the message on the LINE chat screen on their smartphone or tablet and checks the solution. The input is the response message, and the output is the result of sending it to the user.

[0974] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0975] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0976] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0977] [Third Embodiment]

[0978] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0979] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0980] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0981] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0982] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0983] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0984] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0985] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0986] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0987] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0988] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0989] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0990] The present invention will be described based on the following system overview and specific examples.

[0991] System Overview

[0992] This system allows users to send questions and consultations about childcare through an official LINE account. The server receives and analyzes these messages and provides appropriate information. The system is available 24 hours a day and can also provide information tailored to the user's residential area.

[0993] Program Processing Overview

[0994] Step 1: The user sends a message.

[0995] Users use the chat function of the official LINE account to send messages such as, "Please tell me how to enroll my child in daycare."

[0996] Step 2: The server receives the message.

[0997] The server receives messages sent by users via the LINE API.

[0998] The server converts the received message into a format that can be parsed.

[0999] Step 3: The server parses the message.

[1000] The server uses natural language processing techniques to analyze the message.

[1001] Example: Extract the keywords "nursery school" and "how to enroll," and determine the category to be "information on finding childcare."

[1002] Step 4: The server retrieves the user's residential area information.

[1003] The server retrieves residential area information (for example, Shinjuku Ward) from the user's profile.

[1004] If the profile does not contain information about the user's residential area, the server will generate a response message asking, "Please tell us where you live."

[1005] Step 5: The server searches for the appropriate information.

[1006] The server uses message analysis results and residential area information to search the database for information such as nursery school admission requirements, necessary documents, and application procedures.

[1007] Step 6: The server matches with the local government information.

[1008] The server retrieves the latest information from the local government's API and official website, and compares it with the searched information.

[1009] If the most recent information matches, select that information.

[1010] Step 7: The server generates a response message.

[1011] Based on the information acquired by the server, a response message is generated to be provided to the user.

[1012] Example: "Details regarding admission to a nursery school in Shinjuku Ward are as follows. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: You can apply online through the ward office website."

[1013] Step 8: The server sends the message

[1014] The server sends a response message to the user via the LINE API.

[1015] Specific example

[1016] Case 1: Inquiry about childcare application information (nursery school enrollment)

[1017] 1. User: "Please tell me how to enroll my child in daycare."

[1018] 2. The server receives and analyzes the message. Based on the keywords "nursery school" and "how to enroll," it determines the category to be "childcare information."

[1019] 3. The server retrieves the user's residential area information (Shinjuku Ward) from their profile.

[1020] 4. The server searches the database for the latest information regarding childcare applications in Shinjuku Ward (conditions, documents, and methods).

[1021] 5. The server retrieves the latest information from the local government's API and compares it with the search results.

[1022] 6. The server generates a message stating, "Here are the details for enrolling in a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website."

[1023] 7. The server sends the generated message to the user via LINE.

[1024] Case 2: Medical information for sudden fever or injury

[1025] 1. User: "My child has a fever. Where can I get them examined?"

[1026] 2. The server receives and analyzes the message. It determines whether it is an emergency medical event based on the keywords "fever" and "medical institution."

[1027] 3. The server retrieves residential area information (Kita Ward, Osaka City).

[1028] 4. The server searches its database for medical institutions in Kita Ward, Osaka City that can provide emergency medical care.

[1029] 5. The server retrieves the latest medical institution information from the local government API and compares it with the search results.

[1030] 6. The server generates the message: "Osaka City Kita Ward General Hospital is open 24 hours a day. The emergency center is also available. The address is ○○."

[1031] 7. The server sends the generated message to the user via LINE.

[1032] In this way, this system efficiently processes user inquiries, providing prompt responses and accurate information. This will enable it to address a wide range of needs related to childcare.

[1033] The following describes the processing flow.

[1034] Step 1:

[1035] A user sends a message to the official LINE account. This message might be something like, "Please tell me how to enroll my child in daycare."

[1036] Step 2:

[1037] The server receives messages sent by users via the LINE API. The received messages are then converted into an analyzable format.

[1038] Step 3:

[1039] The server invokes a natural language processing (NLP) engine to analyze the received message. This analysis extracts keywords such as "nursery school" and "how to enroll," and the question category is determined to be "childcare information."

[1040] Step 4:

[1041] The server retrieves residential area information from the user's profile information. For example, if the user has previously registered "Shinjuku Ward," that information will be used. If residential area information is not registered, the server will ask the user for their residential area in a subsequent process.

[1042] Step 5:

[1043] The server searches the database for relevant information based on the message analysis results and residential area information. For example, it extracts information about childcare activities in Shinjuku Ward (admission requirements, necessary documents, application methods, etc.).

[1044] Step 6:

[1045] The server retrieves the latest local government information from the local government's API and official website. This allows the server to compare the latest childcare information with the contents of the database, ensuring the consistency of the information.

[1046] Step 7:

[1047] The server generates a response message to the user based on the collected and verified information.

[1048] For example, the content might read: "Details regarding admission to a nursery school in Shinjuku Ward are as follows. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: You can apply online through the ward office website."

[1049] Step 8:

[1050] The server sends a generated response message to the user via the LINE API. The user can receive the message on the LINE chat screen and check the suggested solution.

[1051] Specific example (in the case of an inquiry about childcare information):

[1052] Step 1:

[1053] User: Sends a message saying, "Please tell me how to enroll my child in daycare."

[1054] Step 2:

[1055] The server receives this message using the LINE API.

[1056] Step 3:

[1057] The server analyzes the message using an NLP engine, extracts "nursery school" and "how to enroll" as keywords, and classifies them as "childcare information."

[1058] Step 4:

[1059] The server retrieves residential area information for "Shinjuku Ward" from the user's profile.

[1060] Step 5:

[1061] The server searches the database for nursery school enrollment information related to Shinjuku Ward.

[1062] Step 6:

[1063] The server retrieves the latest nursery school enrollment information from the Shinjuku Ward official website and compares it with the database.

[1064] Step 7:

[1065] The server generates a response message stating, "Details regarding admission to a nursery school in Shinjuku Ward are as follows. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: You can apply online through the ward office website."

[1066] Step 8:

[1067] The server sends this message to the user via LINE, and the user receives and confirms its contents.

[1068] (Example 1)

[1069] Next, we will describe Example 1. 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."

[1070] Conventional information systems struggled to respond quickly and accurately to user questions and inquiries. Furthermore, they often failed to adequately address users' residential areas, resulting in inconsistencies with the latest information from local governments. Additionally, the lack of message optimization meant users often received unclear and easily understandable responses.

[1071] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1072] In this invention, the server includes a message receiving means, a message analysis means for analyzing the message using natural language processing technology, a means for acquiring the user's residential area information based on the content analyzed by the message analysis means, an information retrieval means for searching for appropriate information from a database based on the analyzed content and residential area information, a means for comparing with administrative agency information that provides appropriate information, a message generation means for generating a response message based on the comparison result, a message sending means for sending the response message to the user, and a means for optimizing the generated message using a generation AI model. This enables the rapid and accurate provision of information in response to user questions and consultations, provides optimal information tailored to the residential area, ensures consistency with the latest information from administrative agencies, and provides a response message that is easy for the user to understand.

[1073] "Message receiving means" refers to a combination of a system and process that receives messages sent by users and converts those messages into a parseable format.

[1074] "Natural language processing technology" refers to the techniques that enable computers to understand, analyze, and generate human language, and includes methods for interpreting the meaning of text.

[1075] A "message analysis system" refers to a system that analyzes received messages and has the function of extracting and understanding keywords and context within those messages.

[1076] "User residential area information" refers to data related to the geographical area where the user resides, including address and region name.

[1077] "Information retrieval means" refers to a system that has the function of extracting highly relevant information from a database based on message analysis results and residential area information.

[1078] A "database" is a systematically organized collection of data, and refers to a system that allows for the fast and efficient searching, adding, updating, and deleting of specific information.

[1079] "Government agency information" refers to data and information officially provided by public institutions such as local governments.

[1080] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and generates an optimized response for a specific task.

[1081] "Message generation means" refers to a system that has the function of creating an appropriate response message based on the analyzed content and matching results.

[1082] "Message sending means" refers to a communication means for sending a generated response message to the user.

[1083] As an embodiment of the present invention, a system is described in which a user sends questions or requests for advice regarding childcare using an online messaging platform (e.g., LINE official account), a server receives and analyzes the message, and provides appropriate information.

[1084] The server first receives messages sent by users using a message receiving method. LINE's Messaging API is used for message reception. Next, the server analyzes the messages using natural language processing technology (for example, Google Cloud Natural Language API). This makes it possible to extract keywords and intent from the message content.

[1085] Based on the analyzed data, the server retrieves the user's residential area information. This includes a function to refer to the user's profile information, and if residential area information is missing, it generates a response message asking the user, "Please tell us where you live."

[1086] Next, the server uses the analysis results and residential area information to search for appropriate information from the database. The database can be a relational or non-relational database such as MySQL or MongoDB. The retrieved information includes specific details such as nursery school admission requirements, necessary documents, and application procedures.

[1087] The server then retrieves the latest information from the local government's APIs and official websites and compares it with the previously retrieved database information. For example, it ensures the accuracy of the information provided by comparing it with the latest information obtained from Shinjuku Ward's open data API.

[1088] Next, the server generates a response message based on the matching results. Here, a generative AI model (e.g., GPT-4) is used to optimize the response message. This ensures that the user receives clear and relevant information.

[1089] Finally, the server uses a message sending method to send the generated response message to the user. The message is sent to the user's LINE account via LINE's Messaging API.

[1090] Specific example

[1091] Case 1: Inquiry about nursery school enrollment information

[1092] 1. User: "Please tell me how to enroll my child in daycare."

[1093] 2. The server receives the message and analyzes it using natural language processing technology. Based on the keywords "nursery school" and "how to enroll," it determines the category to be "childcare information."

[1094] 3. The server retrieves the user's residential area information (Shinjuku Ward).

[1095] 4. The server searches the database for the latest information regarding childcare applications in Shinjuku Ward (conditions, documents, and methods).

[1096] 5. The server retrieves the latest information from the local government's API and compares it with the search results.

[1097] 6. The server generates a message stating, "Here are the details for enrolling in a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website."

[1098] 7. The server sends the generated message to the user via LINE.

[1099] Case 2: Medical information for sudden fever or injury

[1100] 1. User: "My child has a fever. Where can I get them examined?"

[1101] 2. The server receives and analyzes the message. It determines whether it is an emergency medical event based on the keywords "fever" and "medical institution."

[1102] 3. The server retrieves residential area information (Kita Ward, Osaka City).

[1103] 4. The server searches its database for medical institutions in Kita Ward, Osaka City that can provide emergency medical care.

[1104] 5. The server retrieves the latest medical institution information from the local government API and compares it with the search results.

[1105] 6. The server generates the message: "Osaka City Kita Ward General Hospital is open 24 hours a day. The emergency center is also available. The address is ○○."

[1106] 7. The server sends the generated message to the user via LINE.

[1107] This invention allows users to obtain quick and accurate information, enabling them to address diverse childcare needs. The system is particularly useful as it is available 24 / 7 through messaging platforms like LINE, significantly improving user convenience.

[1108] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1109] Program processing flow

[1110] Step 1:

[1111] Users can use the chat function of the official LINE account to enter questions or requests for advice and send messages.

[1112] Input: Message from the user (e.g., "Please tell me how to enroll my child in daycare.")

[1113] Output: A message is sent to the LINE server.

[1114] Specific action: The user types a message on the LINE app on their smartphone or PC and presses the send button.

[1115] Step 2:

[1116] The server uses LINE's Messaging API to retrieve incoming messages.

[1117] Input: Message sent from LINE server

[1118] Output: The message arrives on the server in JSON format (Example: { "type": "text", "text": "Please tell me how to enroll my child in daycare"})

[1119] Specific operation: The server polls for new messages via the LINE Messaging API endpoint.

[1120] Step 3:

[1121] The server uses natural language processing techniques to analyze the message.

[1122] Input: Message in JSON format (Example: { "type": "text", "text": "Please tell me how to enroll my child in daycare"})

[1123] Output: Analysis results (Keywords: "nursery school", "how to enroll", Category: "childcare information")

[1124] Specific operation: The server uses an NLP engine such as the Google Cloud Natural Language API to extract keywords from the message text and classify the intent.

[1125] Step 4:

[1126] The server retrieves the user's residential area information.

[1127] Input: Analysis results (Category "Childcare Information")

[1128] Output: Residential area information (e.g., Shinjuku Ward)

[1129] Specific operation: The server searches for the user's residential area from their LINE profile information and retrieves the information. If residential area information is insufficient, it generates a message asking "Please tell us where you live" and sends it to the user.

[1130] Step 5:

[1131] The server uses the analysis results and residential area information to search for appropriate information from the database.

[1132] Input: Analysis results, residential area information

[1133] Output: Appropriate information (e.g., nursery school admission requirements, necessary documents, application procedures)

[1134] Specific operation: The server queries databases such as MySQL or MongoDB to retrieve analysis results and related data based on residential area information.

[1135] Step 6:

[1136] The server retrieves the latest information from local government APIs and official websites and compares it with search results.

[1137] Input: Appropriate information (search results from the database), up-to-date local government information (obtained from API or official website)

[1138] Output: Matching results (latest matching information)

[1139] Specific operation: The server retrieves the latest information from sources such as Shinjuku Ward's open data API, and verifies its consistency by comparing it with information obtained from the database.

[1140] Step 7:

[1141] The server generates a response message based on the matching results.

[1142] Input: Matching result

[1143] Output: Response message (Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website.")

[1144] Specific operation: The server uses a generated AI model (e.g., GPT-4) to create a response message that provides information to the user in an easily understandable format.

[1145] Step 8:

[1146] The server sends a response message to the user.

[1147] Input: Response message

[1148] Output: Message delivered to the user

[1149] Specific operation: The server sends the generated response message to the user's LINE account via LINE's Messaging API.

[1150] (Application Example 1)

[1151] Next, we will explain Application Example 1. In the following explanation, 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."

[1152] In today's lifestyle, obtaining information about childcare quickly and accurately is crucial. Furthermore, there is a need for a means to quickly obtain appropriate information, even in situations requiring urgent action. To utilize such information services more diversely, convenience is needed not only for information provision but also for paid services and content purchases using electronic payments. However, current systems struggle to simultaneously meet all these requirements.

[1153] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1154] In this invention, the server includes a message receiving means, a message analysis means for analyzing the message using natural language processing technology, a means for acquiring the user's residential area information based on the content analyzed by the message analysis means, an information retrieval means for searching a database for appropriate information based on the analyzed content and the residential area information, a means for comparing the appropriate information with local government information, a message generation means for generating a response message based on the matching result, a message transmission means for sending the response message to the user, and an electronic payment means. This enables the user to receive information suitable for their residential area, receive emergency consultations, and even purchase paid consultations and childcare-related content using electronic payment.

[1155] A "message receiving means" is a means that has the function of receiving messages sent by a user.

[1156] A "message analysis tool" is a means of analyzing a received message using natural language processing technology to understand its content.

[1157] "Means for obtaining residential area information" refers to methods for extracting and obtaining information about a user's residential area from their profile information or inquiry messages.

[1158] An "information retrieval method" is a means of searching for appropriate information from a database based on the content of the analyzed message and the acquired residential area information.

[1159] "Means of cross-referencing with local government information" refers to methods for verifying and cross-referencing the searched information with the latest information from the local government.

[1160] A "message generation means" is a means for creating a response message to be provided to the user based on the verified information.

[1161] "Message sending means" refers to means for sending the generated response message to the user.

[1162] "Electronic payment methods" refer to means that have the functionality of electronic payment and can be used by users when purchasing paid services or content.

[1163] A "generative AI model" is an artificial intelligence model used to generate appropriate answers or response messages in response to user inquiries.

[1164] A "prompt sentence" is a sentence of instruction or question that is input to a generative AI model, and it is the input sentence that enables the model to generate an appropriate answer.

[1165] The system for carrying out the present invention is constructed using the following hardware and software.

[1166] hardware

[1167] Server: Used as a central processing unit for database management, communication processing, message analysis, and generation.

[1168] User terminal: A device, such as a smartphone, used by a user to send and receive messages.

[1169] Internet connection: A network infrastructure that facilitates communication between servers and user terminals.

[1170] software

[1171] LINE Messaging API: Used to receive messages from users and forward them to the server.

[1172] Natural language processing libraries (e.g., NLTK): Provide natural language processing techniques for message analysis.

[1173] SQLite: A database system that stores user information and childcare information by region.

[1174] Python: Used as the programming language to integrate all of the above parts.

[1175] Processing flow

[1176] 1. Message Reception: Users send questions and requests for advice regarding childcare using the LINE app on their device. For example, they might send a message such as, "Please tell me how to enroll my child in daycare."

[1177] 2. Message Analysis: After receiving a message via the LINE Messaging API, the server uses NLTK to analyze the message and extract keywords (e.g., "nursery school," "how to enroll").

[1178] 3. Obtaining residential area information: The server obtains residential area information (e.g., "Shinjuku Ward") from the user profile information.

[1179] 4. Information Retrieval: The server searches for appropriate information from the SQLite database based on the analyzed keywords and residential area information.

[1180] 5. Verification with local government information: The server retrieves the latest information from local government APIs and official websites and verifies it against the search results.

[1181] 6. Generating a response message: The server generates a response message based on the matching results (e.g., "Details regarding admission to a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website.").

[1182] 7. Message Sending: The generated response message is sent to the user via the LINE Messaging API.

[1183] 8. Electronic payment: Users utilize electronic payment functions to purchase paid consultations and childcare-related content.

[1184] This system allows users to quickly and accurately obtain childcare information tailored to their residential area. Furthermore, it enables prompt and appropriate responses to urgent inquiries and emergencies, and allows for paid consultations and content purchases using electronic payment.

[1185] Specific example

[1186] User: "My child has a fever. Where can I get them examined?"

[1187] server:

[1188] The message was analyzed, and the keywords "fever" and "medical institution" were extracted.

[1189] Retrieve residential area information (e.g., "Kita Ward, Osaka City").

[1190] Search the database for information on medical institutions in the relevant area.

[1191] Check against the latest local government information.

[1192] Generate a response message (e.g., "Osaka City Kita Ward General Hospital is open 24 hours. The emergency center is also available. The address is XX.").

[1193] Send a message to the user.

[1194] Examples of prompts for generative AI models

[1195] User: "Please tell me how to enroll my child in daycare."

[1196] AI: "I will now explain the specific procedures for enrolling your child in daycare. First, please prepare the necessary documents. Next, I will explain how to apply online."

[1197] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1198] Step 1:

[1199] Users send questions and requests for advice about childcare using the LINE app on their devices. The input is a text message, such as "Please tell me how to enroll my child in daycare." This message is then sent to the server.

[1200] Step 2:

[1201] The server receives messages from users via the LINE Messaging API. The received messages are converted into a parseable format. The input is the user's text message, and the output is text data for parsing.

[1202] Step 3:

[1203] The server parses incoming messages using a natural language processing library (such as NLTK). It extracts keywords from the messages (e.g., "nursery school," "how to enroll"). The input is text data for analysis, and the output is a list of keywords.

[1204] Step 4:

[1205] The server retrieves residential area information from the user's profile information. This ensures that the analyzed keywords and the user's residential area information are matched. The input is the user ID, and the output is the user's residential area information (e.g., "Shinjuku Ward").

[1206] Step 5:

[1207] The server searches for appropriate information from the SQLite database based on the analyzed keywords and acquired residential area information. The input is a list of keywords and residential area information, and the output is the initial search result.

[1208] Step 6:

[1209] The server retrieves the latest information from local government APIs and official websites and compares it with the initial search results. This verifies the timeliness of the information. The input is the initial search results, and the output is the final, verified information.

[1210] Step 7:

[1211] The server generates a response message based on the final information it has verified. The input is the final information, and the output is a text message sent to the user (e.g., "Here are the details for nursery school enrollment in Shinjuku Ward. Required documents: resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website.").

[1212] Step 8:

[1213] The server sends the generated response message to the user via the LINE Messaging API. The input is the response message, and the output is the message displayed on the user's device.

[1214] Step 9:

[1215] Users utilize in-app electronic payment methods to access paid consultations and childcare-related content. The input is the user's electronic payment information, and the output is a confirmation message upon completion of the payment.

[1216] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1217] The present invention will be described based on the following system overview and specific examples.

[1218] System Overview

[1219] This system allows users to send questions and consultations about childcare via a LINE official account. The server receives and analyzes these messages and provides appropriate information. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it can provide even more appropriate responses. The system is available 24 hours a day and can also provide information tailored to the user's residential area.

[1220] Program Processing Overview

[1221] Step 1: The user sends a message.

[1222] Users use the chat function of the official LINE account to send messages such as, "Please tell me how to enroll my child in daycare."

[1223] Step 2: The server receives the message.

[1224] The server receives messages sent by users via the LINE API. The received messages are converted into an analyzable format.

[1225] Step 3: The server parses the message.

[1226] The server invokes a natural language processing (NLP) engine to analyze the received message. This analysis extracts the keywords "nursery school" and "how to enroll," and the question category is determined to be "nursery school information."

[1227] Step 4: The server uses the emotion engine to recognize emotions.

[1228] The server uses an emotion engine to recognize emotions from the content of the user's message. For example, the emotion engine can detect emotions such as "anxiety" or "impatience" from the user's message.

[1229] Step 5: The server retrieves the user's residential area information.

[1230] The server retrieves residential area information from the user's profile information. For example, if the user has previously registered "Shinjuku Ward," that information will be used. If residential area information is not registered, the server will ask the user for their residential area in a subsequent process.

[1231] Step 6: The server searches for the appropriate information.

[1232] The server searches the database for relevant information based on the message analysis results and residential area information. For example, it extracts information about childcare activities in Shinjuku Ward (admission requirements, necessary documents, application methods, etc.).

[1233] Step 7: The server matches with the local government information.

[1234] The server retrieves the latest local government information from the local government's API and official website. This allows the server to compare the latest childcare information with the contents of the database, ensuring the consistency of the information.

[1235] Step 8: The server generates a response message.

[1236] The server generates a response message based on the emotions recognized by the emotion engine. The content and tone of the response message are adjusted to match the user's emotions. For example, if anxiety is detected, the message will include reassuring language.

[1237] Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. There's no need to worry unnecessarily. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[1238] Step 9: The server sends the message

[1239] The server sends a generated response message to the user via the LINE API. The user can receive the message on the LINE chat screen and check the suggested solution.

[1240] Specific example (in the case of an inquiry about childcare information):

[1241] Case 1: Inquiry about childcare application information (nursery school enrollment)

[1242] 1. User: Sends a message saying, "Please tell me how to enroll my child in daycare."

[1243] 2. The server receives this message using the LINE API.

[1244] 3. The server uses an NLP engine to analyze the message, extracts keywords such as "nursery school" and "how to enroll," and classifies it as "childcare information."

[1245] 4. The server uses an emotion engine to recognize the emotion of "anxiety" from the user's message.

[1246] 5. The server retrieves residential area information for "Shinjuku Ward" from the user's profile.

[1247] 6. The server searches the database for nursery school enrollment information related to Shinjuku Ward.

[1248] 7. The server retrieves the latest nursery school enrollment information from the Shinjuku Ward official website and compares it with the database.

[1249] 8. The server generates a response message that includes reassuring wording such as, "Here are the details for enrolling in a nursery school in Shinjuku Ward. There is no need to worry unnecessarily. Required documents include a resident registration certificate and a maternal and child health handbook. You can apply online through the ward office website."

[1250] 9. The server sends this message to the user via LINE, and the user receives and confirms its contents.

[1251] In this way, the system efficiently processes user inquiries and provides accurate information along with prompt, empathetic responses. This makes it possible to address diverse childcare needs while also considering their emotional aspects.

[1252] The following describes the processing flow.

[1253] Step 1:

[1254] A user sends a message to the official LINE account saying, "Please tell me how to enroll my child in daycare."

[1255] Step 2:

[1256] The server receives this message via the LINE API. The received message is converted into a parseable format.

[1257] Step 3:

[1258] The server invokes a natural language processing (NLP) engine to analyze the message. It extracts specific keywords (in this case, "nursery school" and "how to enroll") and determines that the question falls under the category of "nursery school information."

[1259] Step 4:

[1260] The server invokes an emotion engine to recognize emotions from the user's message. For example, it can detect emotions such as "anxiety" or "restlessness" from the user's message.

[1261] Step 5:

[1262] The server accesses the user's profile information and retrieves their residential area information (e.g., "Shinjuku Ward"). If the residential area information is not registered, a message is generated in the subsequent process asking the user to provide their residential area.

[1263] Step 6:

[1264] The server searches the database for relevant information based on the message analysis results and acquired residential area information. For example, it might retrieve information such as admission requirements, necessary documents, and application procedures for daycare centers in Shinjuku Ward.

[1265] Step 7:

[1266] The server retrieves the latest information from the local government's API and official website. This latest information is then compared with the database information to verify consistency.

[1267] Step 8:

[1268] The server generates a response message based on the recognition results from the emotion engine. If the user is feeling anxious, a message designed to reassure them will be generated.

[1269] Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. Please rest assured. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[1270] Step 9:

[1271] The server sends a generated response message to the user via the LINE API. The user can receive the message on the LINE chat screen and check the suggested solution.

[1272] Specific example (in the case of an inquiry about childcare information):

[1273] Step 1:

[1274] User: Sends a message saying, "Please tell me how to enroll my child in daycare."

[1275] Step 2:

[1276] The server uses the LINE API to receive messages.

[1277] Step 3:

[1278] The server uses an NLP engine to analyze the message, extracts the keywords "nursery school" and "how to enroll," and classifies it as "information on finding childcare."

[1279] Step 4:

[1280] The server uses an emotion engine to recognize the emotion of "anxiety" from the user's message.

[1281] Step 5:

[1282] The server retrieves residential area information for "Shinjuku Ward" from the user's profile information.

[1283] Step 6:

[1284] The server searches the database for nursery school enrollment information related to Shinjuku Ward.

[1285] Step 7:

[1286] The server retrieves the latest nursery school enrollment information from the local government's API and compares it with the database.

[1287] Step 8:

[1288] The server, responding to the emotion of "anxiety," generates a response message that reads, "Here are the details for enrolling in a nursery school in Shinjuku Ward. Please rest assured. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[1289] Step 9:

[1290] The server sends this message to the user via the LINE API. The user can then view the received message.

[1291] (Example 2)

[1292] Next, we will describe Example 2. 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."

[1293] In modern society, providing timely and appropriate information about childcare is crucial. However, existing systems struggle to provide information that takes users' emotions into account, and there are challenges in adequately addressing the needs of users who require emotional support. Furthermore, the lack of up-to-date information specific to a particular residential area makes it difficult to provide appropriate advice for each region.

[1294] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1295] In this invention, the server includes message receiving means, message analysis means for analyzing the message using natural language processing technology, emotion recognition means for recognizing the user's emotions from the message, means for acquiring the user's residential area information based on the content analyzed by the message analysis means, information retrieval means for searching a database for appropriate information based on the analyzed content and the residential area information, means for comparing the information with local government information that provides the appropriate information, message generation means for generating a response message based on the emotions recognized by the emotion recognition means, and message transmission means for sending the response message to the user. This makes it possible to quickly provide the latest and most appropriate information for each residential area while being attentive to the user's emotions.

[1296] A "message receiving means" is a means for receiving messages sent by a user.

[1297] A "message analysis means" is a means for analyzing a received message using natural language processing technology.

[1298] "Emotion recognition means" refers to a method for recognizing a user's emotions from a received message.

[1299] "Means for obtaining user residential area information" refers to means for obtaining information about the user's place of residence.

[1300] An "information retrieval method" is a means of searching for appropriate information from a database based on the analyzed content and residential area information.

[1301] "Means of cross-referencing with local government information" refers to means of cross-referencing appropriate information with the latest information provided by local governments.

[1302] A "message generation means" is a means for generating a response message based on the emotion recognized by the emotion recognition means.

[1303] "Message sending means" refers to means for sending the generated response message to the user.

[1304] Modes for carrying out the invention

[1305] This invention relates to a system in which a server receives, analyzes, and provides appropriate information in response to questions and consultations about childcare sent by users through an online chat platform. A key feature of this system is its ability to provide responses that take the user's emotions into consideration, particularly through the integration of emotion recognition functionality. The embodiments of this system are described in detail below.

[1306] System Overview

[1307] This system consists of the following main hardware and software components:

[1308] server

[1309] User devices (smartphones, tablets, PCs)

[1310] LINE official accounts and their APIs

[1311] Natural language processing engines (e.g., SpaCy, NLTK)

[1312] Emotion recognition engine (e.g., IBM Watson Tone Analyzer)

[1313] Databases (e.g., MySQL, MongoDB)

[1314] Local government API or official website

[1315] Specific operation of the system

[1316] 1. The user sends a message.

[1317] Users can send questions and inquiries through the chat window of the official LINE account. For example, specific questions such as "Please tell me how to enroll my child in daycare" are possible.

[1318] 2. The server receives the message.

[1319] The server receives messages from users via the LINE API. At this time, the message data is transferred to the server in JSON format.

[1320] 3. The server parses the message.

[1321] The server uses a natural language processing engine (e.g., SpaCy) to analyze the received message. This analysis extracts keywords such as "nursery school" and "how to enroll," and the question category is classified as "nursery school information."

[1322] 4. The server recognizes emotions.

[1323] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to detect the user's emotions from the message. For example, it can identify emotions such as "anxiety" or "restlessness."

[1324] 5. The server retrieves the user's residential area information.

[1325] The server queries the user's profile information to obtain information about their residential area. For example, if the user has previously registered "Shinjuku Ward," that information will be used. If the residential area is not registered, the system will prompt the user to enter the information.

[1326] 6. The server searches for the appropriate information.

[1327] The server searches for relevant information from databases (e.g., MySQL, MongoDB) based on the analysis results and residential area information. For example, it extracts information on nursery school enrollment in Shinjuku Ward (enrollment conditions, required documents, application methods, etc.).

[1328] 7. The server compares the information with that of the local government.

[1329] The server uses the latest information obtained from the local government's API and official website to compare it with the information in the database. This verifies the accuracy of the information provided.

[1330] 8. The server generates a response message.

[1331] The server generates a response message that takes the user's emotions into consideration, based on the results of the emotion recognition engine. If anxiety is detected, it will include reassuring phrases such as, "There's no need to worry unnecessarily."

[1332] 9. The server sends the message.

[1333] The server sends the generated response message to the user via the LINE API. The user can then view the response message in the LINE chat window.

[1334] Specific example

[1335] For example, if a user sends a message such as "Please tell me how to enroll my child in daycare," the server will process it in the following steps:

[1336] 1. The user sends a message through the LINE official account.

[1337] 2. The server receives the message via the LINE API.

[1338] 3. The server uses a natural language processing engine to parse the message.

[1339] 4. The server uses an emotion recognition engine to recognize emotions.

[1340] 5. The server retrieves the user's residential area information.

[1341] 6. The server searches the database for relevant information.

[1342] 7. The server compares the municipal information it has obtained with the contents of the database.

[1343] 8. The server generates a response message.

[1344] 9. The server sends a response message to the user via LINE.

[1345] Example of a prompt:

[1346] "Please tell me how to enroll my child in daycare."

[1347] "Please tell me about childhood vaccinations."

[1348] "I'm looking for a nearby childcare facility."

[1349] By following the above steps, this system can provide accurate and timely information while being sensitive to the user's emotions.

[1350] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1351] Program processing flow

[1352] Step 1:

[1353] Input: The user sends a message using the chat function of the LINE official account. Example: "Please tell me how to enroll my child in daycare."

[1354] Specific action: The user types a message in the chat window and presses the send button.

[1355] Output: The message is transferred to the server via the LINE API.

[1356] Step 2:

[1357] Input: The server receives message data from the LINE API.

[1358] Specific operation: The server waits for incoming requests and retrieves message data.

[1359] Output: The received message data is saved on the server and becomes ready for analysis.

[1360] Step 3:

[1361] Input: The server that receives the message data invokes a natural language processing engine (e.g., SpaCy).

[1362] Specific operation: The server instantiates an NLP engine and parses the incoming message.

[1363] Data processing / calculation: Extract keywords and phrases from messages and understand the context.

[1364] Output: Keywords such as "nursery school" and "how to enroll" are extracted, and the question category is classified as "childcare information."

[1365] Step 4:

[1366] Input: The server receives the results of the natural language processing engine's analysis.

[1367] Specific operation: The server calls an emotion recognition engine (e.g., IBM Watson Tone Analyzer) and sends the analysis results.

[1368] Data processing / calculation: Identify emotions (e.g., anxiety, impatience) from messages.

[1369] Output: The emotion analysis results in the detection of "anxiety."

[1370] Step 5:

[1371] Input: The server, having received the sentiment analysis results, retrieves the user's residential area information from the database.

[1372] Specific operation: The server executes a database query to extract the user's residential area from their profile information.

[1373] Data processing / calculation: Obtain residential area information in JSON format.

[1374] Output: Information about "Shinjuku Ward" that the user registered in advance is retrieved.

[1375] Step 6:

[1376] Input: Based on residential area information and analysis results, the server searches the database for relevant information.

[1377] Specific operation: The server executes a database query to extract childcare information related to Shinjuku Ward.

[1378] Data processing / calculation: Filter search results and organize relevant information.

[1379] Output: Information on childcare activities in Shinjuku Ward (e.g., admission requirements, necessary documents, application procedures) will be obtained.

[1380] Step 7:

[1381] Input: The server that retrieves the search results cross-references the latest information with the local government's API and official website.

[1382] Specific operation: The server sends an API request to retrieve the latest information from the local government.

[1383] Data processing / calculation: Compare and verify the contents of the database with the latest information obtained.

[1384] Output: Information matching and updates are confirmed, and the latest information is reflected in the database.

[1385] Step 8:

[1386] Input: Based on the latest information matched with the sentiment analysis results, the server generates a response message.

[1387] Specific operation: The server uses a template engine to construct emotionally sensitive response messages.

[1388] Data processing / calculation: Generate appropriate wording based on emotions and incorporate it into the message.

[1389] Output: Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. There's no need to worry unnecessarily. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[1390] Step 9:

[1391] Input: The server receives the generated response message.

[1392] Specific operation: The server uses the LINE API to send a response message.

[1393] Output: The user receives and confirms the response message in the LINE chat window.

[1394] The above outlines the specific processing steps of this system. This enables the provision of accurate information that resonates with the user's emotions.

[1395] (Application Example 2)

[1396] Next, we will explain application example 2. In the following explanation, 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."

[1397] Current information processing systems are required to respond quickly and accurately to user inquiries and emergency reports. However, conventional systems struggle to adequately consider emotions and urgency in their responses, leaving challenges in ensuring user confidence and safety. Furthermore, there is a lack of mechanisms to acquire the latest information from local governments in real time and provide appropriate information immediately. As a result, users are prone to feeling anxious due to a lack of information and delayed responses, and a system that provides efficient information and a sense of security is needed.

[1398] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a message receiving means, a message analysis means for analyzing a message using natural language processing technology, a means for acquiring user residential area information based on the content analyzed by the message analysis means, an information retrieval means for searching for appropriate information from a database based on the analyzed content and residential area information, a means for comparing with local government information that provides appropriate information, a message generation means for generating a response message based on the matching result, a message transmission means for sending the response message to the user, a means for receiving reports of emergencies and suspicious person information from the user, recognizing the user's emotions using an emotion engine, and generating a message including highly urgent countermeasures, and a means for providing the latest information from the local government and presenting methods for ensuring safety. This enables the rapid and accurate provision of information that takes into account the user's emotions and urgency, thereby realizing a system that enhances the user's sense of security and contributes to ensuring safety.

[1399] "Message receiving means" refers to a device or software for receiving messages sent by a user.

[1400] A "message analysis means" is a device or software that analyzes a received message using natural language processing technology and extracts important information.

[1401] "Residential area information" refers to information about the region where the user lives, and is obtained from profile information.

[1402] "Information retrieval means" refers to a device or software that retrieves appropriate information from a database based on the analyzed message content and residential area information.

[1403] "Local government information" refers to official information provided by local administrative agencies, which is obtained from online APIs and official websites.

[1404] A "message generation means" is a device or software that generates a response message to send to the user based on analyzed information and sentiment data.

[1405] "Message transmission means" refers to a device or software for sending a generated response message to a user.

[1406] An "emotion engine" is a device or software that recognizes and analyzes emotions from a user's message.

[1407] "Reporting emergencies or suspicious person information" refers to the act of a user reporting an emergency situation or information about a suspicious person to the system.

[1408] "Appropriate information" refers to useful and accurate information in response to user inquiries or emergencies.

[1409] "Methods for ensuring safety" refer to specific means and advice for ensuring safety when a user feels anxious or in danger.

[1410] A security service system capable of ensuring safety and responding quickly to emergencies is described below as an embodiment of this invention.

[1411] The system consists of the following hardware and software:

[1412] Server: The server will use a cloud server (e.g., AWS, Google Cloud, Microsoft Azure).

[1413] User device: A smartphone or tablet used to send messages.

[1414] The server includes the following software modules:

[1415] 1. Message receiving method: The server receives messages sent by the user via the LINE API.

[1416] 2. Message analysis method: The server analyzes the received message using a natural language processing (NLP) engine (e.g., NLTK, Google Cloud Natural Language API) and extracts keywords.

[1417] 3. Means for obtaining residential area information: The server obtains residential area information from the user's profile information.

[1418] 4. Information Retrieval Method: The server searches the database for relevant information based on the analyzed message content and residential area information. This database includes information such as police station contact information and emergency procedures.

[1419] 5. Local Government Information Verification Method: The server retrieves the latest local government information from the local government's online API or official website (e.g., local government API) and verifies it against the information in the database.

[1420] 6. Message generation means: The server generates a response message that takes into account the user's emotions and urgency, based on emotions recognized by an emotion engine (e.g., IBM Watson Sentiment Analysis API).

[1421] 7. Message sending method: The server sends the generated response message back to the user via the LINE API.

[1422] As an example, the following shows what happens when a user sends the message, "I saw a suspicious person in my neighborhood. What should I do?"

[1423] 1. The server receives the message using the message receiving means and analyzes it using the message analysis means.

[1424] 2. Obtain the user's residential area information and search the database for contact information for the local police station and emergency response information.

[1425] 3. Obtain the latest information from the local government's API and verify its accuracy by comparing it with the information provided.

[1426] 4. The emotion engine analyzes the user's emotions, and if it detects feelings of "anxiety" or "fear," it generates a reassuring response message that takes these feelings into account.

[1427] 5. Finally, send the generated response message to the user, informing them of the necessary actions to take.

[1428] In this way, this system can provide information quickly and accurately, taking into account the user's emotions and urgency, thereby enhancing the user's sense of security and contributing to safety.

[1429] Example of a prompt:

[1430] "I saw a suspicious person in my neighborhood. What should I do?"

[1431] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1432] Step 1:

[1433] The user's device sends a message using the chat function of the LINE official account or dedicated app. This message becomes the input. Example: "I saw a suspicious person in my neighborhood."

[1434] Step 2:

[1435] The server uses a message receiving mechanism to receive messages sent by users via the LINE API. The received messages become the input. This input data (messages) is converted into an analyzable format.

[1436] Step 3:

[1437] The server activates an NLP engine as a message analysis tool and analyzes the received message. This analysis extracts keywords. Example: "suspicious person," "neighborhood." The input is the received message, and the output is the extracted keywords.

[1438] Step 4:

[1439] The server retrieves the user's residential area information. It obtains this information from the user's profile; for example, "Minato-ku, Tokyo." The input is the user's profile data, and the output is the residential area information.

[1440] Step 5:

[1441] The server uses an information retrieval tool to search for relevant information from the database based on the analyzed keywords and residential area information. Example: Contact information for police stations and information on what to do. The input is keywords and residential area information, and the output is relevant information.

[1442] Step 6:

[1443] The server retrieves the latest municipal information from the municipality's API or official website. For example, it can retrieve the latest police station contact information and notices. The input is residential area information, and the output is the latest municipal information.

[1444] Step 7:

[1445] The server compares the municipality information it retrieves with existing database information to verify consistency. If the comparison does not result in a match, the database is updated. The input is the search results and the latest municipality information, and the output is the consistent information.

[1446] Step 8:

[1447] The server uses an emotion engine to recognize emotions from the content of the user's message. Example: Detecting the emotion "anxiety". The input is the received message, and the output is the recognized emotion.

[1448] Step 9:

[1449] The server uses a message generation mechanism to generate a response message based on the emotions recognized by the emotion engine. Example: "This is a report of a suspicious person in Minato Ward. First, please evacuate to a safe place. Please make a note of the suspicious person's characteristics in as much detail as possible and immediately contact the nearest police station (phone number: xxx-xxxx-xxxx)." The input is the consistent information and recognized emotions, and the output is the response message.

[1450] Step 10:

[1451] The server uses a message sending method to send the generated response message to the user via the LINE API. The user receives the message on the LINE chat screen on their smartphone or tablet and checks the solution. The input is the response message, and the output is the result of sending it to the user.

[1452] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1453] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1454] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1455] [Fourth Embodiment]

[1456] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1457] As shown in Figure 7, the 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.

[1458] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1459] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1460] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1461] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1462] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1463] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1464] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1465] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1466] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1467] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1468] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1469] The present invention will be described based on the following system overview and specific examples.

[1470] System Overview

[1471] This system allows users to send questions and consultations about childcare through an official LINE account. The server receives and analyzes these messages and provides appropriate information. The system is available 24 hours a day and can also provide information tailored to the user's residential area.

[1472] Program Processing Overview

[1473] Step 1: The user sends a message.

[1474] Users use the chat function of the official LINE account to send messages such as, "Please tell me how to enroll my child in daycare."

[1475] Step 2: The server receives the message.

[1476] The server receives messages sent by users via the LINE API.

[1477] The server converts the received message into a format that can be parsed.

[1478] Step 3: The server parses the message.

[1479] The server uses natural language processing techniques to analyze the message.

[1480] Example: Extract the keywords "nursery school" and "how to enroll," and determine the category to be "information on finding childcare."

[1481] Step 4: The server retrieves the user's residential area information.

[1482] The server retrieves residential area information (for example, Shinjuku Ward) from the user's profile.

[1483] If the profile does not contain information about the user's residential area, the server will generate a response message asking, "Please tell us where you live."

[1484] Step 5: The server searches for the appropriate information.

[1485] The server uses message analysis results and residential area information to search the database for information such as nursery school admission requirements, necessary documents, and application procedures.

[1486] Step 6: The server matches with the local government information.

[1487] The server retrieves the latest information from the local government's API and official website, and compares it with the searched information.

[1488] If the most recent information matches, select that information.

[1489] Step 7: The server generates a response message.

[1490] Based on the information acquired by the server, a response message is generated to be provided to the user.

[1491] Example: "Details regarding admission to a nursery school in Shinjuku Ward are as follows. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: You can apply online through the ward office website."

[1492] Step 8: The server sends the message

[1493] The server sends a response message to the user via the LINE API.

[1494] Specific example

[1495] Case 1: Inquiry about childcare application information (nursery school enrollment)

[1496] 1. User: "Please tell me how to enroll my child in daycare."

[1497] 2. The server receives and analyzes the message. Based on the keywords "nursery school" and "how to enroll," it determines the category to be "childcare information."

[1498] 3. The server retrieves the user's residential area information (Shinjuku Ward) from their profile.

[1499] 4. The server searches the database for the latest information regarding childcare applications in Shinjuku Ward (conditions, documents, and methods).

[1500] 5. The server retrieves the latest information from the local government's API and compares it with the search results.

[1501] 6. The server generates a message stating, "Here are the details for enrolling in a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website."

[1502] 7. The server sends the generated message to the user via LINE.

[1503] Case 2: Medical information for sudden fever or injury

[1504] 1. User: "My child has a fever. Where can I get them examined?"

[1505] 2. The server receives and analyzes the message. It determines whether it is an emergency medical event based on the keywords "fever" and "medical institution."

[1506] 3. The server retrieves residential area information (Kita Ward, Osaka City).

[1507] 4. The server searches its database for medical institutions in Kita Ward, Osaka City that can provide emergency medical care.

[1508] 5. The server retrieves the latest medical institution information from the local government API and compares it with the search results.

[1509] 6. The server generates the message: "Osaka City Kita Ward General Hospital is open 24 hours a day. The emergency center is also available. The address is ○○."

[1510] 7. The server sends the generated message to the user via LINE.

[1511] In this way, this system efficiently processes user inquiries, providing prompt responses and accurate information. This will enable it to address a wide range of needs related to childcare.

[1512] The following describes the processing flow.

[1513] Step 1:

[1514] A user sends a message to the official LINE account. This message might be something like, "Please tell me how to enroll my child in daycare."

[1515] Step 2:

[1516] The server receives messages sent by users via the LINE API. The received messages are then converted into an analyzable format.

[1517] Step 3:

[1518] The server invokes a natural language processing (NLP) engine to analyze the received message. This analysis extracts keywords such as "nursery school" and "how to enroll," and the question category is determined to be "childcare information."

[1519] Step 4:

[1520] The server retrieves residential area information from the user's profile information. For example, if the user has previously registered "Shinjuku Ward," that information will be used. If residential area information is not registered, the server will ask the user for their residential area in a subsequent process.

[1521] Step 5:

[1522] The server searches the database for relevant information based on the message analysis results and residential area information. For example, it extracts information about childcare activities in Shinjuku Ward (admission requirements, necessary documents, application methods, etc.).

[1523] Step 6:

[1524] The server retrieves the latest local government information from the local government's API and official website. This allows the server to compare the latest childcare information with the contents of the database, ensuring the consistency of the information.

[1525] Step 7:

[1526] The server generates a response message to the user based on the collected and verified information.

[1527] For example, the content might read: "Details regarding admission to a nursery school in Shinjuku Ward are as follows. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: You can apply online through the ward office website."

[1528] Step 8:

[1529] The server sends a generated response message to the user via the LINE API. The user can receive the message on the LINE chat screen and check the suggested solution.

[1530] Specific example (in the case of an inquiry about childcare information):

[1531] Step 1:

[1532] User: Sends a message saying, "Please tell me how to enroll my child in daycare."

[1533] Step 2:

[1534] The server receives this message using the LINE API.

[1535] Step 3:

[1536] The server analyzes the message using an NLP engine, extracts "nursery school" and "how to enroll" as keywords, and classifies them as "childcare information."

[1537] Step 4:

[1538] The server retrieves residential area information for "Shinjuku Ward" from the user's profile.

[1539] Step 5:

[1540] The server searches the database for nursery school enrollment information related to Shinjuku Ward.

[1541] Step 6:

[1542] The server retrieves the latest nursery school enrollment information from the Shinjuku Ward official website and compares it with the database.

[1543] Step 7:

[1544] The server generates a response message stating, "Details regarding admission to a nursery school in Shinjuku Ward are as follows. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: You can apply online through the ward office website."

[1545] Step 8:

[1546] The server sends this message to the user via LINE, and the user receives and confirms its contents.

[1547] (Example 1)

[1548] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1549] Conventional information systems struggled to respond quickly and accurately to user questions and inquiries. Furthermore, they often failed to adequately address users' residential areas, resulting in inconsistencies with the latest information from local governments. Additionally, the lack of message optimization meant users often received unclear and easily understandable responses.

[1550] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1551] In this invention, the server includes a message receiving means, a message analysis means for analyzing the message using natural language processing technology, a means for acquiring the user's residential area information based on the content analyzed by the message analysis means, an information retrieval means for searching for appropriate information from a database based on the analyzed content and residential area information, a means for comparing with administrative agency information that provides appropriate information, a message generation means for generating a response message based on the comparison result, a message sending means for sending the response message to the user, and a means for optimizing the generated message using a generation AI model. This enables the rapid and accurate provision of information in response to user questions and consultations, provides optimal information tailored to the residential area, ensures consistency with the latest information from administrative agencies, and provides a response message that is easy for the user to understand.

[1552] "Message receiving means" refers to a combination of a system and process that receives messages sent by users and converts those messages into a parseable format.

[1553] "Natural language processing technology" refers to the techniques that enable computers to understand, analyze, and generate human language, and includes methods for interpreting the meaning of text.

[1554] A "message analysis system" refers to a system that analyzes received messages and has the function of extracting and understanding keywords and context within those messages.

[1555] "User residential area information" refers to data related to the geographical area where the user resides, including address and region name.

[1556] "Information retrieval means" refers to a system that has the function of extracting highly relevant information from a database based on message analysis results and residential area information.

[1557] A "database" is a systematically organized collection of data, and refers to a system that allows for the fast and efficient searching, adding, updating, and deleting of specific information.

[1558] "Government agency information" refers to data and information officially provided by public institutions such as local governments.

[1559] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and generates an optimized response for a specific task.

[1560] "Message generation means" refers to a system that has the function of creating an appropriate response message based on the analyzed content and matching results.

[1561] "Message sending means" refers to a communication means for sending a generated response message to the user.

[1562] As an embodiment of the present invention, a system is described in which a user sends questions or requests for advice regarding childcare using an online messaging platform (e.g., LINE official account), a server receives and analyzes the message, and provides appropriate information.

[1563] The server first receives messages sent by users using a message receiving method. LINE's Messaging API is used for message reception. Next, the server analyzes the messages using natural language processing technology (for example, Google Cloud Natural Language API). This makes it possible to extract keywords and intent from the message content.

[1564] Based on the analyzed data, the server retrieves the user's residential area information. This includes a function to refer to the user's profile information, and if residential area information is missing, it generates a response message asking the user, "Please tell us where you live."

[1565] Next, the server uses the analysis results and residential area information to search for appropriate information from the database. The database can be a relational or non-relational database such as MySQL or MongoDB. The retrieved information includes specific details such as nursery school admission requirements, necessary documents, and application procedures.

[1566] The server then retrieves the latest information from the local government's APIs and official websites and compares it with the previously retrieved database information. For example, it ensures the accuracy of the information provided by comparing it with the latest information obtained from Shinjuku Ward's open data API.

[1567] Next, the server generates a response message based on the matching results. Here, a generative AI model (e.g., GPT-4) is used to optimize the response message. This ensures that the user receives clear and relevant information.

[1568] Finally, the server uses a message sending method to send the generated response message to the user. The message is sent to the user's LINE account via LINE's Messaging API.

[1569] Specific example

[1570] Case 1: Inquiry about nursery school enrollment information

[1571] 1. User: "Please tell me how to enroll my child in daycare."

[1572] 2. The server receives the message and analyzes it using natural language processing technology. Based on the keywords "nursery school" and "how to enroll," it determines the category to be "childcare information."

[1573] 3. The server retrieves the user's residential area information (Shinjuku Ward).

[1574] 4. The server searches the database for the latest information regarding childcare applications in Shinjuku Ward (conditions, documents, and methods).

[1575] 5. The server retrieves the latest information from the local government's API and compares it with the search results.

[1576] 6. The server generates a message stating, "Here are the details for enrolling in a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website."

[1577] 7. The server sends the generated message to the user via LINE.

[1578] Case 2: Medical information for sudden fever or injury

[1579] 1. User: "My child has a fever. Where can I get them examined?"

[1580] 2. The server receives and analyzes the message. It determines whether it is an emergency medical event based on the keywords "fever" and "medical institution."

[1581] 3. The server retrieves residential area information (Kita Ward, Osaka City).

[1582] 4. The server searches its database for medical institutions in Kita Ward, Osaka City that can provide emergency medical care.

[1583] 5. The server retrieves the latest medical institution information from the local government API and compares it with the search results.

[1584] 6. The server generates the message: "Osaka City Kita Ward General Hospital is open 24 hours a day. The emergency center is also available. The address is ○○."

[1585] 7. The server sends the generated message to the user via LINE.

[1586] This invention allows users to obtain quick and accurate information, enabling them to address diverse childcare needs. The system is particularly useful as it is available 24 / 7 through messaging platforms like LINE, significantly improving user convenience.

[1587] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1588] Program processing flow

[1589] Step 1:

[1590] Users can use the chat function of the official LINE account to enter questions or requests for advice and send messages.

[1591] Input: Message from the user (e.g., "Please tell me how to enroll my child in daycare.")

[1592] Output: A message is sent to the LINE server.

[1593] Specific action: The user types a message on the LINE app on their smartphone or PC and presses the send button.

[1594] Step 2:

[1595] The server uses LINE's Messaging API to retrieve incoming messages.

[1596] Input: Message sent from LINE server

[1597] Output: The message arrives on the server in JSON format (Example: { "type": "text", "text": "Please tell me how to enroll my child in daycare"})

[1598] Specific operation: The server polls for new messages via the LINE Messaging API endpoint.

[1599] Step 3:

[1600] The server uses natural language processing techniques to analyze the message.

[1601] Input: Message in JSON format (Example: { "type": "text", "text": "Please tell me how to enroll my child in daycare"})

[1602] Output: Analysis results (Keywords: "nursery school", "how to enroll", Category: "childcare information")

[1603] Specific operation: The server uses an NLP engine such as the Google Cloud Natural Language API to extract keywords from the message text and classify the intent.

[1604] Step 4:

[1605] The server retrieves the user's residential area information.

[1606] Input: Analysis results (Category "Childcare Information")

[1607] Output: Residential area information (e.g., Shinjuku Ward)

[1608] Specific operation: The server searches for the user's residential area from their LINE profile information and retrieves the information. If residential area information is insufficient, it generates a message asking "Please tell us where you live" and sends it to the user.

[1609] Step 5:

[1610] The server uses the analysis results and residential area information to search for appropriate information from the database.

[1611] Input: Analysis results, residential area information

[1612] Output: Appropriate information (e.g., nursery school admission requirements, necessary documents, application procedures)

[1613] Specific operation: The server queries databases such as MySQL or MongoDB to retrieve analysis results and related data based on residential area information.

[1614] Step 6:

[1615] The server retrieves the latest information from local government APIs and official websites and compares it with search results.

[1616] Input: Appropriate information (search results from the database), up-to-date local government information (obtained from API or official website)

[1617] Output: Matching results (latest matching information)

[1618] Specific operation: The server retrieves the latest information from sources such as Shinjuku Ward's open data API, and verifies its consistency by comparing it with information obtained from the database.

[1619] Step 7:

[1620] The server generates a response message based on the matching results.

[1621] Input: Matching result

[1622] Output: Response message (Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website.")

[1623] Specific operation: The server uses a generated AI model (e.g., GPT-4) to create a response message that provides information to the user in an easily understandable format.

[1624] Step 8:

[1625] The server sends a response message to the user.

[1626] Input: Response message

[1627] Output: Message delivered to the user

[1628] Specific operation: The server sends the generated response message to the user's LINE account via LINE's Messaging API.

[1629] (Application Example 1)

[1630] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1631] In today's lifestyle, obtaining information about childcare quickly and accurately is crucial. Furthermore, there is a need for a means to quickly obtain appropriate information, even in situations requiring urgent action. To utilize such information services more diversely, convenience is needed not only for information provision but also for paid services and content purchases using electronic payments. However, current systems struggle to simultaneously meet all these requirements.

[1632] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1633] In this invention, the server includes a message receiving means, a message analysis means for analyzing the message using natural language processing technology, a means for acquiring the user's residential area information based on the content analyzed by the message analysis means, an information retrieval means for searching a database for appropriate information based on the analyzed content and the residential area information, a means for comparing the appropriate information with local government information, a message generation means for generating a response message based on the matching result, a message transmission means for sending the response message to the user, and an electronic payment means. This enables the user to receive information suitable for their residential area, receive emergency consultations, and even purchase paid consultations and childcare-related content using electronic payment.

[1634] A "message receiving means" is a means that has the function of receiving messages sent by a user.

[1635] A "message analysis tool" is a means of analyzing a received message using natural language processing technology to understand its content.

[1636] "Means for obtaining residential area information" refers to methods for extracting and obtaining information about a user's residential area from their profile information or inquiry messages.

[1637] An "information retrieval method" is a means of searching for appropriate information from a database based on the content of the analyzed message and the acquired residential area information.

[1638] "Means of cross-referencing with local government information" refers to methods for verifying and cross-referencing the searched information with the latest information from the local government.

[1639] A "message generation means" is a means for creating a response message to be provided to the user based on the verified information.

[1640] "Message sending means" refers to means for sending the generated response message to the user.

[1641] "Electronic payment methods" refer to means that have the functionality of electronic payment and can be used by users when purchasing paid services or content.

[1642] A "generative AI model" is an artificial intelligence model used to generate appropriate answers or response messages in response to user inquiries.

[1643] A "prompt sentence" is a sentence of instruction or question that is input to a generative AI model, and it is the input sentence that enables the model to generate an appropriate answer.

[1644] The system for carrying out the present invention is constructed using the following hardware and software.

[1645] hardware

[1646] Server: Used as a central processing unit for database management, communication processing, message analysis, and generation.

[1647] User terminal: A device, such as a smartphone, used by a user to send and receive messages.

[1648] Internet connection: A network infrastructure that facilitates communication between servers and user terminals.

[1649] software

[1650] LINE Messaging API: Used to receive messages from users and forward them to the server.

[1651] Natural language processing libraries (e.g., NLTK): Provide natural language processing techniques for message analysis.

[1652] SQLite: A database system that stores user information and childcare information by region.

[1653] Python: Used as the programming language to integrate all of the above parts.

[1654] Processing flow

[1655] 1. Message Reception: Users send questions and requests for advice regarding childcare using the LINE app on their device. For example, they might send a message such as, "Please tell me how to enroll my child in daycare."

[1656] 2. Message Analysis: After receiving a message via the LINE Messaging API, the server uses NLTK to analyze the message and extract keywords (e.g., "nursery school," "how to enroll").

[1657] 3. Obtaining residential area information: The server obtains residential area information (e.g., "Shinjuku Ward") from the user profile information.

[1658] 4. Information Retrieval: The server searches for appropriate information from the SQLite database based on the analyzed keywords and residential area information.

[1659] 5. Verification with local government information: The server retrieves the latest information from local government APIs and official websites and verifies it against the search results.

[1660] 6. Generating a response message: The server generates a response message based on the matching results (e.g., "Details regarding admission to a nursery school in Shinjuku Ward. Required documents: Resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website.").

[1661] 7. Message Sending: The generated response message is sent to the user via the LINE Messaging API.

[1662] 8. Electronic payment: Users utilize electronic payment functions to purchase paid consultations and childcare-related content.

[1663] This system allows users to quickly and accurately obtain childcare information tailored to their residential area. Furthermore, it enables prompt and appropriate responses to urgent inquiries and emergencies, and allows for paid consultations and content purchases using electronic payment.

[1664] Specific example

[1665] User: "My child has a fever. Where can I get them examined?"

[1666] server:

[1667] The message was analyzed, and the keywords "fever" and "medical institution" were extracted.

[1668] Retrieve residential area information (e.g., "Kita Ward, Osaka City").

[1669] Search the database for information on medical institutions in the relevant area.

[1670] Check against the latest local government information.

[1671] Generate a response message (e.g., "Osaka City Kita Ward General Hospital is open 24 hours. The emergency center is also available. The address is XX.").

[1672] Send a message to the user.

[1673] Examples of prompts for generative AI models

[1674] User: "Please tell me how to enroll my child in daycare."

[1675] AI: "I will now explain the specific procedures for enrolling your child in daycare. First, please prepare the necessary documents. Next, I will explain how to apply online."

[1676] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1677] Step 1:

[1678] Users send questions and requests for advice about childcare using the LINE app on their devices. The input is a text message, such as "Please tell me how to enroll my child in daycare." This message is then sent to the server.

[1679] Step 2:

[1680] The server receives messages from users via the LINE Messaging API. The received messages are converted into a parseable format. The input is the user's text message, and the output is text data for parsing.

[1681] Step 3:

[1682] The server parses incoming messages using a natural language processing library (such as NLTK). It extracts keywords from the messages (e.g., "nursery school," "how to enroll"). The input is text data for analysis, and the output is a list of keywords.

[1683] Step 4:

[1684] The server retrieves residential area information from the user's profile information. This ensures that the analyzed keywords and the user's residential area information are matched. The input is the user ID, and the output is the user's residential area information (e.g., "Shinjuku Ward").

[1685] Step 5:

[1686] The server searches for appropriate information from the SQLite database based on the analyzed keywords and acquired residential area information. The input is a list of keywords and residential area information, and the output is the initial search result.

[1687] Step 6:

[1688] The server retrieves the latest information from local government APIs and official websites and compares it with the initial search results. This verifies the timeliness of the information. The input is the initial search results, and the output is the final, verified information.

[1689] Step 7:

[1690] The server generates a response message based on the final information it has verified. The input is the final information, and the output is a text message sent to the user (e.g., "Here are the details for nursery school enrollment in Shinjuku Ward. Required documents: resident registration certificate, maternal and child health handbook, etc. Application method: Online application is possible from the ward office website.").

[1691] Step 8:

[1692] The server sends the generated response message to the user via the LINE Messaging API. The input is the response message, and the output is the message displayed on the user's device.

[1693] Step 9:

[1694] Users utilize in-app electronic payment methods to access paid consultations and childcare-related content. The input is the user's electronic payment information, and the output is a confirmation message upon completion of the payment.

[1695] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1696] The present invention will be described based on the following system overview and specific examples.

[1697] System Overview

[1698] This system allows users to send questions and consultations about childcare via a LINE official account. The server receives and analyzes these messages and provides appropriate information. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it can provide even more appropriate responses. The system is available 24 hours a day and can also provide information tailored to the user's residential area.

[1699] Program Processing Overview

[1700] Step 1: The user sends a message.

[1701] Users use the chat function of the official LINE account to send messages such as, "Please tell me how to enroll my child in daycare."

[1702] Step 2: The server receives the message.

[1703] The server receives messages sent by users via the LINE API. The received messages are converted into an analyzable format.

[1704] Step 3: The server parses the message.

[1705] The server invokes a natural language processing (NLP) engine to analyze the received message. This analysis extracts the keywords "nursery school" and "how to enroll," and the question category is determined to be "nursery school information."

[1706] Step 4: The server uses the emotion engine to recognize emotions.

[1707] The server uses an emotion engine to recognize emotions from the content of the user's message. For example, the emotion engine can detect emotions such as "anxiety" or "impatience" from the user's message.

[1708] Step 5: The server retrieves the user's residential area information.

[1709] The server retrieves residential area information from the user's profile information. For example, if the user has previously registered "Shinjuku Ward," that information will be used. If residential area information is not registered, the server will ask the user for their residential area in a subsequent process.

[1710] Step 6: The server searches for the appropriate information.

[1711] The server searches the database for relevant information based on the message analysis results and residential area information. For example, it extracts information about childcare activities in Shinjuku Ward (admission requirements, necessary documents, application methods, etc.).

[1712] Step 7: The server matches with the local government information.

[1713] The server retrieves the latest local government information from the local government's API and official website. This allows the server to compare the latest childcare information with the contents of the database, ensuring the consistency of the information.

[1714] Step 8: The server generates a response message.

[1715] The server generates a response message based on the emotions recognized by the emotion engine. The content and tone of the response message are adjusted to match the user's emotions. For example, if anxiety is detected, the message will include reassuring language.

[1716] Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. There's no need to worry unnecessarily. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[1717] Step 9: The server sends the message

[1718] The server sends a generated response message to the user via the LINE API. The user can receive the message on the LINE chat screen and check the suggested solution.

[1719] Specific example (in the case of an inquiry about childcare information):

[1720] Case 1: Inquiry about childcare application information (nursery school enrollment)

[1721] 1. User: Sends a message saying, "Please tell me how to enroll my child in daycare."

[1722] 2. The server receives this message using the LINE API.

[1723] 3. The server uses an NLP engine to analyze the message, extracts keywords such as "nursery school" and "how to enroll," and classifies it as "childcare information."

[1724] 4. The server uses an emotion engine to recognize the emotion of "anxiety" from the user's message.

[1725] 5. The server retrieves residential area information for "Shinjuku Ward" from the user's profile.

[1726] 6. The server searches the database for nursery school enrollment information related to Shinjuku Ward.

[1727] 7. The server retrieves the latest nursery school enrollment information from the Shinjuku Ward official website and compares it with the database.

[1728] 8. The server generates a response message that includes reassuring wording such as, "Here are the details for enrolling in a nursery school in Shinjuku Ward. There is no need to worry unnecessarily. Required documents include a resident registration certificate and a maternal and child health handbook. You can apply online through the ward office website."

[1729] 9. The server sends this message to the user via LINE, and the user receives and confirms its contents.

[1730] In this way, the system efficiently processes user inquiries and provides accurate information along with prompt, empathetic responses. This makes it possible to address diverse childcare needs while also considering their emotional aspects.

[1731] The following describes the processing flow.

[1732] Step 1:

[1733] A user sends a message to the official LINE account saying, "Please tell me how to enroll my child in daycare."

[1734] Step 2:

[1735] The server receives this message via the LINE API. The received message is converted into a parseable format.

[1736] Step 3:

[1737] The server invokes a natural language processing (NLP) engine to analyze the message. It extracts specific keywords (in this case, "nursery school" and "how to enroll") and determines that the question falls under the category of "nursery school information."

[1738] Step 4:

[1739] The server invokes an emotion engine to recognize emotions from the user's message. For example, it can detect emotions such as "anxiety" or "restlessness" from the user's message.

[1740] Step 5:

[1741] The server accesses the user's profile information and retrieves their residential area information (e.g., "Shinjuku Ward"). If the residential area information is not registered, a message is generated in the subsequent process asking the user to provide their residential area.

[1742] Step 6:

[1743] The server searches the database for relevant information based on the message analysis results and acquired residential area information. For example, it might retrieve information such as admission requirements, necessary documents, and application procedures for daycare centers in Shinjuku Ward.

[1744] Step 7:

[1745] The server retrieves the latest information from the local government's API and official website. This latest information is then compared with the database information to verify consistency.

[1746] Step 8:

[1747] The server generates a response message based on the recognition results from the emotion engine. If the user is feeling anxious, a message designed to reassure them will be generated.

[1748] Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. Please rest assured. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[1749] Step 9:

[1750] The server sends a generated response message to the user via the LINE API. The user can receive the message on the LINE chat screen and check the suggested solution.

[1751] Specific example (in the case of an inquiry about childcare information):

[1752] Step 1:

[1753] User: Sends a message saying, "Please tell me how to enroll my child in daycare."

[1754] Step 2:

[1755] The server uses the LINE API to receive messages.

[1756] Step 3:

[1757] The server uses an NLP engine to analyze the message, extracts the keywords "nursery school" and "how to enroll," and classifies it as "information on finding childcare."

[1758] Step 4:

[1759] The server uses an emotion engine to recognize the emotion of "anxiety" from the user's message.

[1760] Step 5:

[1761] The server retrieves residential area information for "Shinjuku Ward" from the user's profile information.

[1762] Step 6:

[1763] The server searches the database for nursery school enrollment information related to Shinjuku Ward.

[1764] Step 7:

[1765] The server retrieves the latest nursery school enrollment information from the local government's API and compares it with the database.

[1766] Step 8:

[1767] The server, responding to the emotion of "anxiety," generates a response message that reads, "Here are the details for enrolling in a nursery school in Shinjuku Ward. Please rest assured. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[1768] Step 9:

[1769] The server sends this message to the user via the LINE API. The user can then view the received message.

[1770] (Example 2)

[1771] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1772] In modern society, providing timely and appropriate information about childcare is crucial. However, existing systems struggle to provide information that takes users' emotions into account, and there are challenges in adequately addressing the needs of users who require emotional support. Furthermore, the lack of up-to-date information specific to a particular residential area makes it difficult to provide appropriate advice for each region.

[1773] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1774] In this invention, the server includes message receiving means, message analysis means for analyzing the message using natural language processing technology, emotion recognition means for recognizing the user's emotions from the message, means for acquiring the user's residential area information based on the content analyzed by the message analysis means, information retrieval means for searching a database for appropriate information based on the analyzed content and the residential area information, means for comparing the information with local government information that provides the appropriate information, message generation means for generating a response message based on the emotions recognized by the emotion recognition means, and message transmission means for sending the response message to the user. This makes it possible to quickly provide the latest and most appropriate information for each residential area while being attentive to the user's emotions.

[1775] A "message receiving means" is a means for receiving messages sent by a user.

[1776] A "message analysis means" is a means for analyzing a received message using natural language processing technology.

[1777] "Emotion recognition means" refers to a method for recognizing a user's emotions from a received message.

[1778] "Means for obtaining user residential area information" refers to means for obtaining information about the user's place of residence.

[1779] An "information retrieval method" is a means of searching for appropriate information from a database based on the analyzed content and residential area information.

[1780] "Means of cross-referencing with local government information" refers to means of cross-referencing appropriate information with the latest information provided by local governments.

[1781] A "message generation means" is a means for generating a response message based on the emotion recognized by the emotion recognition means.

[1782] "Message sending means" refers to means for sending the generated response message to the user.

[1783] Modes for carrying out the invention

[1784] This invention relates to a system in which a server receives, analyzes, and provides appropriate information in response to questions and consultations about childcare sent by users through an online chat platform. A key feature of this system is its ability to provide responses that take the user's emotions into consideration, particularly through the integration of emotion recognition functionality. The embodiments of this system are described in detail below.

[1785] System Overview

[1786] This system consists of the following main hardware and software components:

[1787] server

[1788] User devices (smartphones, tablets, PCs)

[1789] LINE official accounts and their APIs

[1790] Natural language processing engines (e.g., SpaCy, NLTK)

[1791] Emotion recognition engine (e.g., IBM Watson Tone Analyzer)

[1792] Databases (e.g., MySQL, MongoDB)

[1793] Local government API or official website

[1794] Specific operation of the system

[1795] 1. The user sends a message.

[1796] Users can send questions and inquiries through the chat window of the official LINE account. For example, specific questions such as "Please tell me how to enroll my child in daycare" are possible.

[1797] 2. The server receives the message.

[1798] The server receives messages from users via the LINE API. At this time, the message data is transferred to the server in JSON format.

[1799] 3. The server parses the message.

[1800] The server uses a natural language processing engine (e.g., SpaCy) to analyze the received message. This analysis extracts keywords such as "nursery school" and "how to enroll," and the question category is classified as "nursery school information."

[1801] 4. The server recognizes emotions.

[1802] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to detect the user's emotions from the message. For example, it can identify emotions such as "anxiety" or "restlessness."

[1803] 5. The server retrieves the user's residential area information.

[1804] The server queries the user's profile information to obtain information about their residential area. For example, if the user has previously registered "Shinjuku Ward," that information will be used. If the residential area is not registered, the system will prompt the user to enter the information.

[1805] 6. The server searches for the appropriate information.

[1806] The server searches for relevant information from databases (e.g., MySQL, MongoDB) based on the analysis results and residential area information. For example, it extracts information on nursery school enrollment in Shinjuku Ward (enrollment conditions, required documents, application methods, etc.).

[1807] 7. The server compares the information with that of the local government.

[1808] The server uses the latest information obtained from the local government's API and official website to compare it with the information in the database. This verifies the accuracy of the information provided.

[1809] 8. The server generates a response message.

[1810] The server generates a response message that takes the user's emotions into consideration, based on the results of the emotion recognition engine. If anxiety is detected, it will include reassuring phrases such as, "There's no need to worry unnecessarily."

[1811] 9. The server sends the message.

[1812] The server sends the generated response message to the user via the LINE API. The user can then view the response message in the LINE chat window.

[1813] Specific example

[1814] For example, if a user sends a message such as "Please tell me how to enroll my child in daycare," the server will process it in the following steps:

[1815] 1. The user sends a message through the LINE official account.

[1816] 2. The server receives the message via the LINE API.

[1817] 3. The server uses a natural language processing engine to parse the message.

[1818] 4. The server uses an emotion recognition engine to recognize emotions.

[1819] 5. The server retrieves the user's residential area information.

[1820] 6. The server searches the database for relevant information.

[1821] 7. The server compares the municipal information it has obtained with the contents of the database.

[1822] 8. The server generates a response message.

[1823] 9. The server sends a response message to the user via LINE.

[1824] Example of a prompt:

[1825] "Please tell me how to enroll my child in daycare."

[1826] "Please tell me about childhood vaccinations."

[1827] "I'm looking for a nearby childcare facility."

[1828] By following the above steps, this system can provide accurate and timely information while being sensitive to the user's emotions.

[1829] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1830] Program processing flow

[1831] Step 1:

[1832] Input: The user sends a message using the chat function of the LINE official account. Example: "Please tell me how to enroll my child in daycare."

[1833] Specific action: The user types a message in the chat window and presses the send button.

[1834] Output: The message is transferred to the server via the LINE API.

[1835] Step 2:

[1836] Input: The server receives message data from the LINE API.

[1837] Specific operation: The server waits for incoming requests and retrieves message data.

[1838] Output: The received message data is saved on the server and becomes ready for analysis.

[1839] Step 3:

[1840] Input: The server that receives the message data invokes a natural language processing engine (e.g., SpaCy).

[1841] Specific operation: The server instantiates an NLP engine and parses the incoming message.

[1842] Data processing / calculation: Extract keywords and phrases from messages and understand the context.

[1843] Output: Keywords such as "nursery school" and "how to enroll" are extracted, and the question category is classified as "childcare information."

[1844] Step 4:

[1845] Input: The server receives the results of the natural language processing engine's analysis.

[1846] Specific operation: The server calls an emotion recognition engine (e.g., IBM Watson Tone Analyzer) and sends the analysis results.

[1847] Data processing / calculation: Identify emotions (e.g., anxiety, impatience) from messages.

[1848] Output: The emotion analysis results in the detection of "anxiety."

[1849] Step 5:

[1850] Input: The server, having received the sentiment analysis results, retrieves the user's residential area information from the database.

[1851] Specific operation: The server executes a database query to extract the user's residential area from their profile information.

[1852] Data processing / calculation: Obtain residential area information in JSON format.

[1853] Output: Information about "Shinjuku Ward" that the user registered in advance is retrieved.

[1854] Step 6:

[1855] Input: Based on residential area information and analysis results, the server searches the database for relevant information.

[1856] Specific operation: The server executes a database query to extract childcare information related to Shinjuku Ward.

[1857] Data processing / calculation: Filter search results and organize relevant information.

[1858] Output: Information on childcare activities in Shinjuku Ward (e.g., admission requirements, necessary documents, application procedures) will be obtained.

[1859] Step 7:

[1860] Input: The server that retrieves the search results cross-references the latest information with the local government's API and official website.

[1861] Specific operation: The server sends an API request to retrieve the latest information from the local government.

[1862] Data processing / calculation: Compare and verify the contents of the database with the latest information obtained.

[1863] Output: Information matching and updates are confirmed, and the latest information is reflected in the database.

[1864] Step 8:

[1865] Input: Based on the latest information matched with the sentiment analysis results, the server generates a response message.

[1866] Specific operation: The server uses a template engine to construct emotionally sensitive response messages.

[1867] Data processing / calculation: Generate appropriate wording based on emotions and incorporate it into the message.

[1868] Output: Example: "Here are the details for enrolling in a nursery school in Shinjuku Ward. There's no need to worry unnecessarily. Required documents include your resident registration certificate and maternal and child health handbook. You can apply online through the ward office website."

[1869] Step 9:

[1870] Input: The server receives the generated response message.

[1871] Specific operation: The server uses the LINE API to send a response message.

[1872] Output: The user receives and confirms the response message in the LINE chat window.

[1873] The above outlines the specific processing steps of this system. This enables the provision of accurate information that resonates with the user's emotions.

[1874] (Application Example 2)

[1875] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1876] Current information processing systems are required to respond quickly and accurately to user inquiries and emergency reports. However, conventional systems struggle to adequately consider emotions and urgency in their responses, leaving challenges in ensuring user confidence and safety. Furthermore, there is a lack of mechanisms to acquire the latest information from local governments in real time and provide appropriate information immediately. As a result, users are prone to feeling anxious due to a lack of information and delayed responses, and a system that provides efficient information and a sense of security is needed.

[1877] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a message receiving means, a message analysis means for analyzing a message using natural language processing technology, a means for acquiring user residential area information based on the content analyzed by the message analysis means, an information retrieval means for searching for appropriate information from a database based on the analyzed content and residential area information, a means for comparing with local government information that provides appropriate information, a message generation means for generating a response message based on the matching result, a message transmission means for sending the response message to the user, a means for receiving reports of emergencies and suspicious person information from the user, recognizing the user's emotions using an emotion engine, and generating a message including highly urgent countermeasures, and a means for providing the latest information from the local government and presenting methods for ensuring safety. This enables the rapid and accurate provision of information that takes into account the user's emotions and urgency, thereby realizing a system that enhances the user's sense of security and contributes to ensuring safety.

[1878] "Message receiving means" refers to a device or software for receiving messages sent by a user.

[1879] A "message analysis means" is a device or software that analyzes a received message using natural language processing technology and extracts important information.

[1880] "Residential area information" refers to information about the region where the user lives, and is obtained from profile information.

[1881] "Information retrieval means" refers to a device or software that retrieves appropriate information from a database based on the analyzed message content and residential area information.

[1882] "Local government information" refers to official information provided by local administrative agencies, which is obtained from online APIs and official websites.

[1883] A "message generation means" is a device or software that generates a response message to send to the user based on analyzed information and sentiment data.

[1884] "Message transmission means" refers to a device or software for sending a generated response message to a user.

[1885] An "emotion engine" is a device or software that recognizes and analyzes emotions from a user's message.

[1886] "Reporting emergencies or suspicious person information" refers to the act of a user reporting an emergency situation or information about a suspicious person to the system.

[1887] "Appropriate information" refers to useful and accurate information in response to user inquiries or emergencies.

[1888] "Methods for ensuring safety" refer to specific means and advice for ensuring safety when a user feels anxious or in danger.

[1889] A security service system capable of ensuring safety and responding quickly to emergencies is described below as an embodiment of this invention.

[1890] The system consists of the following hardware and software:

[1891] Server: The server will use a cloud server (e.g., AWS, Google Cloud, Microsoft Azure).

[1892] User device: A smartphone or tablet used to send messages.

[1893] The server includes the following software modules:

[1894] 1. Message receiving method: The server receives messages sent by the user via the LINE API.

[1895] 2. Message analysis method: The server analyzes the received message using a natural language processing (NLP) engine (e.g., NLTK, Google Cloud Natural Language API) and extracts keywords.

[1896] 3. Means for obtaining residential area information: The server obtains residential area information from the user's profile information.

[1897] 4. Information Retrieval Method: The server searches the database for relevant information based on the analyzed message content and residential area information. This database includes information such as police station contact information and emergency procedures.

[1898] 5. Local Government Information Verification Method: The server retrieves the latest local government information from the local government's online API or official website (e.g., local government API) and verifies it against the information in the database.

[1899] 6. Message generation means: The server generates a response message that takes into account the user's emotions and urgency, based on emotions recognized by an emotion engine (e.g., IBM Watson Sentiment Analysis API).

[1900] 7. Message sending method: The server sends the generated response message back to the user via the LINE API.

[1901] As an example, the following shows what happens when a user sends the message, "I saw a suspicious person in my neighborhood. What should I do?"

[1902] 1. The server receives the message using the message receiving means and analyzes it using the message analysis means.

[1903] 2. Obtain the user's residential area information and search the database for contact information for the local police station and emergency response information.

[1904] 3. Obtain the latest information from the local government's API and verify its accuracy by comparing it with the information provided.

[1905] 4. The emotion engine analyzes the user's emotions, and if it detects feelings of "anxiety" or "fear," it generates a reassuring response message that takes these feelings into account.

[1906] 5. Finally, send the generated response message to the user, informing them of the necessary actions to take.

[1907] In this way, this system can provide information quickly and accurately, taking into account the user's emotions and urgency, thereby enhancing the user's sense of security and contributing to safety.

[1908] Example of a prompt:

[1909] "I saw a suspicious person in my neighborhood. What should I do?"

[1910] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1911] Step 1:

[1912] The user's device sends a message using the chat function of the LINE official account or dedicated app. This message becomes the input. Example: "I saw a suspicious person in my neighborhood."

[1913] Step 2:

[1914] The server uses a message receiving mechanism to receive messages sent by users via the LINE API. The received messages become the input. This input data (messages) is converted into an analyzable format.

[1915] Step 3:

[1916] The server activates an NLP engine as a message analysis tool and analyzes the received message. This analysis extracts keywords. Example: "suspicious person," "neighborhood." The input is the received message, and the output is the extracted keywords.

[1917] Step 4:

[1918] The server retrieves the user's residential area information. It obtains this information from the user's profile; for example, "Minato-ku, Tokyo." The input is the user's profile data, and the output is the residential area information.

[1919] Step 5:

[1920] The server uses an information retrieval tool to search for relevant information from the database based on the analyzed keywords and residential area information. Example: Contact information for police stations and information on what to do. The input is keywords and residential area information, and the output is relevant information.

[1921] Step 6:

[1922] The server retrieves the latest municipal information from the municipality's API or official website. For example, it can retrieve the latest police station contact information and notices. The input is residential area information, and the output is the latest municipal information.

[1923] Step 7:

[1924] The server compares the municipality information it retrieves with existing database information to verify consistency. If the comparison does not result in a match, the database is updated. The input is the search results and the latest municipality information, and the output is the consistent information.

[1925] Step 8:

[1926] The server uses an emotion engine to recognize emotions from the content of the user's message. Example: Detecting the emotion "anxiety". The input is the received message, and the output is the recognized emotion.

[1927] Step 9:

[1928] The server uses a message generation mechanism to generate a response message based on the emotions recognized by the emotion engine. Example: "This is a report of a suspicious person in Minato Ward. First, please evacuate to a safe place. Please make a note of the suspicious person's characteristics in as much detail as possible and immediately contact the nearest police station (phone number: xxx-xxxx-xxxx)." The input is the consistent information and recognized emotions, and the output is the response message.

[1929] Step 10:

[1930] The server uses a message sending method to send the generated response message to the user via the LINE API. The user receives the message on the LINE chat screen on their smartphone or tablet and checks the solution. The input is the response message, and the output is the result of sending it to the user.

[1931] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1932] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1933] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1934] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1935] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1936] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1937] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1938] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1939] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1940] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1941] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1942] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1943] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1944] 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.

[1945] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1946] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1947] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1948] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1949] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the m...

Claims

1. Message receiving method, A message analysis means that analyzes the aforementioned message using natural language processing technology, A means for acquiring user residential area information based on the content analyzed by the message analysis means, Information retrieval means for searching for appropriate information from a database based on the analyzed content and the residential area information, A means for comparing the aforementioned appropriate information with information from a local government, A message generation means that generates a response message based on the aforementioned verification result, Message sending means for sending the aforementioned response message to the user, A system that includes this.

2. The system according to claim 1, further comprising means for obtaining the user's residential area information by referring to the user's profile information.

3. The system according to claim 1, comprising means for obtaining the aforementioned local government information from an online API or official website.

Images