system

Abstract

Provide a system. The method comprises: a means for a user to send a query through a messaging service on a communication terminal; means for a server to receive said inquiry via said messaging service; A means for the server to analyze the inquiry and generate an answer using a generation AI; means for the server to send the generated response to the user via the messaging service; a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded; A system including:

Description

[Technical Field]

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

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

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

[0004] Small and medium-sized enterprises and sole proprietors often lack the resources and time to seek prompt advice on daily business operations and management issues. Conventional consulting services have high fees and complicated reservation procedures, making them difficult to use. For this reason, there is a demand for business and management consultation services that are easily accessible and provide quick answers. There is also a need for a system that allows many users to easily start using the service by setting up a free consultation quota. [Means for solving the problem]

[0005] The present invention provides a means for a user to send an inquiry via a messaging service using a communication terminal, and a means for a server to receive the inquiry via the messaging service. The system further includes a means for the server to analyze the inquiry and generate an answer using a generation AI, and a means for the server to send the generated answer to the user via the messaging service. The system also provides a means for monitoring the number of inquiries and introducing paid plans when a predetermined free consultation limit is exceeded. The system further includes a means for the server to introduce an expert when detailed expert advice is required. This allows small and medium-sized enterprises and sole proprietors to easily receive advice from consultants, improving business efficiency and resolving management issues.

[0006] "Users" refer to small and medium-sized enterprises and sole proprietors who use this system.

[0007] A "communication terminal" is a device used by a user to send and receive messages, and includes smartphones, tablets, PCs, etc.

[0008] "Messaging Service" refers to an application for sending and receiving messages over the Internet, including, for example, LINE and other chat applications.

[0009] "Inquiry" refers to a question or consultation that a user has about business or management issues.

[0010] "Server" refers to the computer system that manages the process of receiving messages, analyzing them, generating answers using generative AI, and sending them to users.

[0011] "Generative AI" refers to an artificial intelligence model that uses natural language processing technology to automatically generate answers to user inquiries.

[0012] The "free consultation limit" refers to the number of times a user can receive free consultation within a certain period of time.

[0013] "Paid Plan" refers to a paid service plan that applies to consultations that exceed the free consultation limit.

[0014] "Expert" refers to a consultant with advanced knowledge and experience in a specific business or management issue.

[0015] "Referral" refers to the process of connecting users with experts based on their needs. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] Here, the program processing will be explained in natural language to explain how the system of the present invention can be specifically implemented.

[0038] Overall system configuration

[0039] In this system, users make inquiries via a messaging service on their communication device, and the server receives and analyzes the inquiries, generates a response using the AI, and then sends the response back to the user via the messaging service. Furthermore, a free consultation limit is set up so that users can easily make inquiries, and if the limit is exceeded, the system will guide users to paid plans. It also has a function to introduce experts when expert advice is needed.

[0040] Program processing

[0041] 1. Add as a friend on LINE

[0042] Users can add the system's official account as a friend via a messaging service (such as LINE) on a communication device (such as a smartphone) by scanning a QR code (registered trademark) or by searching for the official account.

[0043] 2. Sending your consultation

[0044] Users can input and send their business or management-related inquiries on the LINE chat screen. For example, they can input and send "Please tell me how to increase employee motivation."

[0045] 3. Message Reception and Analysis

[0046] The server receives the user's message via the LINE Messaging API, and then analyzes the message using natural language processing (NLP) technology to extract the user's intent and question.

[0047] 4. Check the free consultation slots

[0048] The server accesses the database and checks the user's consultation history. It determines whether the received consultation is within the free consultation limit (3 times) for that month. If there are free consultation limits remaining, it proceeds to the next process.

[0049] 5. Answer generation using generative AI

[0050] The server inputs the analyzed question content into the generation AI to generate an answer. For example, the generation AI may suggest specific methods and strategies for "how to increase employee motivation."

[0051] 6. Submit your response

[0052] The server then sends the generated answer to the user using the LINE Messaging API. For example, it could say, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[0053] 7. What to do when the free limit is exceeded

[0054] If the free consultation limit is exceeded, the server generates a message informing the user about a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan."

[0055] 8. Introduction to professional consultants

[0056] When a user requests expert advice, the server will introduce the expert. Specifically, it will work with a consulting company to introduce the appropriate expert to the user. At that time, the server will notify the user of the expert's information and contact details via LINE.

[0057] Specific examples

[0058] For example, imagine a small business owner sends an inquiry via LINE asking, "Please tell me about the marketing strategy for our new product." The server receives this message, analyzes it, and extracts keywords such as "new product" and "marketing strategy." The AI ​​then generates a response based on this information, replying, "It's important to clarify your target market and use social media for promotion." The user can then receive the response and implement it immediately.

[0059] In this way, this system provides an environment where small and medium-sized enterprises and sole proprietors can easily receive professional advice, which is expected to improve business efficiency and make it easier to resolve management issues.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] A user adds the service's official account as a friend on LINE.

[0063] Example: A user scans a service's QR code in the LINE app and becomes a friend of the official account.

[0064] Step 2:

[0065] The user enters the details of their inquiry on LINE and sends it.

[0066] Example: A user types and sends a message to LINE chat saying, "Please tell me your marketing strategy."

[0067] Step 3:

[0068] The server receives the message via the LINE Messaging API.

[0069] Example: A message reception event is notified to the server via LINE's Webhook.

[0070] Step 4:

[0071] The server extracts the message content and analyzes it using natural language processing (NLP).

[0072] Example: Extract the keywords "marketing" and "strategy" from the content of received messages.

[0073] Step 5:

[0074] The server retrieves the user's consultation history from the database and checks the free consultation limit.

[0075] Example: Check the number of free consultations this month by looking up the consultation history corresponding to the user ID in the database.

[0076] Step 6:

[0077] If the server has free consultation slots remaining, it sends the inquiry to the generation AI to generate an answer.

[0078] Example: A generative AI model is sent a query in the form of "Please give me some advice on marketing strategy," and the AI ​​generates a specific answer.

[0079] Step 7:

[0080] The server takes the generated answer and formats it for sending to the user.

[0081] Example: The answer obtained from the AI ​​is formatted as, "It is important to clarify the target market and promote using social media."

[0082] Step 8:

[0083] The server formats the response and sends it to the user using the LINE Messaging API.

[0084] Example: A user receives the message, "To answer your questions about marketing strategy: It's important to identify your target market and promote your business through social media."

[0085] Step 9:

[0086] The server records in the database that one free consultation slot has been used and updates the remaining number of slots.

[0087] Example: Update the user's consultation history in the database and reduce the number of free consultations this month by one.

[0088] Step 10:

[0089] If there are no free consultation slots remaining, the server generates a message informing the user of a paid plan and sends it to the user.

[0090] Example: A message is sent to the user saying, "You have used up your free consultation slots for this month. Please consider a paid plan."

[0091] Step 11:

[0092] If a user needs detailed expert advice, they can send a message on LINE saying, "I would like to be introduced to an expert."

[0093] Example: A user types "I would like to be introduced to an expert" in a LINE chat and sends it.

[0094] Step 12:

[0095] The server receives the request for an expert introduction and contacts the partner consulting firm.

[0096] Example: Search for experts who fit the user's needs through a consulting company's API and initiate the referral process.

[0097] Step 13:

[0098] The server receives the expert's information and generates a message to notify the user.

[0099] Example: Generate the message "If you need professional advice, please contact a professional consultant via this link."

[0100] Step 14:

[0101] The server generates a message and sends it to the user via the LINE Messaging API.

[0102] Example: Send the above informational message to the user and provide a way to contact an expert.

[0103] Example 1

[0104] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0105] In modern society, there are many situations in which professional advice on business and management is needed, but cost and time constraints make it difficult to easily consult with experts. Small and medium-sized enterprises and sole proprietors in particular need a way to receive professional advice quickly and affordably. While providing a free consultation limit can help reduce costs, there is also a need for a system that directs users to a paid plan once a certain number of inquiries have been made. Furthermore, when professional advice is needed, there is also a need for referrals to appropriate experts.

[0106] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0107] In this invention, the server includes: a means for a user to send an inquiry via a messaging service using a wireless communication device; a means for the server to receive the inquiry via the messaging service; a means for the server to analyze the inquiry using natural language processing technology and generate an answer using a generative AI model; a means for the server to send the generated answer to the user via the messaging service; a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded; and a means for the server to store the user's consultation history in a database. This allows users to easily receive professional advice, and smoothly guides them to a paid plan when the free consultation limit is exceeded. Furthermore, when expert advice is needed, appropriate experts can be introduced.

[0108] A "user" is an entity that accesses the system and makes a query.

[0109] "Wireless communication device" refers to a device that transmits and receives data using wireless communication technology. Examples include smartphones and tablets.

[0110] "Messaging Service" means software or applications that enable the sending and receiving of messages over the Internet. An example is an instant messenger application.

[0111] "Server" refers to the central computer system that handles queries, analyzes data, records data, and generates responses.

[0112] "Natural language processing technology" refers to technology for understanding and analyzing human language and extracting intent. Examples include grammatical analysis and semantic analysis.

[0113] "Generative AI model" refers to an artificial intelligence model that generates answers or text in natural language based on input data. Examples include GPT-3® and other large-scale language models.

[0114] A "database" refers to a storage system that can efficiently store, manage, and retrieve data.

[0115] The "free consultation quota" refers to the limit on the number of times a user can receive free consultation within a certain period of time.

[0116] "Paid Plan" refers to a service plan in which a user is charged if the free consultation limit is exceeded.

[0117] An "expert" is a person or institution with in-depth knowledge and experience in a particular field.

[0118] "Consultation history" refers to historical information such as inquiries and responses made by the user.

[0119] In the system of the present invention, a user makes an inquiry via a messaging service using a wireless communication device, a server receives and analyzes the inquiry, generates an answer using a generative AI model, and sends the answer back to the user via the messaging service. This system also includes a mechanism that provides a free consultation limit, and when the free limit is exceeded, introduces paid plans, and a function that introduces experts when expert advice is needed.

[0120] Hardware and software used

[0121] A user uses a messaging application (e.g., LINE) on a wireless communication device (e.g., a smartphone or tablet). The server receives and analyzes these messages and uses a generative AI model (e.g., GPT-3) to generate appropriate responses. The server also uses the LINE Messaging API to receive messages and BERT or similar natural language processing technology.

[0122] Specific examples of program processing

[0123] A user sends a query via LINE, asking, "Please tell me how to motivate employees." The server receives this message via the LINE Messaging API and uses natural language processing technology to extract the keywords "employee," "motivation," and "method." The server then inputs the analyzed question content into a generative AI model (GPT-3) as a prompt sentence to generate a specific answer. The generated answer (for example, "Establishing a transparent evaluation system and providing regular feedback are effective") is then sent to the user again via the LINE Messaging API.

[0124] The system's unique feature is that it can provide users with expert advice in a simple and fast way. It also reduces costs by setting up a free consultation quota, allowing users to smoothly transition to paid consultations. Furthermore, it can provide higher quality services by introducing users to experts when expert advice is needed.

[0125] Prompt Sentence Examples

[0126] For example, the following prompts can be fed into a generative AI model:

[0127] "How can I motivate my employees?"

[0128] In this way, the system of the present invention provides an environment in which small and medium-sized enterprises and sole proprietors can easily receive professional advice, and supports the improvement of business efficiency and the resolution of management issues.

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1:

[0131] A user can use a messaging service (e.g., LINE) on a wireless communication device (e.g., a smartphone) to add the system's official account as a friend by scanning the QR code or by searching for the account name and tapping "Add to Friend."

[0132] Input: User's friend addition operation

[0133] Output: The official account is added to the user's friends list.

[0134] Specific operation: The user scans the official account's QR code with the camera, the LINE app automatically redirects to the official account's page, and taps the "Add friend" button.

[0135] Step 2:

[0136] Users open the chat screen with the official LINE account, enter the details of their business or management needs, and tap the send button. For example, they could type, "Please tell me how to increase employee motivation."

[0137] Input: User's question

[0138] Output: A query message is sent to the server

[0139] Specific actions: The user types "Please tell me how to motivate employees" into the LINE text box and taps the "Send" button.

[0140] Step 3:

[0141] The server receives messages sent by users via the LINE Messaging API, then uses natural language processing technology to analyze the content of the user's question and extract important keywords and intent.

[0142] Input: Question message from user

[0143] Output: Parsed keywords and intent

[0144] Specific operation: The server receives the message "Please tell me how to motivate employees" using the LINE Messaging API, and extracts keywords such as "employee," "motivation," and "method" using natural language processing technology (e.g., the BERT model).

[0145] Step 4:

[0146] The server accesses the database, checks the user's consultation history, and determines whether the received consultation is within the free consultation limit for that month (e.g., 3 consultations).

[0147] Input: Parsed keywords and user ID

[0148] Output: Result of remaining free consultation slots

[0149] Specific operation: The server searches the database using the user ID as a key and confirms that the number of consultations for the current month has still not exceeded two.

[0150] Step 5:

[0151] The server converts the parsed question content into a prompt and inputs it into a generative AI model (e.g., GPT-3), which then generates an appropriate answer to the question.

[0152] Input: Parsed question prompt

[0153] Output: The answer generated by the generative AI model

[0154] Specific operation: The server inputs the prompt "Please tell me how to motivate employees" into the generating AI model, and the AI ​​generates an answer such as "Establishing a transparent evaluation system and providing regular feedback are effective."

[0155] Step 6:

[0156] The server sends the generated response to the user using the LINE Messaging API.

[0157] Input: Answer from a generative AI model

[0158] Output: A reply message is sent to the user

[0159] Specific operation: The server sends a response to the user via the LINE API stating that "It would be effective to establish a transparent evaluation system and provide regular feedback."

[0160] Step 7:

[0161] If the free consultation limit is exceeded, the server generates a message informing the user of the paid plan and sends it via LINE.

[0162] Input: Number of consultations judged

[0163] Output: Paid plan information message

[0164] Specific operation: The server generates a message saying "You have used up this month's free consultation quota. Please consider a paid plan" and sends it to the user.

[0165] Step 8:

[0166] When a user requests professional advice, the server will introduce them to an expert. The server will work with a consulting company to obtain information on appropriate experts and notify the user via LINE.

[0167] Input: User request for expert referral

[0168] Output: Expert information and contact details

[0169] Specific operation: The server calls the consulting company's API, retrieves information about the appropriate expert, and sends the expert's contact information to the user along with a message such as "Please contact our expert."

[0170] (Application example 1)

[0171] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0172] In conventional content distribution services, users have limited means to ask questions or obtain related information in real time about the content they are viewing, making it difficult to improve the user experience. Furthermore, when users ask many questions, it is difficult to provide appropriate answers to some of the questions quickly. Furthermore, when the number of free assistance sessions is exceeded, there is a lack of guidance on appropriate paid plans.

[0173] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0174] In this invention, the server includes: means for a user to send an inquiry via a digital message service on a communication terminal; means for the server to receive the inquiry via the digital message service; means for the server to analyze the inquiry and generate an answer using a generative AI model; means for the server to send the generated answer to the user via the digital message service; and means for monitoring the number of inquiries, introducing paid plans when a predetermined free consultation limit is exceeded, and providing an automatic answer function for questions about content distribution. This allows users to receive quick and accurate answers to their questions, improving their experience.

[0175] "User" means an individual or entity that makes an inquiry using the Digital Message Service.

[0176] A "communication terminal" is an electronic device that a user uses to send and receive messages, and specific examples include smartphones and tablets.

[0177] "Digital message service" refers to an application that sends and receives messages over the Internet, and specifically includes messaging applications.

[0178] A "server" is a computer system that receives messages from users, analyzes them, generates answers using a generative AI model, and sends them back to the user.

[0179] A "generative AI model" is a type of artificial intelligence that uses natural language processing technology to generate answers to user inquiries.

[0180] The "means for generating an answer" is the process by which the server utilizes the generative AI model to generate an appropriate answer to the user's inquiry.

[0181] The "free consultation limit" is a limit on the number of inquiries a user can receive free of charge.

[0182] "Paid Plan" means a plan for additional assistance or services that is provided to a User for a fee when the free consultation limit is exceeded.

[0183] A "content distribution question" is an inquiry that asks for information related to a movie, drama, or other digital content that a user is watching.

[0184] Here, we will explain detailed embodiments of the present invention. The present invention involves a user making an inquiry using a digital messaging service (e.g., LINE), a server receiving the inquiry, generating an answer using a generative AI model, and providing the answer to the user again via the digital messaging service. It also has a function to monitor the number of inquiries made by the user and, if the free consultation limit is exceeded, introduce paid plans.

[0185] Specifically, a user first uses a communication device such as a smartphone or tablet to add the official account of the digital messaging service as a friend. Then, via a messaging application such as LINE, the user can type and send a question about the content distribution on the chat screen. For example, a question like, "What movie do you recommend I watch next?"

[0186] The server receives messages from the user through the LINE Messaging API. The server analyzes the messages and uses natural language processing (NLP) technology to understand their content. It then uses the analyzed information to generate an appropriate response using a generative AI model (e.g., OpenAI® GPT-3).

[0187] The generated answer is then sent to the user again using the LINE Messaging API. For example, a specific answer such as "A popular movie right now is 'XX'" is sent. The server also monitors the number of questions the user has asked, and if the free consultation limit (for example, three times a month) is exceeded, the system automatically introduces users to a paid plan.

[0188] The implementation of this system uses the following hardware and software:

[0189] Communication devices: smartphones, tablets, etc.

[0190] Digital messaging services: Messaging applications such as LINE

[0191] Server: A computer server for receiving queries, analyzing them, and generating answers.

[0192] Natural language processing technology (NLP): Used to analyze inquiry content

[0193] Generative AI models: AI models that generate answers, such as OpenAI GPT-3

[0194] As a specific example, if a user sends a query such as "What dramas are recommended to watch now?", the server receives this message and uses NLP technology to extract keywords such as "recommended dramas." Next, a prompt such as "User question: What dramas are recommended to watch now?" is input into the generative AI model, which then generates an answer. The generated answer is returned to the user as "Currently popular dramas include 'XX'."

[0195] In this way, the system of the present invention provides an environment in which the user can obtain information related to the content he or she is viewing in real time, thereby improving user satisfaction.

[0196] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0197] Step 1:

[0198] Users can add an official account of a digital messaging service (e.g., LINE) as a friend on a communication device (such as a smartphone) by scanning a QR code or searching for the official account.

[0199] Step 2:

[0200] Users can input and send questions about content distribution on the LINE chat screen. For example, they might input and send, "What movie do you recommend I watch next?" The input data is the user's question or inquiry, and the output is message data sent to the server via the digital messaging service.

[0201] Step 3:

[0202] The server receives the user's message via the LINE Messaging API. The received message arrives at the server as unstructured data.

[0203] Step 4:

[0204] The server analyzes the received message using natural language processing (NLP) technology. Specifically, it extracts the user's intent and question from the message. The input data is the received message, and the output is structured data (e.g., keywords such as "recommended movies") as the analysis result.

[0205] Step 5:

[0206] The server inputs the analyzed question content into a generative AI model (e.g., OpenAI GPT-3) as a prompt. An example of a specific prompt is, "User asks: What movie would you recommend I watch next?" The generative AI model generates an answer based on this input data, and outputs a natural language answer (e.g., "Currently, a popular movie is 'XX'").

[0207] Step 6:

[0208] The server sends the generated response to the user using the LINE Messaging API. The input data is the response generated by the generative AI model, and the output is a message sent to the user.

[0209] Step 7:

[0210] The server accesses the database and checks the user's consultation history. It determines whether there are any free consultation slots remaining, and if there are, it proceeds to the next step. The input data is the user's consultation history, and the output is information about the remaining number of free consultation slots.

[0211] Step 8:

[0212] If the free consultation limit is exceeded, the server generates a message informing the user of a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan." The input data is information about whether the free limit has been exceeded, and the output is a message informing the user of a paid plan.

[0213] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0214] Here, the program processing will be explained in natural language in a form in which an emotion engine is combined with the system of the present invention.

[0215] Overall system configuration

[0216] In this system, users make inquiries via a messaging service on their communications device, and the server receives and analyzes the inquiries, generates a response using a generation AI, and then sends the response back to the user via the messaging service. Furthermore, a free consultation limit is set up so that users can easily make inquiries, and if the limit is exceeded, the system will guide users to paid plans. It also has a function to introduce experts if expert advice is needed. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotions and provide more personalized responses.

[0217] Program processing

[0218] 1. Add as a friend on LINE

[0219] Users can add the system's official account as a friend via a messaging service (such as LINE) on a communication device (such as a smartphone) by scanning a QR code or searching for the official account.

[0220] 2. Sending your consultation

[0221] Users can input and send their business or management-related inquiries on the LINE chat screen. For example, they can input and send "Please tell me how to increase employee motivation."

[0222] 3. Message Reception and Analysis

[0223] The server receives the user's message via the LINE Messaging API, and then analyzes the message using natural language processing (NLP) technology to extract the user's intent and question.

[0224] 4. Emotion analysis using an emotion engine

[0225] The server analyzes the user's emotions contained in the received message using an emotion engine, which identifies at least three types of emotions from the user's message: positive, negative, and neutral.

[0226] 5. Check the free consultation slots

[0227] The server accesses the database and checks the user's consultation history. It determines whether the received consultation is within the free consultation limit (3 times) for that month. If there are free consultation limits remaining, it proceeds to the next process.

[0228] 6. Answer generation using generative AI

[0229] The server then sends the analyzed question and emotional information as input data to the AI ​​generator, which then generates an answer. For example, the AI ​​generator might suggest specific methods and strategies for "how to increase employee motivation," taking the user's emotions into account.

[0230] 7. Submit your response

[0231] The server then formats the generated answer and sends it to the user via the messaging service (LINE), for example, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[0232] 8. What to do when the free quota is exceeded

[0233] If the free consultation limit is exceeded, the server generates a message informing the user about a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan."

[0234] 9. Introduction to professional consultants

[0235] When a user requests expert advice, the server will introduce the expert. Specifically, it will work with a consulting company to introduce the appropriate expert to the user. At that time, the server will notify the user of the expert's information and contact details via LINE.

[0236] Specific examples

[0237] For example, imagine a small business owner sends an inquiry via LINE asking, "Please tell me about the marketing strategy for our new product." The server receives this message, analyzes it, and extracts keywords such as "new product" and "marketing strategy." At the same time, the emotion engine reads "positive and proactive" emotions from the user's message. The generation AI generates a response based on this information, replying, "It's important to clarify your target market and promote your product using social media." The generated response also includes encouraging comments that match the user's positive emotions, making it more approachable and trustworthy. The user can then receive the response and implement it immediately.

[0238] In this way, this system provides an environment where small and medium-sized enterprises and sole proprietors can easily receive expert advice, and offers more accurate, personalized support that takes into account the user's emotions. This is expected to improve business efficiency and make it easier to solve management issues.

[0239] The processing flow will be explained below.

[0240] Step 1:

[0241] A user adds the service's official account as a friend on LINE.

[0242] Example: A user scans a service's QR code in the LINE app and becomes a friend of the official account.

[0243] Step 2:

[0244] The user enters the details of their inquiry on LINE and sends it.

[0245] Example: A user types and sends a message to LINE chat saying, "Please tell me about the marketing strategy for our new product."

[0246] Step 3:

[0247] The server receives the message via the LINE Messaging API.

[0248] Example: A message reception event is notified to the server via LINE's Webhook.

[0249] Step 4:

[0250] The server extracts and analyzes the received message content.

[0251] Example: Extract the keywords "new product," "marketing," and "strategy" from the content of received messages.

[0252] Step 5:

[0253] The server uses an emotion engine to analyze the user's emotion based on the message content.

[0254] Example: The emotion engine classifies the emotion of the received message as positive, negative, or neutral, and determines it as "positive and proactive."

[0255] Step 6:

[0256] The server retrieves the user's consultation history from the database and checks the free consultation limit.

[0257] Example: Check the number of consultations this month corresponding to the user ID in the database and determine whether there are any free consultation slots remaining.

[0258] Step 7:

[0259] If the server has free consultation slots remaining, it sends the inquiry and emotional information to the generation AI to generate an answer.

[0260] Example: Send a query to the generative AI in the form of "Users have positive feelings about the marketing strategy for a new product," and generate an answer.

[0261] Step 8:

[0262] The server takes the generated answer and formats it for sending to the user.

[0263] Example: The answer obtained from the AI ​​can be formulated as, "It is important to clarify your target market and promote using social media. Good luck!"

[0264] Step 9:

[0265] The server formats the response and sends it to the user using the LINE Messaging API.

[0266] Example: A message is sent to users saying, "It's important to identify your target market and promote your business through social media. Good luck!"

[0267] Step 10:

[0268] The server records in the database that one free consultation slot has been used and updates the remaining number of slots.

[0269] Example: Update the user's consultation history in the database and reduce the number of free consultations this month by one.

[0270] Step 11:

[0271] If there are no free consultation slots remaining, the server generates a message informing the user of a paid plan and sends it to the user.

[0272] Example: A message is sent to the user saying, "You have used up your free consultation slots for this month. Please consider a paid plan."

[0273] Step 12:

[0274] If a user needs detailed expert advice, they can send a message on LINE saying, "I would like to be introduced to an expert."

[0275] Example: A user types "I would like to be introduced to an expert" in a LINE chat and sends it.

[0276] Step 13:

[0277] The server receives the request for an expert introduction and contacts the partner consulting firm.

[0278] Example: Search for experts who fit the user's needs through a consulting company's API and initiate the referral process.

[0279] Step 14:

[0280] The server receives the expert's information and generates a message to notify the user.

[0281] Example: Generate the message "If you need professional advice, please contact a professional consultant via this link."

[0282] Step 15:

[0283] The server generates a message and sends it to the user via the LINE Messaging API.

[0284] Example: Send the above informational message to the user and provide a way to contact an expert.

[0285] Example 2

[0286] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0287] When receiving business consultations or management advice over the Internet, it is necessary to properly analyze the user's emotions and the content of the consultation and provide an effective answer. However, conventional systems have been unable to provide individual responses that take the user's emotions into consideration or manage free consultation quotas adequately, making it difficult to provide high-quality personalized service. Another issue is the complicated process of obtaining expert advice when needed.

[0288] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0289] In this invention, the server includes: a means for a user to send an inquiry via a messaging service using a communication terminal; a means for the server to receive the inquiry via the messaging service; a means for the server to analyze the inquiry using natural language processing technology and generate an answer using a generative AI model; a means for the server to send the generated answer to the user via the messaging service; a means for the server to analyze the user's emotions contained in the message using an emotion engine; and a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded. This makes it possible to provide personalized answers that take the user's emotions into consideration and efficiently manage the user's free consultation limit.

[0290] A "communication terminal" is a device that can use messaging services via the Internet, and specifically refers to smartphones, tablets, PCs, etc.

[0291] "Messaging Service" means an application or platform that enables users to send and receive text messages and multimedia content over the Internet.

[0292] A "server" is a computer system responsible for receiving queries from users, analyzing them, and generating responses.

[0293] "Natural language processing technology" refers to technology that enables computers to understand and process human language, and includes technology for analyzing text and extracting intent.

[0294] A "generative AI model" refers to an artificial intelligence technology that generates natural language answers or content based on specific input data.

[0295] An "emotion engine" is a system that analyzes user emotions from text data and identifies emotion categories such as positive, negative, and neutral.

[0296] The "free consultation quota" refers to the number of times or time limit that a user can receive free consultation within a certain period of time.

[0297] "Paid Plan" refers to the fee structure or plan that applies when a user requests additional consultations after exceeding the free consultation quota.

[0298] An "expert" refers to a person who has advanced knowledge and experience in a particular field and can provide users with specialized advice and consulting.

[0299] In the system of the present invention, a user makes an inquiry via a messaging service using a communication terminal, the server receives and analyzes the inquiry, generates a response using a generative AI model, and sends the response back to the user via the messaging service. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotions and provide personalized responses.

[0300] Hardware and software used

[0301] Music recommendation system: LINE Messaging API, NLP tools (e.g., Google® Cloud Natural Language API), generative AI (e.g., OpenAI GPT-3), emotion engine (e.g., IBM Watson® Tone Analyzer)

[0302] Communication devices: smartphones, tablets, computers, etc.

[0303] Database: Relational database such as MySQL (registered trademark), PostgreSQL, etc.

[0304] Data processing flow and explanation

[0305] 1. Add as a friend on LINE

[0306] Users launch the LINE app on their smartphone or other communication device and add the system's official account as a friend. At this point, they scan the QR code or search for and add the official account, and an automatic response message is displayed.

[0307] 2. Sending your consultation

[0308] The user enters the content of their business or management consultation on the LINE chat screen and sends it. For example, they can type "Please tell me how to increase employee motivation." The message is then forwarded to the system's server via the LINE server.

[0309] 3. Message Reception and Analysis

[0310] The server receives messages sent by users using the LINE Messaging API. The received messages are then analyzed using natural language processing (NLP) technology. During this analysis stage, NLP tools such as Google Cloud Natural Language API are used to extract the message's intent and keywords.

[0311] 4. Emotion analysis using an emotion engine

[0312] The server uses an emotion engine to analyze the emotions contained in the user's message. The emotion engine uses IBM Watson Tone Analyzer to identify positive, negative, neutral, and other emotions from the message.

[0313] 5. Check the free consultation slots

[0314] The server accesses a database (e.g., MySQL) and checks the user's consultation history. It determines whether there are any free consultation slots remaining, and if so, proceeds to the next step.

[0315] 6. Answer generation using generative AI

[0316] The server then sends the analyzed question and emotional information as a prompt to a generative AI model. Using generative AI such as OpenAI's GPT-3, the server generates an appropriate answer for the user. For example, the server might suggest specific methods or strategies, such as, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[0317] 7. Submit your response

[0318] The server formats the generated response and sends it to the user again using the LINE Messaging API. The user can then view the response on the LINE chat screen and immediately respond or put it into practice.

[0319] 8. What to do when the free quota is exceeded

[0320] If the free consultation limit is exceeded, the server generates a message informing the user about a paid plan. The message, which will be sent to the user again via LINE, will say something like, "You have used up your free consultation limit for this month. Please consider a paid plan."

[0321] 9. Introduction to professional consultants

[0322] If the user requests expert advice, the server will work with a consulting company to introduce the expert. In this case, the server will notify the user via LINE of the expert's information and contact details. A message such as "We will introduce you to a consultant specializing in business strategy. Please contact the following address for details" will be sent.

[0323] Specific examples

[0324] For example, if a small business owner sends an inquiry on LINE asking, "Please tell me about the marketing strategy for a new product," the server receives and analyzes this message and uses a generation AI to suggest specific marketing methods. The emotion engine reads the user's positive emotions, and the generation AI makes suggestions that include encouraging comments that match those emotions. The generated answer is specific, such as "It is important to clarify the target market and promote using social media," and is easy for the user to implement.

[0325] In this way, this system provides an environment where small and medium-sized enterprises and sole proprietors can easily receive expert advice and can provide highly accurate personalized support that takes into account the user's emotions, which is expected to improve business efficiency and solve management issues.

[0326] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0327] Program processing flow and detailed explanation

[0328] Step 1:

[0329] A user adds the official account of the system as a friend via a messaging service on a communication terminal.

[0330] Input: User scans QR code or searches for official account

[0331] Specific operation: The user launches the LINE app and either scans the official account's QR code or searches for the account by name to add it as a friend.

[0332] Step 2:

[0333] A user uses a communication terminal to send the consultation content on a messaging service.

[0334] Input: Text of the consultation (e.g., "Please tell me how to motivate my employees.")

[0335] Specific operation: The user enters the content of the consultation on the LINE chat screen and taps the send button. The message is then forwarded to the system server via the LINE server.

[0336] Step 3:

[0337] The server receives the user's message using the LINE Messaging API.

[0338] Input: Consult message sent

[0339] Specific operation: The server monitors the LINE Messaging API and receives new messages from users. The received messages are stored in text format.

[0340] Step 4:

[0341] The server uses natural language processing (NLP) techniques to analyze the message and extract the question.

[0342] Input: Received message text

[0343] How it works: The server calls NLP tools such as Google Cloud Natural Language API to extract the intent of the message and key keywords, such as "employee motivation" and "how to increase it."

[0344] Output: Extracted intents and keywords

[0345] Step 5:

[0346] The server uses an emotion engine to analyze the user's emotions.

[0347] Input: Received message text

[0348] What it does: Uses a sentiment engine (such as IBM Watson Tone Analyzer) to identify positive, negative, or neutral sentiment in a message. For example, the phrase "Tell me how" can be interpreted as positive sentiment.

[0349] Output: Sentiment analysis result (e.g., positive)

[0350] Step 6:

[0351] The server checks the user's consultation history and determines whether there are any free consultation slots remaining.

[0352] Input: User ID, consultation history

[0353] Specific operation: The server accesses a database (e.g., MySQL) and retrieves the consultation history associated with the user ID. Based on the history, it determines whether there are any free consultation slots remaining for that month.

[0354] Output: Free consultation slots remaining

[0355] Step 7:

[0356] The server uses a generative AI model to generate an answer based on the question and emotional information.

[0357] Input: Keywords in the question, sentiment analysis results

[0358] How it works: The server sends the analysis results as prompts to a generative AI model such as OpenAI's GPT-3, which then generates an appropriate response. For example, it might generate a message like, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[0359] Output: Generated answer text

[0360] Step 8:

[0361] The server formats the generated response and sends it to the user, again via the messaging service.

[0362] Input: Generated answer text

[0363] Specific operation: The server formats the reply text and sends it to the user using the LINE Messaging API. The user can then view the reply on the LINE chat screen.

[0364] Output: Message sent to the user

[0365] Step 9:

[0366] If the server exceeds the free consultation limit, it will send a message informing you about paid plans.

[0367] Input: Check if free consultation limit has been exceeded

[0368] Specific operation: If the free consultation limit is exceeded, the server generates a notification message and sends it to the user via LINE, stating that "You have used up your free consultation limit for this month. Please consider a paid plan."

[0369] Output: Paid plan information message

[0370] Step 10:

[0371] If the user requests expert advice, the server sends expert referral information.

[0372] Input: User's referral request

[0373] Specific operation: The server works with the consulting company to identify an appropriate expert. The server then notifies the user via LINE of the expert's information and contact details. A message such as "We will introduce you to a consultant specializing in business strategy. Please contact the following number for more information" is sent.

[0374] Output: Expert introduction information message

[0375] (Application example 2)

[0376] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0377] In production sites, it can be difficult for workers to obtain appropriate advice in real time. Quick and accurate access to information is especially important when operating new machinery or troubleshooting. Furthermore, if the answers provided do not take into consideration the worker's feelings, it can cause stress and confusion. Furthermore, to improve productivity, an optimal billing model for worker inquiries is also necessary. Conventional systems make it difficult to solve all of these issues at once.

[0378] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0379] In this invention, the server includes: means for a user to send an inquiry via a messaging service using a communication terminal; means for the server to receive the inquiry via the messaging service; means for the server to analyze the inquiry and generate an answer using a generation AI; means for the server to send the generated answer to the user via the messaging service; means for the server to analyze the user's emotion contained in the inquiry using an emotion engine; and means for monitoring the number of inquiries and introducing paid plans when a predetermined free consultation limit is exceeded. This allows workers to receive appropriate advice in real time and enables individual responses based on EMOTION, thereby reducing stress and improving productivity.

[0380] A "user" is someone who accesses and queries the system.

[0381] "Communication terminal" refers to a device that can connect to the Internet, such as a smartphone, tablet, or PC.

[0382] "Messaging Service" is an application service for sending and receiving messages over the Internet.

[0383] An "inquiry" refers to a question or request made by a user to the system.

[0384] A "server" is a computer system that processes and stores data over a network.

[0385] "Generative AI" refers to artificial intelligence technology that analyzes and generates natural language.

[0386] The "emotion engine" is dedicated software for analyzing the emotions contained in users' messages.

[0387] "Monitoring the number of times" means recording the frequency with which users use the system and checking the number of times they use it within a specific period of time.

[0388] "Free consultation quota" refers to the number of times and scope of services that a user can use free of charge.

[0389] "Paid Plan" refers to a service for which a fee is charged for use beyond the free limit.

[0390] An "expert" is someone who has advanced knowledge or skills in a particular field.

[0391] "Detailed advice" refers to specific, practical advice based on specialized knowledge.

[0392] "Operating over the Internet" means exchanging information or providing services using the Internet.

[0393] Here, we will explain how the system of the present invention is applied to a production site. Specifically, we will explain how to install a productivity improvement support application equipped with an emotion analysis function on a factory robot.

[0394] Overall system configuration

[0395] In this system, users (workers) make inquiries using a messaging service (e.g., LINE) on their communication devices, which are then received and analyzed by a server. The server then uses the analysis results and emotion engine data to utilize a generative AI model to generate a response, which is then sent back to the user via the messaging service. There is also a free consultation limit, and if the limit is exceeded, a function is included to introduce paid plans. Furthermore, there is also a function to introduce experts if expert advice is needed.

[0396] Hardware and Software Used

[0397] Hardware:

[0398] Internet-connected factory robots (e.g., industrial robots from Fanuc and KUKA)

[0399] software:

[0400] Messaging API (e.g., LINE Messaging API)

[0401] Natural Language Processing (NLP) engines (e.g., SpaCy or Google Cloud NLP)

[0402] Sentiment analysis engine (e.g., Emotion API)

[0403] Generative AI models (e.g., OpenAI's GPT-4®)

[0404] A database (e.g., MySQL or MongoDB)

[0405] Program processing explanation

[0406] 1. Add as a friend on LINE

[0407] The user (worker) uses LINE on their smartphone to add the factory robot's official account as a friend by scanning the QR code or by searching for the official account.

[0408] 2. Submit an inquiry

[0409] Users can type and send questions about productivity or work content on the LINE chat screen. For example, they can type and send, "Please tell me how to troubleshoot the machine."

[0410] 3. Message Reception and Analysis

[0411] The server receives the user's message through the LINE Messaging API and analyzes the message content using an NLP engine.

[0412] 4. Analysis by Emotion Engine

[0413] The server analyzes the user's emotions from the received message using the Emotion API and identifies whether the emotion is positive, negative, or neutral.

[0414] 5. Answer generation using generative AI

[0415] The server sends the analyzed question content and emotional information as input data to a generative AI model such as GPT-4, which then generates a specific answer.

[0416] 6. Formatting and Submitting Your Answer

[0417] The server formats the generated answer and sends it to the user via LINE, for example, "When troubleshooting a machine, we recommend first checking the power status and then rechecking the connections."

[0418] Examples and prompts

[0419] For example, imagine a worker sends an inquiry via LINE saying, "I want to know how to operate a new machine." The server receives this message, analyzes it, and extracts keywords such as "new machine" and "how to operate." At the same time, the emotion engine reads the user's emotion of "confusion" from the message. The generative AI uses this information to generate a response that is specific and reassuring, such as, "It seems you're having trouble operating this new machine. I'll start by explaining the basics, so please stay calm and proceed. It's easy to operate. First, turn it on, and then..."

[0420] Prompt Sentence Examples

[0421] User message: "I want to know how to operate a new machine."

[0422] Sentiment analysis result: "Confused"

[0423] Prompt for the generative AI model: The user is confused and wants to know how to operate a new machine. Please generate a specific, easy-to-understand answer that provides a sense of security.

[0424] This allows workers to obtain quick and accurate information, and because the information is emotionally sensitive, they can work on solving problems with peace of mind.

[0425] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0426] Step 1:

[0427] A user uses LINE on a communication device to add the factory robot's official account as a friend. To do this, the user scans the QR code or searches for the official account and adds it. The user is then ready to make an inquiry. The input is "LINE official account information" and "user's LINE account," and the output is "Friend addition completed."

[0428] Step 2:

[0429] A user types and sends a question about productivity or work content on the LINE chat screen. For example, "Please tell me how to troubleshoot a machine." The input is the "user's question," and the output is "the server receiving the message."

[0430] Step 3:

[0431] The server receives the user's message via the LINE Messaging API. The server analyzes the received message using an NLP engine (for example, SpaCy or Google Cloud NLP) to extract the question keywords and intent. The input is the "user's message" and the output is the "analyzed question content."

[0432] Step 4:

[0433] The server uses an emotion engine (e.g., Emotion API) to analyze the emotions contained in the user's message. The emotion engine identifies at least three types of emotions from the message: positive, negative, and neutral. The input is the "user's message" and the "analyzed question content," and the output is the "analyzed emotion information."

[0434] Step 5:

[0435] The server sends the analyzed question content and emotional information as input data to a generative AI model (for example, OpenAI's GPT-4), which generates a specific answer. The generative AI model generates an answer based on the prompt text. The input is the "analyzed question content" and "analyzed emotional information," and the output is the "generated answer."

[0436] Step 6:

[0437] The server formats the generated answer and sends it to the user via LINE. For example, it might reply, "When troubleshooting a machine, we recommend first checking the power status and then rechecking the connections." The input is the "generated answer," and the output is "sent to the user."

[0438] Step 7:

[0439] The server monitors the number of inquiries made by the user, and if the number of free consultations exceeds a certain limit (for example, three), it generates a message informing the user of a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan." The inputs are the "number of inquiries" and the "free consultation limit limit," and the output is "send information about a paid plan."

[0440] Step 8:

[0441] When a user requests detailed advice from an expert, the server initiates a procedure to introduce an appropriate expert. Specifically, it retrieves relevant expert information from the database and provides it to the user via LINE. The input is the user's request for expert introduction and the expert's database information, and the output is sending the expert introduction information.

[0442] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0443] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0444] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0445] [Second embodiment]

[0446] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0447] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0448] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0449] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0450] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0451] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0452] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0453] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0454] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0455] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0456] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0457] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0458] Here, the program processing will be explained in natural language to explain how the system of the present invention can be specifically implemented.

[0459] Overall system configuration

[0460] In this system, users make inquiries via a messaging service on their communication device, and the server receives and analyzes the inquiries, generates a response using the AI, and then sends the response back to the user via the messaging service. Furthermore, a free consultation limit is set up so that users can easily make inquiries, and if the limit is exceeded, the system will guide users to paid plans. It also has a function to introduce experts when expert advice is needed.

[0461] Program processing

[0462] 1. Add as a friend on LINE

[0463] Users can add the system's official account as a friend via a messaging service (such as LINE) on a communication device (such as a smartphone) by scanning a QR code or searching for the official account.

[0464] 2. Sending your consultation

[0465] Users can input and send their business or management-related inquiries on the LINE chat screen. For example, they can input and send "Please tell me how to increase employee motivation."

[0466] 3. Message Reception and Analysis

[0467] The server receives the user's message via the LINE Messaging API, and then analyzes the message using natural language processing (NLP) technology to extract the user's intent and question.

[0468] 4. Check the free consultation slots

[0469] The server accesses the database and checks the user's consultation history. It determines whether the received consultation is within the free consultation limit (3 times) for that month. If there are free consultation limits remaining, it proceeds to the next process.

[0470] 5. Answer generation using generative AI

[0471] The server inputs the analyzed question content into the generation AI to generate an answer. For example, the generation AI may suggest specific methods and strategies for "how to increase employee motivation."

[0472] 6. Submit your response

[0473] The server then sends the generated answer to the user using the LINE Messaging API. For example, it could say, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[0474] 7. What to do when the free limit is exceeded

[0475] If the free consultation limit is exceeded, the server generates a message informing the user about a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan."

[0476] 8. Introduction to professional consultants

[0477] When a user requests expert advice, the server will introduce the expert. Specifically, it will work with a consulting company to introduce the appropriate expert to the user. At that time, the server will notify the user of the expert's information and contact details via LINE.

[0478] Specific examples

[0479] For example, imagine a small business owner sends an inquiry via LINE asking, "Please tell me about the marketing strategy for our new product." The server receives this message, analyzes it, and extracts keywords such as "new product" and "marketing strategy." The AI ​​then generates a response based on this information, replying, "It's important to clarify your target market and use social media for promotion." The user can then receive the response and implement it immediately.

[0480] In this way, this system provides an environment where small and medium-sized enterprises and sole proprietors can easily receive professional advice, which is expected to improve business efficiency and make it easier to resolve management issues.

[0481] The processing flow will be explained below.

[0482] Step 1:

[0483] A user adds the service's official account as a friend on LINE.

[0484] Example: A user scans a service's QR code in the LINE app and becomes a friend of the official account.

[0485] Step 2:

[0486] The user enters the details of their inquiry on LINE and sends it.

[0487] Example: A user types and sends a message to LINE chat saying, "Please tell me your marketing strategy."

[0488] Step 3:

[0489] The server receives the message via the LINE Messaging API.

[0490] Example: A message reception event is notified to the server via LINE's Webhook.

[0491] Step 4:

[0492] The server extracts the message content and analyzes it using natural language processing (NLP).

[0493] Example: Extract the keywords "marketing" and "strategy" from the content of received messages.

[0494] Step 5:

[0495] The server retrieves the user's consultation history from the database and checks the free consultation limit.

[0496] Example: Check the number of free consultations this month by looking up the consultation history corresponding to the user ID in the database.

[0497] Step 6:

[0498] If the server has free consultation slots remaining, it sends the inquiry to the generation AI to generate an answer.

[0499] Example: A generative AI model is sent a query in the form of "Please give me some advice on marketing strategy," and the AI ​​generates a specific answer.

[0500] Step 7:

[0501] The server takes the generated answer and formats it for sending to the user.

[0502] Example: The answer obtained from the AI ​​is formatted as, "It is important to clarify the target market and promote using social media."

[0503] Step 8:

[0504] The server formats the response and sends it to the user using the LINE Messaging API.

[0505] Example: A user receives the message, "To answer your questions about marketing strategy: It's important to identify your target market and promote your business through social media."

[0506] Step 9:

[0507] The server records in the database that one free consultation slot has been used and updates the remaining number of slots.

[0508] Example: Update the user's consultation history in the database and reduce the number of free consultations this month by one.

[0509] Step 10:

[0510] If there are no free consultation slots remaining, the server generates a message informing the user of a paid plan and sends it to the user.

[0511] Example: A message is sent to the user saying, "You have used up your free consultation slots for this month. Please consider a paid plan."

[0512] Step 11:

[0513] If a user needs detailed expert advice, they can send a message on LINE saying, "I would like to be introduced to an expert."

[0514] Example: A user types "I would like to be introduced to an expert" in a LINE chat and sends it.

[0515] Step 12:

[0516] The server receives the request for an expert introduction and contacts the partner consulting firm.

[0517] Example: Search for experts who fit the user's needs through a consulting company's API and initiate the referral process.

[0518] Step 13:

[0519] The server receives the expert's information and generates a message to notify the user.

[0520] Example: Generate the message "If you need professional advice, please contact a professional consultant via this link."

[0521] Step 14:

[0522] The server generates a message and sends it to the user via the LINE Messaging API.

[0523] Example: Send the above informational message to the user and provide a way to contact an expert.

[0524] Example 1

[0525] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0526] In modern society, there are many situations in which professional advice on business and management is needed, but cost and time constraints make it difficult to easily consult with experts. Small and medium-sized enterprises and sole proprietors in particular need a way to receive professional advice quickly and affordably. While providing a free consultation limit can help reduce costs, there is also a need for a system that directs users to a paid plan once a certain number of inquiries have been made. Furthermore, when professional advice is needed, there is also a need for referrals to appropriate experts.

[0527] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0528] In this invention, the server includes: a means for a user to send an inquiry via a messaging service using a wireless communication device; a means for the server to receive the inquiry via the messaging service; a means for the server to analyze the inquiry using natural language processing technology and generate an answer using a generative AI model; a means for the server to send the generated answer to the user via the messaging service; a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded; and a means for the server to store the user's consultation history in a database. This allows users to easily receive professional advice, and smoothly guides them to a paid plan when the free consultation limit is exceeded. Furthermore, when expert advice is needed, appropriate experts can be introduced.

[0529] A "user" is an entity that accesses the system and makes a query.

[0530] "Wireless communication device" refers to a device that transmits and receives data using wireless communication technology. Examples include smartphones and tablets.

[0531] "Messaging Service" means software or applications that enable the sending and receiving of messages over the Internet. An example is an instant messenger application.

[0532] "Server" refers to the central computer system that handles queries, analyzes data, records data, and generates responses.

[0533] "Natural language processing technology" refers to technology for understanding and analyzing human language and extracting intent. Examples include grammatical analysis and semantic analysis.

[0534] A "generative AI model" refers to an artificial intelligence model that generates answers or text in natural language based on input data. Examples include GPT-3 and other large-scale language models.

[0535] A "database" refers to a storage system that can efficiently store, manage, and retrieve data.

[0536] The "free consultation quota" refers to the limit on the number of times a user can receive free consultation within a certain period of time.

[0537] "Paid Plan" refers to a service plan in which a user is charged if the free consultation limit is exceeded.

[0538] An "expert" is a person or institution with in-depth knowledge and experience in a particular field.

[0539] "Consultation history" refers to historical information such as inquiries and responses made by the user.

[0540] In the system of the present invention, a user makes an inquiry via a messaging service using a wireless communication device, a server receives and analyzes the inquiry, generates an answer using a generative AI model, and sends the answer back to the user via the messaging service. This system also includes a mechanism that provides a free consultation limit, and when the free limit is exceeded, introduces paid plans, and a function that introduces experts when expert advice is needed.

[0541] Hardware and software used

[0542] A user uses a messaging application (e.g., LINE) on a wireless communication device (e.g., a smartphone or tablet). The server receives and analyzes these messages and uses a generative AI model (e.g., GPT-3) to generate appropriate responses. The server also uses the LINE Messaging API to receive messages and BERT or similar natural language processing technology.

[0543] Specific examples of program processing

[0544] A user sends a query via LINE, asking, "Please tell me how to motivate employees." The server receives this message via the LINE Messaging API and uses natural language processing technology to extract the keywords "employee," "motivation," and "method." The server then inputs the analyzed question content into a generative AI model (GPT-3) as a prompt sentence to generate a specific answer. The generated answer (for example, "Establishing a transparent evaluation system and providing regular feedback are effective") is then sent to the user again via the LINE Messaging API.

[0545] The system's unique feature is that it can provide users with expert advice in a simple and fast way. It also reduces costs by setting up a free consultation quota, allowing users to smoothly transition to paid consultations. Furthermore, it can provide higher quality services by introducing users to experts when expert advice is needed.

[0546] Prompt Sentence Examples

[0547] For example, the following prompts can be fed into a generative AI model:

[0548] "How can I motivate my employees?"

[0549] In this way, the system of the present invention provides an environment in which small and medium-sized enterprises and sole proprietors can easily receive professional advice, and supports the improvement of business efficiency and the resolution of management issues.

[0550] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0551] Step 1:

[0552] A user can use a messaging service (e.g., LINE) on a wireless communication device (e.g., a smartphone) to add the system's official account as a friend by scanning the QR code or by searching for the account name and tapping "Add to Friend."

[0553] Input: User's friend addition operation

[0554] Output: The official account is added to the user's friends list.

[0555] Specific operation: The user scans the official account's QR code with the camera, the LINE app automatically redirects to the official account's page, and taps the "Add friend" button.

[0556] Step 2:

[0557] Users open the chat screen with the official LINE account, enter the details of their business or management needs, and tap the send button. For example, they could type, "Please tell me how to increase employee motivation."

[0558] Input: User's question

[0559] Output: A query message is sent to the server

[0560] Specific actions: The user types "Please tell me how to motivate employees" into the LINE text box and taps the "Send" button.

[0561] Step 3:

[0562] The server receives messages sent by users via the LINE Messaging API, then uses natural language processing technology to analyze the content of the user's question and extract important keywords and intent.

[0563] Input: Question message from user

[0564] Output: Parsed keywords and intent

[0565] Specific operation: The server receives the message "Please tell me how to motivate employees" using the LINE Messaging API, and extracts keywords such as "employee," "motivation," and "method" using natural language processing technology (e.g., the BERT model).

[0566] Step 4:

[0567] The server accesses the database, checks the user's consultation history, and determines whether the received consultation is within the free consultation limit for that month (e.g., 3 consultations).

[0568] Input: Parsed keywords and user ID

[0569] Output: Result of remaining free consultation slots

[0570] Specific operation: The server searches the database using the user ID as a key and confirms that the number of consultations for the current month has still not exceeded two.

[0571] Step 5:

[0572] The server converts the parsed question content into a prompt and inputs it into a generative AI model (e.g., GPT-3), which then generates an appropriate answer to the question.

[0573] Input: Parsed question prompt

[0574] Output: The answer generated by the generative AI model

[0575] Specific operation: The server inputs the prompt "Please tell me how to motivate employees" into the generating AI model, and the AI ​​generates an answer such as "Establishing a transparent evaluation system and providing regular feedback are effective."

[0576] Step 6:

[0577] The server sends the generated response to the user using the LINE Messaging API.

[0578] Input: Answer from a generative AI model

[0579] Output: A reply message is sent to the user

[0580] Specific operation: The server sends a response to the user via the LINE API stating that "It would be effective to establish a transparent evaluation system and provide regular feedback."

[0581] Step 7:

[0582] If the free consultation limit is exceeded, the server generates a message informing the user of the paid plan and sends it via LINE.

[0583] Input: Number of consultations judged

[0584] Output: Paid plan information message

[0585] Specific operation: The server generates a message saying "You have used up this month's free consultation quota. Please consider a paid plan" and sends it to the user.

[0586] Step 8:

[0587] When a user requests professional advice, the server will introduce them to an expert. The server will work with a consulting company to obtain information on appropriate experts and notify the user via LINE.

[0588] Input: User request for expert referral

[0589] Output: Expert information and contact details

[0590] Specific operation: The server calls the consulting company's API, retrieves information about the appropriate expert, and sends the expert's contact information to the user along with a message such as "Please contact our expert."

[0591] (Application example 1)

[0592] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0593] In conventional content distribution services, users have limited means to ask questions or obtain related information in real time about the content they are viewing, making it difficult to improve the user experience. Furthermore, when users ask many questions, it is difficult to provide appropriate answers to some of the questions quickly. Furthermore, when the number of free assistance sessions is exceeded, there is a lack of guidance on appropriate paid plans.

[0594] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0595] In this invention, the server includes: means for a user to send an inquiry via a digital message service on a communication terminal; means for the server to receive the inquiry via the digital message service; means for the server to analyze the inquiry and generate an answer using a generative AI model; means for the server to send the generated answer to the user via the digital message service; and means for monitoring the number of inquiries, introducing paid plans when a predetermined free consultation limit is exceeded, and providing an automatic answer function for questions about content distribution. This allows users to receive quick and accurate answers to their questions, improving their experience.

[0596] "User" means an individual or entity that makes an inquiry using the Digital Message Service.

[0597] A "communication terminal" is an electronic device that a user uses to send and receive messages, and specific examples include smartphones and tablets.

[0598] "Digital message service" refers to an application that sends and receives messages over the Internet, and specifically includes messaging applications.

[0599] A "server" is a computer system that receives messages from users, analyzes them, generates answers using a generative AI model, and sends them back to the user.

[0600] A "generative AI model" is a type of artificial intelligence that uses natural language processing technology to generate answers to user inquiries.

[0601] The "means for generating an answer" is the process by which the server utilizes the generative AI model to generate an appropriate answer to the user's inquiry.

[0602] The "free consultation limit" is a limit on the number of inquiries a user can receive free of charge.

[0603] "Paid Plan" means a plan for additional assistance or services that is provided to a User for a fee when the free consultation limit is exceeded.

[0604] A "content distribution question" is an inquiry that asks for information related to a movie, drama, or other digital content that a user is watching.

[0605] Here, we will explain detailed embodiments of the present invention. The present invention involves a user making an inquiry using a digital messaging service (e.g., LINE), a server receiving the inquiry, generating an answer using a generative AI model, and providing the answer to the user again via the digital messaging service. It also has a function to monitor the number of inquiries made by the user and, if the free consultation limit is exceeded, introduce paid plans.

[0606] Specifically, a user first uses a communication device such as a smartphone or tablet to add the official account of the digital messaging service as a friend. Then, via a messaging application such as LINE, the user can type and send a question about the content distribution on the chat screen. For example, a question like, "What movie do you recommend I watch next?"

[0607] The server receives the message from the user through the LINE Messaging API. The server analyzes the message and uses natural language processing (NLP) technology to understand its content. It then uses the analyzed information to generate an appropriate response using a generative AI model (e.g., OpenAI GPT-3).

[0608] The generated answer is then sent to the user again using the LINE Messaging API. For example, a specific answer such as "A popular movie right now is 'XX'" is sent. The server also monitors the number of questions the user has asked, and if the free consultation limit (for example, three times a month) is exceeded, the system automatically introduces users to a paid plan.

[0609] The implementation of this system uses the following hardware and software:

[0610] Communication devices: smartphones, tablets, etc.

[0611] Digital messaging services: Messaging applications such as LINE

[0612] Server: A computer server for receiving queries, analyzing them, and generating answers.

[0613] Natural language processing technology (NLP): Used to analyze inquiry content

[0614] Generative AI models: AI models that generate answers, such as OpenAI GPT-3

[0615] As a specific example, if a user sends a query such as "What dramas are recommended to watch now?", the server receives this message and uses NLP technology to extract keywords such as "recommended dramas." Next, a prompt such as "User question: What dramas are recommended to watch now?" is input into the generative AI model, which then generates an answer. The generated answer is returned to the user as "Currently popular dramas include 'XX'."

[0616] In this way, the system of the present invention provides an environment in which the user can obtain information related to the content he or she is viewing in real time, thereby improving user satisfaction.

[0617] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0618] Step 1:

[0619] Users can add an official account of a digital messaging service (e.g., LINE) as a friend on a communication device (such as a smartphone) by scanning a QR code or searching for the official account.

[0620] Step 2:

[0621] Users can input and send questions about content distribution on the LINE chat screen. For example, they might input and send, "What movie do you recommend I watch next?" The input data is the user's question or inquiry, and the output is message data sent to the server via the digital messaging service.

[0622] Step 3:

[0623] The server receives the user's message via the LINE Messaging API. The received message arrives at the server as unstructured data.

[0624] Step 4:

[0625] The server analyzes the received message using natural language processing (NLP) technology. Specifically, it extracts the user's intent and question from the message. The input data is the received message, and the output is structured data (e.g., keywords such as "recommended movies") as the analysis result.

[0626] Step 5:

[0627] The server inputs the analyzed question content into a generative AI model (e.g., OpenAI GPT-3) as a prompt. An example of a specific prompt is, "User asks: What movie would you recommend I watch next?" The generative AI model generates an answer based on this input data, and outputs a natural language answer (e.g., "Currently, a popular movie is 'XX'").

[0628] Step 6:

[0629] The server sends the generated response to the user using the LINE Messaging API. The input data is the response generated by the generative AI model, and the output is a message sent to the user.

[0630] Step 7:

[0631] The server accesses the database and checks the user's consultation history. It determines whether there are any free consultation slots remaining, and if there are, it proceeds to the next step. The input data is the user's consultation history, and the output is information about the remaining number of free consultation slots.

[0632] Step 8:

[0633] If the free consultation limit is exceeded, the server generates a message informing the user of a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan." The input data is information about whether the free limit has been exceeded, and the output is a message informing the user of a paid plan.

[0634] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0635] Here, the program processing will be explained in natural language in a form in which an emotion engine is combined with the system of the present invention.

[0636] Overall system configuration

[0637] In this system, users make inquiries via a messaging service on their communications device, and the server receives and analyzes the inquiries, generates a response using a generation AI, and then sends the response back to the user via the messaging service. Furthermore, a free consultation limit is set up so that users can easily make inquiries, and if the limit is exceeded, the system will guide users to paid plans. It also has a function to introduce experts if expert advice is needed. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotions and provide more personalized responses.

[0638] Program processing

[0639] 1. Add as a friend on LINE

[0640] Users can add the system's official account as a friend via a messaging service (such as LINE) on a communication device (such as a smartphone) by scanning a QR code or searching for the official account.

[0641] 2. Sending your consultation

[0642] Users can input and send their business or management-related inquiries on the LINE chat screen. For example, they can input and send "Please tell me how to increase employee motivation."

[0643] 3. Message Reception and Analysis

[0644] The server receives the user's message via the LINE Messaging API, and then analyzes the message using natural language processing (NLP) technology to extract the user's intent and question.

[0645] 4. Emotion analysis using an emotion engine

[0646] The server analyzes the user's emotions contained in the received message using an emotion engine, which identifies at least three types of emotions from the user's message: positive, negative, and neutral.

[0647] 5. Check the free consultation slots

[0648] The server accesses the database and checks the user's consultation history. It determines whether the received consultation is within the free consultation limit (3 times) for that month. If there are free consultation limits remaining, it proceeds to the next process.

[0649] 6. Answer generation using generative AI

[0650] The server then sends the analyzed question and emotional information as input data to the AI ​​generator, which then generates an answer. For example, the AI ​​generator might suggest specific methods and strategies for "how to increase employee motivation," taking the user's emotions into account.

[0651] 7. Submit your response

[0652] The server then formats the generated answer and sends it to the user via the messaging service (LINE), for example, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[0653] 8. What to do when the free quota is exceeded

[0654] If the free consultation limit is exceeded, the server generates a message informing the user about a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan."

[0655] 9. Introduction to professional consultants

[0656] When a user requests expert advice, the server will introduce the expert. Specifically, it will work with a consulting company to introduce the appropriate expert to the user. At that time, the server will notify the user of the expert's information and contact details via LINE.

[0657] Specific examples

[0658] For example, imagine a small business owner sends an inquiry via LINE asking, "Please tell me about the marketing strategy for our new product." The server receives this message, analyzes it, and extracts keywords such as "new product" and "marketing strategy." At the same time, the emotion engine reads "positive and proactive" emotions from the user's message. The generation AI generates a response based on this information, replying, "It's important to clarify your target market and promote your product using social media." The generated response also includes encouraging comments that match the user's positive emotions, making it more approachable and trustworthy. The user can then receive the response and implement it immediately.

[0659] In this way, this system provides an environment where small and medium-sized enterprises and sole proprietors can easily receive expert advice, and offers more accurate, personalized support that takes into account the user's emotions. This is expected to improve business efficiency and make it easier to solve management issues.

[0660] The processing flow will be explained below.

[0661] Step 1:

[0662] A user adds the service's official account as a friend on LINE.

[0663] Example: A user scans a service's QR code in the LINE app and becomes a friend of the official account.

[0664] Step 2:

[0665] The user enters the details of their inquiry on LINE and sends it.

[0666] Example: A user types and sends a message to LINE chat saying, "Please tell me about the marketing strategy for our new product."

[0667] Step 3:

[0668] The server receives the message via the LINE Messaging API.

[0669] Example: A message reception event is notified to the server via LINE's Webhook.

[0670] Step 4:

[0671] The server extracts and analyzes the received message content.

[0672] Example: Extract the keywords "new product," "marketing," and "strategy" from the content of received messages.

[0673] Step 5:

[0674] The server uses an emotion engine to analyze the user's emotion based on the message content.

[0675] Example: The emotion engine classifies the emotion of the received message as positive, negative, or neutral, and determines it as "positive and proactive."

[0676] Step 6:

[0677] The server retrieves the user's consultation history from the database and checks the free consultation limit.

[0678] Example: Check the number of consultations this month corresponding to the user ID in the database and determine whether there are any free consultation slots remaining.

[0679] Step 7:

[0680] If the server has free consultation slots remaining, it sends the inquiry and emotional information to the generation AI to generate an answer.

[0681] Example: Send a query to the generative AI in the form of "Users have positive feelings about the marketing strategy for a new product," and generate an answer.

[0682] Step 8:

[0683] The server takes the generated answer and formats it for sending to the user.

[0684] Example: The answer obtained from the AI ​​can be formulated as, "It is important to clarify your target market and promote using social media. Good luck!"

[0685] Step 9:

[0686] The server formats the response and sends it to the user using the LINE Messaging API.

[0687] Example: A message is sent to users saying, "It's important to identify your target market and promote your business through social media. Good luck!"

[0688] Step 10:

[0689] The server records in the database that one free consultation slot has been used and updates the remaining number of slots.

[0690] Example: Update the user's consultation history in the database and reduce the number of free consultations this month by one.

[0691] Step 11:

[0692] If there are no free consultation slots remaining, the server generates a message informing the user of a paid plan and sends it to the user.

[0693] Example: A message is sent to the user saying, "You have used up your free consultation slots for this month. Please consider a paid plan."

[0694] Step 12:

[0695] If a user needs detailed expert advice, they can send a message on LINE saying, "I would like to be introduced to an expert."

[0696] Example: A user types "I would like to be introduced to an expert" in a LINE chat and sends it.

[0697] Step 13:

[0698] The server receives the request for an expert introduction and contacts the partner consulting firm.

[0699] Example: Search for experts who fit the user's needs through a consulting company's API and initiate the referral process.

[0700] Step 14:

[0701] The server receives the expert's information and generates a message to notify the user.

[0702] Example: Generate the message "If you need professional advice, please contact a professional consultant via this link."

[0703] Step 15:

[0704] The server generates a message and sends it to the user via the LINE Messaging API.

[0705] Example: Send the above informational message to the user and provide a way to contact an expert.

[0706] Example 2

[0707] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0708] When receiving business consultations or management advice over the Internet, it is necessary to properly analyze the user's emotions and the content of the consultation and provide an effective answer. However, conventional systems have been unable to provide individual responses that take the user's emotions into consideration or manage free consultation quotas adequately, making it difficult to provide high-quality personalized service. Another issue is the complicated process of obtaining expert advice when needed.

[0709] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0710] In this invention, the server includes: a means for a user to send an inquiry via a messaging service using a communication terminal; a means for the server to receive the inquiry via the messaging service; a means for the server to analyze the inquiry using natural language processing technology and generate an answer using a generative AI model; a means for the server to send the generated answer to the user via the messaging service; a means for the server to analyze the user's emotions contained in the message using an emotion engine; and a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded. This makes it possible to provide personalized answers that take the user's emotions into consideration and efficiently manage the user's free consultation limit.

[0711] A "communication terminal" is a device that can use messaging services via the Internet, and specifically refers to smartphones, tablets, PCs, etc.

[0712] "Messaging Service" means an application or platform that enables users to send and receive text messages and multimedia content over the Internet.

[0713] A "server" is a computer system responsible for receiving queries from users, analyzing them, and generating responses.

[0714] "Natural language processing technology" refers to technology that enables computers to understand and process human language, and includes technology for analyzing text and extracting intent.

[0715] A "generative AI model" refers to an artificial intelligence technology that generates natural language answers or content based on specific input data.

[0716] An "emotion engine" is a system that analyzes user emotions from text data and identifies emotion categories such as positive, negative, and neutral.

[0717] The "free consultation quota" refers to the number of times or time limit that a user can receive free consultation within a certain period of time.

[0718] "Paid Plan" refers to the fee structure or plan that applies when a user requests additional consultations after exceeding the free consultation quota.

[0719] An "expert" refers to a person who has advanced knowledge and experience in a particular field and can provide users with specialized advice and consulting.

[0720] In the system of the present invention, a user makes an inquiry via a messaging service using a communication terminal, the server receives and analyzes the inquiry, generates a response using a generative AI model, and sends the response back to the user via the messaging service. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotions and provide personalized responses.

[0721] Hardware and software used

[0722] Music recommendation system: LINE Messaging API, NLP tools (e.g., Google Cloud Natural Language API), generative AI (e.g., OpenAI GPT-3), emotion engine (e.g., IBM Watson Tone Analyzer)

[0723] Communication devices: smartphones, tablets, computers, etc.

[0724] Database: Relational database such as MySQL, PostgreSQL, etc.

[0725] Data processing flow and explanation

[0726] 1. Add as a friend on LINE

[0727] Users launch the LINE app on their smartphone or other communication device and add the system's official account as a friend. At this point, they scan the QR code or search for and add the official account, and an automatic response message is displayed.

[0728] 2. Sending your consultation

[0729] The user enters the content of their business or management consultation on the LINE chat screen and sends it. For example, they can type "Please tell me how to increase employee motivation." The message is then forwarded to the system's server via the LINE server.

[0730] 3. Message Reception and Analysis

[0731] The server receives messages sent by users using the LINE Messaging API. The received messages are then analyzed using natural language processing (NLP) technology. During this analysis stage, NLP tools such as Google Cloud Natural Language API are used to extract the message's intent and keywords.

[0732] 4. Emotion analysis using an emotion engine

[0733] The server uses an emotion engine to analyze the emotions contained in the user's message. The emotion engine uses IBM Watson Tone Analyzer to identify positive, negative, neutral, and other emotions from the message.

[0734] 5. Check the free consultation slots

[0735] The server accesses a database (e.g., MySQL) and checks the user's consultation history. It determines whether there are any free consultation slots remaining, and if so, proceeds to the next step.

[0736] 6. Answer generation using generative AI

[0737] The server then sends the analyzed question and emotional information as a prompt to a generative AI model. Using generative AI such as OpenAI's GPT-3, the server generates an appropriate answer for the user. For example, the server might suggest specific methods or strategies, such as, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[0738] 7. Submit your response

[0739] The server formats the generated response and sends it to the user again using the LINE Messaging API. The user can then view the response on the LINE chat screen and immediately respond or put it into practice.

[0740] 8. What to do when the free quota is exceeded

[0741] If the free consultation limit is exceeded, the server generates a message informing the user about a paid plan. The message, which will be sent to the user again via LINE, will say something like, "You have used up your free consultation limit for this month. Please consider a paid plan."

[0742] 9. Introduction to professional consultants

[0743] If the user requests expert advice, the server will work with a consulting company to introduce the expert. In this case, the server will notify the user via LINE of the expert's information and contact details. A message such as "We will introduce you to a consultant specializing in business strategy. Please contact the following address for details" will be sent.

[0744] Specific examples

[0745] For example, if a small business owner sends an inquiry on LINE asking, "Please tell me about the marketing strategy for a new product," the server receives and analyzes this message and uses a generation AI to suggest specific marketing methods. The emotion engine reads the user's positive emotions, and the generation AI makes suggestions that include encouraging comments that match those emotions. The generated answer is specific, such as "It is important to clarify the target market and promote using social media," and is easy for the user to implement.

[0746] In this way, this system provides an environment where small and medium-sized enterprises and sole proprietors can easily receive expert advice and can provide highly accurate personalized support that takes into account the user's emotions, which is expected to improve business efficiency and solve management issues.

[0747] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0748] Program processing flow and detailed explanation

[0749] Step 1:

[0750] A user adds the official account of the system as a friend via a messaging service on a communication terminal.

[0751] Input: User scans QR code or searches for official account

[0752] Specific operation: The user launches the LINE app and either scans the official account's QR code or searches for the account by name to add it as a friend.

[0753] Step 2:

[0754] A user uses a communication terminal to send the consultation content on a messaging service.

[0755] Input: Text of the consultation (e.g., "Please tell me how to motivate my employees.")

[0756] Specific operation: The user enters the content of the consultation on the LINE chat screen and taps the send button. The message is then forwarded to the system server via the LINE server.

[0757] Step 3:

[0758] The server receives the user's message using the LINE Messaging API.

[0759] Input: Consult message sent

[0760] Specific operation: The server monitors the LINE Messaging API and receives new messages from users. The received messages are stored in text format.

[0761] Step 4:

[0762] The server uses natural language processing (NLP) techniques to analyze the message and extract the question.

[0763] Input: Received message text

[0764] How it works: The server calls NLP tools such as Google Cloud Natural Language API to extract the intent of the message and key keywords, such as "employee motivation" and "how to increase it."

[0765] Output: Extracted intents and keywords

[0766] Step 5:

[0767] The server uses an emotion engine to analyze the user's emotions.

[0768] Input: Received message text

[0769] What it does: Uses a sentiment engine (such as IBM Watson Tone Analyzer) to identify positive, negative, or neutral sentiment in a message. For example, the phrase "Tell me how" can be interpreted as positive sentiment.

[0770] Output: Sentiment analysis result (e.g., positive)

[0771] Step 6:

[0772] The server checks the user's consultation history and determines whether there are any free consultation slots remaining.

[0773] Input: User ID, consultation history

[0774] Specific operation: The server accesses a database (e.g., MySQL) and retrieves the consultation history associated with the user ID. Based on the history, it determines whether there are any free consultation slots remaining for that month.

[0775] Output: Free consultation slots remaining

[0776] Step 7:

[0777] The server uses a generative AI model to generate an answer based on the question and emotional information.

[0778] Input: Keywords in the question, sentiment analysis results

[0779] How it works: The server sends the analysis results as prompts to a generative AI model such as OpenAI's GPT-3, which then generates an appropriate response. For example, it might generate a message like, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[0780] Output: Generated answer text

[0781] Step 8:

[0782] The server formats the generated response and sends it to the user, again via the messaging service.

[0783] Input: Generated answer text

[0784] Specific operation: The server formats the reply text and sends it to the user using the LINE Messaging API. The user can then view the reply on the LINE chat screen.

[0785] Output: Message sent to the user

[0786] Step 9:

[0787] If the server exceeds the free consultation limit, it will send a message informing you about paid plans.

[0788] Input: Check if free consultation limit has been exceeded

[0789] Specific operation: If the free consultation limit is exceeded, the server generates a notification message and sends it to the user via LINE, stating that "You have used up your free consultation limit for this month. Please consider a paid plan."

[0790] Output: Paid plan information message

[0791] Step 10:

[0792] If the user requests expert advice, the server sends expert referral information.

[0793] Input: User's referral request

[0794] Specific operation: The server works with the consulting company to identify an appropriate expert. The server then notifies the user via LINE of the expert's information and contact details. A message such as "We will introduce you to a consultant specializing in business strategy. Please contact the following number for more information" is sent.

[0795] Output: Expert introduction information message

[0796] (Application example 2)

[0797] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0798] In production sites, it can be difficult for workers to obtain appropriate advice in real time. Quick and accurate access to information is especially important when operating new machinery or troubleshooting. Furthermore, if the answers provided do not take into consideration the worker's feelings, it can cause stress and confusion. Furthermore, to improve productivity, an optimal billing model for worker inquiries is also necessary. Conventional systems make it difficult to solve all of these issues at once.

[0799] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0800] In this invention, the server includes: means for a user to send an inquiry via a messaging service using a communication terminal; means for the server to receive the inquiry via the messaging service; means for the server to analyze the inquiry and generate an answer using a generation AI; means for the server to send the generated answer to the user via the messaging service; means for the server to analyze the user's emotion contained in the inquiry using an emotion engine; and means for monitoring the number of inquiries and introducing paid plans when a predetermined free consultation limit is exceeded. This allows workers to receive appropriate advice in real time and enables individual responses based on EMOTION, thereby reducing stress and improving productivity.

[0801] A "user" is someone who accesses and queries the system.

[0802] "Communication terminal" refers to a device that can connect to the Internet, such as a smartphone, tablet, or PC.

[0803] "Messaging Service" is an application service for sending and receiving messages over the Internet.

[0804] An "inquiry" refers to a question or request made by a user to the system.

[0805] A "server" is a computer system that processes and stores data over a network.

[0806] "Generative AI" refers to artificial intelligence technology that analyzes and generates natural language.

[0807] The "emotion engine" is dedicated software for analyzing the emotions contained in users' messages.

[0808] "Monitoring the number of times" means recording the frequency with which users use the system and checking the number of times they use it within a specific period of time.

[0809] "Free consultation quota" refers to the number of times and scope of services that a user can use free of charge.

[0810] "Paid Plan" refers to a service for which a fee is charged for use beyond the free limit.

[0811] An "expert" is someone who has advanced knowledge or skills in a particular field.

[0812] "Detailed advice" refers to specific, practical advice based on specialized knowledge.

[0813] "Operating over the Internet" means exchanging information or providing services using the Internet.

[0814] Here, we will explain how the system of the present invention is applied to a production site. Specifically, we will explain how to install a productivity improvement support application equipped with an emotion analysis function on a factory robot.

[0815] Overall system configuration

[0816] In this system, users (workers) make inquiries using a messaging service (e.g., LINE) on their communication devices, which are then received and analyzed by a server. The server then uses the analysis results and emotion engine data to utilize a generative AI model to generate a response, which is then sent back to the user via the messaging service. There is also a free consultation limit, and if the limit is exceeded, a function is included to introduce paid plans. Furthermore, there is also a function to introduce experts if expert advice is needed.

[0817] Hardware and Software Used

[0818] Hardware:

[0819] Internet-connected factory robots (e.g., industrial robots from Fanuc and KUKA)

[0820] software:

[0821] Messaging API (e.g., LINE Messaging API)

[0822] Natural Language Processing (NLP) engines (e.g., SpaCy or Google Cloud NLP)

[0823] Sentiment analysis engine (e.g., Emotion API)

[0824] Generative AI models (e.g., OpenAI's GPT-4)

[0825] A database (e.g., MySQL or MongoDB)

[0826] Program processing explanation

[0827] 1. Add as a friend on LINE

[0828] The user (worker) uses LINE on their smartphone to add the factory robot's official account as a friend by scanning the QR code or by searching for the official account.

[0829] 2. Submit an inquiry

[0830] Users can type and send questions about productivity or work content on the LINE chat screen. For example, they can type and send, "Please tell me how to troubleshoot the machine."

[0831] 3. Message Reception and Analysis

[0832] The server receives the user's message through the LINE Messaging API and analyzes the message content using an NLP engine.

[0833] 4. Analysis by Emotion Engine

[0834] The server analyzes the user's emotions from the received message using the Emotion API and identifies whether the emotion is positive, negative, or neutral.

[0835] 5. Answer generation using generative AI

[0836] The server sends the analyzed question content and emotional information as input data to a generative AI model such as GPT-4, which then generates a specific answer.

[0837] 6. Formatting and Submitting Your Answer

[0838] The server formats the generated answer and sends it to the user via LINE, for example, "When troubleshooting a machine, we recommend first checking the power status and then rechecking the connections."

[0839] Examples and prompts

[0840] For example, imagine a worker sends an inquiry via LINE saying, "I want to know how to operate a new machine." The server receives this message, analyzes it, and extracts keywords such as "new machine" and "how to operate." At the same time, the emotion engine reads the user's emotion of "confusion" from the message. The generative AI uses this information to generate a response that is specific and reassuring, such as, "It seems you're having trouble operating this new machine. I'll start by explaining the basics, so please stay calm and proceed. It's easy to operate. First, turn it on, and then..."

[0841] Prompt Sentence Examples

[0842] User message: "I want to know how to operate a new machine."

[0843] Sentiment analysis result: "Confused"

[0844] Prompt for the generative AI model: The user is confused and wants to know how to operate a new machine. Please generate a specific, easy-to-understand answer that provides a sense of security.

[0845] This allows workers to obtain quick and accurate information, and because the information is emotionally sensitive, they can work on solving problems with peace of mind.

[0846] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0847] Step 1:

[0848] A user uses LINE on a communication device to add the factory robot's official account as a friend. To do this, the user scans the QR code or searches for the official account and adds it. The user is then ready to make an inquiry. The input is "LINE official account information" and "user's LINE account," and the output is "Friend addition completed."

[0849] Step 2:

[0850] A user types and sends a question about productivity or work content on the LINE chat screen. For example, "Please tell me how to troubleshoot a machine." The input is the "user's question," and the output is "the server receiving the message."

[0851] Step 3:

[0852] The server receives the user's message via the LINE Messaging API. The server analyzes the received message using an NLP engine (for example, SpaCy or Google Cloud NLP) to extract the question keywords and intent. The input is the "user's message" and the output is the "analyzed question content."

[0853] Step 4:

[0854] The server uses an emotion engine (e.g., Emotion API) to analyze the emotions contained in the user's message. The emotion engine identifies at least three types of emotions from the message: positive, negative, and neutral. The input is the "user's message" and the "analyzed question content," and the output is the "analyzed emotion information."

[0855] Step 5:

[0856] The server sends the analyzed question content and emotional information as input data to a generative AI model (for example, OpenAI's GPT-4), which generates a specific answer. The generative AI model generates an answer based on the prompt text. The input is the "analyzed question content" and "analyzed emotional information," and the output is the "generated answer."

[0857] Step 6:

[0858] The server formats the generated answer and sends it to the user via LINE. For example, it might reply, "When troubleshooting a machine, we recommend first checking the power status and then rechecking the connections." The input is the "generated answer," and the output is "sent to the user."

[0859] Step 7:

[0860] The server monitors the number of inquiries made by the user, and if the number of free consultations exceeds a certain limit (for example, three), it generates a message informing the user of a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan." The inputs are the "number of inquiries" and the "free consultation limit limit," and the output is "send information about a paid plan."

[0861] Step 8:

[0862] When a user requests detailed advice from an expert, the server initiates a procedure to introduce an appropriate expert. Specifically, it retrieves relevant expert information from the database and provides it to the user via LINE. The input is the user's request for expert introduction and the expert's database information, and the output is sending the expert introduction information.

[0863] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0864] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0865] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0866] [Third embodiment]

[0867] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0868] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0869] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0870] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0871] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0872] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0873] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0874] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0875] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0876] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0877] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0878] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0879] Here, the program processing will be explained in natural language to explain how the system of the present invention can be specifically implemented.

[0880] Overall system configuration

[0881] In this system, users make inquiries via a messaging service on their communication device, and the server receives and analyzes the inquiries, generates a response using the AI, and then sends the response back to the user via the messaging service. Furthermore, a free consultation limit is set up so that users can easily make inquiries, and if the limit is exceeded, the system will guide users to paid plans. It also has a function to introduce experts when expert advice is needed.

[0882] Program processing

[0883] 1. Add as a friend on LINE

[0884] Users can add the system's official account as a friend via a messaging service (such as LINE) on a communication device (such as a smartphone) by scanning a QR code or searching for the official account.

[0885] 2. Sending your consultation

[0886] Users can input and send their business or management-related inquiries on the LINE chat screen. For example, they can input and send "Please tell me how to increase employee motivation."

[0887] 3. Message Reception and Analysis

[0888] The server receives the user's message via the LINE Messaging API, and then analyzes the message using natural language processing (NLP) technology to extract the user's intent and question.

[0889] 4. Check the free consultation slots

[0890] The server accesses the database and checks the user's consultation history. It determines whether the received consultation is within the free consultation limit (3 times) for that month. If there are free consultation limits remaining, it proceeds to the next process.

[0891] 5. Answer generation using generative AI

[0892] The server inputs the analyzed question content into the generation AI to generate an answer. For example, the generation AI may suggest specific methods and strategies for "how to increase employee motivation."

[0893] 6. Submit your response

[0894] The server then sends the generated answer to the user using the LINE Messaging API. For example, it could say, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[0895] 7. What to do when the free limit is exceeded

[0896] If the free consultation limit is exceeded, the server generates a message informing the user about a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan."

[0897] 8. Introduction to professional consultants

[0898] When a user requests expert advice, the server will introduce the expert. Specifically, it will work with a consulting company to introduce the appropriate expert to the user. At that time, the server will notify the user of the expert's information and contact details via LINE.

[0899] Specific examples

[0900] For example, imagine a small business owner sends an inquiry via LINE asking, "Please tell me about the marketing strategy for our new product." The server receives this message, analyzes it, and extracts keywords such as "new product" and "marketing strategy." The AI ​​then generates a response based on this information, replying, "It's important to clarify your target market and use social media for promotion." The user can then receive the response and implement it immediately.

[0901] In this way, this system provides an environment where small and medium-sized enterprises and sole proprietors can easily receive professional advice, which is expected to improve business efficiency and make it easier to resolve management issues.

[0902] The processing flow will be explained below.

[0903] Step 1:

[0904] A user adds the service's official account as a friend on LINE.

[0905] Example: A user scans a service's QR code in the LINE app and becomes a friend of the official account.

[0906] Step 2:

[0907] The user enters the details of their inquiry on LINE and sends it.

[0908] Example: A user types and sends a message to LINE chat saying, "Please tell me your marketing strategy."

[0909] Step 3:

[0910] The server receives the message via the LINE Messaging API.

[0911] Example: A message reception event is notified to the server via LINE's Webhook.

[0912] Step 4:

[0913] The server extracts the message content and analyzes it using natural language processing (NLP).

[0914] Example: Extract the keywords "marketing" and "strategy" from the content of received messages.

[0915] Step 5:

[0916] The server retrieves the user's consultation history from the database and checks the free consultation limit.

[0917] Example: Check the number of free consultations this month by looking up the consultation history corresponding to the user ID in the database.

[0918] Step 6:

[0919] If the server has free consultation slots remaining, it sends the inquiry to the generation AI to generate an answer.

[0920] Example: A generative AI model is sent a query in the form of "Please give me some advice on marketing strategy," and the AI ​​generates a specific answer.

[0921] Step 7:

[0922] The server takes the generated answer and formats it for sending to the user.

[0923] Example: The answer obtained from the AI ​​is formatted as, "It is important to clarify the target market and promote using social media."

[0924] Step 8:

[0925] The server formats the response and sends it to the user using the LINE Messaging API.

[0926] Example: A user receives the message, "To answer your questions about marketing strategy: It's important to identify your target market and promote your business through social media."

[0927] Step 9:

[0928] The server records in the database that one free consultation slot has been used and updates the remaining number of slots.

[0929] Example: Update the user's consultation history in the database and reduce the number of free consultations this month by one.

[0930] Step 10:

[0931] If there are no free consultation slots remaining, the server generates a message informing the user of a paid plan and sends it to the user.

[0932] Example: A message is sent to the user saying, "You have used up your free consultation slots for this month. Please consider a paid plan."

[0933] Step 11:

[0934] If a user needs detailed expert advice, they can send a message on LINE saying, "I would like to be introduced to an expert."

[0935] Example: A user types "I would like to be introduced to an expert" in a LINE chat and sends it.

[0936] Step 12:

[0937] The server receives the request for an expert introduction and contacts the partner consulting firm.

[0938] Example: Search for experts who fit the user's needs through a consulting company's API and initiate the referral process.

[0939] Step 13:

[0940] The server receives the expert's information and generates a message to notify the user.

[0941] Example: Generate the message "If you need professional advice, please contact a professional consultant via this link."

[0942] Step 14:

[0943] The server generates a message and sends it to the user via the LINE Messaging API.

[0944] Example: Send the above informational message to the user and provide a way to contact an expert.

[0945] Example 1

[0946] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0947] In modern society, there are many situations in which professional advice on business and management is needed, but cost and time constraints make it difficult to easily consult with experts. Small and medium-sized enterprises and sole proprietors in particular need a way to receive professional advice quickly and affordably. While providing a free consultation limit can help reduce costs, there is also a need for a system that directs users to a paid plan once a certain number of inquiries have been made. Furthermore, when professional advice is needed, there is also a need for referrals to appropriate experts.

[0948] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0949] In this invention, the server includes: a means for a user to send an inquiry via a messaging service using a wireless communication device; a means for the server to receive the inquiry via the messaging service; a means for the server to analyze the inquiry using natural language processing technology and generate an answer using a generative AI model; a means for the server to send the generated answer to the user via the messaging service; a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded; and a means for the server to store the user's consultation history in a database. This allows users to easily receive professional advice, and smoothly guides them to a paid plan when the free consultation limit is exceeded. Furthermore, when expert advice is needed, appropriate experts can be introduced.

[0950] A "user" is an entity that accesses the system and makes a query.

[0951] "Wireless communication device" refers to a device that transmits and receives data using wireless communication technology. Examples include smartphones and tablets.

[0952] "Messaging Service" means software or applications that enable the sending and receiving of messages over the Internet. An example is an instant messenger application.

[0953] "Server" refers to the central computer system that handles queries, analyzes data, records data, and generates responses.

[0954] "Natural language processing technology" refers to technology for understanding and analyzing human language and extracting intent. Examples include grammatical analysis and semantic analysis.

[0955] A "generative AI model" refers to an artificial intelligence model that generates answers or text in natural language based on input data. Examples include GPT-3 and other large-scale language models.

[0956] A "database" refers to a storage system that can efficiently store, manage, and retrieve data.

[0957] The "free consultation quota" refers to the limit on the number of times a user can receive free consultation within a certain period of time.

[0958] "Paid Plan" refers to a service plan in which a user is charged if the free consultation limit is exceeded.

[0959] An "expert" is a person or institution with in-depth knowledge and experience in a particular field.

[0960] "Consultation history" refers to historical information such as inquiries and responses made by the user.

[0961] In the system of the present invention, a user makes an inquiry via a messaging service using a wireless communication device, a server receives and analyzes the inquiry, generates an answer using a generative AI model, and sends the answer back to the user via the messaging service. This system also includes a mechanism that provides a free consultation limit, and when the free limit is exceeded, introduces paid plans, and a function that introduces experts when expert advice is needed.

[0962] Hardware and software used

[0963] A user uses a messaging application (e.g., LINE) on a wireless communication device (e.g., a smartphone or tablet). The server receives and analyzes these messages and uses a generative AI model (e.g., GPT-3) to generate appropriate responses. The server also uses the LINE Messaging API to receive messages and BERT or similar natural language processing technology.

[0964] Specific examples of program processing

[0965] A user sends a query via LINE, asking, "Please tell me how to motivate employees." The server receives this message via the LINE Messaging API and uses natural language processing technology to extract the keywords "employee," "motivation," and "method." The server then inputs the analyzed question content into a generative AI model (GPT-3) as a prompt sentence to generate a specific answer. The generated answer (for example, "Establishing a transparent evaluation system and providing regular feedback are effective") is then sent to the user again via the LINE Messaging API.

[0966] The system's unique feature is that it can provide users with expert advice in a simple and fast way. It also reduces costs by setting up a free consultation quota, allowing users to smoothly transition to paid consultations. Furthermore, it can provide higher quality services by introducing users to experts when expert advice is needed.

[0967] Prompt Sentence Examples

[0968] For example, the following prompts can be fed into a generative AI model:

[0969] "How can I motivate my employees?"

[0970] In this way, the system of the present invention provides an environment in which small and medium-sized enterprises and sole proprietors can easily receive professional advice, and supports the improvement of business efficiency and the resolution of management issues.

[0971] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0972] Step 1:

[0973] A user can use a messaging service (e.g., LINE) on a wireless communication device (e.g., a smartphone) to add the system's official account as a friend by scanning the QR code or by searching for the account name and tapping "Add to Friend."

[0974] Input: User's friend addition operation

[0975] Output: The official account is added to the user's friends list.

[0976] Specific operation: The user scans the official account's QR code with the camera, the LINE app automatically redirects to the official account's page, and taps the "Add friend" button.

[0977] Step 2:

[0978] Users open the chat screen with the official LINE account, enter the details of their business or management needs, and tap the send button. For example, they could type, "Please tell me how to increase employee motivation."

[0979] Input: User's question

[0980] Output: A query message is sent to the server

[0981] Specific actions: The user types "Please tell me how to motivate employees" into the LINE text box and taps the "Send" button.

[0982] Step 3:

[0983] The server receives messages sent by users via the LINE Messaging API, then uses natural language processing technology to analyze the content of the user's question and extract important keywords and intent.

[0984] Input: Question message from user

[0985] Output: Parsed keywords and intent

[0986] Specific operation: The server receives the message "Please tell me how to motivate employees" using the LINE Messaging API, and extracts keywords such as "employee," "motivation," and "method" using natural language processing technology (e.g., the BERT model).

[0987] Step 4:

[0988] The server accesses the database, checks the user's consultation history, and determines whether the received consultation is within the free consultation limit for that month (e.g., 3 consultations).

[0989] Input: Parsed keywords and user ID

[0990] Output: Result of remaining free consultation slots

[0991] Specific operation: The server searches the database using the user ID as a key and confirms that the number of consultations for the current month has still not exceeded two.

[0992] Step 5:

[0993] The server converts the parsed question content into a prompt and inputs it into a generative AI model (e.g., GPT-3), which then generates an appropriate answer to the question.

[0994] Input: Parsed question prompt

[0995] Output: The answer generated by the generative AI model

[0996] Specific operation: The server inputs the prompt "Please tell me how to motivate employees" into the generating AI model, and the AI ​​generates an answer such as "Establishing a transparent evaluation system and providing regular feedback are effective."

[0997] Step 6:

[0998] The server sends the generated response to the user using the LINE Messaging API.

[0999] Input: Answer from a generative AI model

[1000] Output: A reply message is sent to the user

[1001] Specific operation: The server sends a response to the user via the LINE API stating that "It would be effective to establish a transparent evaluation system and provide regular feedback."

[1002] Step 7:

[1003] If the free consultation limit is exceeded, the server generates a message informing the user of the paid plan and sends it via LINE.

[1004] Input: Number of consultations judged

[1005] Output: Paid plan information message

[1006] Specific operation: The server generates a message saying "You have used up this month's free consultation quota. Please consider a paid plan" and sends it to the user.

[1007] Step 8:

[1008] When a user requests professional advice, the server will introduce them to an expert. The server will work with a consulting company to obtain information on appropriate experts and notify the user via LINE.

[1009] Input: User request for expert referral

[1010] Output: Expert information and contact details

[1011] Specific operation: The server calls the consulting company's API, retrieves information about the appropriate expert, and sends the expert's contact information to the user along with a message such as "Please contact our expert."

[1012] (Application example 1)

[1013] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1014] In conventional content distribution services, users have limited means to ask questions or obtain related information in real time about the content they are viewing, making it difficult to improve the user experience. Furthermore, when users ask many questions, it is difficult to provide appropriate answers to some of the questions quickly. Furthermore, when the number of free assistance sessions is exceeded, there is a lack of guidance on appropriate paid plans.

[1015] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1016] In this invention, the server includes: means for a user to send an inquiry via a digital message service on a communication terminal; means for the server to receive the inquiry via the digital message service; means for the server to analyze the inquiry and generate an answer using a generative AI model; means for the server to send the generated answer to the user via the digital message service; and means for monitoring the number of inquiries, introducing paid plans when a predetermined free consultation limit is exceeded, and providing an automatic answer function for questions about content distribution. This allows users to receive quick and accurate answers to their questions, improving their experience.

[1017] "User" means an individual or entity that makes an inquiry using the Digital Message Service.

[1018] A "communication terminal" is an electronic device that a user uses to send and receive messages, and specific examples include smartphones and tablets.

[1019] "Digital message service" refers to an application that sends and receives messages over the Internet, and specifically includes messaging applications.

[1020] A "server" is a computer system that receives messages from users, analyzes them, generates answers using a generative AI model, and sends them back to the user.

[1021] A "generative AI model" is a type of artificial intelligence that uses natural language processing technology to generate answers to user inquiries.

[1022] The "means for generating an answer" is the process by which the server utilizes the generative AI model to generate an appropriate answer to the user's inquiry.

[1023] The "free consultation limit" is a limit on the number of inquiries a user can receive free of charge.

[1024] "Paid Plan" means a plan for additional assistance or services that is provided to a User for a fee when the free consultation limit is exceeded.

[1025] A "content distribution question" is an inquiry that asks for information related to a movie, drama, or other digital content that a user is watching.

[1026] Here, we will explain detailed embodiments of the present invention. The present invention involves a user making an inquiry using a digital messaging service (e.g., LINE), a server receiving the inquiry, generating an answer using a generative AI model, and providing the answer to the user again via the digital messaging service. It also has a function to monitor the number of inquiries made by the user and, if the free consultation limit is exceeded, introduce paid plans.

[1027] Specifically, a user first uses a communication device such as a smartphone or tablet to add the official account of the digital messaging service as a friend. Then, via a messaging application such as LINE, the user can type and send a question about the content distribution on the chat screen. For example, a question like, "What movie do you recommend I watch next?"

[1028] The server receives the message from the user through the LINE Messaging API. The server analyzes the message and uses natural language processing (NLP) technology to understand its content. It then uses the analyzed information to generate an appropriate response using a generative AI model (e.g., OpenAI GPT-3).

[1029] The generated answer is then sent to the user again using the LINE Messaging API. For example, a specific answer such as "A popular movie right now is 'XX'" is sent. The server also monitors the number of questions the user has asked, and if the free consultation limit (for example, three times a month) is exceeded, the system automatically introduces users to a paid plan.

[1030] The implementation of this system uses the following hardware and software:

[1031] Communication devices: smartphones, tablets, etc.

[1032] Digital messaging services: Messaging applications such as LINE

[1033] Server: A computer server for receiving queries, analyzing them, and generating answers.

[1034] Natural language processing technology (NLP): Used to analyze inquiry content

[1035] Generative AI models: AI models that generate answers, such as OpenAI GPT-3

[1036] As a specific example, if a user sends a query such as "What dramas are recommended to watch now?", the server receives this message and uses NLP technology to extract keywords such as "recommended dramas." Next, a prompt such as "User question: What dramas are recommended to watch now?" is input into the generative AI model, which then generates an answer. The generated answer is returned to the user as "Currently popular dramas include 'XX'."

[1037] In this way, the system of the present invention provides an environment in which the user can obtain information related to the content he or she is viewing in real time, thereby improving user satisfaction.

[1038] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1039] Step 1:

[1040] Users can add an official account of a digital messaging service (e.g., LINE) as a friend on a communication device (such as a smartphone) by scanning a QR code or searching for the official account.

[1041] Step 2:

[1042] Users can input and send questions about content distribution on the LINE chat screen. For example, they might input and send, "What movie do you recommend I watch next?" The input data is the user's question or inquiry, and the output is message data sent to the server via the digital messaging service.

[1043] Step 3:

[1044] The server receives the user's message via the LINE Messaging API. The received message arrives at the server as unstructured data.

[1045] Step 4:

[1046] The server analyzes the received message using natural language processing (NLP) technology. Specifically, it extracts the user's intent and question from the message. The input data is the received message, and the output is structured data (e.g., keywords such as "recommended movies") as the analysis result.

[1047] Step 5:

[1048] The server inputs the analyzed question content into a generative AI model (e.g., OpenAI GPT-3) as a prompt. An example of a specific prompt is, "User asks: What movie would you recommend I watch next?" The generative AI model generates an answer based on this input data, and outputs a natural language answer (e.g., "Currently, a popular movie is 'XX'").

[1049] Step 6:

[1050] The server sends the generated response to the user using the LINE Messaging API. The input data is the response generated by the generative AI model, and the output is a message sent to the user.

[1051] Step 7:

[1052] The server accesses the database and checks the user's consultation history. It determines whether there are any free consultation slots remaining, and if there are, it proceeds to the next step. The input data is the user's consultation history, and the output is information about the remaining number of free consultation slots.

[1053] Step 8:

[1054] If the free consultation limit is exceeded, the server generates a message informing the user of a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan." The input data is information about whether the free limit has been exceeded, and the output is a message informing the user of a paid plan.

[1055] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1056] Here, the program processing will be explained in natural language in a form in which an emotion engine is combined with the system of the present invention.

[1057] Overall system configuration

[1058] In this system, users make inquiries via a messaging service on their communications device, and the server receives and analyzes the inquiries, generates a response using a generation AI, and then sends the response back to the user via the messaging service. Furthermore, a free consultation limit is set up so that users can easily make inquiries, and if the limit is exceeded, the system will guide users to paid plans. It also has a function to introduce experts if expert advice is needed. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotions and provide more personalized responses.

[1059] Program processing

[1060] 1. Add as a friend on LINE

[1061] Users can add the system's official account as a friend via a messaging service (such as LINE) on a communication device (such as a smartphone) by scanning a QR code or searching for the official account.

[1062] 2. Sending your consultation

[1063] Users can input and send their business or management-related inquiries on the LINE chat screen. For example, they can input and send "Please tell me how to increase employee motivation."

[1064] 3. Message Reception and Analysis

[1065] The server receives the user's message via the LINE Messaging API, and then analyzes the message using natural language processing (NLP) technology to extract the user's intent and question.

[1066] 4. Emotion analysis using an emotion engine

[1067] The server analyzes the user's emotions contained in the received message using an emotion engine, which identifies at least three types of emotions from the user's message: positive, negative, and neutral.

[1068] 5. Check the free consultation slots

[1069] The server accesses the database and checks the user's consultation history. It determines whether the received consultation is within the free consultation limit (3 times) for that month. If there are free consultation limits remaining, it proceeds to the next process.

[1070] 6. Answer generation using generative AI

[1071] The server then sends the analyzed question and emotional information as input data to the AI ​​generator, which then generates an answer. For example, the AI ​​generator might suggest specific methods and strategies for "how to increase employee motivation," taking the user's emotions into account.

[1072] 7. Submit your response

[1073] The server then formats the generated answer and sends it to the user via the messaging service (LINE), for example, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[1074] 8. What to do when the free quota is exceeded

[1075] If the free consultation limit is exceeded, the server generates a message informing the user about a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan."

[1076] 9. Introduction to professional consultants

[1077] When a user requests expert advice, the server will introduce the expert. Specifically, it will work with a consulting company to introduce the appropriate expert to the user. At that time, the server will notify the user of the expert's information and contact details via LINE.

[1078] Specific examples

[1079] For example, imagine a small business owner sends an inquiry via LINE asking, "Please tell me about the marketing strategy for our new product." The server receives this message, analyzes it, and extracts keywords such as "new product" and "marketing strategy." At the same time, the emotion engine reads "positive and proactive" emotions from the user's message. The generation AI generates a response based on this information, replying, "It's important to clarify your target market and promote your product using social media." The generated response also includes encouraging comments that match the user's positive emotions, making it more approachable and trustworthy. The user can then receive the response and implement it immediately.

[1080] In this way, this system provides an environment where small and medium-sized enterprises and sole proprietors can easily receive expert advice, and offers more accurate, personalized support that takes into account the user's emotions. This is expected to improve business efficiency and make it easier to solve management issues.

[1081] The processing flow will be explained below.

[1082] Step 1:

[1083] A user adds the service's official account as a friend on LINE.

[1084] Example: A user scans a service's QR code in the LINE app and becomes a friend of the official account.

[1085] Step 2:

[1086] The user enters the details of their inquiry on LINE and sends it.

[1087] Example: A user types and sends a message to LINE chat saying, "Please tell me about the marketing strategy for our new product."

[1088] Step 3:

[1089] The server receives the message via the LINE Messaging API.

[1090] Example: A message reception event is notified to the server via LINE's Webhook.

[1091] Step 4:

[1092] The server extracts and analyzes the received message content.

[1093] Example: Extract the keywords "new product," "marketing," and "strategy" from the content of received messages.

[1094] Step 5:

[1095] The server uses an emotion engine to analyze the user's emotion based on the message content.

[1096] Example: The emotion engine classifies the emotion of the received message as positive, negative, or neutral, and determines it as "positive and proactive."

[1097] Step 6:

[1098] The server retrieves the user's consultation history from the database and checks the free consultation limit.

[1099] Example: Check the number of consultations this month corresponding to the user ID in the database and determine whether there are any free consultation slots remaining.

[1100] Step 7:

[1101] If the server has free consultation slots remaining, it sends the inquiry and emotional information to the generation AI to generate an answer.

[1102] Example: Send a query to the generative AI in the form of "Users have positive feelings about the marketing strategy for a new product," and generate an answer.

[1103] Step 8:

[1104] The server takes the generated answer and formats it for sending to the user.

[1105] Example: The answer obtained from the AI ​​can be formulated as, "It is important to clarify your target market and promote using social media. Good luck!"

[1106] Step 9:

[1107] The server formats the response and sends it to the user using the LINE Messaging API.

[1108] Example: A message is sent to users saying, "It's important to identify your target market and promote your business through social media. Good luck!"

[1109] Step 10:

[1110] The server records in the database that one free consultation slot has been used and updates the remaining number of slots.

[1111] Example: Update the user's consultation history in the database and reduce the number of free consultations this month by one.

[1112] Step 11:

[1113] If there are no free consultation slots remaining, the server generates a message informing the user of a paid plan and sends it to the user.

[1114] Example: A message is sent to the user saying, "You have used up your free consultation slots for this month. Please consider a paid plan."

[1115] Step 12:

[1116] If a user needs detailed expert advice, they can send a message on LINE saying, "I would like to be introduced to an expert."

[1117] Example: A user types "I would like to be introduced to an expert" in a LINE chat and sends it.

[1118] Step 13:

[1119] The server receives the request for an expert introduction and contacts the partner consulting firm.

[1120] Example: Search for experts who fit the user's needs through a consulting company's API and initiate the referral process.

[1121] Step 14:

[1122] The server receives the expert's information and generates a message to notify the user.

[1123] Example: Generate the message "If you need professional advice, please contact a professional consultant via this link."

[1124] Step 15:

[1125] The server generates a message and sends it to the user via the LINE Messaging API.

[1126] Example: Send the above informational message to the user and provide a way to contact an expert.

[1127] Example 2

[1128] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1129] When receiving business consultations or management advice over the Internet, it is necessary to properly analyze the user's emotions and the content of the consultation and provide an effective answer. However, conventional systems have been unable to provide individual responses that take the user's emotions into consideration or manage free consultation quotas adequately, making it difficult to provide high-quality personalized service. Another issue is the complicated process of obtaining expert advice when needed.

[1130] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1131] In this invention, the server includes: a means for a user to send an inquiry via a messaging service using a communication terminal; a means for the server to receive the inquiry via the messaging service; a means for the server to analyze the inquiry using natural language processing technology and generate an answer using a generative AI model; a means for the server to send the generated answer to the user via the messaging service; a means for the server to analyze the user's emotions contained in the message using an emotion engine; and a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded. This makes it possible to provide personalized answers that take the user's emotions into consideration and efficiently manage the user's free consultation limit.

[1132] A "communication terminal" is a device that can use messaging services via the Internet, and specifically refers to smartphones, tablets, PCs, etc.

[1133] "Messaging Service" means an application or platform that enables users to send and receive text messages and multimedia content over the Internet.

[1134] A "server" is a computer system responsible for receiving queries from users, analyzing them, and generating responses.

[1135] "Natural language processing technology" refers to technology that enables computers to understand and process human language, and includes technology for analyzing text and extracting intent.

[1136] A "generative AI model" refers to an artificial intelligence technology that generates natural language answers or content based on specific input data.

[1137] An "emotion engine" is a system that analyzes user emotions from text data and identifies emotion categories such as positive, negative, and neutral.

[1138] The "free consultation quota" refers to the number of times or time limit that a user can receive free consultation within a certain period of time.

[1139] "Paid Plan" refers to the fee structure or plan that applies when a user requests additional consultations after exceeding the free consultation quota.

[1140] An "expert" refers to a person who has advanced knowledge and experience in a particular field and can provide users with specialized advice and consulting.

[1141] In the system of the present invention, a user makes an inquiry via a messaging service using a communication terminal, the server receives and analyzes the inquiry, generates a response using a generative AI model, and sends the response back to the user via the messaging service. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotions and provide personalized responses.

[1142] Hardware and software used

[1143] Music recommendation system: LINE Messaging API, NLP tools (e.g., Google Cloud Natural Language API), generative AI (e.g., OpenAI GPT-3), emotion engine (e.g., IBM Watson Tone Analyzer)

[1144] Communication devices: smartphones, tablets, computers, etc.

[1145] Database: Relational database such as MySQL, PostgreSQL, etc.

[1146] Data processing flow and explanation

[1147] 1. Add as a friend on LINE

[1148] Users launch the LINE app on their smartphone or other communication device and add the system's official account as a friend. At this point, they scan the QR code or search for and add the official account, and an automatic response message is displayed.

[1149] 2. Sending your consultation

[1150] The user enters the content of their business or management consultation on the LINE chat screen and sends it. For example, they can type "Please tell me how to increase employee motivation." The message is then forwarded to the system's server via the LINE server.

[1151] 3. Message Reception and Analysis

[1152] The server receives messages sent by users using the LINE Messaging API. The received messages are then analyzed using natural language processing (NLP) technology. During this analysis stage, NLP tools such as Google Cloud Natural Language API are used to extract the message's intent and keywords.

[1153] 4. Emotion analysis using an emotion engine

[1154] The server uses an emotion engine to analyze the emotions contained in the user's message. The emotion engine uses IBM Watson Tone Analyzer to identify positive, negative, neutral, and other emotions from the message.

[1155] 5. Check the free consultation slots

[1156] The server accesses a database (e.g., MySQL) and checks the user's consultation history. It determines whether there are any free consultation slots remaining, and if so, proceeds to the next step.

[1157] 6. Answer generation using generative AI

[1158] The server then sends the analyzed question and emotional information as a prompt to a generative AI model. Using generative AI such as OpenAI's GPT-3, the server generates an appropriate answer for the user. For example, the server might suggest specific methods or strategies, such as, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[1159] 7. Submit your response

[1160] The server formats the generated response and sends it to the user again using the LINE Messaging API. The user can then view the response on the LINE chat screen and immediately respond or put it into practice.

[1161] 8. What to do when the free quota is exceeded

[1162] If the free consultation limit is exceeded, the server generates a message informing the user about a paid plan. The message, which will be sent to the user again via LINE, will say something like, "You have used up your free consultation limit for this month. Please consider a paid plan."

[1163] 9. Introduction to professional consultants

[1164] If the user requests expert advice, the server will work with a consulting company to introduce the expert. In this case, the server will notify the user via LINE of the expert's information and contact details. A message such as "We will introduce you to a consultant specializing in business strategy. Please contact the following address for details" will be sent.

[1165] Specific examples

[1166] For example, if a small business owner sends an inquiry on LINE asking, "Please tell me about the marketing strategy for a new product," the server receives and analyzes this message and uses a generation AI to suggest specific marketing methods. The emotion engine reads the user's positive emotions, and the generation AI makes suggestions that include encouraging comments that match those emotions. The generated answer is specific, such as "It is important to clarify the target market and promote using social media," and is easy for the user to implement.

[1167] In this way, this system provides an environment where small and medium-sized enterprises and sole proprietors can easily receive expert advice and can provide highly accurate personalized support that takes into account the user's emotions, which is expected to improve business efficiency and solve management issues.

[1168] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1169] Program processing flow and detailed explanation

[1170] Step 1:

[1171] A user adds the official account of the system as a friend via a messaging service on a communication terminal.

[1172] Input: User scans QR code or searches for official account

[1173] Specific operation: The user launches the LINE app and either scans the official account's QR code or searches for the account by name to add it as a friend.

[1174] Step 2:

[1175] A user uses a communication terminal to send the consultation content on a messaging service.

[1176] Input: Text of the consultation (e.g., "Please tell me how to motivate my employees.")

[1177] Specific operation: The user enters the content of the consultation on the LINE chat screen and taps the send button. The message is then forwarded to the system server via the LINE server.

[1178] Step 3:

[1179] The server receives the user's message using the LINE Messaging API.

[1180] Input: Consult message sent

[1181] Specific operation: The server monitors the LINE Messaging API and receives new messages from users. The received messages are stored in text format.

[1182] Step 4:

[1183] The server uses natural language processing (NLP) techniques to analyze the message and extract the question.

[1184] Input: Received message text

[1185] How it works: The server calls NLP tools such as Google Cloud Natural Language API to extract the intent of the message and key keywords, such as "employee motivation" and "how to increase it."

[1186] Output: Extracted intents and keywords

[1187] Step 5:

[1188] The server uses an emotion engine to analyze the user's emotions.

[1189] Input: Received message text

[1190] What it does: Uses a sentiment engine (such as IBM Watson Tone Analyzer) to identify positive, negative, or neutral sentiment in a message. For example, the phrase "Tell me how" can be interpreted as positive sentiment.

[1191] Output: Sentiment analysis result (e.g., positive)

[1192] Step 6:

[1193] The server checks the user's consultation history and determines whether there are any free consultation slots remaining.

[1194] Input: User ID, consultation history

[1195] Specific operation: The server accesses a database (e.g., MySQL) and retrieves the consultation history associated with the user ID. Based on the history, it determines whether there are any free consultation slots remaining for that month.

[1196] Output: Free consultation slots remaining

[1197] Step 7:

[1198] The server uses a generative AI model to generate an answer based on the question and emotional information.

[1199] Input: Keywords in the question, sentiment analysis results

[1200] How it works: The server sends the analysis results as prompts to a generative AI model such as OpenAI's GPT-3, which then generates an appropriate response. For example, it might generate a message like, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[1201] Output: Generated answer text

[1202] Step 8:

[1203] The server formats the generated response and sends it to the user, again via the messaging service.

[1204] Input: Generated answer text

[1205] Specific operation: The server formats the reply text and sends it to the user using the LINE Messaging API. The user can then view the reply on the LINE chat screen.

[1206] Output: Message sent to the user

[1207] Step 9:

[1208] If the server exceeds the free consultation limit, it will send a message informing you about paid plans.

[1209] Input: Check if free consultation limit has been exceeded

[1210] Specific operation: If the free consultation limit is exceeded, the server generates a notification message and sends it to the user via LINE, stating that "You have used up your free consultation limit for this month. Please consider a paid plan."

[1211] Output: Paid plan information message

[1212] Step 10:

[1213] If the user requests expert advice, the server sends expert referral information.

[1214] Input: User's referral request

[1215] Specific operation: The server works with the consulting company to identify an appropriate expert. The server then notifies the user via LINE of the expert's information and contact details. A message such as "We will introduce you to a consultant specializing in business strategy. Please contact the following number for more information" is sent.

[1216] Output: Expert introduction information message

[1217] (Application example 2)

[1218] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1219] In production sites, it can be difficult for workers to obtain appropriate advice in real time. Quick and accurate access to information is especially important when operating new machinery or troubleshooting. Furthermore, if the answers provided do not take into consideration the worker's feelings, it can cause stress and confusion. Furthermore, to improve productivity, an optimal billing model for worker inquiries is also necessary. Conventional systems make it difficult to solve all of these issues at once.

[1220] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1221] In this invention, the server includes: means for a user to send an inquiry via a messaging service using a communication terminal; means for the server to receive the inquiry via the messaging service; means for the server to analyze the inquiry and generate an answer using a generation AI; means for the server to send the generated answer to the user via the messaging service; means for the server to analyze the user's emotion contained in the inquiry using an emotion engine; and means for monitoring the number of inquiries and introducing paid plans when a predetermined free consultation limit is exceeded. This allows workers to receive appropriate advice in real time and enables individual responses based on EMOTION, thereby reducing stress and improving productivity.

[1222] A "user" is someone who accesses and queries the system.

[1223] "Communication terminal" refers to a device that can connect to the Internet, such as a smartphone, tablet, or PC.

[1224] "Messaging Service" is an application service for sending and receiving messages over the Internet.

[1225] An "inquiry" refers to a question or request made by a user to the system.

[1226] A "server" is a computer system that processes and stores data over a network.

[1227] "Generative AI" refers to artificial intelligence technology that analyzes and generates natural language.

[1228] The "emotion engine" is dedicated software for analyzing the emotions contained in users' messages.

[1229] "Monitoring the number of times" means recording the frequency with which users use the system and checking the number of times they use it within a specific period of time.

[1230] "Free consultation quota" refers to the number of times and scope of services that a user can use free of charge.

[1231] "Paid Plan" refers to a service for which a fee is charged for use beyond the free limit.

[1232] An "expert" is someone who has advanced knowledge or skills in a particular field.

[1233] "Detailed advice" refers to specific, practical advice based on specialized knowledge.

[1234] "Operating over the Internet" means exchanging information or providing services using the Internet.

[1235] Here, we will explain how the system of the present invention is applied to a production site. Specifically, we will explain how to install a productivity improvement support application equipped with an emotion analysis function on a factory robot.

[1236] Overall system configuration

[1237] In this system, users (workers) make inquiries using a messaging service (e.g., LINE) on their communication devices, which are then received and analyzed by a server. The server then uses the analysis results and emotion engine data to utilize a generative AI model to generate a response, which is then sent back to the user via the messaging service. There is also a free consultation limit, and if the limit is exceeded, a function is included to introduce paid plans. Furthermore, there is also a function to introduce experts if expert advice is needed.

[1238] Hardware and Software Used

[1239] Hardware:

[1240] Internet-connected factory robots (e.g., industrial robots from Fanuc and KUKA)

[1241] software:

[1242] Messaging API (e.g., LINE Messaging API)

[1243] Natural Language Processing (NLP) engines (e.g., SpaCy or Google Cloud NLP)

[1244] Sentiment analysis engine (e.g., Emotion API)

[1245] Generative AI models (e.g., OpenAI's GPT-4)

[1246] A database (e.g., MySQL or MongoDB)

[1247] Program processing explanation

[1248] 1. Add as a friend on LINE

[1249] The user (worker) uses LINE on their smartphone to add the factory robot's official account as a friend by scanning the QR code or by searching for the official account.

[1250] 2. Submit an inquiry

[1251] Users can type and send questions about productivity or work content on the LINE chat screen. For example, they can type and send, "Please tell me how to troubleshoot the machine."

[1252] 3. Message Reception and Analysis

[1253] The server receives the user's message through the LINE Messaging API and analyzes the message content using an NLP engine.

[1254] 4. Analysis by Emotion Engine

[1255] The server analyzes the user's emotions from the received message using the Emotion API and identifies whether the emotion is positive, negative, or neutral.

[1256] 5. Answer generation using generative AI

[1257] The server sends the analyzed question content and emotional information as input data to a generative AI model such as GPT-4, which then generates a specific answer.

[1258] 6. Formatting and Submitting Your Answer

[1259] The server formats the generated answer and sends it to the user via LINE, for example, "When troubleshooting a machine, we recommend first checking the power status and then rechecking the connections."

[1260] Examples and prompts

[1261] For example, imagine a worker sends an inquiry via LINE saying, "I want to know how to operate a new machine." The server receives this message, analyzes it, and extracts keywords such as "new machine" and "how to operate." At the same time, the emotion engine reads the user's emotion of "confusion" from the message. The generative AI uses this information to generate a response that is specific and reassuring, such as, "It seems you're having trouble operating this new machine. I'll start by explaining the basics, so please stay calm and proceed. It's easy to operate. First, turn it on, and then..."

[1262] Prompt Sentence Examples

[1263] User message: "I want to know how to operate a new machine."

[1264] Sentiment analysis result: "Confused"

[1265] Prompt for the generative AI model: The user is confused and wants to know how to operate a new machine. Please generate a specific, easy-to-understand answer that provides a sense of security.

[1266] This allows workers to obtain quick and accurate information, and because the information is emotionally sensitive, they can work on solving problems with peace of mind.

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

[1268] Step 1:

[1269] A user uses LINE on a communication device to add the factory robot's official account as a friend. To do this, the user scans the QR code or searches for the official account and adds it. The user is then ready to make an inquiry. The input is "LINE official account information" and "user's LINE account," and the output is "Friend addition completed."

[1270] Step 2:

[1271] A user types and sends a question about productivity or work content on the LINE chat screen. For example, "Please tell me how to troubleshoot a machine." The input is the "user's question," and the output is "the server receiving the message."

[1272] Step 3:

[1273] The server receives the user's message via the LINE Messaging API. The server analyzes the received message using an NLP engine (for example, SpaCy or Google Cloud NLP) to extract the question keywords and intent. The input is the "user's message" and the output is the "analyzed question content."

[1274] Step 4:

[1275] The server uses an emotion engine (e.g., Emotion API) to analyze the emotions contained in the user's message. The emotion engine identifies at least three types of emotions from the message: positive, negative, and neutral. The input is the "user's message" and the "analyzed question content," and the output is the "analyzed emotion information."

[1276] Step 5:

[1277] The server sends the analyzed question content and emotional information as input data to a generative AI model (for example, OpenAI's GPT-4), which generates a specific answer. The generative AI model generates an answer based on the prompt text. The input is the "analyzed question content" and "analyzed emotional information," and the output is the "generated answer."

[1278] Step 6:

[1279] The server formats the generated answer and sends it to the user via LINE. For example, it might reply, "When troubleshooting a machine, we recommend first checking the power status and then rechecking the connections." The input is the "generated answer," and the output is "sent to the user."

[1280] Step 7:

[1281] The server monitors the number of inquiries made by the user, and if the number of free consultations exceeds a certain limit (for example, three), it generates a message informing the user of a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan." The inputs are the "number of inquiries" and the "free consultation limit limit," and the output is "send information about a paid plan."

[1282] Step 8:

[1283] When a user requests detailed advice from an expert, the server initiates a procedure to introduce an appropriate expert. Specifically, it retrieves relevant expert information from the database and provides it to the user via LINE. The input is the user's request for expert introduction and the expert's database information, and the output is sending the expert introduction information.

[1284] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1285] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1286] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1287] [Fourth embodiment]

[1288] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1289] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1290] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1291] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1292] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1293] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1294] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1295] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1296] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1297] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1298] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1299] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1300] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1301] Here, the program processing will be explained in natural language to explain how the system of the present invention can be specifically implemented.

[1302] Overall system configuration

[1303] In this system, users make inquiries via a messaging service on their communication device, and the server receives and analyzes the inquiries, generates a response using the AI, and then sends the response back to the user via the messaging service. Furthermore, a free consultation limit is set up so that users can easily make inquiries, and if the limit is exceeded, the system will guide users to paid plans. It also has a function to introduce experts when expert advice is needed.

[1304] Program processing

[1305] 1. Add as a friend on LINE

[1306] Users can add the system's official account as a friend via a messaging service (such as LINE) on a communication device (such as a smartphone) by scanning a QR code or searching for the official account.

[1307] 2. Sending your consultation

[1308] Users can input and send their business or management-related inquiries on the LINE chat screen. For example, they can input and send "Please tell me how to increase employee motivation."

[1309] 3. Message Reception and Analysis

[1310] The server receives the user's message via the LINE Messaging API, and then analyzes the message using natural language processing (NLP) technology to extract the user's intent and question.

[1311] 4. Check the free consultation slots

[1312] The server accesses the database and checks the user's consultation history. It determines whether the received consultation is within the free consultation limit (3 times) for that month. If there are free consultation limits remaining, it proceeds to the next process.

[1313] 5. Answer generation using generative AI

[1314] The server inputs the analyzed question content into the generation AI to generate an answer. For example, the generation AI may suggest specific methods and strategies for "how to increase employee motivation."

[1315] 6. Submit your response

[1316] The server then sends the generated answer to the user using the LINE Messaging API. For example, it could say, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[1317] 7. What to do when the free limit is exceeded

[1318] If the free consultation limit is exceeded, the server generates a message informing the user about a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan."

[1319] 8. Introduction to professional consultants

[1320] When a user requests expert advice, the server will introduce the expert. Specifically, it will work with a consulting company to introduce the appropriate expert to the user. At that time, the server will notify the user of the expert's information and contact details via LINE.

[1321] Specific examples

[1322] For example, imagine a small business owner sends an inquiry via LINE asking, "Please tell me about the marketing strategy for our new product." The server receives this message, analyzes it, and extracts keywords such as "new product" and "marketing strategy." The AI ​​then generates a response based on this information, replying, "It's important to clarify your target market and use social media for promotion." The user can then receive the response and implement it immediately.

[1323] In this way, this system provides an environment where small and medium-sized enterprises and sole proprietors can easily receive professional advice, which is expected to improve business efficiency and make it easier to resolve management issues.

[1324] The processing flow will be explained below.

[1325] Step 1:

[1326] A user adds the service's official account as a friend on LINE.

[1327] Example: A user scans a service's QR code in the LINE app and becomes a friend of the official account.

[1328] Step 2:

[1329] The user enters the details of their inquiry on LINE and sends it.

[1330] Example: A user types and sends a message to LINE chat saying, "Please tell me your marketing strategy."

[1331] Step 3:

[1332] The server receives the message via the LINE Messaging API.

[1333] Example: A message reception event is notified to the server via LINE's Webhook.

[1334] Step 4:

[1335] The server extracts the message content and analyzes it using natural language processing (NLP).

[1336] Example: Extract the keywords "marketing" and "strategy" from the content of received messages.

[1337] Step 5:

[1338] The server retrieves the user's consultation history from the database and checks the free consultation limit.

[1339] Example: Check the number of free consultations this month by looking up the consultation history corresponding to the user ID in the database.

[1340] Step 6:

[1341] If the server has free consultation slots remaining, it sends the inquiry to the generation AI to generate an answer.

[1342] Example: A generative AI model is sent a query in the form of "Please give me some advice on marketing strategy," and the AI ​​generates a specific answer.

[1343] Step 7:

[1344] The server takes the generated answer and formats it for sending to the user.

[1345] Example: The answer obtained from the AI ​​is formatted as, "It is important to clarify the target market and promote using social media."

[1346] Step 8:

[1347] The server formats the response and sends it to the user using the LINE Messaging API.

[1348] Example: A user receives the message, "To answer your questions about marketing strategy: It's important to identify your target market and promote your business through social media."

[1349] Step 9:

[1350] The server records in the database that one free consultation slot has been used and updates the remaining number of slots.

[1351] Example: Update the user's consultation history in the database and reduce the number of free consultations this month by one.

[1352] Step 10:

[1353] If there are no free consultation slots remaining, the server generates a message informing the user of a paid plan and sends it to the user.

[1354] Example: A message is sent to the user saying, "You have used up your free consultation slots for this month. Please consider a paid plan."

[1355] Step 11:

[1356] If a user needs detailed expert advice, they can send a message on LINE saying, "I would like to be introduced to an expert."

[1357] Example: A user types "I would like to be introduced to an expert" in a LINE chat and sends it.

[1358] Step 12:

[1359] The server receives the request for an expert introduction and contacts the partner consulting firm.

[1360] Example: Search for experts who fit the user's needs through a consulting company's API and initiate the referral process.

[1361] Step 13:

[1362] The server receives the expert's information and generates a message to notify the user.

[1363] Example: Generate the message "If you need professional advice, please contact a professional consultant via this link."

[1364] Step 14:

[1365] The server generates a message and sends it to the user via the LINE Messaging API.

[1366] Example: Send the above informational message to the user and provide a way to contact an expert.

[1367] Example 1

[1368] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1369] In modern society, there are many situations in which professional advice on business and management is needed, but cost and time constraints make it difficult to easily consult with experts. Small and medium-sized enterprises and sole proprietors in particular need a way to receive professional advice quickly and affordably. While providing a free consultation limit can help reduce costs, there is also a need for a system that directs users to a paid plan once a certain number of inquiries have been made. Furthermore, when professional advice is needed, there is also a need for referrals to appropriate experts.

[1370] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1371] In this invention, the server includes: a means for a user to send an inquiry via a messaging service using a wireless communication device; a means for the server to receive the inquiry via the messaging service; a means for the server to analyze the inquiry using natural language processing technology and generate an answer using a generative AI model; a means for the server to send the generated answer to the user via the messaging service; a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded; and a means for the server to store the user's consultation history in a database. This allows users to easily receive professional advice, and smoothly guides them to a paid plan when the free consultation limit is exceeded. Furthermore, when expert advice is needed, appropriate experts can be introduced.

[1372] A "user" is an entity that accesses the system and makes a query.

[1373] "Wireless communication device" refers to a device that transmits and receives data using wireless communication technology. Examples include smartphones and tablets.

[1374] "Messaging Service" means software or applications that enable the sending and receiving of messages over the Internet. An example is an instant messenger application.

[1375] "Server" refers to the central computer system that handles queries, analyzes data, records data, and generates responses.

[1376] "Natural language processing technology" refers to technology for understanding and analyzing human language and extracting intent. Examples include grammatical analysis and semantic analysis.

[1377] A "generative AI model" refers to an artificial intelligence model that generates answers or text in natural language based on input data. Examples include GPT-3 and other large-scale language models.

[1378] A "database" refers to a storage system that can efficiently store, manage, and retrieve data.

[1379] The "free consultation quota" refers to the limit on the number of times a user can receive free consultation within a certain period of time.

[1380] "Paid Plan" refers to a service plan in which a user is charged if the free consultation limit is exceeded.

[1381] An "expert" is a person or institution with in-depth knowledge and experience in a particular field.

[1382] "Consultation history" refers to historical information such as inquiries and responses made by the user.

[1383] In the system of the present invention, a user makes an inquiry via a messaging service using a wireless communication device, a server receives and analyzes the inquiry, generates an answer using a generative AI model, and sends the answer back to the user via the messaging service. This system also includes a mechanism that provides a free consultation limit, and when the free limit is exceeded, introduces paid plans, and a function that introduces experts when expert advice is needed.

[1384] Hardware and software used

[1385] A user uses a messaging application (e.g., LINE) on a wireless communication device (e.g., a smartphone or tablet). The server receives and analyzes these messages and uses a generative AI model (e.g., GPT-3) to generate appropriate responses. The server also uses the LINE Messaging API to receive messages and BERT or similar natural language processing technology.

[1386] Specific examples of program processing

[1387] A user sends a query via LINE, asking, "Please tell me how to motivate employees." The server receives this message via the LINE Messaging API and uses natural language processing technology to extract the keywords "employee," "motivation," and "method." The server then inputs the analyzed question content into a generative AI model (GPT-3) as a prompt sentence to generate a specific answer. The generated answer (for example, "Establishing a transparent evaluation system and providing regular feedback are effective") is then sent to the user again via the LINE Messaging API.

[1388] The system's unique feature is that it can provide users with expert advice in a simple and fast way. It also reduces costs by setting up a free consultation quota, allowing users to smoothly transition to paid consultations. Furthermore, it can provide higher quality services by introducing users to experts when expert advice is needed.

[1389] Prompt Sentence Examples

[1390] For example, the following prompts can be fed into a generative AI model:

[1391] "How can I motivate my employees?"

[1392] In this way, the system of the present invention provides an environment in which small and medium-sized enterprises and sole proprietors can easily receive professional advice, and supports the improvement of business efficiency and the resolution of management issues.

[1393] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1394] Step 1:

[1395] A user can use a messaging service (e.g., LINE) on a wireless communication device (e.g., a smartphone) to add the system's official account as a friend by scanning the QR code or by searching for the account name and tapping "Add to Friend."

[1396] Input: User's friend addition operation

[1397] Output: The official account is added to the user's friends list.

[1398] Specific operation: The user scans the official account's QR code with the camera, the LINE app automatically redirects to the official account's page, and taps the "Add friend" button.

[1399] Step 2:

[1400] Users open the chat screen with the official LINE account, enter the details of their business or management needs, and tap the send button. For example, they could type, "Please tell me how to increase employee motivation."

[1401] Input: User's question

[1402] Output: A query message is sent to the server

[1403] Specific actions: The user types "Please tell me how to motivate employees" into the LINE text box and taps the "Send" button.

[1404] Step 3:

[1405] The server receives messages sent by users via the LINE Messaging API, then uses natural language processing technology to analyze the content of the user's question and extract important keywords and intent.

[1406] Input: Question message from user

[1407] Output: Parsed keywords and intent

[1408] Specific operation: The server receives the message "Please tell me how to motivate employees" using the LINE Messaging API, and extracts keywords such as "employee," "motivation," and "method" using natural language processing technology (e.g., the BERT model).

[1409] Step 4:

[1410] The server accesses the database, checks the user's consultation history, and determines whether the received consultation is within the free consultation limit for that month (e.g., 3 consultations).

[1411] Input: Parsed keywords and user ID

[1412] Output: Result of remaining free consultation slots

[1413] Specific operation: The server searches the database using the user ID as a key and confirms that the number of consultations for the current month has still not exceeded two.

[1414] Step 5:

[1415] The server converts the parsed question content into a prompt and inputs it into a generative AI model (e.g., GPT-3), which then generates an appropriate answer to the question.

[1416] Input: Parsed question prompt

[1417] Output: The answer generated by the generative AI model

[1418] Specific operation: The server inputs the prompt "Please tell me how to motivate employees" into the generating AI model, and the AI ​​generates an answer such as "Establishing a transparent evaluation system and providing regular feedback are effective."

[1419] Step 6:

[1420] The server sends the generated response to the user using the LINE Messaging API.

[1421] Input: Answer from a generative AI model

[1422] Output: A reply message is sent to the user

[1423] Specific operation: The server sends a response to the user via the LINE API stating that "It would be effective to establish a transparent evaluation system and provide regular feedback."

[1424] Step 7:

[1425] If the free consultation limit is exceeded, the server generates a message informing the user of the paid plan and sends it via LINE.

[1426] Input: Number of consultations judged

[1427] Output: Paid plan information message

[1428] Specific operation: The server generates a message saying "You have used up this month's free consultation quota. Please consider a paid plan" and sends it to the user.

[1429] Step 8:

[1430] When a user requests professional advice, the server will introduce them to an expert. The server will work with a consulting company to obtain information on appropriate experts and notify the user via LINE.

[1431] Input: User request for expert referral

[1432] Output: Expert information and contact details

[1433] Specific operation: The server calls the consulting company's API, retrieves information about the appropriate expert, and sends the expert's contact information to the user along with a message such as "Please contact our expert."

[1434] (Application example 1)

[1435] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1436] In conventional content distribution services, users have limited means to ask questions or obtain related information in real time about the content they are viewing, making it difficult to improve the user experience. Furthermore, when users ask many questions, it is difficult to provide appropriate answers to some of the questions quickly. Furthermore, when the number of free assistance sessions is exceeded, there is a lack of guidance on appropriate paid plans.

[1437] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1438] In this invention, the server includes: means for a user to send an inquiry via a digital message service on a communication terminal; means for the server to receive the inquiry via the digital message service; means for the server to analyze the inquiry and generate an answer using a generative AI model; means for the server to send the generated answer to the user via the digital message service; and means for monitoring the number of inquiries, introducing paid plans when a predetermined free consultation limit is exceeded, and providing an automatic answer function for questions about content distribution. This allows users to receive quick and accurate answers to their questions, improving their experience.

[1439] "User" means an individual or entity that makes an inquiry using the Digital Message Service.

[1440] A "communication terminal" is an electronic device that a user uses to send and receive messages, and specific examples include smartphones and tablets.

[1441] "Digital message service" refers to an application that sends and receives messages over the Internet, and specifically includes messaging applications.

[1442] A "server" is a computer system that receives messages from users, analyzes them, generates answers using a generative AI model, and sends them back to the user.

[1443] A "generative AI model" is a type of artificial intelligence that uses natural language processing technology to generate answers to user inquiries.

[1444] The "means for generating an answer" is the process by which the server utilizes the generative AI model to generate an appropriate answer to the user's inquiry.

[1445] The "free consultation limit" is a limit on the number of inquiries a user can receive free of charge.

[1446] "Paid Plan" means a plan for additional assistance or services that is provided to a User for a fee when the free consultation limit is exceeded.

[1447] A "content distribution question" is an inquiry that asks for information related to a movie, drama, or other digital content that a user is watching.

[1448] Here, we will explain detailed embodiments of the present invention. The present invention involves a user making an inquiry using a digital messaging service (e.g., LINE), a server receiving the inquiry, generating an answer using a generative AI model, and providing the answer to the user again via the digital messaging service. It also has a function to monitor the number of inquiries made by the user and, if the free consultation limit is exceeded, introduce paid plans.

[1449] Specifically, a user first uses a communication device such as a smartphone or tablet to add the official account of the digital messaging service as a friend. Then, via a messaging application such as LINE, the user can type and send a question about the content distribution on the chat screen. For example, a question like, "What movie do you recommend I watch next?"

[1450] The server receives the message from the user through the LINE Messaging API. The server analyzes the message and uses natural language processing (NLP) technology to understand its content. It then uses the analyzed information to generate an appropriate response using a generative AI model (e.g., OpenAI GPT-3).

[1451] The generated answer is then sent to the user again using the LINE Messaging API. For example, a specific answer such as "A popular movie right now is 'XX'" is sent. The server also monitors the number of questions the user has asked, and if the free consultation limit (for example, three times a month) is exceeded, the system automatically introduces users to a paid plan.

[1452] The implementation of this system uses the following hardware and software:

[1453] Communication devices: smartphones, tablets, etc.

[1454] Digital messaging services: Messaging applications such as LINE

[1455] Server: A computer server for receiving queries, analyzing them, and generating answers.

[1456] Natural language processing technology (NLP): Used to analyze inquiry content

[1457] Generative AI models: AI models that generate answers, such as OpenAI GPT-3

[1458] As a specific example, if a user sends a query such as "What dramas are recommended to watch now?", the server receives this message and uses NLP technology to extract keywords such as "recommended dramas." Next, a prompt such as "User question: What dramas are recommended to watch now?" is input into the generative AI model, which then generates an answer. The generated answer is returned to the user as "Currently popular dramas include 'XX'."

[1459] In this way, the system of the present invention provides an environment in which the user can obtain information related to the content he or she is viewing in real time, thereby improving user satisfaction.

[1460] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1461] Step 1:

[1462] Users can add an official account of a digital messaging service (e.g., LINE) as a friend on a communication device (such as a smartphone) by scanning a QR code or searching for the official account.

[1463] Step 2:

[1464] Users can input and send questions about content distribution on the LINE chat screen. For example, they might input and send, "What movie do you recommend I watch next?" The input data is the user's question or inquiry, and the output is message data sent to the server via the digital messaging service.

[1465] Step 3:

[1466] The server receives the user's message via the LINE Messaging API. The received message arrives at the server as unstructured data.

[1467] Step 4:

[1468] The server analyzes the received message using natural language processing (NLP) technology. Specifically, it extracts the user's intent and question from the message. The input data is the received message, and the output is structured data (e.g., keywords such as "recommended movies") as the analysis result.

[1469] Step 5:

[1470] The server inputs the analyzed question content into a generative AI model (e.g., OpenAI GPT-3) as a prompt. An example of a specific prompt is, "User asks: What movie would you recommend I watch next?" The generative AI model generates an answer based on this input data, and outputs a natural language answer (e.g., "Currently, a popular movie is 'XX'").

[1471] Step 6:

[1472] The server sends the generated response to the user using the LINE Messaging API. The input data is the response generated by the generative AI model, and the output is a message sent to the user.

[1473] Step 7:

[1474] The server accesses the database and checks the user's consultation history. It determines whether there are any free consultation slots remaining, and if there are, it proceeds to the next step. The input data is the user's consultation history, and the output is information about the remaining number of free consultation slots.

[1475] Step 8:

[1476] If the free consultation limit is exceeded, the server generates a message informing the user of a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan." The input data is information about whether the free limit has been exceeded, and the output is a message informing the user of a paid plan.

[1477] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1478] Here, the program processing will be explained in natural language in a form in which an emotion engine is combined with the system of the present invention.

[1479] Overall system configuration

[1480] In this system, users make inquiries via a messaging service on their communications device, and the server receives and analyzes the inquiries, generates a response using a generation AI, and then sends the response back to the user via the messaging service. Furthermore, a free consultation limit is set up so that users can easily make inquiries, and if the limit is exceeded, the system will guide users to paid plans. It also has a function to introduce experts if expert advice is needed. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotions and provide more personalized responses.

[1481] Program processing

[1482] 1. Add as a friend on LINE

[1483] Users can add the system's official account as a friend via a messaging service (such as LINE) on a communication device (such as a smartphone) by scanning a QR code or searching for the official account.

[1484] 2. Sending your consultation

[1485] Users can input and send their business or management-related inquiries on the LINE chat screen. For example, they can input and send "Please tell me how to increase employee motivation."

[1486] 3. Message Reception and Analysis

[1487] The server receives the user's message via the LINE Messaging API, and then analyzes the message using natural language processing (NLP) technology to extract the user's intent and question.

[1488] 4. Emotion analysis using an emotion engine

[1489] The server analyzes the user's emotions contained in the received message using an emotion engine, which identifies at least three types of emotions from the user's message: positive, negative, and neutral.

[1490] 5. Check the free consultation slots

[1491] The server accesses the database and checks the user's consultation history. It determines whether the received consultation is within the free consultation limit (3 times) for that month. If there are free consultation limits remaining, it proceeds to the next process.

[1492] 6. Answer generation using generative AI

[1493] The server then sends the analyzed question and emotional information as input data to the AI ​​generator, which then generates an answer. For example, the AI ​​generator might suggest specific methods and strategies for "how to increase employee motivation," taking the user's emotions into account.

[1494] 7. Submit your response

[1495] The server then formats the generated answer and sends it to the user via the messaging service (LINE), for example, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[1496] 8. What to do when the free quota is exceeded

[1497] If the free consultation limit is exceeded, the server generates a message informing the user about a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan."

[1498] 9. Introduction to professional consultants

[1499] When a user requests expert advice, the server will introduce the expert. Specifically, it will work with a consulting company to introduce the appropriate expert to the user. At that time, the server will notify the user of the expert's information and contact details via LINE.

[1500] Specific examples

[1501] For example, imagine a small business owner sends an inquiry via LINE asking, "Please tell me about the marketing strategy for our new product." The server receives this message, analyzes it, and extracts keywords such as "new product" and "marketing strategy." At the same time, the emotion engine reads "positive and proactive" emotions from the user's message. The generation AI generates a response based on this information, replying, "It's important to clarify your target market and promote your product using social media." The generated response also includes encouraging comments that match the user's positive emotions, making it more approachable and trustworthy. The user can then receive the response and implement it immediately.

[1502] In this way, this system provides an environment where small and medium-sized enterprises and sole proprietors can easily receive expert advice, and offers more accurate, personalized support that takes into account the user's emotions. This is expected to improve business efficiency and make it easier to solve management issues.

[1503] The processing flow will be explained below.

[1504] Step 1:

[1505] A user adds the service's official account as a friend on LINE.

[1506] Example: A user scans a service's QR code in the LINE app and becomes a friend of the official account.

[1507] Step 2:

[1508] The user enters the details of their inquiry on LINE and sends it.

[1509] Example: A user types and sends a message to LINE chat saying, "Please tell me about the marketing strategy for our new product."

[1510] Step 3:

[1511] The server receives the message via the LINE Messaging API.

[1512] Example: A message reception event is notified to the server via LINE's Webhook.

[1513] Step 4:

[1514] The server extracts and analyzes the received message content.

[1515] Example: Extract the keywords "new product," "marketing," and "strategy" from the content of received messages.

[1516] Step 5:

[1517] The server uses an emotion engine to analyze the user's emotion based on the message content.

[1518] Example: The emotion engine classifies the emotion of the received message as positive, negative, or neutral, and determines it as "positive and proactive."

[1519] Step 6:

[1520] The server retrieves the user's consultation history from the database and checks the free consultation limit.

[1521] Example: Check the number of consultations this month corresponding to the user ID in the database and determine whether there are any free consultation slots remaining.

[1522] Step 7:

[1523] If the server has free consultation slots remaining, it sends the inquiry and emotional information to the generation AI to generate an answer.

[1524] Example: Send a query to the generative AI in the form of "Users have positive feelings about the marketing strategy for a new product," and generate an answer.

[1525] Step 8:

[1526] The server takes the generated answer and formats it for sending to the user.

[1527] Example: The answer obtained from the AI ​​can be formulated as, "It is important to clarify your target market and promote using social media. Good luck!"

[1528] Step 9:

[1529] The server formats the response and sends it to the user using the LINE Messaging API.

[1530] Example: A message is sent to users saying, "It's important to identify your target market and promote your business through social media. Good luck!"

[1531] Step 10:

[1532] The server records in the database that one free consultation slot has been used and updates the remaining number of slots.

[1533] Example: Update the user's consultation history in the database and reduce the number of free consultations this month by one.

[1534] Step 11:

[1535] If there are no free consultation slots remaining, the server generates a message informing the user of a paid plan and sends it to the user.

[1536] Example: A message is sent to the user saying, "You have used up your free consultation slots for this month. Please consider a paid plan."

[1537] Step 12:

[1538] If a user needs detailed expert advice, they can send a message on LINE saying, "I would like to be introduced to an expert."

[1539] Example: A user types "I would like to be introduced to an expert" in a LINE chat and sends it.

[1540] Step 13:

[1541] The server receives the request for an expert introduction and contacts the partner consulting firm.

[1542] Example: Search for experts who fit the user's needs through a consulting company's API and initiate the referral process.

[1543] Step 14:

[1544] The server receives the expert's information and generates a message to notify the user.

[1545] Example: Generate the message "If you need professional advice, please contact a professional consultant via this link."

[1546] Step 15:

[1547] The server generates a message and sends it to the user via the LINE Messaging API.

[1548] Example: Send the above informational message to the user and provide a way to contact an expert.

[1549] Example 2

[1550] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1551] When receiving business consultations or management advice over the Internet, it is necessary to properly analyze the user's emotions and the content of the consultation and provide an effective answer. However, conventional systems have been unable to provide individual responses that take the user's emotions into consideration or manage free consultation quotas adequately, making it difficult to provide high-quality personalized service. Another issue is the complicated process of obtaining expert advice when needed.

[1552] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1553] In this invention, the server includes: a means for a user to send an inquiry via a messaging service using a communication terminal; a means for the server to receive the inquiry via the messaging service; a means for the server to analyze the inquiry using natural language processing technology and generate an answer using a generative AI model; a means for the server to send the generated answer to the user via the messaging service; a means for the server to analyze the user's emotions contained in the message using an emotion engine; and a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded. This makes it possible to provide personalized answers that take the user's emotions into consideration and efficiently manage the user's free consultation limit.

[1554] A "communication terminal" is a device that can use messaging services via the Internet, and specifically refers to smartphones, tablets, PCs, etc.

[1555] "Messaging Service" means an application or platform that enables users to send and receive text messages and multimedia content over the Internet.

[1556] A "server" is a computer system responsible for receiving queries from users, analyzing them, and generating responses.

[1557] "Natural language processing technology" refers to technology that enables computers to understand and process human language, and includes technology for analyzing text and extracting intent.

[1558] A "generative AI model" refers to an artificial intelligence technology that generates natural language answers or content based on specific input data.

[1559] An "emotion engine" is a system that analyzes user emotions from text data and identifies emotion categories such as positive, negative, and neutral.

[1560] The "free consultation quota" refers to the number of times or time limit that a user can receive free consultation within a certain period of time.

[1561] "Paid Plan" refers to the fee structure or plan that applies when a user requests additional consultations after exceeding the free consultation quota.

[1562] An "expert" refers to a person who has advanced knowledge and experience in a particular field and can provide users with specialized advice and consulting.

[1563] In the system of the present invention, a user makes an inquiry via a messaging service using a communication terminal, the server receives and analyzes the inquiry, generates a response using a generative AI model, and sends the response back to the user via the messaging service. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotions and provide personalized responses.

[1564] Hardware and software used

[1565] Music recommendation system: LINE Messaging API, NLP tools (e.g., Google Cloud Natural Language API), generative AI (e.g., OpenAI GPT-3), emotion engine (e.g., IBM Watson Tone Analyzer)

[1566] Communication devices: smartphones, tablets, computers, etc.

[1567] Database: Relational database such as MySQL, PostgreSQL, etc.

[1568] Data processing flow and explanation

[1569] 1. Add as a friend on LINE

[1570] Users launch the LINE app on their smartphone or other communication device and add the system's official account as a friend. At this point, they scan the QR code or search for and add the official account, and an automatic response message is displayed.

[1571] 2. Sending your consultation

[1572] The user enters the content of their business or management consultation on the LINE chat screen and sends it. For example, they can type "Please tell me how to increase employee motivation." The message is then forwarded to the system's server via the LINE server.

[1573] 3. Message Reception and Analysis

[1574] The server receives messages sent by users using the LINE Messaging API. The received messages are then analyzed using natural language processing (NLP) technology. During this analysis stage, NLP tools such as Google Cloud Natural Language API are used to extract the message's intent and keywords.

[1575] 4. Emotion analysis using an emotion engine

[1576] The server uses an emotion engine to analyze the emotions contained in the user's message. The emotion engine uses IBM Watson Tone Analyzer to identify positive, negative, neutral, and other emotions from the message.

[1577] 5. Check the free consultation slots

[1578] The server accesses a database (e.g., MySQL) and checks the user's consultation history. It determines whether there are any free consultation slots remaining, and if so, proceeds to the next step.

[1579] 6. Answer generation using generative AI

[1580] The server then sends the analyzed question and emotional information as a prompt to a generative AI model. Using generative AI such as OpenAI's GPT-3, the server generates an appropriate answer for the user. For example, the server might suggest specific methods or strategies, such as, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[1581] 7. Submit your response

[1582] The server formats the generated response and sends it to the user again using the LINE Messaging API. The user can then view the response on the LINE chat screen and immediately respond or put it into practice.

[1583] 8. What to do when the free quota is exceeded

[1584] If the free consultation limit is exceeded, the server generates a message informing the user about a paid plan. The message, which will be sent to the user again via LINE, will say something like, "You have used up your free consultation limit for this month. Please consider a paid plan."

[1585] 9. Introduction to professional consultants

[1586] If the user requests expert advice, the server will work with a consulting company to introduce the expert. In this case, the server will notify the user via LINE of the expert's information and contact details. A message such as "We will introduce you to a consultant specializing in business strategy. Please contact the following address for details" will be sent.

[1587] Specific examples

[1588] For example, if a small business owner sends an inquiry on LINE asking, "Please tell me about the marketing strategy for a new product," the server receives and analyzes this message and uses a generation AI to suggest specific marketing methods. The emotion engine reads the user's positive emotions, and the generation AI makes suggestions that include encouraging comments that match those emotions. The generated answer is specific, such as "It is important to clarify the target market and promote using social media," and is easy for the user to implement.

[1589] In this way, this system provides an environment where small and medium-sized enterprises and sole proprietors can easily receive expert advice and can provide highly accurate personalized support that takes into account the user's emotions, which is expected to improve business efficiency and solve management issues.

[1590] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1591] Program processing flow and detailed explanation

[1592] Step 1:

[1593] A user adds the official account of the system as a friend via a messaging service on a communication terminal.

[1594] Input: User scans QR code or searches for official account

[1595] Specific operation: The user launches the LINE app and either scans the official account's QR code or searches for the account by name to add it as a friend.

[1596] Step 2:

[1597] A user uses a communication terminal to send the consultation content on a messaging service.

[1598] Input: Text of the consultation (e.g., "Please tell me how to motivate my employees.")

[1599] Specific operation: The user enters the content of the consultation on the LINE chat screen and taps the send button. The message is then forwarded to the system server via the LINE server.

[1600] Step 3:

[1601] The server receives the user's message using the LINE Messaging API.

[1602] Input: Consult message sent

[1603] Specific operation: The server monitors the LINE Messaging API and receives new messages from users. The received messages are stored in text format.

[1604] Step 4:

[1605] The server uses natural language processing (NLP) techniques to analyze the message and extract the question.

[1606] Input: Received message text

[1607] How it works: The server calls NLP tools such as Google Cloud Natural Language API to extract the intent of the message and key keywords, such as "employee motivation" and "how to increase it."

[1608] Output: Extracted intents and keywords

[1609] Step 5:

[1610] The server uses an emotion engine to analyze the user's emotions.

[1611] Input: Received message text

[1612] What it does: Uses a sentiment engine (such as IBM Watson Tone Analyzer) to identify positive, negative, or neutral sentiment in a message. For example, the phrase "Tell me how" can be interpreted as positive sentiment.

[1613] Output: Sentiment analysis result (e.g., positive)

[1614] Step 6:

[1615] The server checks the user's consultation history and determines whether there are any free consultation slots remaining.

[1616] Input: User ID, consultation history

[1617] Specific operation: The server accesses a database (e.g., MySQL) and retrieves the consultation history associated with the user ID. Based on the history, it determines whether there are any free consultation slots remaining for that month.

[1618] Output: Free consultation slots remaining

[1619] Step 7:

[1620] The server uses a generative AI model to generate an answer based on the question and emotional information.

[1621] Input: Keywords in the question, sentiment analysis results

[1622] How it works: The server sends the analysis results as prompts to a generative AI model such as OpenAI's GPT-3, which then generates an appropriate response. For example, it might generate a message like, "To increase employee motivation, it is effective to establish a transparent evaluation system and provide regular feedback."

[1623] Output: Generated answer text

[1624] Step 8:

[1625] The server formats the generated response and sends it to the user, again via the messaging service.

[1626] Input: Generated answer text

[1627] Specific operation: The server formats the reply text and sends it to the user using the LINE Messaging API. The user can then view the reply on the LINE chat screen.

[1628] Output: Message sent to the user

[1629] Step 9:

[1630] If the server exceeds the free consultation limit, it will send a message informing you about paid plans.

[1631] Input: Check if free consultation limit has been exceeded

[1632] Specific operation: If the free consultation limit is exceeded, the server generates a notification message and sends it to the user via LINE, stating that "You have used up your free consultation limit for this month. Please consider a paid plan."

[1633] Output: Paid plan information message

[1634] Step 10:

[1635] If the user requests expert advice, the server sends expert referral information.

[1636] Input: User's referral request

[1637] Specific operation: The server works with the consulting company to identify an appropriate expert. The server then notifies the user via LINE of the expert's information and contact details. A message such as "We will introduce you to a consultant specializing in business strategy. Please contact the following number for more information" is sent.

[1638] Output: Expert introduction information message

[1639] (Application example 2)

[1640] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1641] In production sites, it can be difficult for workers to obtain appropriate advice in real time. Quick and accurate access to information is especially important when operating new machinery or troubleshooting. Furthermore, if the answers provided do not take into consideration the worker's feelings, it can cause stress and confusion. Furthermore, to improve productivity, an optimal billing model for worker inquiries is also necessary. Conventional systems make it difficult to solve all of these issues at once.

[1642] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1643] In this invention, the server includes: means for a user to send an inquiry via a messaging service using a communication terminal; means for the server to receive the inquiry via the messaging service; means for the server to analyze the inquiry and generate an answer using a generation AI; means for the server to send the generated answer to the user via the messaging service; means for the server to analyze the user's emotion contained in the inquiry using an emotion engine; and means for monitoring the number of inquiries and introducing paid plans when a predetermined free consultation limit is exceeded. This allows workers to receive appropriate advice in real time and enables individual responses based on EMOTION, thereby reducing stress and improving productivity.

[1644] A "user" is someone who accesses and queries the system.

[1645] "Communication terminal" refers to a device that can connect to the Internet, such as a smartphone, tablet, or PC.

[1646] "Messaging Service" is an application service for sending and receiving messages over the Internet.

[1647] An "inquiry" refers to a question or request made by a user to the system.

[1648] A "server" is a computer system that processes and stores data over a network.

[1649] "Generative AI" refers to artificial intelligence technology that analyzes and generates natural language.

[1650] The "emotion engine" is dedicated software for analyzing the emotions contained in users' messages.

[1651] "Monitoring the number of times" means recording the frequency with which users use the system and checking the number of times they use it within a specific period of time.

[1652] "Free consultation quota" refers to the number of times and scope of services that a user can use free of charge.

[1653] "Paid Plan" refers to a service for which a fee is charged for use beyond the free limit.

[1654] An "expert" is someone who has advanced knowledge or skills in a particular field.

[1655] "Detailed advice" refers to specific, practical advice based on specialized knowledge.

[1656] "Operating over the Internet" means exchanging information or providing services using the Internet.

[1657] Here, we will explain how the system of the present invention is applied to a production site. Specifically, we will explain how to install a productivity improvement support application equipped with an emotion analysis function on a factory robot.

[1658] Overall system configuration

[1659] In this system, users (workers) make inquiries using a messaging service (e.g., LINE) on their communication devices, which are then received and analyzed by a server. The server then uses the analysis results and emotion engine data to utilize a generative AI model to generate a response, which is then sent back to the user via the messaging service. There is also a free consultation limit, and if the limit is exceeded, a function is included to introduce paid plans. Furthermore, there is also a function to introduce experts if expert advice is needed.

[1660] Hardware and Software Used

[1661] Hardware:

[1662] Internet-connected factory robots (e.g., industrial robots from Fanuc and KUKA)

[1663] software:

[1664] Messaging API (e.g., LINE Messaging API)

[1665] Natural Language Processing (NLP) engines (e.g., SpaCy or Google Cloud NLP)

[1666] Sentiment analysis engine (e.g., Emotion API)

[1667] Generative AI models (e.g., OpenAI's GPT-4)

[1668] A database (e.g., MySQL or MongoDB)

[1669] Program processing explanation

[1670] 1. Add as a friend on LINE

[1671] The user (worker) uses LINE on their smartphone to add the factory robot's official account as a friend by scanning the QR code or by searching for the official account.

[1672] 2. Submit an inquiry

[1673] Users can type and send questions about productivity or work content on the LINE chat screen. For example, they can type and send, "Please tell me how to troubleshoot the machine."

[1674] 3. Message Reception and Analysis

[1675] The server receives the user's message through the LINE Messaging API and analyzes the message content using an NLP engine.

[1676] 4. Analysis by Emotion Engine

[1677] The server analyzes the user's emotions from the received message using the Emotion API and identifies whether the emotion is positive, negative, or neutral.

[1678] 5. Answer generation using generative AI

[1679] The server sends the analyzed question content and emotional information as input data to a generative AI model such as GPT-4, which then generates a specific answer.

[1680] 6. Formatting and Submitting Your Answer

[1681] The server formats the generated answer and sends it to the user via LINE, for example, "When troubleshooting a machine, we recommend first checking the power status and then rechecking the connections."

[1682] Examples and prompts

[1683] For example, imagine a worker sends an inquiry via LINE saying, "I want to know how to operate a new machine." The server receives this message, analyzes it, and extracts keywords such as "new machine" and "how to operate." At the same time, the emotion engine reads the user's emotion of "confusion" from the message. The generative AI uses this information to generate a response that is specific and reassuring, such as, "It seems you're having trouble operating this new machine. I'll start by explaining the basics, so please stay calm and proceed. It's easy to operate. First, turn it on, and then..."

[1684] Prompt Sentence Examples

[1685] User message: "I want to know how to operate a new machine."

[1686] Sentiment analysis result: "Confused"

[1687] Prompt for the generative AI model: The user is confused and wants to know how to operate a new machine. Please generate a specific, easy-to-understand answer that provides a sense of security.

[1688] This allows workers to obtain quick and accurate information, and because the information is emotionally sensitive, they can work on solving problems with peace of mind.

[1689] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1690] Step 1:

[1691] A user uses LINE on a communication device to add the factory robot's official account as a friend. To do this, the user scans the QR code or searches for the official account and adds it. The user is then ready to make an inquiry. The input is "LINE official account information" and "user's LINE account," and the output is "Friend addition completed."

[1692] Step 2:

[1693] A user types and sends a question about productivity or work content on the LINE chat screen. For example, "Please tell me how to troubleshoot a machine." The input is the "user's question," and the output is "the server receiving the message."

[1694] Step 3:

[1695] The server receives the user's message via the LINE Messaging API. The server analyzes the received message using an NLP engine (for example, SpaCy or Google Cloud NLP) to extract the question keywords and intent. The input is the "user's message" and the output is the "analyzed question content."

[1696] Step 4:

[1697] The server uses an emotion engine (e.g., Emotion API) to analyze the emotions contained in the user's message. The emotion engine identifies at least three types of emotions from the message: positive, negative, and neutral. The input is the "user's message" and the "analyzed question content," and the output is the "analyzed emotion information."

[1698] Step 5:

[1699] The server sends the analyzed question content and emotional information as input data to a generative AI model (for example, OpenAI's GPT-4), which generates a specific answer. The generative AI model generates an answer based on the prompt text. The input is the "analyzed question content" and "analyzed emotional information," and the output is the "generated answer."

[1700] Step 6:

[1701] The server formats the generated answer and sends it to the user via LINE. For example, it might reply, "When troubleshooting a machine, we recommend first checking the power status and then rechecking the connections." The input is the "generated answer," and the output is "sent to the user."

[1702] Step 7:

[1703] The server monitors the number of inquiries made by the user, and if the number of free consultations exceeds a certain limit (for example, three), it generates a message informing the user of a paid plan and sends it to the user via LINE. For example, it may say, "You have used up this month's free consultation limit. Please consider a paid plan." The inputs are the "number of inquiries" and the "free consultation limit limit," and the output is "send information about a paid plan."

[1704] Step 8:

[1705] When a user requests detailed advice from an expert, the server initiates a procedure to introduce an appropriate expert. Specifically, it retrieves relevant expert information from the database and provides it to the user via LINE. The input is the user's request for expert introduction and the expert's database information, and the output is sending the expert introduction information.

[1706] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1707] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1708] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1709] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1710] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1711] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1712] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1713] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1714] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1715] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1716] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1717] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1718] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1719] 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.

[1720] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1721] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1722] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1723] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1724] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1725] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1726] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1727] The following is further disclosed regarding the above embodiment.

[1728] (Claim 1)

[1729] means for a user to send a query through a messaging service on a communication terminal;

[1730] means for a server to receive said inquiry via said messaging service;

[1731] A means for the server to analyze the inquiry and generate an answer using a generation AI;

[1732] means for the server to send the generated response to the user via the messaging service;

[1733] a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded;

[1734] A system including:

[1735] (Claim 2)

[1736] 10. The system of claim 1, further comprising means for introducing an expert when the server requires detailed expert advice.

[1737] (Claim 3)

[1738] 10. The system of claim 1, wherein the messaging service is a messaging application that operates over the Internet.

[1739] "Example 1"

[1740] (Claim 1)

[1741] means for a user to send a query through a messaging service on a wireless communication device;

[1742] means for a server to receive said inquiry via said messaging service;

[1743] a means for the server to analyze the query using natural language processing technology and generate an answer using a generative AI model;

[1744] means for the server to send the generated response to the user via the messaging service;

[1745] a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded;

[1746] a means for the server to store the user's consultation history in a database;

[1747] A system including:

[1748] (Claim 2)

[1749] 10. The system of claim 1, further comprising means for introducing an expert when the server requires detailed expert advice.

[1750] (Claim 3)

[1751] 10. The system of claim 1, wherein the messaging service is a messaging application that operates over the Internet.

[1752] "Application Example 1"

[1753] (Claim 1)

[1754] means for a user to send a query through a digital message service at a communication terminal;

[1755] means for a server to receive the inquiry via the digital message service;

[1756] means for the server to analyze the query and generate an answer using a generative AI model;

[1757] means for the server to transmit the generated response to the user via the digital messaging service;

[1758] a means for monitoring the number of inquiries, and when a predetermined free consultation limit is exceeded, introducing a paid plan and providing an automatic answer function for questions regarding content distribution;

[1759] A system including:

[1760] (Claim 2)

[1761] 10. The system of claim 1, further comprising means for introducing an expert when the server requires detailed expert advice.

[1762] (Claim 3)

[1763] 10. The system of claim 1, wherein the digital messaging service is an application that operates over the Internet.

[1764] "Example 2: Combining Emotion Engines"

[1765] (Claim 1)

[1766] means for a user to send a query through a messaging service on a communication terminal;

[1767] means for a server to receive said inquiry via said messaging service;

[1768] means for the server to analyze the query using natural language processing technology and generate an answer using a generative AI model;

[1769] means for the server to send the generated response to the user via the messaging service;

[1770] A server analyzes the user's emotion contained in the message using an emotion engine;

[1771] a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded;

[1772] A system including:

[1773] (Claim 2)

[1774] 10. The system of claim 1, further comprising means for introducing an expert when the server requires detailed expert advice.

[1775] (Claim 3)

[1776] 10. The system of claim 1, wherein the messaging service is a messaging application that operates over the Internet.

[1777] "Application example 2 when combining emotion engines"

[1778] (Claim 1)

[1779] means for a user to send a query through a messaging service on a communication terminal;

[1780] means for a server to receive said inquiry via said messaging service;

[1781] A means for the server to analyze the inquiry and generate an answer using a generation AI;

[1782] means for the server to send the generated response to the user via the messaging service;

[1783] means for the server to analyze the user's emotion included in the query using an emotion engine;

[1784] a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded;

[1785] A system including:

[1786] (Claim 2)

[1787] 10. The system of claim 1, further comprising means for introducing an expert when the server requires detailed expert advice.

[1788] (Claim 3)

[1789] 10. The system of claim 1, wherein the messaging service is a messaging application that operates over the Internet. [Explanation of symbols]

[1790] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for a user to send a query through a messaging service on a communication terminal; means for a server to receive said inquiry via said messaging service; A means for the server to analyze the inquiry and generate an answer using a generation AI; means for the server to send the generated response to the user via the messaging service; a means for monitoring the number of inquiries and introducing a paid plan when a predetermined free consultation limit is exceeded; A system including:

2. 2. The system of claim 1, further comprising means for introducing an expert when the server requires detailed expert advice.

3. The system of claim 1 , wherein the messaging service is a messaging application that operates over the Internet.

Images