system

Abstract

Provide a system. [Solution] a means for receiving questions about a particular subject area; a means for analyzing the received question to identify the topic of the question; A means of selecting generative models that are specialized for specific expertise based on the identified topics; and means for generating an expert answer to the received question using the selected generative model; and means for transmitting the generated answer to a user terminal.

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] Current generative AI systems often produce vague and insufficient answers unless the questioner provides appropriate assumptions. This presents a challenge, preventing many users from fully enjoying the benefits of these systems. Furthermore, for questions that require specialized knowledge, it is difficult for general generative AI to provide satisfactory answers. This makes it difficult for beginners and non-experts seeking detailed information in specific fields to receive appropriate knowledge. The goal of this project is to improve this situation. [Means for solving the problem]

[0005] This invention provides a system that receives questions about a specific field, analyzes the content of the question to identify a topic, and selects a generative model specialized in specific expertise based on that topic. A specialized answer is generated using the selected generative model, and the generated answer is sent to a user terminal, allowing the user to easily acquire advanced expertise. This system receives questions from the user terminal in the form of HTTP requests, and because the generative model has advanced text analysis capabilities, it is able to generate detailed answers based on specialized knowledge.

[0006] A "special field" refers to a specific area or topic related to a particular expertise or skill.

[0007] A "question" refers to a sentence or phrase submitted by a user requesting information or advice.

[0008] "Receiving" refers to the system acquiring data transmitted from a user terminal.

[0009] "Analysis" refers to the function or process of processing received data to reveal its meaning or purpose.

[0010] "Topic" refers to a subject or theme identified based on the content of a question.

[0011] A "generative model" refers to an artificial intelligence algorithm or program that generatively provides an output for a given input.

[0012] "Choice" refers to the act of selecting the most appropriate option from among multiple options or possibilities.

[0013] A "professional answer" is an answer that provides detailed and accurate information based on specific knowledge or skills.

[0014] "Generation" refers to the process of creating new data or information based on input.

[0015] "User terminal" refers to a device, such as a computer or smartphone, that a user uses to input or obtain information.

[0016] "Transmitting" refers to the act or process of moving data or information from one place to another. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The system of the present invention executes a series of processes: it receives a question about a specific field, analyzes the content of the question to identify a topic, selects a generative model specialized in specific expertise based on that topic, generates a specialized answer, and sends it to the user terminal.

[0039] Explanation of program processing

[0040] Basic system operation

[0041] 1. User Submission:

[0042] A user uses their device to submit a question about a specific subject. The user types the question into the device's interface and presses the "Submit" button. For example, the user types the question, "What do I need to do to become a YouTuber?"

[0043] 2. Receiving and parsing questions:

[0044] The terminal receives the user's input and sends it to the server in the form of an HTTP request.

[0045] The server receives an HTTP request from the terminal and extracts the question text.

[0046] The question text is passed to a text analysis engine for analysis. This analysis identifies the topic and keywords of the question. For example, the topic "YouTuber" is identified from the question.

[0047] 3. Selecting specialized AI models:

[0048] Based on the analysis results, the server selects an appropriate generative AI model from its built-in database, in this case a model with specialized knowledge about YouTubers.

[0049] 4. Generate answers:

[0050] The server inputs the question text into the selected generative AI model, which generates a professional answer, with the generative model having advanced text analysis capabilities to provide detailed and accurate answers.

[0051] For example, you might generate an answer like, "Make sure you have the equipment and editing software to deliver high-quality content. Also, engaging with your audience and SEO are important."

[0052] 5. Packaging and sending your response:

[0053] The server packages the generated answer and sends it to the user's terminal as an HTTP response.

[0054] The terminal analyzes the response received from the server and displays the extracted answer on the user interface.

[0055] Specific examples

[0056] For example, if a user asks "What should I do to become a YouTuber?", the following would work:

[0057] When a user inputs a question and presses the send button on the terminal, the terminal sends the question to the server in the form of an HTTP request.

[0058] The server receives the question and uses a text analysis engine to identify the topic "YouTuber."

[0059] Based on the topic, the server selects a generative AI model with YouTuber-related expertise.

[0060] The model generates a detailed answer to the question: "First, make sure you have the equipment and editing software to deliver high-quality content. Second, it's important to engage with your audience and take care of SEO."

[0061] The server sends the generated answer to the user's terminal, and the user checks the answer displayed on the terminal.

[0062] In this way, users can easily obtain specialized and detailed answers. This system allows users who do not have advanced knowledge of a particular field to quickly obtain high-quality information.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] A user uses the device's interface to enter a question and presses the submit button. For example, the user enters a question such as "What should I do to become a YouTuber?"

[0066] Step 2:

[0067] The device sends the user's question to the server in the form of an HTTP request, which includes the question text.

[0068] Step 3:

[0069] The server extracts the question text from the HTTP request it receives and stores it in its internal memory.

[0070] Step 4:

[0071] The server sends the question text to a text analysis engine for analysis. The text analysis engine extracts the question's topic and key keywords. For example, the topic "YouTuber" is identified.

[0072] Step 5:

[0073] The server selects an appropriate generative AI model based on the analysis results, and calls up a generative AI model specialized for YouTubers from its internal database.

[0074] Step 6:

[0075] The server inputs the question text into the selected generative AI model. The model generates a professional answer to the question. For example, the answer might be, "Make sure you have the equipment and editing software to deliver high-quality content. It's also important to engage with your audience and take SEO measures."

[0076] Step 7:

[0077] The server packages the generated answer as an HTTP response, which contains the answer text in a user-readable format.

[0078] Step 8:

[0079] The server sends the HTTP response to the user's device.

[0080] Step 9:

[0081] The terminal analyzes the response received from the server, extracts the answer text, and displays the extracted answer on the user interface.

[0082] Step 10:

[0083] Users review the expert answers displayed and decide what to do next based on the results, such as buying equipment or starting to learn about SEO.

[0084] Example 1

[0085] 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."

[0086] Conventional question-answering systems often return generic, non-specialized answers to user questions, making it difficult to provide fully satisfactory answers to questions that require in-depth knowledge of a specific field. Furthermore, there is no established technology for selecting an appropriate generative model for the information a user wants to obtain, which means that obtaining specialized answers requires a great deal of time and effort.

[0087] 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.

[0088] In this invention, the server includes: means for receiving a question related to a specific field from a user terminal; means for analyzing the received question and identifying the topic of the question; means for selecting a generative model specialized in specific expertise based on the identified topic; means for generating a specialized answer to the received question using the selected generative model; means for transmitting the generated answer to the user terminal; means for the user terminal to display the received answer on a user interface; means including a text analysis engine for analyzing the question text; means for selecting an appropriate generative AI model from a built-in database; means for inputting the question text into the selected generative AI model and generating a detailed and accurate answer; and means for packaging the generated answer as an HTTP response and transmitting it to the user terminal. This enables users to obtain quick and specialized answers to questions related to a specific field.

[0089] A "user terminal" is a device through which a user inputs a question and communicates with a server.

[0090] A "question" is text entered by a user seeking knowledge or information.

[0091] A "server" is a central computer system that processes questions received from user terminals and generates answers.

[0092] An "HTTP request" is a request message defined by a communication protocol that is sent from a user terminal to a server.

[0093] A "text analysis engine" is software that analyzes incoming questions and identifies their topics and keywords.

[0094] A "topic" is a major theme or subject that represents the content of a question.

[0095] A "generative model" is an artificial intelligence model that generates expert answers based on a specific topic.

[0096] The "built-in database" is a database in which multiple generative models are stored.

[0097] A "professional response" is a response that contains detailed and accurate information about a specific subject.

[0098] "Packaging" is the process of preparing the generated answer for transmission to the user terminal as an HTTP response.

[0099] An "HTTP response" is a response message defined by a communication protocol that is sent from a server to a user terminal.

[0100] A "user interface" refers to a screen or operating means that allows a user to operate a terminal to input questions and check answers.

[0101] A "detailed and accurate answer" is an answer that provides high-quality information and accurately responds to a user's question.

[0102] The system of the present invention executes a series of processes: it receives a question about a specific field, analyzes the content of the question to identify a topic, selects a generative model specialized in specific expertise based on that topic, generates a specialized answer, and sends it to the user terminal.

[0103] The system components include a user terminal, a server, a text analysis engine, a generative AI model, an embedded database, and a user interface.

[0104] First, a user uses their device to enter a question about a specific field and presses the send button. For example, they can enter a question like, "What should I do to become a YouTuber?"

[0105] The device then sends this question to the server in the form of an HTTP request. The server extracts the question text from the received HTTP request and passes it to a text analysis engine (e.g., SpaCy or NLTK) for analysis. This analysis identifies the topic and keywords of the question. For example, the topic "YouTuber" may be identified from the question text.

[0106] Based on the analysis results, the server then selects an appropriate generative AI model (such as OpenAI® GPT-3®) from its built-in database, which is capable of generating detailed and accurate answers based on specific expertise.

[0107] The server inputs the question text into the selected generative AI model and obtains the resulting expert answer. For example, the generative AI model may generate a detailed answer such as, "First, prepare the equipment and editing software to provide high-quality content. Also, audience engagement and SEO are important."

[0108] The server packages this generated answer as an HTTP response and sends it to the user's device. The user's device analyzes the received response and displays it in a user interface. The user can then view the professional and detailed answer on their device screen.

[0109] For example, if a user submits the question "What should I do to become a YouTuber?", the system works as follows:

[0110] The user inputs a question and presses the send button on the terminal.

[0111] The terminal sends the question to the server in the form of an HTTP request.

[0112] The server receives the HTTP request and uses a text analysis engine to identify the topic "YouTuber."

[0113] Based on the topic, the server selects a generative AI model with YouTuber-related expertise.

[0114] The model generates a detailed answer to the question: "First, make sure you have the equipment and editing software to deliver high-quality content. Second, it's important to engage with your audience and take care of SEO."

[0115] The server sends the generated answer to the user's terminal, and the user checks the answer displayed on the terminal.

[0116] Through this process, users can easily obtain specialized and detailed answers. This system allows even users without advanced knowledge of a particular field to quickly obtain high-quality information.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1:

[0119] User questions submitted

[0120] A user types a question about a specific topic into an input field on their device. For example, a user types "What should I do to become a YouTuber?" into their device.

[0121] The user then clicks the "Send" button on the terminal interface.

[0122] Input: The question text entered by the user in the input field.

[0123] Output: The HTTP request made on the device side.

[0124] Step 2:

[0125] Receiving and parsing questions

[0126] The device captures the user's question and sends it to the server as an HTTP request.

[0127] The server receives the HTTP request from the terminal and extracts the question text from it.

[0128] The server passes the question text to a text analysis engine (e.g., SpaCy) for analysis.

[0129] Analysis: Use a text analysis engine to identify topics and keywords in the question. For example, identify the topic "YouTuber."

[0130] Input: The HTTP request sent from the device.

[0131] Output: Parsed topic information.

[0132] Step 3:

[0133] Selection of specialized AI models

[0134] Based on the analysis results, the server accesses its built-in database and selects an appropriate generative AI model (e.g., GPT-3).

[0135] The server loads the selected generative AI model and prepares it for query processing.

[0136] Input: Parsed topic information.

[0137] Output: The selected generative AI model.

[0138] Step 4:

[0139] Generate answers

[0140] The server inputs a question text to the selected generative AI model. For example, the server inputs the question "What should I do to become a YouTuber?"

[0141] Generative AI models use advanced text analytics to generate expert answers to questions.

[0142] Generate: For example, generate a specific answer like, "First, make sure you have the equipment and editing software to deliver high-quality content. Also, audience engagement and SEO are important."

[0143] Input: The user's question text.

[0144] Output: The generated expert answer.

[0145] Step 5:

[0146] Packaging and sending answers

[0147] The server packages the generated answer as an HTTP response and sends it to the terminal.

[0148] The terminal analyzes the received HTTP response and displays it on the user interface.

[0149] Packaging: Converting the generated answer into an HTTP response format.

[0150] Input: Generated expert answers.

[0151] Output: The HTTP response sent to the user device.

[0152] Step 6:

[0153] Show Answers

[0154] The terminal analyzes the HTTP response received from the server and extracts the answer text to the question.

[0155] The terminal displays the extracted answers on a user interface.

[0156] Input: Answer data in HTTP response format.

[0157] Output: The answer text that is displayed in the user interface.

[0158] This allows users to view professional and detailed answers on their device screen.

[0159] (Application example 1)

[0160] 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."

[0161] In modern brick-and-mortar stores, staff are required to provide prompt and professional answers to customer questions. However, since not all staff have expert knowledge in all fields, there are problems with delayed or inaccurate answers. The present invention aims to provide a system that enables brick-and-mortar store staff to provide prompt and accurate professional answers to customer questions.

[0162] 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.

[0163] In this invention, the server includes means for receiving a question related to a specific field, means for analyzing the received question to identify the topic of the question, means for selecting a generative model specialized in specific expertise based on the identified topic, means for generating a specialized answer to the received question using the selected generative model, means for transmitting the generated answer to a user terminal, and means for inputting a question from a terminal used by staff at a physical store and presenting the specialized answer, thereby enabling staff at the physical store to provide specialized answers to customers quickly and accurately.

[0164] A "question about a specific field" is a question or inquiry entered by a user based on a specific knowledge area or theme.

[0165] The "receiving means" is an interface for receiving input from the user and transmitting it to the server.

[0166] The "means of analyzing and identifying the topic of the question" is a function that performs natural language analysis on the content of the received question and extracts and identifies the topic and keywords.

[0167] A "generative model with specialized knowledge" is an artificial intelligence model that is trained on specialized data about a specific field or topic.

[0168] The "selection means" is a process for selecting an appropriate generative model from the database based on the analysis results.

[0169] The "means for generating expert answers" is a function that uses a selected generative model to create an answer to a received question.

[0170] The "means for transmitting to the user terminal" is a function for transmitting the generated answer to the terminal used by the user and displaying it.

[0171] "Store staff" refers to employees who actually deal with customers in the store.

[0172] "Means for inputting questions from a terminal and receiving expert answers" refers to an interface that allows staff at a physical store to input questions on a device used by the staff and receive and display answers from the server.

[0173] The system of the present invention executes a series of processes: it receives a question about a specific field, analyzes the content of the question to identify a topic, and selects a generative model specialized in a specific expertise based on the topic, thereby generating a specialized answer and sending it to the user's terminal. A specific method for implementing this system is described below, so that staff in a physical store can quickly and accurately answer questions from customers.

[0174] In this system, store staff first input questions from customers using user devices such as smartphones and tablets. The input questions are sent to the server in the form of HTTP requests. The server then analyzes the received questions and uses a text analysis engine to identify specific topics. The text analysis engine used includes a natural language processing library.

[0175] Next, the server selects an appropriate generative AI model from its built-in database based on the identified topic. This generative AI model is trained on specialized data related to a specific field and is capable of providing detailed and accurate answers. By inputting a question into the selected generative AI model, a specialized answer is generated.

[0176] The generated answer is packaged by the server and sent to the user's device in the form of an HTTP response. The user's device then analyzes the received answer and presents it to the staff via a display interface, allowing the staff to provide the answer to the customer quickly and accurately.

[0177] As a concrete example, consider the case where a staff member at a home appliance retail store receives a question from a customer: "Can this TV connect to the Internet?" In this case, the staff member types "Can this TV connect to the Internet?" into their smartphone and sends it. The server receives and analyzes this question, and identifies the topics "Internet connection" and "TV." Then, based on this topic, a generative AI model specialized in home appliances is selected. Finally, the generative AI model generates the answer: "This TV has Wi-Fi functionality and can connect to the Internet," which is then sent to the staff member's smartphone and displayed.

[0178] An example prompt might look like this:

[0179] Q: A customer asks, "Can this TV connect to the Internet?" Please generate a suitable answer.

[0180] In this way, the system enables store staff to provide customers with professional information quickly and accurately.

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1:

[0183] The user inputs a question. A staff member (user) at a physical store inputs the customer's question using a device such as a smartphone or tablet. Once input is complete, the user presses the "Send" button. The input data is the question text. For example, a question might be input such as "Can this TV connect to the Internet?"

[0184] Step 2:

[0185] The device sends the question to the server. The device sends the entered question to the server in the form of an HTTP request. At this time, the information sent is the question text. Specifically, the question text is sent to the server in JSON format.

[0186] Step 3:

[0187] The server receives and analyzes the question. The server extracts the question text from the received HTTP request and passes it to a text analysis engine. The text analysis engine analyzes the question text and identifies topics and keywords. For example, the topics "Internet connection" and "television" are extracted.

[0188] Step 4:

[0189] The server selects a specific generative AI model. Based on the analysis results, the server selects an appropriate generative AI model from its built-in database. In this case, a generative AI model with expertise in "television" and "internet connection" is selected. The input data is the extracted topics, and the output data is the selected generative AI model.

[0190] Step 5:

[0191] The server inputs a question into the generative AI model to generate an answer. The selected generative AI model is then input with the question text to generate an answer. The generative AI model performs advanced text analysis based on the question to create a specialized and detailed answer. For example, the answer generated is "This TV has Wi-Fi functionality and can connect to the Internet." The input data is the question text, and the output data is the generated answer.

[0192] Step 6:

[0193] The server packages the generated answer and sends it. The server packages the generated answer in HTTP response format and sends it to the user terminal. The input data is the generated answer, and the output data is the HTTP response.

[0194] Step 7:

[0195] The terminal receives and displays the answer. The user terminal receives the HTTP response from the server, extracts the answer text, and displays it. The staff member can check the answer displayed on the terminal and provide it to the customer. The input data is the HTTP response, and the output data is the displayed answer text.

[0196] 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.

[0197] The system of the present invention includes a process of receiving a question about a specific field, analyzing the content of the question to identify a topic, selecting a generative model specialized in a specific expertise based on the topic, and further adding an emotion engine that recognizes the user's emotions and adjusts the tone and content of the generated answer to match the user's emotions. This process is realized by the following specific steps.

[0198] Explanation of program processing

[0199] Basic system operation

[0200] 1. User Submission:

[0201] Users use their devices to submit questions about a specific subject, for example, "What should I do to become a YouTuber?", and press the submit button.

[0202] 2. Sending Emotional Data:

[0203] The device analyzes emotional data from the user's facial expressions, voice, and input text, and sends it to the server along with the question.

[0204] 3. Receiving and analyzing question and emotion data:

[0205] The server receives the HTTP request from the device, extracts the question text and emotion data, and stores the question text and emotion data in its internal memory.

[0206] The question text is sent to a text analysis engine to extract the topic and key keywords of the question. For example, the topic "YouTuber" is identified.

[0207] The emotion engine analyzes the emotion data and understands the user's emotional state. For example, emotions such as "excitement" and "anxiety" are recognized.

[0208] 4. Specialized AI model selection and emotion consideration:

[0209] The server selects an appropriate generative AI model based on the analysis results, and calls a generative AI model specialized for YouTubers.

[0210] Based on the analysis results of the emotion engine, the generative AI model is instructed to generate responses with appropriate tone and content. For example, if the user expresses the emotion "anxiety," the response will be generated in a gentle, encouraging tone.

[0211] 5. Generate answers:

[0212] The server inputs the question text and emotional data into the generative AI model, which then generates professional and emotionally sensitive answers, adjusting the content and tone of the answers to match the user's emotions.

[0213] For example, an encouraging response might be generated such as, "Start with small steps. First, make sure you have the equipment and editing software to provide high-quality content. Then, it's important to engage with your audience and take SEO measures. Take it one step at a time and you'll be successful."

[0214] 6. Packaging and sending your response:

[0215] The server packages the generated answer in an HTTP response format and sends it to the user's terminal.

[0216] 7. Show Answer:

[0217] The terminal analyzes the response received from the server, extracts the answer text, and displays it on the user interface.

[0218] 8. User confirmation and next actions:

[0219] Users review the expert answers and emotionally sensitive advice displayed and then decide what to do next, such as buying equipment or starting to learn about SEO.

[0220] Specific examples

[0221] For example, if a user asks "What should I do to become a YouTuber?" and indicates the emotion "anxiety," the following would work:

[0222] The user enters a question, and the emotion engine recognizes anxious facial expressions and tone of voice.

[0223] The device sends the question and emotion data to the server in the form of an HTTP request.

[0224] The server passes the question to a text analysis engine, which identifies the topic "YouTuber."

[0225] The emotion engine reports the emotion "anxiety" to the server.

[0226] The server selects a generative AI model with expertise related to YouTubers and instructs it to generate answers in a tone that takes "anxiety" into consideration.

[0227] The model responds in a gentle tone, saying, "Let's start with small steps. First, make sure you have the equipment and editing software to provide high-quality content. Then, it's important to engage with your audience and take SEO measures. Take it easy, just one step at a time and you'll be successful."

[0228] The server generates a response and sends it to the user's terminal, where the user confirms it.

[0229] In this way, the system of the present invention can provide specialized answers in a particular field that take into consideration the user's feelings.

[0230] The processing flow will be explained below.

[0231] Step 1:

[0232] A user uses the device's interface to enter a question and presses the submit button. For example, the user enters a question such as "What should I do to become a YouTuber?"

[0233] Step 2:

[0234] The device records the user's input as text and uses an emotion engine to analyze the user's emotions based on the user's facial expressions, tone of voice, and the text content entered.

[0235] Step 3:

[0236] The device sends an HTTP request to the server, which includes the question text and the analyzed emotion data. This request includes the question entered by the user and the emotion data analyzed by the emotion engine.

[0237] Step 4:

[0238] The server analyzes the received HTTP request, extracts the question text and emotion data, and stores them in the internal memory.

[0239] Step 5:

[0240] The server sends the question text to a text analysis engine, which analyzes it for topics and keywords. For example, the topic "YouTuber" is identified.

[0241] Step 6:

[0242] Based on the results of the text analysis engine, the server selects the most suitable generative AI model from its internal database, for example, a generative AI model specialized in the YouTuber field.

[0243] Step 7:

[0244] The server evaluates the analysis results of the emotion engine and recognizes the user's emotional state. For example, "anxiety" is recognized from the emotion data.

[0245] Step 8:

[0246] The server inputs the question text and emotional data into the selected generative AI model, which then generates an answer that adjusts the tone and content to match the user's emotional state.

[0247] Step 9:

[0248] The server packages the generated answer and sends it to the user's device in an HTTP response, which contains the answer text in a format that is easily understandable to the user.

[0249] Step 10:

[0250] The terminal analyzes the HTTP response received, extracts the answer text, and displays the extracted answer in the user interface.

[0251] Step 11:

[0252] Users review the expert answers and emotionally sensitive advice displayed and then decide what to do next, such as buying equipment or starting to learn about SEO.

[0253] Example 2

[0254] 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."

[0255] While conventional systems can respond to user questions with specialized content, they are unable to generate answers that take the user's emotions into consideration. As a result, if the user is feeling a particular emotion, such as anxiety or excitement, the answer provided will not be in a tone appropriate to that emotion, resulting in a poor user experience.

[0256] 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.

[0257] In this invention, the server includes means for receiving a question related to a specific field from a user terminal, means for analyzing the received question to identify the topic of the question, means for analyzing the user's emotional data included in the question, means for selecting a generative model specialized in specific expertise based on the identified topic, means for issuing an instruction to generate an answer with adjusted tone and content based on the analyzed emotional data, means for generating a professional and emotionally sensitive answer to the received question using the selected generative model, and means for transmitting the generated answer to the user terminal. This makes it possible to provide a professional answer with content that takes the user's emotions into consideration.

[0258] "User terminal" refers to an electronic device that allows a user to input and send a question, and includes a PC, smartphone, tablet, etc.

[0259] A "question" refers to a user's inquiry about a particular field, and refers to information expressed in natural language format.

[0260] "Receiving" refers to the process of transferring data from a user terminal to a server and having the server take in the data.

[0261] "Analysis" refers to the process of analyzing received questions and sentiment data through computational processing and extracting specific information (topics and sentiments).

[0262] "Topics" refer to the major themes or keywords identified from the content of the question.

[0263] "Emotional data" refers to information that indicates the emotional state of a user analyzed from facial expressions, voice, text input, and the like.

[0264] A "generative model" refers to an algorithm or dataset that generates specialized answers based on a specific topic.

[0265] "Tone" refers to the style used to adjust the expression and emotional nuances of the generated answers.

[0266] "Answer" refers to a professional answer to a user's question generated by a generative model.

[0267] "Sending" refers to the process by which the server transfers the generated response to the user terminal.

[0268] MODE FOR CARRYING OUT THE INVENTION

[0269] The system of this invention includes a process of receiving a question about a specific field, analyzing the content of the question to identify a topic, and selecting a generative model specialized in specific expertise based on that topic.It also includes a process of adding an emotion engine that recognizes the user's emotions and adjusting the tone and content of the generated answer to match the user's emotions.

[0270] To implement this system, the following hardware and software are used.

[0271] 1. User device: An electronic device that allows a user to input and send questions. This can be a PC, tablet, or smartphone. The user device has a built-in camera and microphone that are used to capture the user's facial expressions and tone of voice.

[0272] 2. Server: This is the central hardware that receives questions and emotion data, analyzes them, selects the appropriate generative AI model, and generates answers. The server is equipped with a high-performance processor and is capable of rapid data processing.

[0273] 3. Text analysis engine: Software that runs on a server and analyzes the content of questions and extracts topics and key keywords. A specific example is the Google® Cloud Natural Language API.

[0274] 4. Emotion analysis software: Software for analyzing emotional data from a user's facial expressions, voice, and text input. An example is Microsoft® Azure® Cognitive Services.

[0275] 5. Generative AI model: Refers to an algorithm or dataset that generates expert answers based on a specific topic. The server calls this generative model to generate answers for the user. An example is OpenAI GPT-3.

[0276] A specific example of the process flow and operation is shown below.

[0277] Initial setup and data reception

[0278] 1. The user uses the user device to input a question about a specific field. For example, they input "What should I do to become a YouTuber?" and press the send button.

[0279] 2. The device uses its built-in camera and microphone to capture the user's facial expressions and tone of voice, and then analyzes this data to generate emotion data.

[0280] Data analysis and model selection

[0281] 3. The device sends the analyzed emotion data and the question to the server in the form of an HTTP request.

[0282] 4. The server analyzes the received data and uses a text analysis engine (Google Cloud Natural Language API) to identify the topic and main keywords of the question.

[0283] 5. Using emotion analysis software (Microsoft Azure Cognitive Services), the emotion data is analyzed to identify the user's emotional state (e.g., anxiety).

[0284] Generate and submit answers

[0285] 6. The server selects an appropriate generative AI model (e.g., OpenAI GPT-3) based on the identified topic.

[0286] 7. Based on the emotion data, we create prompts for the generative AI model to generate responses with appropriate tone and content. An example of this prompt is below.

[0287] Q: How do I become a YouTuber?

[0288] Emotion: Anxiety

[0289] Tone: Gentle and encouraging

[0290] 8. The generative AI model generates an answer based on the prompt. For example, it might generate an answer like, "Start with small steps. First, make sure you have the equipment and editing software to provide high-quality content. Then, it's important to engage with your audience and take SEO measures. Take your time and take it one step at a time, and you'll definitely be successful."

[0291] 9. The server sends the generated answer to the user terminal in the form of an HTTP response.

[0292] What the user sees and what to do next

[0293] 10. The user terminal analyzes the received response and displays it on the user interface.

[0294] 11. The user reviews the displayed answers and decides on their next course of action, such as purchasing equipment or starting to learn SEO.

[0295] This enables the system of the present invention to provide specialized answers in a specific field while taking into consideration the user's feelings.

[0296] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0297] Step 1:

[0298] User Submit Question:

[0299] Input: The user types in a question about a specific subject.

[0300] Specific actions: The user enters "What should I do to become a YouTuber?" into the input field on the device and presses the send button.

[0301] Output: The device collects the question text.

[0302] Step 2:

[0303] Sending Emotion Data:

[0304] Input: User facial expressions, voice, and typed text.

[0305] How it works: The device uses a built-in camera and microphone to capture facial expressions and voice, and generates emotion data using emotion analysis software, for example, using Microsoft Azure Cognitive Services.

[0306] Output: The generated emotion data and question text are sent to the server.

[0307] Step 3:

[0308] Receiving and parsing question and sentiment data:

[0309] Input: Question text and emotion data sent from the user's device.

[0310] What it does: The server receives an HTTP request, extracts the question and sentiment data, and stores them in its internal memory. It then sends the question text to a text analysis engine (e.g., Google Cloud Natural Language API) to extract topics and key keywords. It also analyzes the sentiment data using sentiment analysis software to understand the user's emotional state.

[0311] Output: Extracted topics (e.g., "YouTuber") and parsed emotional states (e.g., "anxiety").

[0312] Step 4:

[0313] Specialized AI model selection and emotion consideration:

[0314] Input: Topic, sentiment data.

[0315] Specific operation: The server selects an appropriate generative AI model (e.g., OpenAI GPT-3) based on the topic, and creates prompts based on the emotion data to generate answers with appropriate tone and content for the generative AI model.

[0316] Output: Example prompt:

[0317] Q: How do I become a YouTuber?

[0318] Emotion: Anxiety

[0319] Tone: Gentle and encouraging

[0320] Step 5:

[0321] Generate an answer:

[0322] Input: Question text, emotion data, prompt sentence.

[0323] How it works: The generative AI model receives a prompt and generates a professional and emotionally sensitive response. For example, it generates the following response:

[0324] "Start small. First, make sure you have the equipment and editing software to deliver high-quality content. Then, focus on audience engagement and SEO. Take it one step at a time and you'll be successful."

[0325] Output: The generated answer.

[0326] Step 6:

[0327] Packaging and sending your response:

[0328] Input: The generated answer.

[0329] Specific operation: The server packages the generated answer in the form of an HTTP response, and then sends the answer to the user's device.

[0330] Output: The answer packaged as an HTTP response.

[0331] Step 7:

[0332] Show Answer:

[0333] Input: The response sent by the server.

[0334] Specific operation: The device receives the HTTP response, analyzes and extracts the answer text, and displays the extracted answer in the user interface.

[0335] Output: The answer displayed in the user interface.

[0336] Step 8:

[0337] User confirmation and next actions:

[0338] Input: The displayed answer.

[0339] Specific actions: The user checks the answers displayed on the device, understands them, and decides what to do next. For example, they plan an action such as purchasing a device or starting to learn about SEO.

[0340] Output: Next action plan.

[0341] (Application example 2)

[0342] 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."

[0343] Conventional question-answering systems are unable to provide answers that take into account the user's emotions, limiting their ability to improve user satisfaction. Furthermore, even systems that provide answers specialized in specialized knowledge lack emotional support because they do not consider the user's emotions. The present invention aims to solve these problems and improve the user experience by providing expert advice tailored to the user's emotions.

[0344] 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.

[0345] In this invention, the server includes means for receiving a question related to a specific field, means for analyzing the received question to identify the topic of the question, means for selecting a generative model specialized in specific expertise based on the identified topic, means for receiving and analyzing user emotion data, means for generating a professional and emotion-sensitive answer to the received question and emotion data using the selected generative model, means for transmitting the generated answer to a user terminal, and means for displaying the generated answer on the user terminal, thereby enabling the provision of a professional answer that takes the user's emotions into consideration.

[0346] A "subject-specific question" is a user inquiry related to an area requiring specific expertise.

[0347] "Analysis" is the process of analyzing given data in detail and understanding its structure and meaning.

[0348] "Topic" refers to the central theme or subject of a question.

[0349] A "generative model specialized in specialized knowledge" is an AI model that generates answers based on high levels of specialized knowledge in a specific field.

[0350] "Emotion data" is data that indicates the user's emotional state, and is obtained from voice, text, facial expression information, and the like.

[0351] An "emotionally sensitive response" is a response that reflects the user's current emotional state and is provided in a tone and content that corresponds to that emotion.

[0352] A "generative AI model" is a program or algorithm that uses machine learning and artificial intelligence to generate new information or answers from specific input data.

[0353] A "user terminal" is an electronic device that can be directly operated by a user, and includes a smartphone, a computer, and the like.

[0354] This section describes the mode for carrying out the invention. This system collects user questions and emotion data, and then provides specialized advice based on that data. Each step of this system and the technologies used are described in detail below.

[0355] 1. Basic system configuration

[0356] 1.1 Hardware and Software

[0357] User terminal: A device that is directly operated by the user, such as a smartphone or tablet. This device has the ability to receive user input (text and voice) and send it to a server.

[0358] Server: Located in the cloud, it analyzes the received data and generates appropriate advice. The server uses advanced text analysis engines (e.g., TextBlob) and emotion recognition engines (e.g., EmotionRecognizer).

[0359] Network: The infrastructure that handles data communication between the user terminal and the server, using the HTTP protocol.

[0360] 2. Questions and sentiment data collection

[0361] The user types a question into their smartphone or asks it by voice. The user's device sends the input text and voice data to the server. The emotion recognition engine extracts the user's emotion data from the voice data.

[0362] 3. Data analysis and topic identification

[0363] The server passes the received question to a text analysis engine to identify key topics within the question. This analysis extracts the central theme of the question (e.g., "home security").

[0364] 4. Selecting generative models specialized for expertise

[0365] Once a topic is identified, the server selects a generative AI model that specializes in that topic—for example, a question about home security would select a generative AI model with security-related expertise—while also taking into account the user's emotional data.

[0366] 5. Generating Emotionally Sensitive Answers

[0367] The selected generative AI model uses the question and emotional data to generate a professional answer that takes the user's emotions into consideration. For example, if the user expresses anxiety, the answer will be delivered in a gentle, encouraging tone.

[0368] 6. Submitting and Viewing Your Answers

[0369] The generated answer is sent from the server to the user terminal, which analyzes the answer and displays it on the user interface.

[0370] 7. Specific Examples

[0371] For example, if a user asks on their smartphone, "How can I improve my home security?" along with an anxious tone of voice, the system works as follows:

[0372] The user types a question into their smartphone, and the emotion engine recognizes anxious facial expressions and tone of voice.

[0373] The device sends the question and emotion data to the server in the form of an HTTP request.

[0374] The server passes the question to a text analysis engine, which identifies the topic "home security."

[0375] The emotion engine reports the emotion "anxiety" to the server.

[0376] The server selects a generative AI model with security-related expertise and instructs it to generate answers in a tone that is sensitive to "anxiety."

[0377] The model generates a gentle response: "First, install security cameras and an alarm system. Don't worry, small steps can make a big difference."

[0378] The server generates a response and sends it to the user's terminal, where the user confirms it.

[0379] Prompt Sentence Examples

[0380] "Users are asking, 'How can I make my home more secure?' They're feeling anxious. Be sensitive to their emotions while providing sound advice."

[0381] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0382] Step 1:

[0383] The user uses a smartphone to type or speak a question, and the data entered (text or voice) is collected by the device.

[0384] Step 2:

[0385] The device sends the collected text and voice data to the server in the form of an HTTP request. In the case of voice data, the voice is converted into text beforehand.

[0386] Step 3:

[0387] The server parses the received data and uses a text analysis engine (e.g., TextBlob) to extract key topics from the question, e.g., "How can I improve my home security?", identifying the topic "home security."

[0388] Step 4:

[0389] The server uses an emotion recognition engine (e.g., EmotionRecognizer) to extract emotions from voice and facial expression data, thereby recognizing emotions such as "anxiety" and "excitement."

[0390] Step 5:

[0391] Based on the identified topic, the server selects a generative AI model with the appropriate expertise, for example, a generative AI model specializing in "home security."

[0392] Step 6:

[0393] The selected generative AI model is fed with the question text and emotion data, and an answer is generated based on the prompt (e.g., "The user is asking, 'How can I improve the security of my home?' The user is feeling anxious. Please provide appropriate advice while taking their emotions into consideration.").

[0394] Step 7:

[0395] The generated answer is sent from the server to the user terminal in the form of an HTTP response.

[0396] Step 8:

[0397] The device analyzes the received response and displays it on the user interface in a format that is easy for the user to understand.

[0398] Step 9:

[0399] The user checks the displayed answers and takes appropriate action, such as considering installing security cameras.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] [Second embodiment]

[0404] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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).

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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."

[0416] The system of the present invention executes a series of processes: it receives a question about a specific field, analyzes the content of the question to identify a topic, selects a generative model specialized in specific expertise based on that topic, generates a specialized answer, and sends it to the user terminal.

[0417] Explanation of program processing

[0418] Basic system operation

[0419] 1. User Submission:

[0420] A user uses their device to submit a question about a specific subject. The user enters the question into the device's interface and presses the "Submit" button. For example, the user enters a question like, "What should I do to become a YouTuber?"

[0421] 2. Receiving and parsing questions:

[0422] The terminal receives the user's input and sends it to the server in the form of an HTTP request.

[0423] The server receives an HTTP request from the terminal and extracts the question text.

[0424] The question text is passed to a text analysis engine for analysis. This analysis identifies the topic and keywords of the question. For example, the topic "YouTuber" is identified from the question.

[0425] 3. Selecting specialized AI models:

[0426] Based on the analysis results, the server selects an appropriate generative AI model from its built-in database, in this case a model with specialized knowledge about YouTubers.

[0427] 4. Generate answers:

[0428] The server inputs the question text into the selected generative AI model, which generates a professional answer, with the generative model having advanced text analysis capabilities to provide detailed and accurate answers.

[0429] For example, you might generate an answer like, "Make sure you have the equipment and editing software to deliver high-quality content. Also, engaging with your audience and SEO are important."

[0430] 5. Packaging and sending your response:

[0431] The server packages the generated answer and sends it to the user's terminal as an HTTP response.

[0432] The terminal analyzes the response received from the server and displays the extracted answer on the user interface.

[0433] Specific examples

[0434] For example, if a user asks "What should I do to become a YouTuber?", the following would work:

[0435] When a user inputs a question and presses the send button on the terminal, the terminal sends the question to the server in the form of an HTTP request.

[0436] The server receives the question and uses a text analysis engine to identify the topic "YouTuber."

[0437] Based on the topic, the server selects a generative AI model with YouTuber-related expertise.

[0438] The model generates a detailed answer to the question: "First, make sure you have the equipment and editing software to deliver high-quality content. Second, it's important to engage with your audience and take care of SEO."

[0439] The server sends the generated answer to the user's terminal, and the user checks the answer displayed on the terminal.

[0440] In this way, users can easily obtain specialized and detailed answers. This system allows users who do not have advanced knowledge of a particular field to quickly obtain high-quality information.

[0441] The processing flow will be explained below.

[0442] Step 1:

[0443] A user uses the device's interface to enter a question and presses the submit button. For example, the user enters a question such as "What should I do to become a YouTuber?"

[0444] Step 2:

[0445] The device sends the user's question to the server in the form of an HTTP request, which includes the question text.

[0446] Step 3:

[0447] The server extracts the question text from the HTTP request it receives and stores it in its internal memory.

[0448] Step 4:

[0449] The server sends the question text to a text analysis engine for analysis. The text analysis engine extracts the question's topic and key keywords. For example, the topic "YouTuber" is identified.

[0450] Step 5:

[0451] The server selects an appropriate generative AI model based on the analysis results, and calls up a generative AI model specialized for YouTubers from its internal database.

[0452] Step 6:

[0453] The server inputs the question text into the selected generative AI model. The model generates a professional answer to the question. For example, the answer might be, "Make sure you have the equipment and editing software to deliver high-quality content. It's also important to engage with your audience and take SEO measures."

[0454] Step 7:

[0455] The server packages the generated answer as an HTTP response, which contains the answer text in a user-readable format.

[0456] Step 8:

[0457] The server sends the HTTP response to the user's device.

[0458] Step 9:

[0459] The terminal analyzes the response received from the server, extracts the answer text, and displays the extracted answer on the user interface.

[0460] Step 10:

[0461] Users review the expert answers displayed and decide what to do next based on the results, such as buying equipment or starting to learn about SEO.

[0462] Example 1

[0463] 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."

[0464] Conventional question-answering systems often return generic, non-specialized answers to user questions, making it difficult to provide fully satisfactory answers to questions that require in-depth knowledge of a specific field. Furthermore, there is no established technology for selecting an appropriate generative model for the information a user wants to obtain, which means that obtaining specialized answers requires a great deal of time and effort.

[0465] 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.

[0466] In this invention, the server includes: means for receiving a question related to a specific field from a user terminal; means for analyzing the received question and identifying the topic of the question; means for selecting a generative model specialized in specific expertise based on the identified topic; means for generating a specialized answer to the received question using the selected generative model; means for transmitting the generated answer to the user terminal; means for the user terminal to display the received answer on a user interface; means including a text analysis engine for analyzing the question text; means for selecting an appropriate generative AI model from a built-in database; means for inputting the question text into the selected generative AI model and generating a detailed and accurate answer; and means for packaging the generated answer as an HTTP response and transmitting it to the user terminal. This enables users to obtain quick and specialized answers to questions related to a specific field.

[0467] A "user terminal" is a device through which a user inputs a question and communicates with a server.

[0468] A "question" is text entered by a user seeking knowledge or information.

[0469] A "server" is a central computer system that processes questions received from user terminals and generates answers.

[0470] An "HTTP request" is a request message defined by a communication protocol that is sent from a user terminal to a server.

[0471] A "text analysis engine" is software that analyzes incoming questions and identifies their topics and keywords.

[0472] A "topic" is a major theme or subject that represents the content of a question.

[0473] A "generative model" is an artificial intelligence model that generates expert answers based on a specific topic.

[0474] The "built-in database" is a database in which multiple generative models are stored.

[0475] A "professional response" is a response that contains detailed and accurate information about a specific subject.

[0476] "Packaging" is the process of preparing the generated answer for transmission to the user terminal as an HTTP response.

[0477] An "HTTP response" is a response message defined by a communication protocol that is sent from a server to a user terminal.

[0478] A "user interface" refers to a screen or operating means that allows a user to operate a terminal to input questions and check answers.

[0479] A "detailed and accurate answer" is an answer that provides high-quality information and accurately responds to a user's question.

[0480] The system of the present invention executes a series of processes: it receives a question about a specific field, analyzes the content of the question to identify a topic, selects a generative model specialized in specific expertise based on that topic, generates a specialized answer, and sends it to the user terminal.

[0481] The system components include a user terminal, a server, a text analysis engine, a generative AI model, an embedded database, and a user interface.

[0482] First, a user uses their device to enter a question about a specific field and presses the send button. For example, they can enter a question like, "What should I do to become a YouTuber?"

[0483] The device then sends this question to the server in the form of an HTTP request. The server extracts the question text from the received HTTP request and passes it to a text analysis engine (e.g., SpaCy or NLTK) for analysis. This analysis identifies the topic and keywords of the question. For example, the topic "YouTuber" may be identified from the question text.

[0484] The server then selects an appropriate generative AI model (such as OpenAI GPT-3) from its built-in database based on the analysis results, which is capable of generating detailed and accurate answers based on specific expertise.

[0485] The server inputs the question text into the selected generative AI model and obtains the resulting expert answer. For example, the generative AI model may generate a detailed answer such as, "First, prepare the equipment and editing software to provide high-quality content. Also, audience engagement and SEO are important."

[0486] The server packages this generated answer as an HTTP response and sends it to the user's device. The user's device analyzes the received response and displays it in a user interface. The user can then view the professional and detailed answer on their device screen.

[0487] For example, if a user submits the question "What should I do to become a YouTuber?", the system works as follows:

[0488] The user inputs a question and presses the send button on the terminal.

[0489] The terminal sends the question to the server in the form of an HTTP request.

[0490] The server receives the HTTP request and uses a text analysis engine to identify the topic "YouTuber."

[0491] Based on the topic, the server selects a generative AI model with YouTuber-related expertise.

[0492] The model generates a detailed answer to the question: "First, make sure you have the equipment and editing software to deliver high-quality content. Second, it's important to engage with your audience and take care of SEO."

[0493] The server sends the generated answer to the user's terminal, and the user checks the answer displayed on the terminal.

[0494] Through this process, users can easily obtain specialized and detailed answers. This system allows even users without advanced knowledge of a particular field to quickly obtain high-quality information.

[0495] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0496] Step 1:

[0497] User questions submitted

[0498] A user types a question about a specific topic into an input field on their device. For example, a user types "What should I do to become a YouTuber?" into their device.

[0499] The user then clicks the "Send" button on the terminal interface.

[0500] Input: The question text entered by the user in the input field.

[0501] Output: The HTTP request made on the device side.

[0502] Step 2:

[0503] Receiving and parsing questions

[0504] The device captures the user's question and sends it to the server as an HTTP request.

[0505] The server receives the HTTP request from the terminal and extracts the question text from it.

[0506] The server passes the question text to a text analysis engine (e.g., SpaCy) for analysis.

[0507] Analysis: Use a text analysis engine to identify topics and keywords in the question. For example, identify the topic "YouTuber."

[0508] Input: The HTTP request sent from the device.

[0509] Output: Parsed topic information.

[0510] Step 3:

[0511] Selection of specialized AI models

[0512] Based on the analysis results, the server accesses its built-in database and selects an appropriate generative AI model (e.g., GPT-3).

[0513] The server loads the selected generative AI model and prepares it for query processing.

[0514] Input: Parsed topic information.

[0515] Output: The selected generative AI model.

[0516] Step 4:

[0517] Generate answers

[0518] The server inputs a question text to the selected generative AI model. For example, the server inputs the question "What should I do to become a YouTuber?"

[0519] Generative AI models use advanced text analytics to generate expert answers to questions.

[0520] Generate: For example, generate a specific answer like, "First, make sure you have the equipment and editing software to deliver high-quality content. Also, audience engagement and SEO are important."

[0521] Input: The user's question text.

[0522] Output: The generated expert answer.

[0523] Step 5:

[0524] Packaging and sending answers

[0525] The server packages the generated answer as an HTTP response and sends it to the terminal.

[0526] The terminal analyzes the received HTTP response and displays it on the user interface.

[0527] Packaging: Converting the generated answer into an HTTP response format.

[0528] Input: Generated expert answers.

[0529] Output: The HTTP response sent to the user device.

[0530] Step 6:

[0531] Show Answers

[0532] The terminal analyzes the HTTP response received from the server and extracts the answer text to the question.

[0533] The terminal displays the extracted answers on a user interface.

[0534] Input: Answer data in HTTP response format.

[0535] Output: The answer text that is displayed in the user interface.

[0536] This allows users to view professional and detailed answers on their device screen.

[0537] (Application example 1)

[0538] 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."

[0539] In modern brick-and-mortar stores, staff are required to provide prompt and professional answers to customer questions. However, since not all staff have expert knowledge in all fields, there are problems with delayed or inaccurate answers. The present invention aims to provide a system that enables brick-and-mortar store staff to provide prompt and accurate professional answers to customer questions.

[0540] 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.

[0541] In this invention, the server includes means for receiving a question related to a specific field, means for analyzing the received question to identify the topic of the question, means for selecting a generative model specialized in specific expertise based on the identified topic, means for generating a specialized answer to the received question using the selected generative model, means for transmitting the generated answer to a user terminal, and means for inputting a question from a terminal used by staff at a physical store and presenting the specialized answer, thereby enabling staff at the physical store to provide specialized answers to customers quickly and accurately.

[0542] A "question about a specific field" is a question or inquiry entered by a user based on a specific knowledge area or theme.

[0543] The "receiving means" is an interface for receiving input from the user and transmitting it to the server.

[0544] The "means of analyzing and identifying the topic of the question" is a function that performs natural language analysis on the content of the received question and extracts and identifies the topic and keywords.

[0545] A "generative model with specialized knowledge" is an artificial intelligence model that is trained on specialized data about a specific field or topic.

[0546] The "selection means" is a process for selecting an appropriate generative model from the database based on the analysis results.

[0547] The "means for generating expert answers" is a function that uses a selected generative model to create an answer to a received question.

[0548] The "means for transmitting to the user terminal" is a function for transmitting the generated answer to the terminal used by the user and displaying it.

[0549] "Store staff" refers to employees who actually deal with customers in the store.

[0550] "Means for inputting questions from a terminal and receiving expert answers" refers to an interface that allows staff at a physical store to input questions on a device used by the staff and receive and display answers from the server.

[0551] The system of the present invention executes a series of processes: it receives a question about a specific field, analyzes the content of the question to identify a topic, and selects a generative model specialized in a specific expertise based on the topic, thereby generating a specialized answer and sending it to the user's terminal. A specific method for implementing this system is described below, so that staff in a physical store can quickly and accurately answer questions from customers.

[0552] In this system, store staff first input questions from customers using user devices such as smartphones and tablets. The input questions are sent to the server in the form of HTTP requests. The server then analyzes the received questions and uses a text analysis engine to identify specific topics. The text analysis engine used includes a natural language processing library.

[0553] Next, the server selects an appropriate generative AI model from its built-in database based on the identified topic. This generative AI model is trained on specialized data related to a specific field and is capable of providing detailed and accurate answers. By inputting a question into the selected generative AI model, a specialized answer is generated.

[0554] The generated answer is packaged by the server and sent to the user's device in the form of an HTTP response. The user's device then analyzes the received answer and presents it to the staff via a display interface, allowing the staff to provide the answer to the customer quickly and accurately.

[0555] As a concrete example, consider the case where a staff member at a home appliance retail store receives a question from a customer: "Can this TV connect to the Internet?" In this case, the staff member types "Can this TV connect to the Internet?" into their smartphone and sends it. The server receives and analyzes this question, and identifies the topics "Internet connection" and "TV." Then, based on this topic, a generative AI model specialized in home appliances is selected. Finally, the generative AI model generates the answer: "This TV has Wi-Fi functionality and can connect to the Internet," which is then sent to the staff member's smartphone and displayed.

[0556] An example prompt might look like this:

[0557] Q: A customer asks, "Can this TV connect to the Internet?" Please generate a suitable answer.

[0558] In this way, the system enables store staff to provide customers with professional information quickly and accurately.

[0559] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0560] Step 1:

[0561] The user inputs a question. A staff member (user) at a physical store inputs the customer's question using a device such as a smartphone or tablet. Once input is complete, the user presses the "Send" button. The input data is the question text. For example, a question might be input such as "Can this TV connect to the Internet?"

[0562] Step 2:

[0563] The device sends the question to the server. The device sends the entered question to the server in the form of an HTTP request. At this time, the information sent is the question text. Specifically, the question text is sent to the server in JSON format.

[0564] Step 3:

[0565] The server receives and analyzes the question. The server extracts the question text from the received HTTP request and passes it to a text analysis engine. The text analysis engine analyzes the question text and identifies topics and keywords. For example, the topics "Internet connection" and "television" are extracted.

[0566] Step 4:

[0567] The server selects a specific generative AI model. Based on the analysis results, the server selects an appropriate generative AI model from its built-in database. In this case, a generative AI model with expertise in "television" and "internet connection" is selected. The input data is the extracted topics, and the output data is the selected generative AI model.

[0568] Step 5:

[0569] The server inputs a question into the generative AI model to generate an answer. The selected generative AI model is then input with the question text to generate an answer. The generative AI model performs advanced text analysis based on the question to create a specialized and detailed answer. For example, the answer generated is "This TV has Wi-Fi functionality and can connect to the Internet." The input data is the question text, and the output data is the generated answer.

[0570] Step 6:

[0571] The server packages the generated answer and sends it. The server packages the generated answer in HTTP response format and sends it to the user terminal. The input data is the generated answer, and the output data is the HTTP response.

[0572] Step 7:

[0573] The terminal receives and displays the answer. The user terminal receives the HTTP response from the server, extracts the answer text, and displays it. The staff member can check the answer displayed on the terminal and provide it to the customer. The input data is the HTTP response, and the output data is the displayed answer text.

[0574] 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.

[0575] The system of the present invention includes a process of receiving a question about a specific field, analyzing the content of the question to identify a topic, selecting a generative model specialized in a specific expertise based on the topic, and further adding an emotion engine that recognizes the user's emotions and adjusts the tone and content of the generated answer to match the user's emotions. This process is realized by the following specific steps.

[0576] Explanation of program processing

[0577] Basic system operation

[0578] 1. User Submission:

[0579] Users use their devices to submit questions about a specific subject, for example, "What should I do to become a YouTuber?", and press the submit button.

[0580] 2. Sending Emotional Data:

[0581] The device analyzes emotional data from the user's facial expressions, voice, and input text, and sends it to the server along with the question.

[0582] 3. Receiving and analyzing question and emotion data:

[0583] The server receives the HTTP request from the device, extracts the question text and emotion data, and stores the question text and emotion data in its internal memory.

[0584] The question text is sent to a text analysis engine to extract the topic and key keywords of the question. For example, the topic "YouTuber" is identified.

[0585] The emotion engine analyzes the emotion data and understands the user's emotional state. For example, emotions such as "excitement" and "anxiety" are recognized.

[0586] 4. Specialized AI model selection and emotion consideration:

[0587] The server selects an appropriate generative AI model based on the analysis results, and calls a generative AI model specialized for YouTubers.

[0588] Based on the analysis results of the emotion engine, the generative AI model is instructed to generate responses with appropriate tone and content. For example, if the user expresses the emotion "anxiety," the response will be generated in a gentle, encouraging tone.

[0589] 5. Generate answers:

[0590] The server inputs the question text and emotional data into the generative AI model, which then generates professional and emotionally sensitive answers, adjusting the content and tone of the answers to match the user's emotions.

[0591] For example, an encouraging response might be generated such as, "Start with small steps. First, make sure you have the equipment and editing software to provide high-quality content. Then, it's important to engage with your audience and take SEO measures. Take it one step at a time and you'll be successful."

[0592] 6. Packaging and sending your response:

[0593] The server packages the generated answer in an HTTP response format and sends it to the user's terminal.

[0594] 7. Show Answer:

[0595] The terminal analyzes the response received from the server, extracts the answer text, and displays it on the user interface.

[0596] 8. User confirmation and next actions:

[0597] Users review the expert answers and emotionally sensitive advice displayed and then decide what to do next, such as buying equipment or starting to learn about SEO.

[0598] Specific examples

[0599] For example, if a user asks "What should I do to become a YouTuber?" and indicates the emotion "anxiety," the following would work:

[0600] The user enters a question, and the emotion engine recognizes anxious facial expressions and tone of voice.

[0601] The device sends the question and emotion data to the server in the form of an HTTP request.

[0602] The server passes the question to a text analysis engine, which identifies the topic "YouTuber."

[0603] The emotion engine reports the emotion "anxiety" to the server.

[0604] The server selects a generative AI model with expertise related to YouTubers and instructs it to generate answers in a tone that takes "anxiety" into consideration.

[0605] The model responds in a gentle tone, saying, "Let's start with small steps. First, make sure you have the equipment and editing software to provide high-quality content. Then, it's important to engage with your audience and take SEO measures. Take it easy, just one step at a time and you'll be successful."

[0606] The server generates a response and sends it to the user's terminal, where the user confirms it.

[0607] In this way, the system of the present invention can provide specialized answers in a particular field that take into consideration the user's feelings.

[0608] The processing flow will be explained below.

[0609] Step 1:

[0610] A user uses the device's interface to enter a question and presses the submit button. For example, the user enters a question such as "What should I do to become a YouTuber?"

[0611] Step 2:

[0612] The device records the user's input as text and uses an emotion engine to analyze the user's emotions based on the user's facial expressions, tone of voice, and the text content entered.

[0613] Step 3:

[0614] The device sends an HTTP request to the server, which includes the question text and the analyzed emotion data. This request includes the question entered by the user and the emotion data analyzed by the emotion engine.

[0615] Step 4:

[0616] The server analyzes the received HTTP request, extracts the question text and emotion data, and stores them in the internal memory.

[0617] Step 5:

[0618] The server sends the question text to a text analysis engine, which analyzes it for topics and keywords. For example, the topic "YouTuber" is identified.

[0619] Step 6:

[0620] Based on the results of the text analysis engine, the server selects the most suitable generative AI model from its internal database, for example, a generative AI model specialized in the YouTuber field.

[0621] Step 7:

[0622] The server evaluates the analysis results of the emotion engine and recognizes the user's emotional state. For example, "anxiety" is recognized from the emotion data.

[0623] Step 8:

[0624] The server inputs the question text and emotional data into the selected generative AI model, which then generates an answer that adjusts the tone and content to match the user's emotional state.

[0625] Step 9:

[0626] The server packages the generated answer and sends it to the user's device in an HTTP response, which contains the answer text in a format that is easily understandable to the user.

[0627] Step 10:

[0628] The terminal analyzes the HTTP response received, extracts the answer text, and displays the extracted answer in the user interface.

[0629] Step 11:

[0630] Users review the expert answers and emotionally sensitive advice displayed and then decide what to do next, such as buying equipment or starting to learn about SEO.

[0631] Example 2

[0632] 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."

[0633] While conventional systems can respond to user questions with specialized content, they are unable to generate answers that take the user's emotions into consideration. As a result, if the user is feeling a particular emotion, such as anxiety or excitement, the answer provided will not be in a tone appropriate to that emotion, resulting in a poor user experience.

[0634] 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.

[0635] In this invention, the server includes means for receiving a question related to a specific field from a user terminal, means for analyzing the received question to identify the topic of the question, means for analyzing the user's emotional data included in the question, means for selecting a generative model specialized in specific expertise based on the identified topic, means for issuing an instruction to generate an answer with adjusted tone and content based on the analyzed emotional data, means for generating a professional and emotionally sensitive answer to the received question using the selected generative model, and means for transmitting the generated answer to the user terminal. This makes it possible to provide a professional answer with content that takes the user's emotions into consideration.

[0636] "User terminal" refers to an electronic device that allows a user to input and send a question, and includes a PC, smartphone, tablet, etc.

[0637] A "question" refers to a user's inquiry about a particular field, and refers to information expressed in natural language format.

[0638] "Receiving" refers to the process of transferring data from a user terminal to a server and having the server take in the data.

[0639] "Analysis" refers to the process of analyzing received questions and sentiment data through computational processing and extracting specific information (topics and sentiments).

[0640] "Topics" refer to the major themes or keywords identified from the content of the question.

[0641] "Emotional data" refers to information that indicates the emotional state of a user analyzed from facial expressions, voice, text input, and the like.

[0642] A "generative model" refers to an algorithm or dataset that generates specialized answers based on a specific topic.

[0643] "Tone" refers to the style used to adjust the expression and emotional nuances of the generated answers.

[0644] "Answer" refers to a professional answer to a user's question generated by a generative model.

[0645] "Sending" refers to the process by which the server transfers the generated response to the user terminal.

[0646] MODE FOR CARRYING OUT THE INVENTION

[0647] The system of this invention includes a process of receiving a question about a specific field, analyzing the content of the question to identify a topic, and selecting a generative model specialized in specific expertise based on that topic.It also includes a process of adding an emotion engine that recognizes the user's emotions and adjusting the tone and content of the generated answer to match the user's emotions.

[0648] To implement this system, the following hardware and software are used.

[0649] 1. User device: An electronic device that allows a user to input and send questions. This can be a PC, tablet, or smartphone. The user device has a built-in camera and microphone that are used to capture the user's facial expressions and tone of voice.

[0650] 2. Server: This is the central hardware that receives questions and emotion data, analyzes them, selects the appropriate generative AI model, and generates answers. The server is equipped with a high-performance processor and is capable of rapid data processing.

[0651] 3. Text analysis engine: Software that runs on a server and analyzes the content of questions and extracts topics and key keywords. For example, it uses the Google Cloud Natural Language API.

[0652] 4. Emotion analysis software: Software for analyzing emotional data from a user's facial expressions, voice, and text input. An example is Microsoft Azure Cognitive Services.

[0653] 5. Generative AI model: Refers to an algorithm or dataset that generates expert answers based on a specific topic. The server calls this generative model to generate answers for the user. An example is OpenAI GPT-3.

[0654] A specific example of the process flow and operation is shown below.

[0655] Initial setup and data reception

[0656] 1. The user uses the user device to input a question about a specific field. For example, they input "What should I do to become a YouTuber?" and press the send button.

[0657] 2. The device uses its built-in camera and microphone to capture the user's facial expressions and tone of voice, and then analyzes this data to generate emotion data.

[0658] Data analysis and model selection

[0659] 3. The device sends the analyzed emotion data and the question to the server in the form of an HTTP request.

[0660] 4. The server analyzes the received data and uses a text analysis engine (Google Cloud Natural Language API) to identify the topic and main keywords of the question.

[0661] 5. Using emotion analysis software (Microsoft Azure Cognitive Services), the emotion data is analyzed to identify the user's emotional state (e.g., anxiety).

[0662] Generate and submit answers

[0663] 6. The server selects an appropriate generative AI model (e.g., OpenAI GPT-3) based on the identified topic.

[0664] 7. Based on the emotion data, we create prompts for the generative AI model to generate responses with appropriate tone and content. An example of this prompt is below.

[0665] Q: How do I become a YouTuber?

[0666] Emotion: Anxiety

[0667] Tone: Gentle and encouraging

[0668] 8. The generative AI model generates an answer based on the prompt. For example, it might generate an answer like, "Start with small steps. First, make sure you have the equipment and editing software to provide high-quality content. Then, it's important to engage with your audience and take SEO measures. Take your time and take it one step at a time, and you'll definitely be successful."

[0669] 9. The server sends the generated answer to the user terminal in the form of an HTTP response.

[0670] What the user sees and what to do next

[0671] 10. The user terminal analyzes the received response and displays it on the user interface.

[0672] 11. The user reviews the displayed answers and decides on their next course of action, such as purchasing equipment or starting to learn SEO.

[0673] This enables the system of the present invention to provide specialized answers in a specific field while taking into consideration the user's feelings.

[0674] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0675] Step 1:

[0676] User Submit Question:

[0677] Input: The user types in a question about a specific subject.

[0678] Specific actions: The user enters "What should I do to become a YouTuber?" into the input field on the device and presses the send button.

[0679] Output: The device collects the question text.

[0680] Step 2:

[0681] Sending Emotion Data:

[0682] Input: User facial expressions, voice, and typed text.

[0683] How it works: The device uses a built-in camera and microphone to capture facial expressions and voice, and generates emotion data using emotion analysis software, for example, using Microsoft Azure Cognitive Services.

[0684] Output: The generated emotion data and question text are sent to the server.

[0685] Step 3:

[0686] Receiving and parsing question and sentiment data:

[0687] Input: Question text and emotion data sent from the user's device.

[0688] What it does: The server receives an HTTP request, extracts the question and sentiment data, and stores them in its internal memory. It then sends the question text to a text analysis engine (e.g., Google Cloud Natural Language API) to extract topics and key keywords. It also analyzes the sentiment data using sentiment analysis software to understand the user's emotional state.

[0689] Output: Extracted topics (e.g., "YouTuber") and parsed emotional states (e.g., "anxiety").

[0690] Step 4:

[0691] Specialized AI model selection and emotion consideration:

[0692] Input: Topic, sentiment data.

[0693] Specific operation: The server selects an appropriate generative AI model (e.g., OpenAI GPT-3) based on the topic, and creates prompts based on the emotion data to generate answers with appropriate tone and content for the generative AI model.

[0694] Output: Example prompt:

[0695] Q: How do I become a YouTuber?

[0696] Emotion: Anxiety

[0697] Tone: Gentle and encouraging

[0698] Step 5:

[0699] Generate an answer:

[0700] Input: Question text, emotion data, prompt sentence.

[0701] How it works: The generative AI model receives a prompt and generates a professional and emotionally sensitive response. For example, it generates the following response:

[0702] "Start small. First, make sure you have the equipment and editing software to deliver high-quality content. Then, focus on audience engagement and SEO. Take it one step at a time and you'll be successful."

[0703] Output: The generated answer.

[0704] Step 6:

[0705] Packaging and sending your response:

[0706] Input: The generated answer.

[0707] Specific operation: The server packages the generated answer in the form of an HTTP response, and then sends the answer to the user's device.

[0708] Output: The answer packaged as an HTTP response.

[0709] Step 7:

[0710] Show Answer:

[0711] Input: The response sent by the server.

[0712] Specific operation: The device receives the HTTP response, analyzes and extracts the answer text, and displays the extracted answer in the user interface.

[0713] Output: The answer displayed in the user interface.

[0714] Step 8:

[0715] User confirmation and next actions:

[0716] Input: The displayed answer.

[0717] Specific actions: The user checks the answers displayed on the device, understands them, and decides what to do next. For example, they plan an action such as purchasing a device or starting to learn about SEO.

[0718] Output: Next action plan.

[0719] (Application example 2)

[0720] 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."

[0721] Conventional question-answering systems are unable to provide answers that take into account the user's emotions, limiting their ability to improve user satisfaction. Furthermore, even systems that provide answers specialized in specialized knowledge lack emotional support because they do not consider the user's emotions. The present invention aims to solve these problems and improve the user experience by providing expert advice tailored to the user's emotions.

[0722] 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.

[0723] In this invention, the server includes means for receiving a question related to a specific field, means for analyzing the received question to identify the topic of the question, means for selecting a generative model specialized in specific expertise based on the identified topic, means for receiving and analyzing user emotion data, means for generating a professional and emotion-sensitive answer to the received question and emotion data using the selected generative model, means for transmitting the generated answer to a user terminal, and means for displaying the generated answer on the user terminal, thereby enabling the provision of a professional answer that takes the user's emotions into consideration.

[0724] A "subject-specific question" is a user inquiry related to an area requiring specific expertise.

[0725] "Analysis" is the process of analyzing given data in detail and understanding its structure and meaning.

[0726] "Topic" refers to the central theme or subject of a question.

[0727] A "generative model specialized in specialized knowledge" is an AI model that generates answers based on high levels of specialized knowledge in a specific field.

[0728] "Emotion data" is data that indicates the user's emotional state, and is obtained from voice, text, facial expression information, and the like.

[0729] An "emotionally sensitive response" is a response that reflects the user's current emotional state and is provided in a tone and content that corresponds to that emotion.

[0730] A "generative AI model" is a program or algorithm that uses machine learning and artificial intelligence to generate new information or answers from specific input data.

[0731] A "user terminal" is an electronic device that can be directly operated by a user, and includes a smartphone, a computer, and the like.

[0732] This section describes the mode for carrying out the invention. This system collects user questions and emotion data, and then provides specialized advice based on that data. Each step of this system and the technologies used are described in detail below.

[0733] 1. Basic system configuration

[0734] 1.1 Hardware and Software

[0735] User terminal: A device that is directly operated by the user, such as a smartphone or tablet. This device has the ability to receive user input (text and voice) and send it to a server.

[0736] Server: Located in the cloud, it analyzes the received data and generates appropriate advice. The server uses advanced text analysis engines (e.g., TextBlob) and emotion recognition engines (e.g., EmotionRecognizer).

[0737] Network: The infrastructure that handles data communication between the user terminal and the server, using the HTTP protocol.

[0738] 2. Questions and sentiment data collection

[0739] The user types a question into their smartphone or asks it by voice. The user's device sends the input text and voice data to the server. The emotion recognition engine extracts the user's emotion data from the voice data.

[0740] 3. Data analysis and topic identification

[0741] The server passes the received question to a text analysis engine to identify key topics within the question. This analysis extracts the central theme of the question (e.g., "home security").

[0742] 4. Selecting generative models specialized for expertise

[0743] Once a topic is identified, the server selects a generative AI model that specializes in that topic—for example, a question about home security would select a generative AI model with security-related expertise—while also taking into account the user's emotional data.

[0744] 5. Generating Emotionally Sensitive Answers

[0745] The selected generative AI model uses the question and emotional data to generate a professional answer that takes the user's emotions into consideration. For example, if the user expresses anxiety, the answer will be delivered in a gentle, encouraging tone.

[0746] 6. Submitting and Viewing Your Answers

[0747] The generated answer is sent from the server to the user terminal, which analyzes the answer and displays it on the user interface.

[0748] 7. Specific Examples

[0749] For example, if a user asks on their smartphone, "How can I improve my home security?" along with an anxious tone of voice, the system works as follows:

[0750] The user types a question into their smartphone, and the emotion engine recognizes anxious facial expressions and tone of voice.

[0751] The device sends the question and emotion data to the server in the form of an HTTP request.

[0752] The server passes the question to a text analysis engine, which identifies the topic "home security."

[0753] The emotion engine reports the emotion "anxiety" to the server.

[0754] The server selects a generative AI model with security-related expertise and instructs it to generate answers in a tone that is sensitive to "anxiety."

[0755] The model generates a gentle response: "First, install security cameras and an alarm system. Don't worry, small steps can make a big difference."

[0756] The server generates a response and sends it to the user's terminal, where the user confirms it.

[0757] Prompt Sentence Examples

[0758] "Users are asking, 'How can I make my home more secure?' They're feeling anxious. Be sensitive to their emotions while providing sound advice."

[0759] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0760] Step 1:

[0761] The user uses a smartphone to type or speak a question, and the data entered (text or voice) is collected by the device.

[0762] Step 2:

[0763] The device sends the collected text and voice data to the server in the form of an HTTP request. In the case of voice data, the voice is converted into text beforehand.

[0764] Step 3:

[0765] The server parses the received data and uses a text analysis engine (e.g., TextBlob) to extract key topics from the question, e.g., "How can I improve my home security?", identifying the topic "home security."

[0766] Step 4:

[0767] The server uses an emotion recognition engine (e.g., EmotionRecognizer) to extract emotions from voice and facial expression data, thereby recognizing emotions such as "anxiety" and "excitement."

[0768] Step 5:

[0769] Based on the identified topic, the server selects a generative AI model with the appropriate expertise, for example, a generative AI model specializing in "home security."

[0770] Step 6:

[0771] The selected generative AI model is fed with the question text and emotion data, and an answer is generated based on the prompt (e.g., "The user is asking, 'How can I improve the security of my home?' The user is feeling anxious. Please provide appropriate advice while taking their emotions into consideration.").

[0772] Step 7:

[0773] The generated answer is sent from the server to the user terminal in the form of an HTTP response.

[0774] Step 8:

[0775] The device analyzes the received response and displays it on the user interface in a format that is easy for the user to understand.

[0776] Step 9:

[0777] The user checks the displayed answers and takes appropriate action, such as considering installing security cameras.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] [Third embodiment]

[0782] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0783] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0784] 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).

[0785] 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.

[0786] 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.

[0787] 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).

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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."

[0794] The system of the present invention executes a series of processes: it receives a question about a specific field, analyzes the content of the question to identify a topic, selects a generative model specialized in specific expertise based on that topic, generates a specialized answer, and sends it to the user terminal.

[0795] Explanation of program processing

[0796] Basic system operation

[0797] 1. User Submission:

[0798] A user uses their device to submit a question about a specific subject. The user enters the question into the device's interface and presses the "Submit" button. For example, the user enters a question like, "What should I do to become a YouTuber?"

[0799] 2. Receiving and parsing questions:

[0800] The terminal receives the user's input and sends it to the server in the form of an HTTP request.

[0801] The server receives an HTTP request from the terminal and extracts the question text.

[0802] The question text is passed to a text analysis engine for analysis. This analysis identifies the topic and keywords of the question. For example, the topic "YouTuber" is identified from the question.

[0803] 3. Selecting specialized AI models:

[0804] Based on the analysis results, the server selects an appropriate generative AI model from its built-in database, in this case a model with specialized knowledge about YouTubers.

[0805] 4. Generate answers:

[0806] The server inputs the question text into the selected generative AI model, which generates a professional answer, with the generative model having advanced text analysis capabilities to provide detailed and accurate answers.

[0807] For example, you might generate an answer like, "Make sure you have the equipment and editing software to deliver high-quality content. Also, engaging with your audience and SEO are important."

[0808] 5. Packaging and sending your response:

[0809] The server packages the generated answer and sends it to the user's terminal as an HTTP response.

[0810] The terminal analyzes the response received from the server and displays the extracted answer on the user interface.

[0811] Specific examples

[0812] For example, if a user asks "What should I do to become a YouTuber?", the following would work:

[0813] When a user inputs a question and presses the send button on the terminal, the terminal sends the question to the server in the form of an HTTP request.

[0814] The server receives the question and uses a text analysis engine to identify the topic "YouTuber."

[0815] Based on the topic, the server selects a generative AI model with YouTuber-related expertise.

[0816] The model generates a detailed answer to the question: "First, make sure you have the equipment and editing software to deliver high-quality content. Second, it's important to engage with your audience and take care of SEO."

[0817] The server sends the generated answer to the user's terminal, and the user checks the answer displayed on the terminal.

[0818] In this way, users can easily obtain specialized and detailed answers. This system allows users who do not have advanced knowledge of a particular field to quickly obtain high-quality information.

[0819] The processing flow will be explained below.

[0820] Step 1:

[0821] A user uses the device's interface to enter a question and presses the submit button. For example, the user enters a question such as "What should I do to become a YouTuber?"

[0822] Step 2:

[0823] The device sends the user's question to the server in the form of an HTTP request, which includes the question text.

[0824] Step 3:

[0825] The server extracts the question text from the HTTP request it receives and stores it in its internal memory.

[0826] Step 4:

[0827] The server sends the question text to a text analysis engine for analysis. The text analysis engine extracts the question's topic and key keywords. For example, the topic "YouTuber" is identified.

[0828] Step 5:

[0829] The server selects an appropriate generative AI model based on the analysis results, and calls up a generative AI model specialized for YouTubers from its internal database.

[0830] Step 6:

[0831] The server inputs the question text into the selected generative AI model. The model generates a professional answer to the question. For example, the answer might be, "Make sure you have the equipment and editing software to deliver high-quality content. It's also important to engage with your audience and take SEO measures."

[0832] Step 7:

[0833] The server packages the generated answer as an HTTP response, which contains the answer text in a user-readable format.

[0834] Step 8:

[0835] The server sends the HTTP response to the user's device.

[0836] Step 9:

[0837] The terminal analyzes the response received from the server, extracts the answer text, and displays the extracted answer on the user interface.

[0838] Step 10:

[0839] Users review the expert answers displayed and decide what to do next based on the results, such as buying equipment or starting to learn about SEO.

[0840] Example 1

[0841] 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."

[0842] Conventional question-answering systems often return generic, non-specialized answers to user questions, making it difficult to provide fully satisfactory answers to questions that require in-depth knowledge of a specific field. Furthermore, there is no established technology for selecting an appropriate generative model for the information a user wants to obtain, which means that obtaining specialized answers requires a great deal of time and effort.

[0843] 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.

[0844] In this invention, the server includes: means for receiving a question related to a specific field from a user terminal; means for analyzing the received question and identifying the topic of the question; means for selecting a generative model specialized in specific expertise based on the identified topic; means for generating a specialized answer to the received question using the selected generative model; means for transmitting the generated answer to the user terminal; means for the user terminal to display the received answer on a user interface; means including a text analysis engine for analyzing the question text; means for selecting an appropriate generative AI model from a built-in database; means for inputting the question text into the selected generative AI model and generating a detailed and accurate answer; and means for packaging the generated answer as an HTTP response and transmitting it to the user terminal. This enables users to obtain quick and specialized answers to questions related to a specific field.

[0845] A "user terminal" is a device through which a user inputs a question and communicates with a server.

[0846] A "question" is text entered by a user seeking knowledge or information.

[0847] A "server" is a central computer system that processes questions received from user terminals and generates answers.

[0848] An "HTTP request" is a request message defined by a communication protocol that is sent from a user terminal to a server.

[0849] A "text analysis engine" is software that analyzes incoming questions and identifies their topics and keywords.

[0850] A "topic" is a major theme or subject that represents the content of a question.

[0851] A "generative model" is an artificial intelligence model that generates expert answers based on a specific topic.

[0852] The "built-in database" is a database in which multiple generative models are stored.

[0853] A "professional response" is a response that contains detailed and accurate information about a specific subject.

[0854] "Packaging" is the process of preparing the generated answer for transmission to the user terminal as an HTTP response.

[0855] An "HTTP response" is a response message defined by a communication protocol that is sent from a server to a user terminal.

[0856] A "user interface" refers to a screen or operating means that allows a user to operate a terminal to input questions and check answers.

[0857] A "detailed and accurate answer" is an answer that provides high-quality information and accurately responds to a user's question.

[0858] The system of the present invention executes a series of processes: it receives a question about a specific field, analyzes the content of the question to identify a topic, selects a generative model specialized in specific expertise based on that topic, generates a specialized answer, and sends it to the user terminal.

[0859] The system components include a user terminal, a server, a text analysis engine, a generative AI model, an embedded database, and a user interface.

[0860] First, a user uses their device to enter a question about a specific field and presses the send button. For example, they can enter a question like, "What should I do to become a YouTuber?"

[0861] The device then sends this question to the server in the form of an HTTP request. The server extracts the question text from the received HTTP request and passes it to a text analysis engine (e.g., SpaCy or NLTK) for analysis. This analysis identifies the topic and keywords of the question. For example, the topic "YouTuber" may be identified from the question text.

[0862] The server then selects an appropriate generative AI model (such as OpenAI GPT-3) from its built-in database based on the analysis results, which is capable of generating detailed and accurate answers based on specific expertise.

[0863] The server inputs the question text into the selected generative AI model and obtains the resulting expert answer. For example, the generative AI model may generate a detailed answer such as, "First, prepare the equipment and editing software to provide high-quality content. Also, audience engagement and SEO are important."

[0864] The server packages this generated answer as an HTTP response and sends it to the user's device. The user's device analyzes the received response and displays it in a user interface. The user can then view the professional and detailed answer on their device screen.

[0865] For example, if a user submits the question "What should I do to become a YouTuber?", the system works as follows:

[0866] The user inputs a question and presses the send button on the terminal.

[0867] The terminal sends the question to the server in the form of an HTTP request.

[0868] The server receives the HTTP request and uses a text analysis engine to identify the topic "YouTuber."

[0869] Based on the topic, the server selects a generative AI model with YouTuber-related expertise.

[0870] The model generates a detailed answer to the question: "First, make sure you have the equipment and editing software to deliver high-quality content. Second, it's important to engage with your audience and take care of SEO."

[0871] The server sends the generated answer to the user's terminal, and the user checks the answer displayed on the terminal.

[0872] Through this process, users can easily obtain specialized and detailed answers. This system allows even users without advanced knowledge of a particular field to quickly obtain high-quality information.

[0873] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0874] Step 1:

[0875] User questions submitted

[0876] A user types a question about a specific topic into an input field on their device. For example, a user types "What should I do to become a YouTuber?" into their device.

[0877] The user then clicks the "Send" button on the terminal interface.

[0878] Input: The question text entered by the user in the input field.

[0879] Output: The HTTP request made on the device side.

[0880] Step 2:

[0881] Receiving and parsing questions

[0882] The device captures the user's question and sends it to the server as an HTTP request.

[0883] The server receives the HTTP request from the terminal and extracts the question text from it.

[0884] The server passes the question text to a text analysis engine (e.g., SpaCy) for analysis.

[0885] Analysis: Use a text analysis engine to identify topics and keywords in the question. For example, identify the topic "YouTuber."

[0886] Input: The HTTP request sent from the device.

[0887] Output: Parsed topic information.

[0888] Step 3:

[0889] Selection of specialized AI models

[0890] Based on the analysis results, the server accesses its built-in database and selects an appropriate generative AI model (e.g., GPT-3).

[0891] The server loads the selected generative AI model and prepares it for query processing.

[0892] Input: Parsed topic information.

[0893] Output: The selected generative AI model.

[0894] Step 4:

[0895] Generate answers

[0896] The server inputs a question text to the selected generative AI model. For example, the server inputs the question "What should I do to become a YouTuber?"

[0897] Generative AI models use advanced text analytics to generate expert answers to questions.

[0898] Generate: For example, generate a specific answer like, "First, make sure you have the equipment and editing software to deliver high-quality content. Also, audience engagement and SEO are important."

[0899] Input: The user's question text.

[0900] Output: The generated expert answer.

[0901] Step 5:

[0902] Packaging and sending answers

[0903] The server packages the generated answer as an HTTP response and sends it to the terminal.

[0904] The terminal analyzes the received HTTP response and displays it on the user interface.

[0905] Packaging: Converting the generated answer into an HTTP response format.

[0906] Input: Generated expert answers.

[0907] Output: The HTTP response sent to the user device.

[0908] Step 6:

[0909] Show Answers

[0910] The terminal analyzes the HTTP response received from the server and extracts the answer text to the question.

[0911] The terminal displays the extracted answers on a user interface.

[0912] Input: Answer data in HTTP response format.

[0913] Output: The answer text that is displayed in the user interface.

[0914] This allows users to view professional and detailed answers on their device screen.

[0915] (Application example 1)

[0916] 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."

[0917] In modern brick-and-mortar stores, staff are required to provide prompt and professional answers to customer questions. However, since not all staff have expert knowledge in all fields, there are problems with delayed or inaccurate answers. The present invention aims to provide a system that enables brick-and-mortar store staff to provide prompt and accurate professional answers to customer questions.

[0918] 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.

[0919] In this invention, the server includes means for receiving a question related to a specific field, means for analyzing the received question to identify the topic of the question, means for selecting a generative model specialized in specific expertise based on the identified topic, means for generating a specialized answer to the received question using the selected generative model, means for transmitting the generated answer to a user terminal, and means for inputting a question from a terminal used by staff at a physical store and presenting the specialized answer, thereby enabling staff at the physical store to provide specialized answers to customers quickly and accurately.

[0920] A "question about a specific field" is a question or inquiry entered by a user based on a specific knowledge area or theme.

[0921] The "receiving means" is an interface for receiving input from the user and transmitting it to the server.

[0922] The "means of analyzing and identifying the topic of the question" is a function that performs natural language analysis on the content of the received question and extracts and identifies the topic and keywords.

[0923] A "generative model with specialized knowledge" is an artificial intelligence model that is trained on specialized data about a specific field or topic.

[0924] The "selection means" is a process for selecting an appropriate generative model from the database based on the analysis results.

[0925] The "means for generating expert answers" is a function that uses a selected generative model to create an answer to a received question.

[0926] The "means for transmitting to the user terminal" is a function for transmitting the generated answer to the terminal used by the user and displaying it.

[0927] "Store staff" refers to employees who actually deal with customers in the store.

[0928] "Means for inputting questions from a terminal and receiving expert answers" refers to an interface that allows staff at a physical store to input questions on a device used by the staff and receive and display answers from the server.

[0929] The system of the present invention executes a series of processes: it receives a question about a specific field, analyzes the content of the question to identify a topic, and selects a generative model specialized in a specific expertise based on the topic, thereby generating a specialized answer and sending it to the user's terminal. A specific method for implementing this system is described below, so that staff in a physical store can quickly and accurately answer questions from customers.

[0930] In this system, store staff first input questions from customers using user devices such as smartphones and tablets. The input questions are sent to the server in the form of HTTP requests. The server then analyzes the received questions and uses a text analysis engine to identify specific topics. The text analysis engine used includes a natural language processing library.

[0931] Next, the server selects an appropriate generative AI model from its built-in database based on the identified topic. This generative AI model is trained on specialized data related to a specific field and is capable of providing detailed and accurate answers. By inputting a question into the selected generative AI model, a specialized answer is generated.

[0932] The generated answer is packaged by the server and sent to the user's device in the form of an HTTP response. The user's device then analyzes the received answer and presents it to the staff via a display interface, allowing the staff to provide the answer to the customer quickly and accurately.

[0933] As a concrete example, consider the case where a staff member at a home appliance retail store receives a question from a customer: "Can this TV connect to the Internet?" In this case, the staff member types "Can this TV connect to the Internet?" into their smartphone and sends it. The server receives and analyzes this question, and identifies the topics "Internet connection" and "TV." Then, based on this topic, a generative AI model specialized in home appliances is selected. Finally, the generative AI model generates the answer: "This TV has Wi-Fi functionality and can connect to the Internet," which is then sent to the staff member's smartphone and displayed.

[0934] An example prompt might look like this:

[0935] Q: A customer asks, "Can this TV connect to the Internet?" Please generate a suitable answer.

[0936] In this way, the system enables store staff to provide customers with professional information quickly and accurately.

[0937] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0938] Step 1:

[0939] The user inputs a question. A staff member (user) at a physical store inputs the customer's question using a device such as a smartphone or tablet. Once input is complete, the user presses the "Send" button. The input data is the question text. For example, a question might be input such as "Can this TV connect to the Internet?"

[0940] Step 2:

[0941] The device sends the question to the server. The device sends the entered question to the server in the form of an HTTP request. At this time, the information sent is the question text. Specifically, the question text is sent to the server in JSON format.

[0942] Step 3:

[0943] The server receives and analyzes the question. The server extracts the question text from the received HTTP request and passes it to a text analysis engine. The text analysis engine analyzes the question text and identifies topics and keywords. For example, the topics "Internet connection" and "television" are extracted.

[0944] Step 4:

[0945] The server selects a specific generative AI model. Based on the analysis results, the server selects an appropriate generative AI model from its built-in database. In this case, a generative AI model with expertise in "television" and "internet connection" is selected. The input data is the extracted topics, and the output data is the selected generative AI model.

[0946] Step 5:

[0947] The server inputs a question into the generative AI model to generate an answer. The selected generative AI model is then input with the question text to generate an answer. The generative AI model performs advanced text analysis based on the question to create a specialized and detailed answer. For example, the answer generated is "This TV has Wi-Fi functionality and can connect to the Internet." The input data is the question text, and the output data is the generated answer.

[0948] Step 6:

[0949] The server packages the generated answer and sends it. The server packages the generated answer in HTTP response format and sends it to the user terminal. The input data is the generated answer, and the output data is the HTTP response.

[0950] Step 7:

[0951] The terminal receives and displays the answer. The user terminal receives the HTTP response from the server, extracts the answer text, and displays it. The staff member can check the answer displayed on the terminal and provide it to the customer. The input data is the HTTP response, and the output data is the displayed answer text.

[0952] 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.

[0953] The system of the present invention includes a process of receiving a question about a specific field, analyzing the content of the question to identify a topic, selecting a generative model specialized in a specific expertise based on the topic, and further adding an emotion engine that recognizes the user's emotions and adjusts the tone and content of the generated answer to match the user's emotions. This process is realized by the following specific steps.

[0954] Explanation of program processing

[0955] Basic system operation

[0956] 1. User Submission:

[0957] Users use their devices to submit questions about a specific subject, for example, "What should I do to become a YouTuber?", and press the submit button.

[0958] 2. Sending Emotional Data:

[0959] The device analyzes emotional data from the user's facial expressions, voice, and input text, and sends it to the server along with the question.

[0960] 3. Receiving and analyzing question and emotion data:

[0961] The server receives the HTTP request from the device, extracts the question text and emotion data, and stores the question text and emotion data in its internal memory.

[0962] The question text is sent to a text analysis engine to extract the topic and key keywords of the question. For example, the topic "YouTuber" is identified.

[0963] The emotion engine analyzes the emotion data and understands the user's emotional state. For example, emotions such as "excitement" and "anxiety" are recognized.

[0964] 4. Specialized AI model selection and emotion consideration:

[0965] The server selects an appropriate generative AI model based on the analysis results, and calls a generative AI model specialized for YouTubers.

[0966] Based on the analysis results of the emotion engine, the generative AI model is instructed to generate responses with appropriate tone and content. For example, if the user expresses the emotion "anxiety," the response will be generated in a gentle, encouraging tone.

[0967] 5. Generate answers:

[0968] The server inputs the question text and emotional data into the generative AI model, which then generates professional and emotionally sensitive answers, adjusting the content and tone of the answers to match the user's emotions.

[0969] For example, an encouraging response might be generated such as, "Start with small steps. First, make sure you have the equipment and editing software to provide high-quality content. Then, it's important to engage with your audience and take SEO measures. Take it one step at a time and you'll be successful."

[0970] 6. Packaging and sending your response:

[0971] The server packages the generated answer in an HTTP response format and sends it to the user's terminal.

[0972] 7. Show Answer:

[0973] The terminal analyzes the response received from the server, extracts the answer text, and displays it on the user interface.

[0974] 8. User confirmation and next actions:

[0975] Users review the expert answers and emotionally sensitive advice displayed and then decide what to do next, such as buying equipment or starting to learn about SEO.

[0976] Specific examples

[0977] For example, if a user asks "What should I do to become a YouTuber?" and indicates the emotion "anxiety," the following would work:

[0978] The user enters a question, and the emotion engine recognizes anxious facial expressions and tone of voice.

[0979] The device sends the question and emotion data to the server in the form of an HTTP request.

[0980] The server passes the question to a text analysis engine, which identifies the topic "YouTuber."

[0981] The emotion engine reports the emotion "anxiety" to the server.

[0982] The server selects a generative AI model with expertise related to YouTubers and instructs it to generate answers in a tone that takes "anxiety" into consideration.

[0983] The model responds in a gentle tone, saying, "Let's start with small steps. First, make sure you have the equipment and editing software to provide high-quality content. Then, it's important to engage with your audience and take SEO measures. Take it easy, just one step at a time and you'll be successful."

[0984] The server generates a response and sends it to the user's terminal, where the user confirms it.

[0985] In this way, the system of the present invention can provide specialized answers in a particular field that take into consideration the user's feelings.

[0986] The processing flow will be explained below.

[0987] Step 1:

[0988] A user uses the device's interface to enter a question and presses the submit button. For example, the user enters a question such as "What should I do to become a YouTuber?"

[0989] Step 2:

[0990] The device records the user's input as text and uses an emotion engine to analyze the user's emotions based on the user's facial expressions, tone of voice, and the text content entered.

[0991] Step 3:

[0992] The device sends an HTTP request to the server, which includes the question text and the analyzed emotion data. This request includes the question entered by the user and the emotion data analyzed by the emotion engine.

[0993] Step 4:

[0994] The server analyzes the received HTTP request, extracts the question text and emotion data, and stores them in the internal memory.

[0995] Step 5:

[0996] The server sends the question text to a text analysis engine, which analyzes it for topics and keywords. For example, the topic "YouTuber" is identified.

[0997] Step 6:

[0998] Based on the results of the text analysis engine, the server selects the most suitable generative AI model from its internal database, for example, a generative AI model specialized in the YouTuber field.

[0999] Step 7:

[1000] The server evaluates the analysis results of the emotion engine and recognizes the user's emotional state. For example, "anxiety" is recognized from the emotion data.

[1001] Step 8:

[1002] The server inputs the question text and emotional data into the selected generative AI model, which then generates an answer that adjusts the tone and content to match the user's emotional state.

[1003] Step 9:

[1004] The server packages the generated answer and sends it to the user's device in an HTTP response, which contains the answer text in a format that is easily understandable to the user.

[1005] Step 10:

[1006] The terminal analyzes the HTTP response received, extracts the answer text, and displays the extracted answer in the user interface.

[1007] Step 11:

[1008] Users review the expert answers and emotionally sensitive advice displayed and then decide what to do next, such as buying equipment or starting to learn about SEO.

[1009] Example 2

[1010] 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."

[1011] While conventional systems can respond to user questions with specialized content, they are unable to generate answers that take the user's emotions into consideration. As a result, if the user is feeling a particular emotion, such as anxiety or excitement, the answer provided will not be in a tone appropriate to that emotion, resulting in a poor user experience.

[1012] 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.

[1013] In this invention, the server includes means for receiving a question related to a specific field from a user terminal, means for analyzing the received question to identify the topic of the question, means for analyzing the user's emotional data included in the question, means for selecting a generative model specialized in specific expertise based on the identified topic, means for issuing an instruction to generate an answer with adjusted tone and content based on the analyzed emotional data, means for generating a professional and emotionally sensitive answer to the received question using the selected generative model, and means for transmitting the generated answer to the user terminal. This makes it possible to provide a professional answer with content that takes the user's emotions into consideration.

[1014] "User terminal" refers to an electronic device that allows a user to input and send a question, and includes a PC, smartphone, tablet, etc.

[1015] A "question" refers to a user's inquiry about a particular field, and refers to information expressed in natural language format.

[1016] "Receiving" refers to the process of transferring data from a user terminal to a server and having the server take in the data.

[1017] "Analysis" refers to the process of analyzing received questions and sentiment data through computational processing and extracting specific information (topics and sentiments).

[1018] "Topics" refer to the major themes or keywords identified from the content of the question.

[1019] "Emotional data" refers to information that indicates the emotional state of a user analyzed from facial expressions, voice, text input, and the like.

[1020] A "generative model" refers to an algorithm or dataset that generates specialized answers based on a specific topic.

[1021] "Tone" refers to the style used to adjust the expression and emotional nuances of the generated answers.

[1022] "Answer" refers to a professional answer to a user's question generated by a generative model.

[1023] "Sending" refers to the process by which the server transfers the generated response to the user terminal.

[1024] MODE FOR CARRYING OUT THE INVENTION

[1025] The system of this invention includes a process of receiving a question about a specific field, analyzing the content of the question to identify a topic, and selecting a generative model specialized in specific expertise based on that topic.It also includes a process of adding an emotion engine that recognizes the user's emotions and adjusting the tone and content of the generated answer to match the user's emotions.

[1026] To implement this system, the following hardware and software are used.

[1027] 1. User device: An electronic device that allows a user to input and send questions. This can be a PC, tablet, or smartphone. The user device has a built-in camera and microphone that are used to capture the user's facial expressions and tone of voice.

[1028] 2. Server: This is the central hardware that receives questions and emotion data, analyzes them, selects the appropriate generative AI model, and generates answers. The server is equipped with a high-performance processor and is capable of rapid data processing.

[1029] 3. Text analysis engine: Software that runs on a server and analyzes the content of questions and extracts topics and key keywords. For example, it uses the Google Cloud Natural Language API.

[1030] 4. Emotion analysis software: Software for analyzing emotional data from a user's facial expressions, voice, and text input. An example is Microsoft Azure Cognitive Services.

[1031] 5. Generative AI model: Refers to an algorithm or dataset that generates expert answers based on a specific topic. The server calls this generative model to generate answers for the user. An example is OpenAI GPT-3.

[1032] A specific example of the process flow and operation is shown below.

[1033] Initial setup and data reception

[1034] 1. The user uses the user device to input a question about a specific field. For example, they input "What should I do to become a YouTuber?" and press the send button.

[1035] 2. The device uses its built-in camera and microphone to capture the user's facial expressions and tone of voice, and then analyzes this data to generate emotion data.

[1036] Data analysis and model selection

[1037] 3. The device sends the analyzed emotion data and the question to the server in the form of an HTTP request.

[1038] 4. The server analyzes the received data and uses a text analysis engine (Google Cloud Natural Language API) to identify the topic and main keywords of the question.

[1039] 5. Using emotion analysis software (Microsoft Azure Cognitive Services), the emotion data is analyzed to identify the user's emotional state (e.g., anxiety).

[1040] Generate and submit answers

[1041] 6. The server selects an appropriate generative AI model (e.g., OpenAI GPT-3) based on the identified topic.

[1042] 7. Based on the emotion data, we create prompts for the generative AI model to generate responses with appropriate tone and content. An example of this prompt is below.

[1043] Q: How do I become a YouTuber?

[1044] Emotion: Anxiety

[1045] Tone: Gentle and encouraging

[1046] 8. The generative AI model generates an answer based on the prompt. For example, it might generate an answer like, "Start with small steps. First, make sure you have the equipment and editing software to provide high-quality content. Then, it's important to engage with your audience and take SEO measures. Take your time and take it one step at a time, and you'll definitely be successful."

[1047] 9. The server sends the generated answer to the user terminal in the form of an HTTP response.

[1048] What the user sees and what to do next

[1049] 10. The user terminal analyzes the received response and displays it on the user interface.

[1050] 11. The user reviews the displayed answers and decides on their next course of action, such as purchasing equipment or starting to learn SEO.

[1051] This enables the system of the present invention to provide specialized answers in a specific field while taking into consideration the user's feelings.

[1052] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1053] Step 1:

[1054] User Submit Question:

[1055] Input: The user types in a question about a specific subject.

[1056] Specific actions: The user enters "What should I do to become a YouTuber?" into the input field on the device and presses the send button.

[1057] Output: The device collects the question text.

[1058] Step 2:

[1059] Sending Emotion Data:

[1060] Input: User facial expressions, voice, and typed text.

[1061] How it works: The device uses a built-in camera and microphone to capture facial expressions and voice, and generates emotion data using emotion analysis software, for example, using Microsoft Azure Cognitive Services.

[1062] Output: The generated emotion data and question text are sent to the server.

[1063] Step 3:

[1064] Receiving and parsing question and sentiment data:

[1065] Input: Question text and emotion data sent from the user's device.

[1066] What it does: The server receives an HTTP request, extracts the question and sentiment data, and stores them in its internal memory. It then sends the question text to a text analysis engine (e.g., Google Cloud Natural Language API) to extract topics and key keywords. It also analyzes the sentiment data using sentiment analysis software to understand the user's emotional state.

[1067] Output: Extracted topics (e.g., "YouTuber") and parsed emotional states (e.g., "anxiety").

[1068] Step 4:

[1069] Specialized AI model selection and emotion consideration:

[1070] Input: Topic, sentiment data.

[1071] Specific operation: The server selects an appropriate generative AI model (e.g., OpenAI GPT-3) based on the topic, and creates prompts based on the emotion data to generate answers with appropriate tone and content for the generative AI model.

[1072] Output: Example prompt:

[1073] Q: How do I become a YouTuber?

[1074] Emotion: Anxiety

[1075] Tone: Gentle and encouraging

[1076] Step 5:

[1077] Generate an answer:

[1078] Input: Question text, emotion data, prompt sentence.

[1079] How it works: The generative AI model receives a prompt and generates a professional and emotionally sensitive response. For example, it generates the following response:

[1080] "Start small. First, make sure you have the equipment and editing software to deliver high-quality content. Then, focus on audience engagement and SEO. Take it one step at a time and you'll be successful."

[1081] Output: The generated answer.

[1082] Step 6:

[1083] Packaging and sending your response:

[1084] Input: The generated answer.

[1085] Specific operation: The server packages the generated answer in the form of an HTTP response, and then sends the answer to the user's device.

[1086] Output: The answer packaged as an HTTP response.

[1087] Step 7:

[1088] Show Answer:

[1089] Input: The response sent by the server.

[1090] Specific operation: The device receives the HTTP response, analyzes and extracts the answer text, and displays the extracted answer in the user interface.

[1091] Output: The answer displayed in the user interface.

[1092] Step 8:

[1093] User confirmation and next actions:

[1094] Input: The displayed answer.

[1095] Specific actions: The user checks the answers displayed on the device, understands them, and decides what to do next. For example, they plan an action such as purchasing a device or starting to learn about SEO.

[1096] Output: Next action plan.

[1097] (Application example 2)

[1098] 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."

[1099] Conventional question-answering systems are unable to provide answers that take into account the user's emotions, limiting their ability to improve user satisfaction. Furthermore, even systems that provide answers specialized in specialized knowledge lack emotional support because they do not consider the user's emotions. The present invention aims to solve these problems and improve the user experience by providing expert advice tailored to the user's emotions.

[1100] 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.

[1101] In this invention, the server includes means for receiving a question related to a specific field, means for analyzing the received question to identify the topic of the question, means for selecting a generative model specialized in specific expertise based on the identified topic, means for receiving and analyzing user emotion data, means for generating a professional and emotion-sensitive answer to the received question and emotion data using the selected generative model, means for transmitting the generated answer to a user terminal, and means for displaying the generated answer on the user terminal, thereby enabling the provision of a professional answer that takes the user's emotions into consideration.

[1102] A "subject-specific question" is a user inquiry related to an area requiring specific expertise.

[1103] "Analysis" is the process of analyzing given data in detail and understanding its structure and meaning.

[1104] "Topic" refers to the central theme or subject of a question.

[1105] A "generative model specialized in specialized knowledge" is an AI model that generates answers based on high levels of specialized knowledge in a specific field.

[1106] "Emotion data" is data that indicates the user's emotional state, and is obtained from voice, text, facial expression information, and the like.

[1107] An "emotionally sensitive response" is a response that reflects the user's current emotional state and is provided in a tone and content that corresponds to that emotion.

[1108] A "generative AI model" is a program or algorithm that uses machine learning and artificial intelligence to generate new information or answers from specific input data.

[1109] A "user terminal" is an electronic device that can be directly operated by a user, and includes a smartphone, a computer, and the like.

[1110] This section describes the mode for carrying out the invention. This system collects user questions and emotion data, and then provides specialized advice based on that data. Each step of this system and the technologies used are described in detail below.

[1111] 1. Basic system configuration

[1112] 1.1 Hardware and Software

[1113] User terminal: A device that is directly operated by the user, such as a smartphone or tablet. This device has the ability to receive user input (text and voice) and send it to a server.

[1114] Server: Located in the cloud, it analyzes the received data and generates appropriate advice. The server uses advanced text analysis engines (e.g., TextBlob) and emotion recognition engines (e.g., EmotionRecognizer).

[1115] Network: The infrastructure that handles data communication between the user terminal and the server, using the HTTP protocol.

[1116] 2. Questions and sentiment data collection

[1117] The user types a question into their smartphone or asks it by voice. The user's device sends the input text and voice data to the server. The emotion recognition engine extracts the user's emotion data from the voice data.

[1118] 3. Data analysis and topic identification

[1119] The server passes the received question to a text analysis engine to identify key topics within the question. This analysis extracts the central theme of the question (e.g., "home security").

[1120] 4. Selecting generative models specialized for expertise

[1121] Once a topic is identified, the server selects a generative AI model that specializes in that topic—for example, a question about home security would select a generative AI model with security-related expertise—while also taking into account the user's emotional data.

[1122] 5. Generating Emotionally Sensitive Answers

[1123] The selected generative AI model uses the question and emotional data to generate a professional answer that takes the user's emotions into consideration. For example, if the user expresses anxiety, the answer will be delivered in a gentle, encouraging tone.

[1124] 6. Submitting and Viewing Your Answers

[1125] The generated answer is sent from the server to the user terminal, which analyzes the answer and displays it on the user interface.

[1126] 7. Specific Examples

[1127] For example, if a user asks on their smartphone, "How can I improve my home security?" along with an anxious tone of voice, the system works as follows:

[1128] The user types a question into their smartphone, and the emotion engine recognizes anxious facial expressions and tone of voice.

[1129] The device sends the question and emotion data to the server in the form of an HTTP request.

[1130] The server passes the question to a text analysis engine, which identifies the topic "home security."

[1131] The emotion engine reports the emotion "anxiety" to the server.

[1132] The server selects a generative AI model with security-related expertise and instructs it to generate answers in a tone that is sensitive to "anxiety."

[1133] The model generates a gentle response: "First, install security cameras and an alarm system. Don't worry, small steps can make a big difference."

[1134] The server generates a response and sends it to the user's terminal, where the user confirms it.

[1135] Prompt Sentence Examples

[1136] "Users are asking, 'How can I make my home more secure?' They're feeling anxious. Be sensitive to their emotions while providing sound advice."

[1137] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1138] Step 1:

[1139] The user uses a smartphone to type or speak a question, and the data entered (text or voice) is collected by the device.

[1140] Step 2:

[1141] The device sends the collected text and voice data to the server in the form of an HTTP request. In the case of voice data, the voice is converted into text beforehand.

[1142] Step 3:

[1143] The server parses the received data and uses a text analysis engine (e.g., TextBlob) to extract key topics from the question, e.g., "How can I improve my home security?", identifying the topic "home security."

[1144] Step 4:

[1145] The server uses an emotion recognition engine (e.g., EmotionRecognizer) to extract emotions from voice and facial expression data, thereby recognizing emotions such as "anxiety" and "excitement."

[1146] Step 5:

[1147] Based on the identified topic, the server selects a generative AI model with the appropriate expertise, for example, a generative AI model specializing in "home security."

[1148] Step 6:

[1149] The selected generative AI model is fed with the question text and emotion data, and an answer is generated based on the prompt (e.g., "The user is asking, 'How can I improve the security of my home?' The user is feeling anxious. Please provide appropriate advice while taking their emotions into consideration.").

[1150] Step 7:

[1151] The generated answer is sent from the server to the user terminal in the form of an HTTP response.

[1152] Step 8:

[1153] The device analyzes the received response and displays it on the user interface in a format that is easy for the user to understand.

[1154] Step 9:

[1155] The user checks the displayed answers and takes appropriate action, such as considering installing security cameras.

[1156] 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.

[1157] 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.

[1158] 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.

[1159] [Fourth embodiment]

[1160] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1161] 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.

[1162] 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).

[1163] 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.

[1164] 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.

[1165] 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).

[1166] 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.

[1167] 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.

[1168] 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.

[1169] 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.

[1170] 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.

[1171] 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.

[1172] 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."

[1173] The system of the present invention executes a series of processes: it receives a question about a specific field, analyzes the content of the question to identify a topic, selects a generative model specialized in specific expertise based on that topic, generates a specialized answer, and sends it to the user terminal.

[1174] Explanation of program processing

[1175] Basic system operation

[1176] 1. User Submission:

[1177] A user uses their device to submit a question about a specific subject. The user enters the question into the device's interface and presses the "Submit" button. For example, the user enters a question like, "What should I do to become a YouTuber?"

[1178] 2. Receiving and parsing questions:

[1179] The terminal receives the user's input and sends it to the server in the form of an HTTP request.

[1180] The server receives an HTTP request from the terminal and extracts the question text.

[1181] The question text is passed to a text analysis engine for analysis. This analysis identifies the topic and keywords of the question. For example, the topic "YouTuber" is identified from the question.

[1182] 3. Selecting specialized AI models:

[1183] Based on the analysis results, the server selects an appropriate generative AI model from its built-in database, in this case a model with specialized knowledge about YouTubers.

[1184] 4. Generate answers:

[1185] The server inputs the question text into the selected generative AI model, which generates a professional answer, with the generative model having advanced text analysis capabilities to provide detailed and accurate answers.

[1186] For example, you might generate an answer like, "Make sure you have the equipment and editing software to deliver high-quality content. Also, engaging with your audience and SEO are important."

[1187] 5. Packaging and sending your response:

[1188] The server packages the generated answer and sends it to the user's terminal as an HTTP response.

[1189] The terminal analyzes the response received from the server and displays the extracted answer on the user interface.

[1190] Specific examples

[1191] For example, if a user asks "What should I do to become a YouTuber?", the following would work:

[1192] When a user inputs a question and presses the send button on the terminal, the terminal sends the question to the server in the form of an HTTP request.

[1193] The server receives the question and uses a text analysis engine to identify the topic "YouTuber."

[1194] Based on the topic, the server selects a generative AI model with YouTuber-related expertise.

[1195] The model generates a detailed answer to the question: "First, make sure you have the equipment and editing software to deliver high-quality content. Second, it's important to engage with your audience and take care of SEO."

[1196] The server sends the generated answer to the user's terminal, and the user checks the answer displayed on the terminal.

[1197] In this way, users can easily obtain specialized and detailed answers. This system allows users who do not have advanced knowledge of a particular field to quickly obtain high-quality information.

[1198] The processing flow will be explained below.

[1199] Step 1:

[1200] A user uses the device's interface to enter a question and presses the submit button. For example, the user enters a question such as "What should I do to become a YouTuber?"

[1201] Step 2:

[1202] The device sends the user's question to the server in the form of an HTTP request, which includes the question text.

[1203] Step 3:

[1204] The server extracts the question text from the HTTP request it receives and stores it in its internal memory.

[1205] Step 4:

[1206] The server sends the question text to a text analysis engine for analysis. The text analysis engine extracts the question's topic and key keywords. For example, the topic "YouTuber" is identified.

[1207] Step 5:

[1208] The server selects an appropriate generative AI model based on the analysis results, and calls up a generative AI model specialized for YouTubers from its internal database.

[1209] Step 6:

[1210] The server inputs the question text into the selected generative AI model. The model generates a professional answer to the question. For example, the answer might be, "Make sure you have the equipment and editing software to deliver high-quality content. It's also important to engage with your audience and take SEO measures."

[1211] Step 7:

[1212] The server packages the generated answer as an HTTP response, which contains the answer text in a user-readable format.

[1213] Step 8:

[1214] The server sends the HTTP response to the user's device.

[1215] Step 9:

[1216] The terminal analyzes the response received from the server, extracts the answer text, and displays the extracted answer on the user interface.

[1217] Step 10:

[1218] Users review the expert answers displayed and decide what to do next based on the results, such as buying equipment or starting to learn about SEO.

[1219] Example 1

[1220] 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."

[1221] Conventional question-answering systems often return generic, non-specialized answers to user questions, making it difficult to provide fully satisfactory answers to questions that require in-depth knowledge of a specific field. Furthermore, there is no established technology for selecting an appropriate generative model for the information a user wants to obtain, which means that obtaining specialized answers requires a great deal of time and effort.

[1222] 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.

[1223] In this invention, the server includes: means for receiving a question related to a specific field from a user terminal; means for analyzing the received question and identifying the topic of the question; means for selecting a generative model specialized in specific expertise based on the identified topic; means for generating a specialized answer to the received question using the selected generative model; means for transmitting the generated answer to the user terminal; means for the user terminal to display the received answer on a user interface; means including a text analysis engine for analyzing the question text; means for selecting an appropriate generative AI model from a built-in database; means for inputting the question text into the selected generative AI model and generating a detailed and accurate answer; and means for packaging the generated answer as an HTTP response and transmitting it to the user terminal. This enables users to obtain quick and specialized answers to questions related to a specific field.

[1224] A "user terminal" is a device through which a user inputs a question and communicates with a server.

[1225] A "question" is text entered by a user seeking knowledge or information.

[1226] A "server" is a central computer system that processes questions received from user terminals and generates answers.

[1227] An "HTTP request" is a request message defined by a communication protocol that is sent from a user terminal to a server.

[1228] A "text analysis engine" is software that analyzes incoming questions and identifies their topics and keywords.

[1229] A "topic" is a major theme or subject that represents the content of a question.

[1230] A "generative model" is an artificial intelligence model that generates expert answers based on a specific topic.

[1231] The "built-in database" is a database in which multiple generative models are stored.

[1232] A "professional response" is a response that contains detailed and accurate information about a specific subject.

[1233] "Packaging" is the process of preparing the generated answer for transmission to the user terminal as an HTTP response.

[1234] An "HTTP response" is a response message defined by a communication protocol that is sent from a server to a user terminal.

[1235] A "user interface" refers to a screen or operating means that allows a user to operate a terminal to input questions and check answers.

[1236] A "detailed and accurate answer" is an answer that provides high-quality information and accurately responds to a user's question.

[1237] The system of the present invention executes a series of processes: it receives a question about a specific field, analyzes the content of the question to identify a topic, selects a generative model specialized in specific expertise based on that topic, generates a specialized answer, and sends it to the user terminal.

[1238] The system components include a user terminal, a server, a text analysis engine, a generative AI model, an embedded database, and a user interface.

[1239] First, a user uses their device to enter a question about a specific field and presses the send button. For example, they can enter a question like, "What should I do to become a YouTuber?"

[1240] The device then sends this question to the server in the form of an HTTP request. The server extracts the question text from the received HTTP request and passes it to a text analysis engine (e.g., SpaCy or NLTK) for analysis. This analysis identifies the topic and keywords of the question. For example, the topic "YouTuber" may be identified from the question text.

[1241] The server then selects an appropriate generative AI model (such as OpenAI GPT-3) from its built-in database based on the analysis results, which is capable of generating detailed and accurate answers based on specific expertise.

[1242] The server inputs the question text into the selected generative AI model and obtains the resulting expert answer. For example, the generative AI model may generate a detailed answer such as, "First, prepare the equipment and editing software to provide high-quality content. Also, audience engagement and SEO are important."

[1243] The server packages this generated answer as an HTTP response and sends it to the user's device. The user's device analyzes the received response and displays it in a user interface. The user can then view the professional and detailed answer on their device screen.

[1244] For example, if a user submits the question "What should I do to become a YouTuber?", the system works as follows:

[1245] The user inputs a question and presses the send button on the terminal.

[1246] The terminal sends the question to the server in the form of an HTTP request.

[1247] The server receives the HTTP request and uses a text analysis engine to identify the topic "YouTuber."

[1248] Based on the topic, the server selects a generative AI model with YouTuber-related expertise.

[1249] The model generates a detailed answer to the question: "First, make sure you have the equipment and editing software to deliver high-quality content. Second, it's important to engage with your audience and take care of SEO."

[1250] The server sends the generated answer to the user's terminal, and the user checks the answer displayed on the terminal.

[1251] Through this process, users can easily obtain specialized and detailed answers. This system allows even users without advanced knowledge of a particular field to quickly obtain high-quality information.

[1252] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1253] Step 1:

[1254] User questions submitted

[1255] A user types a question about a specific topic into an input field on their device. For example, a user types "What should I do to become a YouTuber?" into their device.

[1256] The user then clicks the "Send" button on the terminal interface.

[1257] Input: The question text entered by the user in the input field.

[1258] Output: The HTTP request made on the device side.

[1259] Step 2:

[1260] Receiving and parsing questions

[1261] The device captures the user's question and sends it to the server as an HTTP request.

[1262] The server receives the HTTP request from the terminal and extracts the question text from it.

[1263] The server passes the question text to a text analysis engine (e.g., SpaCy) for analysis.

[1264] Analysis: Use a text analysis engine to identify topics and keywords in the question. For example, identify the topic "YouTuber."

[1265] Input: The HTTP request sent from the device.

[1266] Output: Parsed topic information.

[1267] Step 3:

[1268] Selection of specialized AI models

[1269] Based on the analysis results, the server accesses its built-in database and selects an appropriate generative AI model (e.g., GPT-3).

[1270] The server loads the selected generative AI model and prepares it for query processing.

[1271] Input: Parsed topic information.

[1272] Output: The selected generative AI model.

[1273] Step 4:

[1274] Generate answers

[1275] The server inputs a question text to the selected generative AI model. For example, the server inputs the question "What should I do to become a YouTuber?"

[1276] Generative AI models use advanced text analytics to generate expert answers to questions.

[1277] Generate: For example, generate a specific answer like, "First, make sure you have the equipment and editing software to deliver high-quality content. Also, audience engagement and SEO are important."

[1278] Input: The user's question text.

[1279] Output: The generated expert answer.

[1280] Step 5:

[1281] Packaging and sending answers

[1282] The server packages the generated answer as an HTTP response and sends it to the terminal.

[1283] The terminal analyzes the received HTTP response and displays it on the user interface.

[1284] Packaging: Converting the generated answer into an HTTP response format.

[1285] Input: Generated expert answers.

[1286] Output: The HTTP response sent to the user device.

[1287] Step 6:

[1288] Show Answers

[1289] The terminal analyzes the HTTP response received from the server and extracts the answer text to the question.

[1290] The terminal displays the extracted answers on a user interface.

[1291] Input: Answer data in HTTP response format.

[1292] Output: The answer text that is displayed in the user interface.

[1293] This allows users to view professional and detailed answers on their device screen.

[1294] (Application example 1)

[1295] 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."

[1296] In modern brick-and-mortar stores, staff are required to provide prompt and professional answers to customer questions. However, since not all staff have expert knowledge in all fields, there are problems with delayed or inaccurate answers. The present invention aims to provide a system that enables brick-and-mortar store staff to provide prompt and accurate professional answers to customer questions.

[1297] 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.

[1298] In this invention, the server includes means for receiving a question related to a specific field, means for analyzing the received question to identify the topic of the question, means for selecting a generative model specialized in specific expertise based on the identified topic, means for generating a specialized answer to the received question using the selected generative model, means for transmitting the generated answer to a user terminal, and means for inputting a question from a terminal used by staff at a physical store and presenting the specialized answer, thereby enabling staff at the physical store to provide specialized answers to customers quickly and accurately.

[1299] A "question about a specific field" is a question or inquiry entered by a user based on a specific knowledge area or theme.

[1300] The "receiving means" is an interface for receiving input from the user and transmitting it to the server.

[1301] The "means of analyzing and identifying the topic of the question" is a function that performs natural language analysis on the content of the received question and extracts and identifies the topic and keywords.

[1302] A "generative model with specialized knowledge" is an artificial intelligence model that is trained on specialized data about a specific field or topic.

[1303] The "selection means" is a process for selecting an appropriate generative model from the database based on the analysis results.

[1304] The "means for generating expert answers" is a function that uses a selected generative model to create an answer to a received question.

[1305] The "means for transmitting to the user terminal" is a function for transmitting the generated answer to the terminal used by the user and displaying it.

[1306] "Store staff" refers to employees who actually deal with customers in the store.

[1307] "Means for inputting questions from a terminal and receiving expert answers" refers to an interface that allows staff at a physical store to input questions on a device used by the staff and receive and display answers from the server.

[1308] The system of the present invention executes a series of processes: it receives a question about a specific field, analyzes the content of the question to identify a topic, and selects a generative model specialized in a specific expertise based on the topic, thereby generating a specialized answer and sending it to the user's terminal. A specific method for implementing this system is described below, so that staff in a physical store can quickly and accurately answer questions from customers.

[1309] In this system, store staff first input questions from customers using user devices such as smartphones and tablets. The input questions are sent to the server in the form of HTTP requests. The server then analyzes the received questions and uses a text analysis engine to identify specific topics. The text analysis engine used includes a natural language processing library.

[1310] Next, the server selects an appropriate generative AI model from its built-in database based on the identified topic. This generative AI model is trained on specialized data related to a specific field and is capable of providing detailed and accurate answers. By inputting a question into the selected generative AI model, a specialized answer is generated.

[1311] The generated answer is packaged by the server and sent to the user's device in the form of an HTTP response. The user's device then analyzes the received answer and presents it to the staff via a display interface, allowing the staff to provide the answer to the customer quickly and accurately.

[1312] As a concrete example, consider the case where a staff member at a home appliance retail store receives a question from a customer: "Can this TV connect to the Internet?" In this case, the staff member types "Can this TV connect to the Internet?" into their smartphone and sends it. The server receives and analyzes this question, and identifies the topics "Internet connection" and "TV." Then, based on this topic, a generative AI model specialized in home appliances is selected. Finally, the generative AI model generates the answer: "This TV has Wi-Fi functionality and can connect to the Internet," which is then sent to the staff member's smartphone and displayed.

[1313] An example prompt might look like this:

[1314] Q: A customer asks, "Can this TV connect to the Internet?" Please generate a suitable answer.

[1315] In this way, the system enables store staff to provide customers with professional information quickly and accurately.

[1316] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1317] Step 1:

[1318] The user inputs a question. A staff member (user) at a physical store inputs the customer's question using a device such as a smartphone or tablet. Once input is complete, the user presses the "Send" button. The input data is the question text. For example, a question might be input such as "Can this TV connect to the Internet?"

[1319] Step 2:

[1320] The device sends the question to the server. The device sends the entered question to the server in the form of an HTTP request. At this time, the information sent is the question text. Specifically, the question text is sent to the server in JSON format.

[1321] Step 3:

[1322] The server receives and analyzes the question. The server extracts the question text from the received HTTP request and passes it to a text analysis engine. The text analysis engine analyzes the question text and identifies topics and keywords. For example, the topics "Internet connection" and "television" are extracted.

[1323] Step 4:

[1324] The server selects a specific generative AI model. Based on the analysis results, the server selects an appropriate generative AI model from its built-in database. In this case, a generative AI model with expertise in "television" and "internet connection" is selected. The input data is the extracted topics, and the output data is the selected generative AI model.

[1325] Step 5:

[1326] The server inputs a question into the generative AI model to generate an answer. The selected generative AI model is then input with the question text to generate an answer. The generative AI model performs advanced text analysis based on the question to create a specialized and detailed answer. For example, the answer generated is "This TV has Wi-Fi functionality and can connect to the Internet." The input data is the question text, and the output data is the generated answer.

[1327] Step 6:

[1328] The server packages the generated answer and sends it. The server packages the generated answer in HTTP response format and sends it to the user terminal. The input data is the generated answer, and the output data is the HTTP response.

[1329] Step 7:

[1330] The terminal receives and displays the answer. The user terminal receives the HTTP response from the server, extracts the answer text, and displays it. The staff member can check the answer displayed on the terminal and provide it to the customer. The input data is the HTTP response, and the output data is the displayed answer text.

[1331] 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.

[1332] The system of the present invention includes a process of receiving a question about a specific field, analyzing the content of the question to identify a topic, selecting a generative model specialized in a specific expertise based on the topic, and further adding an emotion engine that recognizes the user's emotions and adjusts the tone and content of the generated answer to match the user's emotions. This process is realized by the following specific steps.

[1333] Explanation of program processing

[1334] Basic system operation

[1335] 1. User Submission:

[1336] Users use their devices to submit questions about a specific subject, for example, "What should I do to become a YouTuber?", and press the submit button.

[1337] 2. Sending Emotional Data:

[1338] The device analyzes emotional data from the user's facial expressions, voice, and input text, and sends it to the server along with the question.

[1339] 3. Receiving and analyzing question and emotion data:

[1340] The server receives the HTTP request from the device, extracts the question text and emotion data, and stores the question text and emotion data in its internal memory.

[1341] The question text is sent to a text analysis engine to extract the topic and key keywords of the question. For example, the topic "YouTuber" is identified.

[1342] The emotion engine analyzes the emotion data and understands the user's emotional state. For example, emotions such as "excitement" and "anxiety" are recognized.

[1343] 4. Specialized AI model selection and emotion consideration:

[1344] The server selects an appropriate generative AI model based on the analysis results, and calls a generative AI model specialized for YouTubers.

[1345] Based on the analysis results of the emotion engine, the generative AI model is instructed to generate responses with appropriate tone and content. For example, if the user expresses the emotion "anxiety," the response will be generated in a gentle, encouraging tone.

[1346] 5. Generate answers:

[1347] The server inputs the question text and emotional data into the generative AI model, which then generates professional and emotionally sensitive answers, adjusting the content and tone of the answers to match the user's emotions.

[1348] For example, an encouraging response might be generated such as, "Start with small steps. First, make sure you have the equipment and editing software to provide high-quality content. Then, it's important to engage with your audience and take SEO measures. Take it one step at a time and you'll be successful."

[1349] 6. Packaging and sending your response:

[1350] The server packages the generated answer in an HTTP response format and sends it to the user's terminal.

[1351] 7. Show Answer:

[1352] The terminal analyzes the response received from the server, extracts the answer text, and displays it on the user interface.

[1353] 8. User confirmation and next actions:

[1354] Users review the expert answers and emotionally sensitive advice displayed and then decide what to do next, such as buying equipment or starting to learn about SEO.

[1355] Specific examples

[1356] For example, if a user asks "What should I do to become a YouTuber?" and indicates the emotion "anxiety," the following would work:

[1357] The user enters a question, and the emotion engine recognizes anxious facial expressions and tone of voice.

[1358] The device sends the question and emotion data to the server in the form of an HTTP request.

[1359] The server passes the question to a text analysis engine, which identifies the topic "YouTuber."

[1360] The emotion engine reports the emotion "anxiety" to the server.

[1361] The server selects a generative AI model with expertise related to YouTubers and instructs it to generate answers in a tone that takes "anxiety" into consideration.

[1362] The model responds in a gentle tone, saying, "Let's start with small steps. First, make sure you have the equipment and editing software to provide high-quality content. Then, it's important to engage with your audience and take SEO measures. Take it easy, just one step at a time and you'll be successful."

[1363] The server generates a response and sends it to the user's terminal, where the user confirms it.

[1364] In this way, the system of the present invention can provide specialized answers in a particular field that take into consideration the user's feelings.

[1365] The processing flow will be explained below.

[1366] Step 1:

[1367] A user uses the device's interface to enter a question and presses the submit button. For example, the user enters a question such as "What should I do to become a YouTuber?"

[1368] Step 2:

[1369] The device records the user's input as text and uses an emotion engine to analyze the user's emotions based on the user's facial expressions, tone of voice, and the text content entered.

[1370] Step 3:

[1371] The device sends an HTTP request to the server, which includes the question text and the analyzed emotion data. This request includes the question entered by the user and the emotion data analyzed by the emotion engine.

[1372] Step 4:

[1373] The server analyzes the received HTTP request, extracts the question text and emotion data, and stores them in the internal memory.

[1374] Step 5:

[1375] The server sends the question text to a text analysis engine, which analyzes it for topics and keywords. For example, the topic "YouTuber" is identified.

[1376] Step 6:

[1377] Based on the results of the text analysis engine, the server selects the most suitable generative AI model from its internal database, for example, a generative AI model specialized in the YouTuber field.

[1378] Step 7:

[1379] The server evaluates the analysis results of the emotion engine and recognizes the user's emotional state. For example, "anxiety" is recognized from the emotion data.

[1380] Step 8:

[1381] The server inputs the question text and emotional data into the selected generative AI model, which then generates an answer that adjusts the tone and content to match the user's emotional state.

[1382] Step 9:

[1383] The server packages the generated answer and sends it to the user's device in an HTTP response, which contains the answer text in a format that is easily understandable to the user.

[1384] Step 10:

[1385] The terminal analyzes the HTTP response received, extracts the answer text, and displays the extracted answer in the user interface.

[1386] Step 11:

[1387] Users review the expert answers and emotionally sensitive advice displayed and then decide what to do next, such as buying equipment or starting to learn about SEO.

[1388] Example 2

[1389] 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."

[1390] While conventional systems can respond to user questions with specialized content, they are unable to generate answers that take the user's emotions into consideration. As a result, if the user is feeling a particular emotion, such as anxiety or excitement, the answer provided will not be in a tone appropriate to that emotion, resulting in a poor user experience.

[1391] 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.

[1392] In this invention, the server includes means for receiving a question related to a specific field from a user terminal, means for analyzing the received question to identify the topic of the question, means for analyzing the user's emotional data included in the question, means for selecting a generative model specialized in specific expertise based on the identified topic, means for issuing an instruction to generate an answer with adjusted tone and content based on the analyzed emotional data, means for generating a professional and emotionally sensitive answer to the received question using the selected generative model, and means for transmitting the generated answer to the user terminal. This makes it possible to provide a professional answer with content that takes the user's emotions into consideration.

[1393] "User terminal" refers to an electronic device that allows a user to input and send a question, and includes a PC, smartphone, tablet, etc.

[1394] A "question" refers to a user's inquiry about a particular field, and refers to information expressed in natural language format.

[1395] "Receiving" refers to the process of transferring data from a user terminal to a server and having the server take in the data.

[1396] "Analysis" refers to the process of analyzing received questions and sentiment data through computational processing and extracting specific information (topics and sentiments).

[1397] "Topics" refer to the major themes or keywords identified from the content of the question.

[1398] "Emotional data" refers to information that indicates the emotional state of a user analyzed from facial expressions, voice, text input, and the like.

[1399] A "generative model" refers to an algorithm or dataset that generates specialized answers based on a specific topic.

[1400] "Tone" refers to the style used to adjust the expression and emotional nuances of the generated answers.

[1401] "Answer" refers to a professional answer to a user's question generated by a generative model.

[1402] "Sending" refers to the process by which the server transfers the generated response to the user terminal.

[1403] MODE FOR CARRYING OUT THE INVENTION

[1404] The system of this invention includes a process of receiving a question about a specific field, analyzing the content of the question to identify a topic, and selecting a generative model specialized in specific expertise based on that topic.It also includes a process of adding an emotion engine that recognizes the user's emotions and adjusting the tone and content of the generated answer to match the user's emotions.

[1405] To implement this system, the following hardware and software are used.

[1406] 1. User device: An electronic device that allows a user to input and send questions. This can be a PC, tablet, or smartphone. The user device has a built-in camera and microphone that are used to capture the user's facial expressions and tone of voice.

[1407] 2. Server: This is the central hardware that receives questions and emotion data, analyzes them, selects the appropriate generative AI model, and generates answers. The server is equipped with a high-performance processor and is capable of rapid data processing.

[1408] 3. Text analysis engine: Software that runs on a server and analyzes the content of questions and extracts topics and key keywords. For example, it uses the Google Cloud Natural Language API.

[1409] 4. Emotion analysis software: Software for analyzing emotional data from a user's facial expressions, voice, and text input. An example is Microsoft Azure Cognitive Services.

[1410] 5. Generative AI model: Refers to an algorithm or dataset that generates expert answers based on a specific topic. The server calls this generative model to generate answers for the user. An example is OpenAI GPT-3.

[1411] A specific example of the process flow and operation is shown below.

[1412] Initial setup and data reception

[1413] 1. The user uses the user device to input a question about a specific field. For example, they input "What should I do to become a YouTuber?" and press the send button.

[1414] 2. The device uses its built-in camera and microphone to capture the user's facial expressions and tone of voice, and then analyzes this data to generate emotion data.

[1415] Data analysis and model selection

[1416] 3. The device sends the analyzed emotion data and the question to the server in the form of an HTTP request.

[1417] 4. The server analyzes the received data and uses a text analysis engine (Google Cloud Natural Language API) to identify the topic and main keywords of the question.

[1418] 5. Using emotion analysis software (Microsoft Azure Cognitive Services), the emotion data is analyzed to identify the user's emotional state (e.g., anxiety).

[1419] Generate and submit answers

[1420] 6. The server selects an appropriate generative AI model (e.g., OpenAI GPT-3) based on the identified topic.

[1421] 7. Based on the emotion data, we create prompts for the generative AI model to generate responses with appropriate tone and content. An example of this prompt is below.

[1422] Q: How do I become a YouTuber?

[1423] Emotion: Anxiety

[1424] Tone: Gentle and encouraging

[1425] 8. The generative AI model generates an answer based on the prompt. For example, it might generate an answer like, "Start with small steps. First, make sure you have the equipment and editing software to provide high-quality content. Then, it's important to engage with your audience and take SEO measures. Take your time and take it one step at a time, and you'll definitely be successful."

[1426] 9. The server sends the generated answer to the user terminal in the form of an HTTP response.

[1427] What the user sees and what to do next

[1428] 10. The user terminal analyzes the received response and displays it on the user interface.

[1429] 11. The user reviews the displayed answers and decides on their next course of action, such as purchasing equipment or starting to learn SEO.

[1430] This enables the system of the present invention to provide specialized answers in a specific field while taking into consideration the user's feelings.

[1431] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1432] Step 1:

[1433] User Submit Question:

[1434] Input: The user types in a question about a specific subject.

[1435] Specific actions: The user enters "What should I do to become a YouTuber?" into the input field on the device and presses the send button.

[1436] Output: The device collects the question text.

[1437] Step 2:

[1438] Sending Emotion Data:

[1439] Input: User facial expressions, voice, and typed text.

[1440] How it works: The device uses a built-in camera and microphone to capture facial expressions and voice, and generates emotion data using emotion analysis software, for example, using Microsoft Azure Cognitive Services.

[1441] Output: The generated emotion data and question text are sent to the server.

[1442] Step 3:

[1443] Receiving and parsing question and sentiment data:

[1444] Input: Question text and emotion data sent from the user's device.

[1445] What it does: The server receives an HTTP request, extracts the question and sentiment data, and stores them in its internal memory. It then sends the question text to a text analysis engine (e.g., Google Cloud Natural Language API) to extract topics and key keywords. It also analyzes the sentiment data using sentiment analysis software to understand the user's emotional state.

[1446] Output: Extracted topics (e.g., "YouTuber") and parsed emotional states (e.g., "anxiety").

[1447] Step 4:

[1448] Specialized AI model selection and emotion consideration:

[1449] Input: Topic, sentiment data.

[1450] Specific operation: The server selects an appropriate generative AI model (e.g., OpenAI GPT-3) based on the topic, and creates prompts based on the emotion data to generate answers with appropriate tone and content for the generative AI model.

[1451] Output: Example prompt:

[1452] Q: How do I become a YouTuber?

[1453] Emotion: Anxiety

[1454] Tone: Gentle and encouraging

[1455] Step 5:

[1456] Generate an answer:

[1457] Input: Question text, emotion data, prompt sentence.

[1458] How it works: The generative AI model receives a prompt and generates a professional and emotionally sensitive response. For example, it generates the following response:

[1459] "Start small. First, make sure you have the equipment and editing software to deliver high-quality content. Then, focus on audience engagement and SEO. Take it one step at a time and you'll be successful."

[1460] Output: The generated answer.

[1461] Step 6:

[1462] Packaging and sending your response:

[1463] Input: The generated answer.

[1464] Specific operation: The server packages the generated answer in the form of an HTTP response, and then sends the answer to the user's device.

[1465] Output: The answer packaged as an HTTP response.

[1466] Step 7:

[1467] Show Answer:

[1468] Input: The response sent by the server.

[1469] Specific operation: The device receives the HTTP response, analyzes and extracts the answer text, and displays the extracted answer in the user interface.

[1470] Output: The answer displayed in the user interface.

[1471] Step 8:

[1472] User confirmation and next actions:

[1473] Input: The displayed answer.

[1474] Specific actions: The user checks the answers displayed on the device, understands them, and decides what to do next. For example, they plan an action such as purchasing a device or starting to learn about SEO.

[1475] Output: Next action plan.

[1476] (Application example 2)

[1477] 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."

[1478] Conventional question-answering systems are unable to provide answers that take into account the user's emotions, limiting their ability to improve user satisfaction. Furthermore, even systems that provide answers specialized in specialized knowledge lack emotional support because they do not consider the user's emotions. The present invention aims to solve these problems and improve the user experience by providing expert advice tailored to the user's emotions.

[1479] 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.

[1480] In this invention, the server includes means for receiving a question related to a specific field, means for analyzing the received question to identify the topic of the question, means for selecting a generative model specialized in specific expertise based on the identified topic, means for receiving and analyzing user emotion data, means for generating a professional and emotion-sensitive answer to the received question and emotion data using the selected generative model, means for transmitting the generated answer to a user terminal, and means for displaying the generated answer on the user terminal, thereby enabling the provision of a professional answer that takes the user's emotions into consideration.

[1481] A "subject-specific question" is a user inquiry related to an area requiring specific expertise.

[1482] "Analysis" is the process of analyzing given data in detail and understanding its structure and meaning.

[1483] "Topic" refers to the central theme or subject of a question.

[1484] A "generative model specialized in specialized knowledge" is an AI model that generates answers based on high levels of specialized knowledge in a specific field.

[1485] "Emotion data" is data that indicates the user's emotional state, and is obtained from voice, text, facial expression information, and the like.

[1486] An "emotionally sensitive response" is a response that reflects the user's current emotional state and is provided in a tone and content that corresponds to that emotion.

[1487] A "generative AI model" is a program or algorithm that uses machine learning and artificial intelligence to generate new information or answers from specific input data.

[1488] A "user terminal" is an electronic device that can be directly operated by a user, and includes a smartphone, a computer, and the like.

[1489] This section describes the mode for carrying out the invention. This system collects user questions and emotion data, and then provides specialized advice based on that data. Each step of this system and the technologies used are described in detail below.

[1490] 1. Basic system configuration

[1491] 1.1 Hardware and Software

[1492] User terminal: A device that is directly operated by the user, such as a smartphone or tablet. This device has the ability to receive user input (text and voice) and send it to a server.

[1493] Server: Located in the cloud, it analyzes the received data and generates appropriate advice. The server uses advanced text analysis engines (e.g., TextBlob) and emotion recognition engines (e.g., EmotionRecognizer).

[1494] Network: The infrastructure that handles data communication between the user terminal and the server, using the HTTP protocol.

[1495] 2. Questions and sentiment data collection

[1496] The user types a question into their smartphone or asks it by voice. The user's device sends the input text and voice data to the server. The emotion recognition engine extracts the user's emotion data from the voice data.

[1497] 3. Data analysis and topic identification

[1498] The server passes the received question to a text analysis engine to identify key topics within the question. This analysis extracts the central theme of the question (e.g., "home security").

[1499] 4. Selecting generative models specialized for expertise

[1500] Once a topic is identified, the server selects a generative AI model that specializes in that topic—for example, a question about home security would select a generative AI model with security-related expertise—while also taking into account the user's emotional data.

[1501] 5. Generating Emotionally Sensitive Answers

[1502] The selected generative AI model uses the question and emotional data to generate a professional answer that takes the user's emotions into consideration. For example, if the user expresses anxiety, the answer will be delivered in a gentle, encouraging tone.

[1503] 6. Submitting and Viewing Your Answers

[1504] The generated answer is sent from the server to the user terminal, which analyzes the answer and displays it on the user interface.

[1505] 7. Specific Examples

[1506] For example, if a user asks on their smartphone, "How can I improve my home security?" along with an anxious tone of voice, the system works as follows:

[1507] The user types a question into their smartphone, and the emotion engine recognizes anxious facial expressions and tone of voice.

[1508] The device sends the question and emotion data to the server in the form of an HTTP request.

[1509] The server passes the question to a text analysis engine, which identifies the topic "home security."

[1510] The emotion engine reports the emotion "anxiety" to the server.

[1511] The server selects a generative AI model with security-related expertise and instructs it to generate answers in a tone that is sensitive to "anxiety."

[1512] The model generates a gentle response: "First, install security cameras and an alarm system. Don't worry, small steps can make a big difference."

[1513] The server generates a response and sends it to the user's terminal, where the user confirms it.

[1514] Prompt Sentence Examples

[1515] "Users are asking, 'How can I make my home more secure?' They're feeling anxious. Be sensitive to their emotions while providing sound advice."

[1516] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1517] Step 1:

[1518] The user uses a smartphone to type or speak a question, and the data entered (text or voice) is collected by the device.

[1519] Step 2:

[1520] The device sends the collected text and voice data to the server in the form of an HTTP request. In the case of voice data, the voice is converted into text beforehand.

[1521] Step 3:

[1522] The server parses the received data and uses a text analysis engine (e.g., TextBlob) to extract key topics from the question, e.g., "How can I improve my home security?", identifying the topic "home security."

[1523] Step 4:

[1524] The server uses an emotion recognition engine (e.g., EmotionRecognizer) to extract emotions from voice and facial expression data, thereby recognizing emotions such as "anxiety" and "excitement."

[1525] Step 5:

[1526] Based on the identified topic, the server selects a generative AI model with the appropriate expertise, for example, a generative AI model specializing in "home security."

[1527] Step 6:

[1528] The selected generative AI model is fed with the question text and emotion data, and an answer is generated based on the prompt (e.g., "The user is asking, 'How can I improve the security of my home?' The user is feeling anxious. Please provide appropriate advice while taking their emotions into consideration.").

[1529] Step 7:

[1530] The generated answer is sent from the server to the user terminal in the form of an HTTP response.

[1531] Step 8:

[1532] The device analyzes the received response and displays it on the user interface in a format that is easy for the user to understand.

[1533] Step 9:

[1534] The user checks the displayed answers and takes appropriate action, such as considering installing security cameras.

[1535] 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.

[1536] 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.

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] 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).

[1542] 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.

[1543] 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."

[1544] 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.

[1545] 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).

[1546] 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.

[1547] 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.

[1548] 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.

[1549] 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.

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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.

[1556] The following is further disclosed regarding the above embodiment.

[1557] (Claim 1)

[1558] a means for receiving questions about a particular subject area;

[1559] a means for analyzing the received question to identify the topic of the question;

[1560] A means of selecting generative models that are specialized for specific expertise based on the identified topics; and

[1561] means for generating an expert answer to the received question using the selected generative model;

[1562] and means for transmitting the generated answer to a user terminal.

[1563] (Claim 2)

[1564] 2. The system according to claim 1, wherein the system receives the question from the user terminal in an HTTP request format.

[1565] (Claim 3)

[1566] The system of claim 1, wherein the generative model has advanced text analysis capabilities and generates detailed answers based on specialized knowledge.

[1567] "Example 1"

[1568] (Claim 1)

[1569] means for receiving a question relating to a specific field from a user terminal;

[1570] a means for analyzing the received question to identify the topic of the question;

[1571] A means of selecting generative models that are specialized for specific expertise based on the identified topics; and

[1572] means for generating an expert answer to the received question using the selected generative model;

[1573] means for transmitting the generated answer to a user terminal;

[1574] means for displaying the received answer on a user interface of the user terminal;

[1575] means including a text analysis engine for analyzing question text;

[1576] A means of selecting an appropriate generative AI model from a built-in database; and

[1577] A means for inputting question text into a selected generative AI model to generate detailed and accurate answers; and

[1578] a means for packaging the generated answer as an HTTP response and transmitting it to the user terminal;

[1579] A system including:

[1580] (Claim 2)

[1581] 2. The system according to claim 1, wherein the system receives the question from the user terminal in an HTTP request format.

[1582] (Claim 3)

[1583] The system of claim 1, wherein the generative model has advanced text analysis capabilities and generates detailed answers based on specialized knowledge.

[1584] "Application Example 1"

[1585] (Claim 1)

[1586] a means for receiving questions about a particular subject area;

[1587] a means for analyzing the received question to identify the topic of the question;

[1588] A means of selecting generative models that are specialized for specific expertise based on the identified topics; and

[1589] means for generating an expert answer to the received question using the selected generative model;

[1590] means for transmitting the generated answer to a user terminal;

[1591] A method for staff in physical stores to input questions on devices and receive expert answers.

[1592] A system including:

[1593] (Claim 2)

[1594] 2. The system according to claim 1, wherein the system receives the question from the user terminal in an HTTP request format.

[1595] (Claim 3)

[1596] The system of claim 1, wherein the generative model has advanced text analysis capabilities and generates detailed answers based on specialized knowledge.

[1597] "Example 2: Combining Emotion Engines"

[1598] (Claim 1)

[1599] means for receiving a question relating to a specific field from a user terminal;

[1600] a means for analyzing the received question to identify the topic of the question;

[1601] means for analyzing user emotion data contained in a question;

[1602] A means of selecting generative models that are specialized for specific expertise based on the identified topics; and

[1603] means for instructing the system to generate responses with adjusted tone and content based on the analyzed emotional data;

[1604] means for generating professional and sentiment-sensitive answers to received questions using the selected generative model;

[1605] and means for transmitting the generated answer to a user terminal.

[1606] (Claim 2)

[1607] 2. The system according to claim 1, wherein the system receives the question from the user terminal in an HTTP request format.

[1608] (Claim 3)

[1609] 2. The system according to claim 1, wherein the emotion analysis means analyzes the user's emotions based on facial expressions, voice, and text input.

[1610] "Application example 2 when combining emotion engines"

[1611] (Claim 1)

[1612] a means for receiving questions about a particular subject area;

[1613] a means for analyzing the received question to identify the topic of the question;

[1614] A means of selecting generative models that are specialized for specific expertise based on the identified topics; and

[1615] means for receiving and analyzing user emotion data;

[1616] means for generating, by the selected generative model, an expert and emotion-sensitive answer to the received question and emotion data;

[1617] means for transmitting the generated answer to a user terminal;

[1618] and means for displaying the generated answer on a user terminal.

[1619] (Claim 2)

[1620] 2. The system according to claim 1, wherein the question and emotion data are received from the user terminal in an HTTP request format.

[1621] (Claim 3)

[1622] 10. The system of claim 1, wherein the generative model has advanced text analysis and sentiment analysis capabilities to generate detailed answers based on expertise and sentiment. [Explanation of symbols]

[1623] 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. a means for receiving questions about a particular subject area; a means for analyzing the received question to identify the topic of the question; A means of selecting generative models that are specialized for specific expertise based on the identified topics; and means for generating an expert answer to the received question using the selected generative model; and means for transmitting the generated answer to a user terminal.

2. 2. The system according to claim 1, wherein the system receives a question from a user terminal in the form of an HTTP request.

3. The system of claim 1 , wherein the generative model has advanced text analysis capabilities and generates detailed answers based on specialized knowledge.

Images