System

Abstract

A system is provided.SOLUTION: A system comprising: means for learning from an instruction manual using a generative model to automatically generate an answer to a user query; means for storing query data and analyzing query content; and means for generating a report based on analysis results and providing suggestions for product improvements.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] An increasing number of consumers are becoming confused about how to use home appliances and devices and are experiencing errors. This has resulted in a large number of inquiries being sent to manufacturers' customer support departments, increasing response costs. Furthermore, in a society with a declining birthrate and an aging population, an increasing number of elderly people are unfamiliar with new technologies and products, creating a need for efficient support. Furthermore, while accurate collection and analysis of user feedback is important for product improvement, current systems do not efficiently carry out this process. The present invention aims to provide a new system to address these issues. [Means for solving the problem]

[0005] The present invention solves the above problems by providing a system that includes a means for automatically generating responses to user inquiries by using a generative model to learn from instruction manuals, a means for saving inquiry data and analyzing the content of the inquiries, a means for creating reports based on the analysis results, and a means for providing suggestions for product improvement. Furthermore, by including a means for users to make inquiries in chat format and receive responses, and a means for managing data for each product and providing monthly or quarterly reports to manufacturers, the system simultaneously achieves rapid problem resolution for users and reduces the burden on manufacturers.

[0006] A "generative model" is a program that uses machine learning or artificial intelligence algorithms to generate new information from previously learned data.

[0007] An "instruction manual" is a document containing information on how to use, operate, and troubleshoot an appliance or device.

[0008] "User" refers to a consumer who uses an appliance or device and contacts us for assistance with its use or to resolve any issues.

[0009] "Inquiries" refer to questions about how to use or errors with home appliances or devices, and are sent in chat format.

[0010] "Inquiry data" refers to data that includes information such as the content of inquiries from users, responses to those inquiries, and processing results.

[0011] "Analysis" is the process of analyzing inquiry data to find trends and patterns.

[0012] A "report" is a document summarizing the results of an analysis of inquiry data, and is provided to manufacturers for the purpose of improving products and support quality.

[0013] "Product improvement" refers to making improvements based on analysis results to improve the performance and usability of home appliances and devices.

[0014] "Chat format" refers to an interface for sending and receiving text messages, allowing for real-time communication.

[0015] A "database" is a data management system that efficiently stores and manages large amounts of inquiry data and enables quick access to it. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] The present invention is a user support system for handling home appliances and devices that utilizes generative models. This system allows users to make inquiries in a chat format and quickly obtain information needed to solve problems. Specific embodiments of the present invention are described below.

[0038] User Actions

[0039] Users access the login screen using a device such as a smartphone or PC and enter their account information. After successful login, a chat interface appears. Users use this interface to input questions about home appliances and devices. For example, they might input a question like, "My XYZ manufacturer's ABC123 refrigerator isn't cooling."

[0040] Server Processing

[0041] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model that has been trained in advance from instruction manuals, error code lists, etc. From the analysis results, it generates the optimal answer to the user's question and sends this in chat format to the device. For example, it generates an answer that includes specific steps such as, "If your refrigerator is not cooling, first try the following steps: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked."

[0042] Terminal handling

[0043] The device displays the response received from the server in a chat interface, allowing the user to take steps to resolve the issue and, if necessary, enter further questions for follow-up responses.

[0044] Storage and analysis of inquiry data

[0045] The server stores user inquiries and their responses in a database. This data can then be analyzed later to identify trends and key issues. For example, if the same type of error occurs frequently on a particular model, a solution can be proposed to the manufacturer to fundamentally resolve the issue.

[0046] Report creation and delivery

[0047] Based on the analysis results, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and suggestions for improvement, and are provided to the manufacturer. This information helps the manufacturer improve their products and the quality of their customer support.

[0048] The system of the present invention allows users to enjoy the convenience of quickly resolving problems, and allows manufacturers to obtain data for more efficient response to inquiries and product improvement. As a specific example, when this system was used to handle a refrigerator error, the user was able to resolve the problem in just a few minutes. Furthermore, the manufacturer improved the refrigerator design based on the inquiry data, and the occurrence rate of the same error was significantly reduced in new products.

[0049] As such, the present invention is a system that offers great benefits to both users and manufacturers, and its implementation can significantly improve the user experience of home appliances and devices.

[0050] The processing flow will be explained below.

[0051] Step 1: Log in

[0052] The device displays a login screen and the user enters their account information (username and password).

[0053] The user enters their login information and presses the submit button.

[0054] Step 2: Authentication

[0055] The server receives the login information sent from the terminal.

[0056] The server checks the account information against the database and performs authentication.

[0057] If the authentication is successful, the server generates session information and sends it to the terminal. If the authentication fails, it sends an error message to the terminal.

[0058] Step 3: Displaying the chat interface

[0059] The terminal receives the authentication result from the server, and if the authentication is successful, displays the chat interface.

[0060] Users type questions about home appliances and devices into the chat box.

[0061] Step 4: Receiving and analyzing inquiries

[0062] The server receives the user's inquiry sent from the device, which includes the manufacturer name, model number, and error details.

[0063] The server invokes the generative model to analyze the received query.

[0064] The generative model extracts relevant information from pre-trained instruction manuals and generates the appropriate answer.

[0065] Step 5: Generate and submit your response

[0066] The server organizes the answers received from the generative model and converts them into a user-friendly format.

[0067] The server sends the generated response to the terminal.

[0068] Step 6: View and review your answers

[0069] The terminal displays the response received from the server on the chat interface.

[0070] The user reviews the displayed answer and takes steps, if necessary, to resolve the problem.

[0071] If the user has further questions, they can type them again in the chat box and submit.

[0072] Step 7: Save the inquiry data

[0073] The server stores the user's inquiries and their responses in a database.

[0074] Step 8: Compile data and generate reports

[0075] The server periodically analyzes the accumulated data and compiles information such as inquiry trends and major errors.

[0076] The server creates a report based on the analysis results and provides it to the manufacturer on a monthly or quarterly basis.

[0077] This series of processes allows users to quickly resolve problems with home appliances and devices, and manufacturers to obtain data to respond to inquiries more efficiently and improve their products.

[0078] Example 1

[0079] 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."

[0080] It is difficult to quickly and efficiently answer user questions and resolve issues regarding home appliances and devices, and there is a lack of effective ways to utilize the data obtained during the inquiry process. As a result, it takes time for users to receive appropriate support, and manufacturers also face challenges in improving their products and streamlining the support process.

[0081] 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.

[0082] In this invention, the server includes means for learning from instruction manuals using a generative model and automatically generating responses to user inquiries, means for a user to access a chat interface using a terminal and log in by entering account information, means for inputting a question into the chat interface after logging in and sending it, means for the server to analyze the user's inquiry using the generative model, generate a response, and send it to the terminal, means for the terminal to display the response received from the server on the chat interface and the user to confirm it, means for saving inquiry data and analyzing the content of the inquiry, and means for creating a report based on the analysis results and providing suggestions for product improvement. This allows users to receive quick and accurate support, and enables manufacturers to use the accumulated data to improve their products and streamline their support processes.

[0083] A "generative model" is a mathematical model that uses machine learning algorithms to learn from large amounts of data and generate new data.

[0084] An "instruction manual" is a document that contains information about how to use, set up, and troubleshoot an appliance or device.

[0085] "Inquiry Data" refers to text data regarding questions or problems submitted by users.

[0086] "Chat interface" refers to a user interface that allows a user to communicate with the system in a two-way manner in text format.

[0087] "User" refers to a general consumer or individual who uses this system to receive support for home appliances or devices.

[0088] "Terminal" refers to an information processing device such as a smartphone, PC, or tablet, which is used by a user to access the system.

[0089] A "server" is a computer system that receives data sent by users and performs multiple functions, such as analyzing it using generative models, generating answers, storing data, and creating reports.

[0090] "Login" is the authentication process by which a user enters their account information and begins using the system.

[0091] An "answer" refers to the solution or information provided as a result of the generative model analyzing the user's query.

[0092] A "report" is a document that compiles accumulated inquiry data and analysis results, and is provided to manufacturers to improve their products and the quality of their support processes.

[0093] "Product improvement" refers to efforts to improve the design and functionality of home appliances and devices based on user feedback and inquiry analysis results.

[0094] "Means" is a broad concept that refers to methods, techniques, and devices for realizing a specific function or process.

[0095] This invention is a user support system for home appliances and devices that uses a generative AI model. Its main purpose is to provide fast and effective support by automatically generating answers to user inquiries and storing and analyzing inquiry data.

[0096] Hardware and software used

[0097] Terminal: Information processing device used by the user, such as a smartphone, PC, or tablet.

[0098] Server: A computer system that receives data, analyzes it using a generative AI model, generates answers, stores and analyzes inquiry data, and creates reports.

[0099] Generative AI model: A machine learning algorithm trained from home appliance and device instruction manuals, error code lists, etc. (e.g., OpenAI GPT-4).

[0100] Program processing description

[0101] User Actions

[0102] The user accesses the system's login screen using a device such as a smartphone or PC. By entering their account information (username, password), the user is authenticated to the system. After authentication, the user enters an inquiry through the chat interface. An example of a prompt that the user enters at this time is, "My XYZ manufacturer ABC123 refrigerator is not cooling. What should I do?"

[0103] Server Processing

[0104] The server receives inquiries sent by users. A generative AI model is used to analyze the content of these inquiries. The generative AI model learns from home appliance instruction manuals and error code lists, and generates the optimal answer based on the user's question. For example, if the inquiry is "My refrigerator isn't cooling," the generated answer will include specific steps such as "If your refrigerator isn't cooling, try the following steps: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked."

[0105] The generated answer is sent from the server to the user's device. The server also stores the query and its answer in a database. This stored data is later used to analyze query trends and identify key issues.

[0106] Terminal handling

[0107] The user's device receives the response from the server and displays it in the chat interface. The user can refer to this information to take steps to resolve the issue, and can also enter a new question for further support if necessary.

[0108] Specific examples

[0109] Example of user action: The user types into the chat interface, "My XYZ manufacturer ABC123 refrigerator isn't cooling. What should I do?" and presses the send button.

[0110] Example of server operation: The server sends a query to the generation AI model, generating an answer such as "If the refrigerator is not cooling, try the following steps: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked." and sending it to the device.

[0111] Example of device behavior: The device displays the generated answer in a chat interface, and the user follows the steps to solve the problem.

[0112] This system allows users to receive fast and accurate support, and manufacturers can use the accumulated data to improve their products and streamline their support processes.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1:

[0115] User login and access to the chat interface

[0116] The user accesses the system's login screen using a device (smartphone, PC, etc.). They are authenticated to the system by entering their account information (username, password) on the login screen. If login is successful, the system displays a chat interface to the user.

[0117] Input: Account information (username, password)

[0118] Output: Authentication success / failure, chat interface displayed

[0119] Specific behavior: The user opens a browser or app, accesses the specified URL, enters their account information, and clicks the "Login" button.

[0120] Step 2:

[0121] User inquiries

[0122] Users enter specific inquiries about home appliances and devices into the chat interface and press the send button.

[0123] Input: Text of the inquiry (e.g., "My refrigerator, model ABC123, made by XYZ, is not cooling. What should I do?")

[0124] Output: Sends query data to the server

[0125] Specific operation: The user enters the inquiry content into the chat interface and clicks the "Send" button.

[0126] Step 3:

[0127] Receiving and analyzing inquiries on the server

[0128] The server receives inquiries sent by users. The received text data is sent to a generative AI model, which analyzes the content. The generative AI model is trained from instruction manuals and error code lists.

[0129] Input: Enquiry data

[0130] Output: Analysis results (understanding of query content)

[0131] Specific operation: The server receives the user's query and passes it to the generative AI model to begin analysis.

[0132] Step 4:

[0133] Generating optimal answers on the server

[0134] The generative AI model generates the best possible answer based on the analyzed query, which includes specific instructions and steps.

[0135] Input: Analysis results

[0136] Output: Best answer (text data)

[0137] Specific behavior: The generative AI model generates a specific answer such as, "If your refrigerator is not cooling, try the following steps: 1. Check that the power is supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked."

[0138] Step 5:

[0139] Sending a response from the server to the user's device

[0140] The server then sends the generated response to the user's terminal.

[0141] Input: Best answer (text data)

[0142] Output: Sending response data to the terminal

[0143] Specific operation: The server formats the generated answer and sends it to the user's terminal according to the communication protocol.

[0144] Step 6:

[0145] Display of answers on the device and user responses

[0146] The user's device displays the response received from the server in a chat interface, where the user can review it and try to resolve the issue by following the steps provided.

[0147] Input: Response data

[0148] Output: The response displayed in the chat interface

[0149] Specific operation: The device displays the received response in the chat interface, and the user confirms its content.

[0150] Step 7:

[0151] Storing and post-processing inquiry data

[0152] The server stores the received queries and their responses in a database, which will be used for future analysis and statistics.

[0153] Input: Inquiry data and response data

[0154] Output: Saved database entries

[0155] Specific operation: The server saves the query and response in a database.

[0156] Step 8:

[0157] Regular reporting and provision

[0158] The server periodically analyzes the stored data and generates reports containing inquiry statistics, common problems, and suggestions for improvement. The reports are then provided to the manufacturer.

[0159] Input: Saved data

[0160] Output: Report

[0161] Specific operation: The server analyzes the stored data, generates periodic reports, and provides them to the manufacturer.

[0162] (Application example 1)

[0163] 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."

[0164] With conventional user support systems, it has been difficult for users to quickly obtain appropriate solutions when problems arise with home appliances or electronic devices. Furthermore, manufacturers have limited means to efficiently collect and analyze user inquiry data and use it to improve their products. Virtual stores, in particular, require a system that can provide immediate and accurate support.

[0165] 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.

[0166] In this invention, the server includes means for learning from instruction manuals using a generative model and automatically generating answers to user inquiries, means for saving inquiry data and analyzing the inquiry content, means for creating reports based on the analysis results and providing suggestions for product improvement, means for users to receive support for household appliances and electronic devices in a virtual store, and means for implementing a chatbot function via smartphone to provide quick answers to user questions. This allows users to solve problems in a short time and enables manufacturers to use the collected data to improve their products.

[0167] A "generative model" is an artificial intelligence technology that learns from large amounts of data and automatically generates answers to user inquiries.

[0168] An "instruction manual" is a document that contains detailed instructions on how to use and troubleshoot a household appliance or electronic device.

[0169] "User Inquiry" means a question or problem report submitted by a User seeking support.

[0170] "Auto-generation" is the process of programmatically creating answers or suggestions using artificial intelligence models.

[0171] "Inquiry Data" means records of questions or problems received from users.

[0172] "Analysis of inquiry content" is the process of analyzing received inquiry data and identifying problems and causes.

[0173] A "report" is a document summarizing inquiry data and analysis results, and is intended to be provided to manufacturers.

[0174] A "product improvement proposal" is a specific proposal for improving the performance or quality of a product based on the analysis results of the inquiry data.

[0175] A "virtual store" is a virtual store that sells products and provides services such as customer support over the Internet.

[0176] "Household electrical appliances" refer to electrical equipment used daily in the home.

[0177] An "electronic device" is a device that uses electronic technology to process and communicate information.

[0178] The "chatbot function" is a program that uses artificial intelligence to automatically respond to user input.

[0179] A "smartphone" is a mobile phone that has multiple functions and is capable of running applications.

[0180] The present invention is a system for users to receive support for household appliances and electronic devices in a virtual store. The system uses a generative model to learn from instruction manuals and automatically generate answers to user inquiries. It also stores and analyzes inquiry data to provide reports on product improvements. Specific embodiments of the system are described below.

[0181] User Actions

[0182] Users access the support section of the virtual store using their smartphones. They enter their account information on the login screen, and once logged in, a chat interface appears. Users use this interface to enter questions about their home appliances or electronic devices, for example, "My refrigerator isn't cooling."

[0183] Server Processing

[0184] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model that has been trained in advance from user manuals, error code lists, etc. The generative AI model (e.g., OpenAI's text-davinci-003) is used to generate the optimal answer to the user's question. The generated answer is then sent to the smartphone device in chat format.

[0185] Terminal handling

[0186] The smartphone displays the response received from the server in the chat interface. The user can refer to this and take steps to resolve the problem. For example, in response to a query such as "My refrigerator isn't cooling," the smartphone displays specific steps to improve the situation, such as "Please check that the power is being supplied properly. Please check that the temperature setting is appropriate. Please check that the vents are not blocked." If the user has further questions, they can continue to follow up through the chat interface.

[0187] Storage and analysis of inquiry data

[0188] The server stores user inquiries and their responses in a database. This data can be analyzed to identify trends and key issues. For example, if the same type of error occurs frequently with a particular home appliance, a report can be created to suggest a fundamental solution to the error to the manufacturer. This report is generated monthly or quarterly and provided to the manufacturer.

[0189] Report creation and delivery

[0190] Based on the results of the data analysis, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and suggestions for improvement. The reports are provided to the virtual store manager and the manufacturer, and are used to improve products and customer support quality.

[0191] Examples and prompts

[0192] For example, if a user enters "My refrigerator isn't cooling," the app will call the generative model and automatically generate answers such as, "Please check that the power is coming in properly. Please check that the temperature setting is correct. Please check that the vents are not blocked."

[0193] Prompt Sentence Examples

[0194] User Question: My refrigerator isn't cooling. What should I do?

[0195]

[0196] Generated Answer: If your refrigerator isn't cooling, try these steps first:

[0197] 1. Check if the power is supplied properly.

[0198] 2. Check that the temperature setting is appropriate.

[0199] 3. Check if the ventilation holes are blocked.

[0200] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0201] Step 1:

[0202] Users access the virtual store using their smartphones and log in by entering their account information. After successful login, a chat interface is displayed. Here, users can enter questions about household appliances or electronic devices (e.g., "My refrigerator isn't cooling"). The entered information is then sent to the server.

[0203] Input: User question (text format)

[0204] Output: A query is sent to the server

[0205] Step 2:

[0206] The server receives the question sent by the user and calls a generative AI model (e.g., OpenAI's text-davinci-003) to analyze the received question.

[0207] Input: User's question (in text format)

[0208] Output: The generative AI model is invoked

[0209] Step 3:

[0210] The generative AI model analyzes the content of the inquiry and generates the optimal answer. In this process, it generates a solution to the user's question based on what it has learned in advance from instruction manuals, error code lists, etc.

[0211] Input: User's question (in text format)

[0212] Output: Answers from the model (text format)

[0213] Step 4:

[0214] The server sends the answer obtained from the generative AI model to the user's smartphone device. The answer is sent in a standard format such as JSON.

[0215] Input: Generated answer (text format)

[0216] Output: The answer is sent to the user's device.

[0217] Step 5:

[0218] The terminal displays the answer received from the server in the chat interface, allowing the user to refer to it and follow specific steps to resolve the problem. If the user has further questions, they can also make additional inquiries through the same interface.

[0219] Input: Response from the server (text format)

[0220] Output: The answer is displayed to the user

[0221] Step 6:

[0222] The server stores the user's query and the generative model's response in a database. The stored data is managed in database format for later analysis.

[0223] Input: User queries and model responses (database format)

[0224] Output: Saved to the database

[0225] Step 7:

[0226] The server periodically analyzes the stored data from the database and generates a report, which includes statistical information on inquiries, frequently occurring problems, and improvement suggestions, etc. The generated report is provided to the manufacturer and the virtual store manager.

[0227] Input: query data stored in a database and generated answers

[0228] Output: Periodic reports (document format)

[0229] Prompt Sentence Examples

[0230] When a user types "The refrigerator is not cooling," the server sends the following prompt to the generative AI model:

[0231] User Question: My refrigerator isn't cooling. What should I do?

[0232] The generated answer looks like this:

[0233] If your refrigerator isn't cooling, try these steps first:

[0234] 1. Check if the power is supplied properly.

[0235] 2. Check that the temperature setting is appropriate.

[0236] 3. Check if the ventilation holes are blocked.

[0237]

[0238] 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.

[0239] The present invention is a user support system for handling home appliances and devices that utilizes a generative model and an emotion engine. This system recognizes emotions when a user makes an inquiry in chat format and provides optimal answers based on the results. Specific embodiments of the present invention are described below.

[0240] User Actions

[0241] Users access the login screen using a device such as a smartphone or PC and enter their account information. Once they have successfully logged in, a chat interface will appear. Users can use this interface to enter questions about home appliances and devices. The emotion engine will then recognize emotions from the user's text input and reflect that information in the next inquiry.

[0242] Server Processing

[0243] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model trained in advance from user manuals, error code lists, etc. Next, the emotion engine recognizes emotions from the user's text and adjusts the output response based on those emotions.

[0244] For example, in response to a query such as "XYZ manufacturer ABC123 refrigerator is not cooling," if the emotion engine recognizes emotions such as "anxiety" or "impatience" from the user's text, it will adjust the tone of the response to be more polite and reassuring: "If your refrigerator is not cooling, please try the following steps first: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the vents are not blocked. If you have any concerns, please contact us at any time for additional support."

[0245] Terminal handling

[0246] The device displays the response received from the server in a chat interface, allowing the user to take steps to resolve the issue and, if necessary, enter further questions for follow-up responses.

[0247] Storage and analysis of inquiry data

[0248] The server stores user inquiries, responses, and sentiment data in a database. This data can then be analyzed later to identify trends and key issues. For example, if the same type of error occurs frequently on a particular model, a solution can be proposed to the manufacturer to address the issue.

[0249] Use of Emotional Data

[0250] The server uses the emotional data recognized by the emotion engine and reflects it when creating reports. Based on the emotional data, it identifies areas where users are particularly dissatisfied and areas where support needs improvement, and provides feedback to manufacturers to improve end-user satisfaction.

[0251] Report creation and delivery

[0252] Based on the analysis results, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and improvement suggestions based on emotional data, and are provided to manufacturers. This information helps manufacturers improve their products and customer support quality.

[0253] The system of this invention allows users to enjoy the convenience of quickly resolving problems, and manufacturers can obtain data to improve the efficiency of customer inquiries and improve their products. As a specific example, when this system was used to handle a refrigerator error, the user was able to resolve the problem in just a few minutes. Furthermore, the manufacturer improved the refrigerator design based on the inquiry data and emotion data, and the occurrence rate of the same error was significantly reduced in new products.

[0254] As such, the present invention is a system that offers great benefits to both users and manufacturers, and its implementation can significantly improve the user experience of home appliances and devices.

[0255] The processing flow will be explained below.

[0256] Step 1: Log in

[0257] The device displays a login screen and the user enters their account information (username and password).

[0258] The user enters their login information and presses the submit button.

[0259] Step 2: Authentication

[0260] The server receives the login information sent from the terminal.

[0261] The server checks the account information against the database and performs authentication.

[0262] If the authentication is successful, the server generates session information and sends it to the terminal. If the authentication fails, it sends an error message to the terminal.

[0263] Step 3: Displaying the chat interface

[0264] The terminal receives the authentication result from the server, and if the authentication is successful, displays the chat interface.

[0265] Users type questions about home appliances and devices into the chat box.

[0266] Step 4: Receiving an inquiry

[0267] The server receives the user's inquiry sent from the device, which includes the manufacturer name, model number, and error details.

[0268] Step 5: Recognize emotions

[0269] The server passes the received query text to the emotion engine.

[0270] The emotion engine analyzes the user's emotions from the content of the inquiry.

[0271] The server receives the analysis results from the emotion engine and performs the next process based on the results.

[0272] Step 6: Analyzing the inquiry

[0273] The server invokes the generative model to analyze the query content, taking into account the results of the emotion engine.

[0274] The generative model extracts relevant information from pre-trained instruction manuals and generates answers that take the user's emotions into consideration.

[0275] Step 7: Generate and refine answers

[0276] The server then adjusts the tone and content of the generated response based on the emotion indicated by the emotion engine. For example, if the user is feeling anxious, the server will create a reassuring response.

[0277] The server sends the adjusted response to the terminal.

[0278] Step 8: View and review your answers

[0279] The terminal displays the response received from the server on the chat interface.

[0280] The user reviews the displayed answer and takes steps, if necessary, to resolve the problem.

[0281] If the user has further questions, they can type them again in the chat box and submit.

[0282] Step 9: Save the inquiry data

[0283] The server stores the user's inquiries, responses, and emotional data in a database.

[0284] Step 10: Compile data and generate reports

[0285] The server periodically analyzes the accumulated data and compiles information such as inquiry trends, major errors, and user sentiment.

[0286] The server creates a report based on the analysis results and provides it to the manufacturer on a monthly or quarterly basis.

[0287] This series of processes allows users to quickly resolve problems with home appliances and devices, and manufacturers can obtain data to improve the efficiency of customer inquiries and improve their products. The introduction of an emotion engine makes it possible to provide support that takes into account the user's psychological state, thereby improving user satisfaction.

[0288] Example 2

[0289] 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."

[0290] User support for modern home appliances and devices requires prompt and appropriate responses to inquiries. It is particularly important to consider the user's feelings in addition to resolving their problems. Conventional systems often provide uniform answers that ignore the user's feelings, resulting in low user satisfaction and inefficient inquiry handling. Another issue is the inability to utilize accumulated inquiry data to improve products.

[0291] 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.

[0292] In this invention, the server includes means for automatically generating responses to user inquiries by learning from instruction manuals using a generative model; means for saving inquiry data and emotion data and analyzing the inquiry content and emotion; means for creating a report based on the analysis results and emotion data and providing suggestions for product improvement; and means for adjusting the response by analyzing the user's emotion. This enables the provision of flexible responses that correspond to the user's emotion, improving the efficiency of inquiry responses and user satisfaction. Furthermore, utilizing the accumulated data also contributes to continuous product improvement.

[0293] A "generative model" is an algorithm that uses machine learning techniques to learn patterns from large amounts of data and adaptively respond to and generate new data.

[0294] "Instruction Document" means a document that describes how to use a product and provides troubleshooting information.

[0295] "User" means a person who uses a household appliance or device and seeks support.

[0296] "Inquiry Data" means information relating to user questions, problem reports, etc.

[0297] "Emotion data" is emotional information analyzed from a user's text input.

[0298] "Analysis" is the process of analyzing received data and extracting meaning and patterns.

[0299] A "report" is a document prepared based on the analysis results, and includes suggestions for product improvement.

[0300] "Product Improvement" means a change or addition to a product that improves its quality or performance.

[0301] "Automatic generation" means that the system automatically generates answers or documents without human intervention.

[0302] "Analyzing user emotions" is the process of using emotion recognition technology to identify emotions from a user's text and tailor responses accordingly.

[0303] The present invention is a user support system that utilizes a generative model and an emotion engine. This system accepts user inquiries about how to use home appliances and devices in a chat format, analyzes emotion data, and provides optimal answers. A specific embodiment of the present invention is described below.

[0304] Overall system configuration

[0305] The system consists of the following main components:

[0306] 1. User device (smartphone or PC)

[0307] 2. Server (Cloud server or dedicated server)

[0308] 3. Database (storing inquiry data and emotion data)

[0309] 4. Generative AI Models

[0310] 5. Emotion Engine

[0311] User Actions

[0312] Users access the login screen via a dedicated application or web browser using a device such as a smartphone or PC. After entering their account information, a chat interface is displayed once they have successfully logged in. Users can use this interface to enter questions about their home appliances and devices.

[0313] For example, if a user makes an inquiry such as "The ABC123 refrigerator from XYZ manufacturer is not cooling," they enter their question in the text box and click the send button. The emotion engine then recognizes the emotion from the user's text and reflects that information in the next inquiry.

[0314] Server Processing

[0315] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model that has been trained in advance from user manuals, error code lists, etc. Using reinforcement learning and deep learning techniques, it analyzes the meaning of the inquiry and identifies the problem.

[0316] Next, an emotion engine recognizes specific emotions (e.g., "anxiety" or "impatience") from the user's text. This emotion data is passed to a generative AI model, which takes this into account when generating the best answer.

[0317] Examples of concrete examples and prompts

[0318] For example, if a user asks, "My XYZ manufacturer ABC123 refrigerator isn't cooling. What should I do?" the prompt text would be as follows:

[0319] Example prompt:

[0320] "A user asks, 'My XYZ brand ABC123 refrigerator isn't cooling. What should I do?' The user's emotions seem to include anxiety. Generate a response with appropriate solutions and a reassuring tone."

[0321] Based on this prompt, the generative AI model generates the following answer:

[0322] "If your refrigerator isn't cooling, please try the following steps first: 1. Check that the power is properly supplied. 2. Check that the temperature setting is correct. 3. Check that the vents are not blocked. If you have any concerns, please contact us at any time for additional support."

[0323] Terminal handling

[0324] The device displays the response received from the server in the chat interface, where the user can refer to the response, follow up with the instructions, and enter further questions as needed to follow up.

[0325] Storage and analysis of inquiry and sentiment data

[0326] The server stores the user's inquiries, generated responses, and sentiment data in a database. The accumulated data is later analyzed and used to identify inquiry trends and key issues. For example, if the same type of error occurs frequently on a specific model, a solution to the underlying problem can be proposed to the manufacturer.

[0327] Report creation and delivery

[0328] Based on the analysis results, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and improvement suggestions based on sentiment data, and are provided to manufacturers. This information helps manufacturers improve their products and customer support quality.

[0329] The above is a specific embodiment of the present invention. This system allows users to quickly solve problems and manufacturers to obtain data for efficient response to inquiries and product improvement.

[0330] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0331] Understood. Now, I will explain the processing flow of this system's program by dividing it into processing steps below.

[0332] Step 1:

[0333] Users access the login screen using their smartphone or PC and enter their account information (user ID and password). The device then sends this authentication information to the server. The server compares the received authentication information with a database, and if authentication is successful, displays a chat interface to the user.

[0334] Input: User ID, Password

[0335] Output: Login successful message, chat interface displayed

[0336] Specific operation: The user enters their ID and password into a dedicated app or web browser, and the device sends this information to the server for authentication.

[0337] Step 2:

[0338] The user uses the chat interface to input their inquiry. For example, they might type "The ABC123 refrigerator is not cooling" into the text box and click the send button. The device then sends this inquiry to the server.

[0339] Input: Inquiry content (text)

[0340] Output: Sending query data to the server

[0341] Specific operation: The user enters a question into the chat interface and clicks the send button. The device sends this text to the server.

[0342] Step 3:

[0343] The server inputs the query data into the generative model to analyze the received query. The generative model analyzes the data based on the data it has learned in advance, identifies the problem, and generates a solution.

[0344] Input: Inquiry details

[0345] Output: Analysis results (identification of problems and solutions)

[0346] Specific operation: The server inputs data into the generative model to analyze the query, and the generative model identifies the problem and generates a solution.

[0347] Step 4:

[0348] The server passes the analysis results (problem identification and solution method) from the generative model and the query content to the emotion engine, which recognizes the user's emotions (anxiety, anger, etc.). The emotion engine extracts emotion data from the input text and returns it to the server.

[0349] Input: Inquiry details, analysis results

[0350] Output: Emotion data

[0351] Specific operation: The server passes the analysis results and query content to the emotion engine, which then recognizes the user's emotion and returns the data to the server.

[0352] Step 5:

[0353] The server uses the analysis results of the generative model and the recognition results of the emotion engine to have the generative AI model generate the optimal answer. The generative AI model then generates an appropriate answer for the user based on the prompt sentence.

[0354] For example, a prompt might read: "The user asked, 'My ABC123 refrigerator isn't cooling. What should I do?' The user's emotions seem to include anxiety. Please generate a response with appropriate solutions and a reassuring tone."

[0355] Input: prompt sentence, emotion data, analysis results

[0356] Output: The generated answer

[0357] Specific operation: The server inputs the prompt sentence into the generative AI model and obtains the generated answer.

[0358] Step 6:

[0359] The server sends the generated response to the terminal.

[0360] Input: Generated Answer

[0361] Output: Sending response data to the device

[0362] Specific operation: The server packages the generated response in a message format and sends it to the terminal.

[0363] Step 7:

[0364] The terminal displays the response received from the server on the chat interface, and the user refers to the response and performs the instructed procedure.

[0365] Input: Generated Answer

[0366] Output: Displayed in the chat interface

[0367] Specific operation: The device displays the received response in the chat window in real time, and the user follows the guided steps.

[0368] Step 8:

[0369] The server stores the query content, generated answers, and emotion data in a database.

[0370] Input: Enquiry, generated answer, sentiment data

[0371] Output: Store in database

[0372] Specific operation: The server compiles these data and writes them to the database.

[0373] Step 9:

[0374] The server analyzes the accumulated inquiry data and sentiment data to identify inquiry trends and key issues.

[0375] Input: Accumulated inquiry data, emotion data

[0376] Output: Analysis results (inquiry trends and issues)

[0377] What happens: The server uses data analytics tools to analyze the data and gain insights.

[0378] Step 10:

[0379] The server creates a report based on the analysis results and provides it to the manufacturer, including statistical information on inquiries, frequently occurring problems, and improvement suggestions based on emotional data.

[0380] Input: Analysis results

[0381] Output: Report

[0382] Specific operation: The server organizes the analysis results, automatically generates reports on a regular basis, and sends them to the manufacturer's representative.

[0383] (Application example 2)

[0384] 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."

[0385] Modern user support systems are required to respond to user inquiries quickly and accurately, but current systems often lack consideration for user emotions. Furthermore, mechanisms for analyzing user inquiry data and reflecting the results in product improvements are often inadequate. As a result, issues remain in improving user satisfaction and providing feedback for product improvement. The present invention provides technology to address these issues.

[0386] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for learning from instruction manuals using a generative model and automatically generating responses to user inquiries, means for saving inquiry data and analyzing the content of the inquiry, means for creating a report based on the analysis results and providing suggestions for product improvement, means for analyzing the user's emotions using an emotion recognition engine and adjusting the tone and content of the response, and means for saving the emotion data and later analyzing it for use in service improvement. This makes it possible to provide support that reflects the user's emotions and to realize product improvements through precise analysis of the content of the inquiry.

[0387] A "generative model" is an algorithm that automatically generates answers to user inquiries based on pre-trained data.

[0388] An "instruction manual" is a document that describes how to use a product, its functions, troubleshooting methods, etc., and serves as a guide for users to use the product correctly.

[0389] "User" means an individual or organization that uses the System to make a product inquiry.

[0390] An "answer" is information or instructions provided in response to a user's inquiry that is generated by the server to resolve the problem.

[0391] An "emotion recognition engine" is software or an algorithm that analyzes emotions from a user's text input and takes appropriate action based on the results.

[0392] "Inquiry Data" means data submitted by you containing information relating to your question or problem.

[0393] "Analysis results" are the insights and findings obtained after analyzing inquiry data, which are used to create reports and improve products.

[0394] A "report" is a document that summarizes the results of the analysis and includes suggestions for product improvement and trend analysis.

[0395] "Product improvement" refers to activities aimed at improving the quality and performance of a product based on the analysis of user feedback and inquiry data.

[0396] "Tone" refers to the way the answer is expressed and the atmosphere it conveys, and is adjusted to convey a sense of politeness and security.

[0397] "Emotional data" refers to data containing the user's emotional information analyzed by the emotion recognition engine, and is used to improve the service.

[0398] "Service improvement" refers to the activity of taking specific measures and making adjustments to improve the quality of user support based on emotional data and inquiry data.

[0399] The present invention is a customer support system for an online shopping site that uses a generative model and an emotion recognition engine to provide responses to user inquiries that take emotion into consideration. Specific embodiments of the present invention are described below.

[0400] System Overview

[0401] The system mainly consists of the following elements:

[0402] 1. Generative model: Learns from the instruction manual and automatically generates answers to user inquiries.

[0403] 2. Emotion Recognition Engine: Analyzes emotions from user text input and adjusts the tone and content of responses.

[0404] 3. Data storage and analysis: User inquiry data and sentiment data are stored and later analyzed for use in improving services.

[0405] Program processing

[0406] Emotion Recognition and Answer Generation

[0407] The server first receives a query from the user, typically in chat format and saved as the user's text data. The emotion recognition engine analyzes the text data and identifies the user's emotions (e.g., anxiety, frustration, joy, etc.). Based on the identified emotions, the server builds prompts for the generative model.

[0408] Examples of prompts are:

[0409] The user is concerned. Please answer these questions politely: How do I return a recent purchase? The return deadline may have passed.

[0410] The results of the emotion recognition engine are used to select an appropriate prompt and send it to a generative model, which then uses the generative model (e.g., OpenAI's API) to generate an answer, whose tone and content take the user's emotions into account.

[0411] Data storage and analysis

[0412] The server stores user inquiry data, response data, and emotion data in a database. This stored data is periodically analyzed and a report is generated. The report includes inquiry trends, frequently occurring problems, and improvement suggestions based on the emotion data. This allows manufacturers to improve their products and the quality of user support.

[0413] Specific examples

[0414] If a user asks a question like "How do I return an item?" and the emotion recognition engine detects "anxiety," the prompt will be generated as follows:

[0415] The user is concerned. Please answer these questions politely: How do I return a recent purchase? The return deadline may have passed.

[0416] Based on this prompt, the generative model generates a polite and reassuring answer, such as, "We'll explain how to return the item. First, the return deadline may have passed, but we'll help you with the detailed process, so don't worry."

[0417] This allows users to receive support that takes their emotions into consideration, and their inquiries are responded to quickly and appropriately, resulting in improved user satisfaction and more efficient inquiry response.

[0418] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0419] Step 1:

[0420] A user accesses a customer support application using a smartphone and inputs an inquiry. For example, the user sends an inquiry in text format, such as "How do I return a product?" This text is sent to the server as input data.

[0421] Step 2:

[0422] The server receives the text data sent by the user and sends it to the emotion recognition engine. This emotion recognition engine analyzes the text data and identifies the user's emotion. The input is the user's text data, and the output is the identified emotion information (e.g., anxiety, irritation, etc.).

[0423] Step 3:

[0424] The server constructs a prompt for the generative model based on the emotional information obtained from the emotion recognition engine. The input is the emotional information and the user's inquiry, and the output is a prompt that reflects the emotion. For example, if the user is feeling "anxious," a prompt such as "The user is feeling anxious. Please answer the following questions politely: [User's inquiry]" is generated.

[0425] Step 4:

[0426] The server sends the generated prompt text to the generative AI model, which generates an answer. The input is the prompt text, and the output is an answer text that takes the user's sentiment into account. The generative AI model generates an appropriate answer based on the prompt. For example, it might generate an answer such as, "We will guide you through the return process. First, the return deadline may have passed, but please rest assured that we will support you with the detailed procedures."

[0427] Step 5:

[0428] The server sends the generated answer text to the user's smartphone and displays it on the chat interface. The input is the generated answer text, and the output is the answer displayed on the user's smartphone.

[0429] Step 6:

[0430] The server stores the user's query data, emotion data, and generated response data in a database. The input is this data, and the output is a saved database entry. This accumulates the data in a form that can be analyzed later.

[0431] Step 7:

[0432] The server periodically analyzes the accumulated inquiry data and emotion data and generates a report. The input is the data stored in the database, and the output is the analysis results and a report. This report includes inquiry trends, frequently occurring problems, and improvement suggestions based on the emotion data.

[0433] Step 8:

[0434] The server sends the generated report to the product improvement team or person in charge. The input is the report and the output is the data sent to the person in charge. This allows the manufacturer to improve the quality of their products and user support.

[0435] The above steps will enable fast and appropriate customer support that takes user emotions into consideration.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] [Second embodiment]

[0440] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0441] 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.

[0442] 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).

[0443] 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.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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."

[0452] The present invention is a user support system for handling home appliances and devices that utilizes generative models. This system allows users to make inquiries in a chat format and quickly obtain information needed to solve problems. Specific embodiments of the present invention are described below.

[0453] User Actions

[0454] Users access the login screen using a device such as a smartphone or PC and enter their account information. After successful login, a chat interface appears. Users use this interface to input questions about home appliances and devices. For example, they might input a question like, "My XYZ manufacturer's ABC123 refrigerator isn't cooling."

[0455] Server Processing

[0456] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model that has been trained in advance from instruction manuals, error code lists, etc. From the analysis results, it generates the optimal answer to the user's question and sends this in chat format to the device. For example, it generates an answer that includes specific steps such as, "If your refrigerator is not cooling, first try the following steps: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked."

[0457] Terminal handling

[0458] The device displays the response received from the server in a chat interface, allowing the user to take steps to resolve the issue and, if necessary, enter further questions for follow-up responses.

[0459] Storage and analysis of inquiry data

[0460] The server stores user inquiries and their responses in a database. This data can then be analyzed later to identify trends and key issues. For example, if the same type of error occurs frequently on a particular model, a solution can be proposed to the manufacturer to fundamentally resolve the issue.

[0461] Report creation and delivery

[0462] Based on the analysis results, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and suggestions for improvement, and are provided to the manufacturer. This information helps the manufacturer improve their products and the quality of their customer support.

[0463] The system of the present invention allows users to enjoy the convenience of quickly resolving problems, and allows manufacturers to obtain data for more efficient response to inquiries and product improvement. As a specific example, when this system was used to handle a refrigerator error, the user was able to resolve the problem in just a few minutes. Furthermore, the manufacturer improved the refrigerator design based on the inquiry data, and the occurrence rate of the same error was significantly reduced in new products.

[0464] As such, the present invention is a system that offers great benefits to both users and manufacturers, and its implementation can significantly improve the user experience of home appliances and devices.

[0465] The processing flow will be explained below.

[0466] Step 1: Log in

[0467] The device displays a login screen and the user enters their account information (username and password).

[0468] The user enters their login information and presses the submit button.

[0469] Step 2: Authentication

[0470] The server receives the login information sent from the terminal.

[0471] The server checks the account information against the database and performs authentication.

[0472] If the authentication is successful, the server generates session information and sends it to the terminal. If the authentication fails, it sends an error message to the terminal.

[0473] Step 3: Displaying the chat interface

[0474] The terminal receives the authentication result from the server, and if the authentication is successful, displays the chat interface.

[0475] Users type questions about home appliances and devices into the chat box.

[0476] Step 4: Receiving and analyzing inquiries

[0477] The server receives the user's inquiry sent from the device, which includes the manufacturer name, model number, and error details.

[0478] The server invokes the generative model to analyze the received query.

[0479] The generative model extracts relevant information from pre-trained instruction manuals and generates the appropriate answer.

[0480] Step 5: Generate and submit your response

[0481] The server organizes the answers received from the generative model and converts them into a user-friendly format.

[0482] The server sends the generated response to the terminal.

[0483] Step 6: View and review your answers

[0484] The terminal displays the response received from the server on the chat interface.

[0485] The user reviews the displayed answer and takes steps, if necessary, to resolve the problem.

[0486] If the user has further questions, they can type them again in the chat box and submit.

[0487] Step 7: Save the inquiry data

[0488] The server stores the user's inquiries and their responses in a database.

[0489] Step 8: Compile data and generate reports

[0490] The server periodically analyzes the accumulated data and compiles information such as inquiry trends and major errors.

[0491] The server creates a report based on the analysis results and provides it to the manufacturer on a monthly or quarterly basis.

[0492] This series of processes allows users to quickly resolve problems with home appliances and devices, and manufacturers to obtain data to respond to inquiries more efficiently and improve their products.

[0493] Example 1

[0494] 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."

[0495] It is difficult to quickly and efficiently answer user questions and resolve issues regarding home appliances and devices, and there is a lack of effective ways to utilize the data obtained during the inquiry process. As a result, it takes time for users to receive appropriate support, and manufacturers also face challenges in improving their products and streamlining the support process.

[0496] 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.

[0497] In this invention, the server includes means for learning from instruction manuals using a generative model and automatically generating responses to user inquiries, means for a user to access a chat interface using a terminal and log in by entering account information, means for inputting a question into the chat interface after logging in and sending it, means for the server to analyze the user's inquiry using the generative model, generate a response, and send it to the terminal, means for the terminal to display the response received from the server on the chat interface and the user to confirm it, means for saving inquiry data and analyzing the content of the inquiry, and means for creating a report based on the analysis results and providing suggestions for product improvement. This allows users to receive quick and accurate support, and enables manufacturers to use the accumulated data to improve their products and streamline their support processes.

[0498] A "generative model" is a mathematical model that uses machine learning algorithms to learn from large amounts of data and generate new data.

[0499] An "instruction manual" is a document that contains information about how to use, set up, and troubleshoot an appliance or device.

[0500] "Inquiry Data" refers to text data regarding questions or problems submitted by users.

[0501] "Chat interface" refers to a user interface that allows a user to communicate with the system in a two-way manner in text format.

[0502] "User" refers to a general consumer or individual who uses this system to receive support for home appliances or devices.

[0503] "Terminal" refers to an information processing device such as a smartphone, PC, or tablet, which is used by a user to access the system.

[0504] A "server" is a computer system that receives data sent by users and performs multiple functions, such as analyzing it using generative models, generating answers, storing data, and creating reports.

[0505] "Login" is the authentication process by which a user enters their account information and begins using the system.

[0506] An "answer" refers to the solution or information provided as a result of the generative model analyzing the user's query.

[0507] A "report" is a document that compiles accumulated inquiry data and analysis results, and is provided to manufacturers to improve their products and the quality of their support processes.

[0508] "Product improvement" refers to efforts to improve the design and functionality of home appliances and devices based on user feedback and inquiry analysis results.

[0509] "Means" is a broad concept that refers to methods, techniques, and devices for realizing a specific function or process.

[0510] This invention is a user support system for home appliances and devices that uses a generative AI model. Its main purpose is to provide fast and effective support by automatically generating answers to user inquiries and storing and analyzing inquiry data.

[0511] Hardware and software used

[0512] Terminal: Information processing device used by the user, such as a smartphone, PC, or tablet.

[0513] Server: A computer system that receives data, analyzes it using a generative AI model, generates answers, stores and analyzes inquiry data, and creates reports.

[0514] Generative AI model: A machine learning algorithm trained from home appliance and device instruction manuals, error code lists, etc. (e.g., OpenAI GPT-4).

[0515] Program processing description

[0516] User Actions

[0517] The user accesses the system's login screen using a device such as a smartphone or PC. By entering their account information (username, password), the user is authenticated to the system. After authentication, the user enters an inquiry through the chat interface. An example of a prompt that the user enters at this time is, "My XYZ manufacturer ABC123 refrigerator is not cooling. What should I do?"

[0518] Server Processing

[0519] The server receives inquiries sent by users. A generative AI model is used to analyze the content of these inquiries. The generative AI model learns from home appliance instruction manuals and error code lists, and generates the optimal answer based on the user's question. For example, if the inquiry is "My refrigerator isn't cooling," the generated answer will include specific steps such as "If your refrigerator isn't cooling, try the following steps: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked."

[0520] The generated answer is sent from the server to the user's device. The server also stores the query and its answer in a database. This stored data is later used to analyze query trends and identify key issues.

[0521] Terminal handling

[0522] The user's device receives the response from the server and displays it in the chat interface. The user can refer to this information to take steps to resolve the issue, and can also enter a new question for further support if necessary.

[0523] Specific examples

[0524] Example of user action: The user types into the chat interface, "My XYZ manufacturer ABC123 refrigerator isn't cooling. What should I do?" and presses the send button.

[0525] Example of server operation: The server sends a query to the generation AI model, generating an answer such as "If the refrigerator is not cooling, try the following steps: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked." and sending it to the device.

[0526] Example of device behavior: The device displays the generated answer in a chat interface, and the user follows the steps to solve the problem.

[0527] This system allows users to receive fast and accurate support, and manufacturers can use the accumulated data to improve their products and streamline their support processes.

[0528] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0529] Step 1:

[0530] User login and access to the chat interface

[0531] The user accesses the system's login screen using a device (smartphone, PC, etc.). They are authenticated to the system by entering their account information (username, password) on the login screen. If login is successful, the system displays a chat interface to the user.

[0532] Input: Account information (username, password)

[0533] Output: Authentication success / failure, chat interface displayed

[0534] Specific behavior: The user opens a browser or app, accesses the specified URL, enters their account information, and clicks the "Login" button.

[0535] Step 2:

[0536] User inquiries

[0537] Users enter specific inquiries about home appliances and devices into the chat interface and press the send button.

[0538] Input: Text of the inquiry (e.g., "My refrigerator, model ABC123, made by XYZ, is not cooling. What should I do?")

[0539] Output: Sends query data to the server

[0540] Specific operation: The user enters the inquiry content into the chat interface and clicks the "Send" button.

[0541] Step 3:

[0542] Receiving and analyzing inquiries on the server

[0543] The server receives inquiries sent by users. The received text data is sent to a generative AI model, which analyzes the content. The generative AI model is trained from instruction manuals and error code lists.

[0544] Input: Enquiry data

[0545] Output: Analysis results (understanding of query content)

[0546] Specific operation: The server receives the user's query and passes it to the generative AI model to begin analysis.

[0547] Step 4:

[0548] Generating optimal answers on the server

[0549] The generative AI model generates the best possible answer based on the analyzed query, which includes specific instructions and steps.

[0550] Input: Analysis results

[0551] Output: Best answer (text data)

[0552] Specific behavior: The generative AI model generates a specific answer such as, "If your refrigerator is not cooling, try the following steps: 1. Check that the power is supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked."

[0553] Step 5:

[0554] Sending a response from the server to the user's device

[0555] The server then sends the generated response to the user's terminal.

[0556] Input: Best answer (text data)

[0557] Output: Sending response data to the terminal

[0558] Specific operation: The server formats the generated answer and sends it to the user's terminal according to the communication protocol.

[0559] Step 6:

[0560] Display of answers on the device and user responses

[0561] The user's device displays the response received from the server in a chat interface, where the user can review it and try to resolve the issue by following the steps provided.

[0562] Input: Response data

[0563] Output: The response displayed in the chat interface

[0564] Specific operation: The device displays the received response in the chat interface, and the user confirms its content.

[0565] Step 7:

[0566] Storing and post-processing inquiry data

[0567] The server stores the received queries and their responses in a database, which will be used for future analysis and statistics.

[0568] Input: Inquiry data and response data

[0569] Output: Saved database entries

[0570] Specific operation: The server saves the query and response in a database.

[0571] Step 8:

[0572] Regular reporting and provision

[0573] The server periodically analyzes the stored data and generates reports containing inquiry statistics, common problems, and suggestions for improvement. The reports are then provided to the manufacturer.

[0574] Input: Saved data

[0575] Output: Report

[0576] Specific operation: The server analyzes the stored data, generates periodic reports, and provides them to the manufacturer.

[0577] (Application example 1)

[0578] 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."

[0579] With conventional user support systems, it has been difficult for users to quickly obtain appropriate solutions when problems arise with home appliances or electronic devices. Furthermore, manufacturers have limited means to efficiently collect and analyze user inquiry data and use it to improve their products. Virtual stores, in particular, require a system that can provide immediate and accurate support.

[0580] 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.

[0581] In this invention, the server includes means for learning from instruction manuals using a generative model and automatically generating answers to user inquiries, means for saving inquiry data and analyzing the inquiry content, means for creating reports based on the analysis results and providing suggestions for product improvement, means for users to receive support for household appliances and electronic devices in a virtual store, and means for implementing a chatbot function via smartphone to provide quick answers to user questions. This allows users to solve problems in a short time and enables manufacturers to use the collected data to improve their products.

[0582] A "generative model" is an artificial intelligence technology that learns from large amounts of data and automatically generates answers to user inquiries.

[0583] An "instruction manual" is a document that contains detailed instructions on how to use and troubleshoot a household appliance or electronic device.

[0584] "User Inquiry" means a question or problem report submitted by a User seeking support.

[0585] "Auto-generation" is the process of programmatically creating answers or suggestions using artificial intelligence models.

[0586] "Inquiry Data" means records of questions or problems received from users.

[0587] "Analysis of inquiry content" is the process of analyzing received inquiry data and identifying problems and causes.

[0588] A "report" is a document summarizing inquiry data and analysis results, and is intended to be provided to manufacturers.

[0589] A "product improvement proposal" is a specific proposal for improving the performance or quality of a product based on the analysis results of the inquiry data.

[0590] A "virtual store" is a virtual store that sells products and provides services such as customer support over the Internet.

[0591] "Household electrical appliances" refer to electrical equipment used daily in the home.

[0592] An "electronic device" is a device that uses electronic technology to process and communicate information.

[0593] The "chatbot function" is a program that uses artificial intelligence to automatically respond to user input.

[0594] A "smartphone" is a mobile phone that has multiple functions and is capable of running applications.

[0595] The present invention is a system for users to receive support for household appliances and electronic devices in a virtual store. The system uses a generative model to learn from instruction manuals and automatically generate answers to user inquiries. It also stores and analyzes inquiry data to provide reports on product improvements. Specific embodiments of the system are described below.

[0596] User Actions

[0597] Users access the support section of the virtual store using their smartphones. They enter their account information on the login screen, and once logged in, a chat interface appears. Users use this interface to enter questions about their home appliances or electronic devices, for example, "My refrigerator isn't cooling."

[0598] Server Processing

[0599] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model that has been trained in advance from user manuals, error code lists, etc. The generative AI model (e.g., OpenAI's text-davinci-003) is used to generate the optimal answer to the user's question. The generated answer is then sent to the smartphone device in chat format.

[0600] Terminal handling

[0601] The smartphone displays the response received from the server in the chat interface. The user can refer to this and take steps to resolve the problem. For example, in response to a query such as "My refrigerator isn't cooling," the smartphone displays specific steps to improve the situation, such as "Please check that the power is being supplied properly. Please check that the temperature setting is appropriate. Please check that the vents are not blocked." If the user has further questions, they can continue to follow up through the chat interface.

[0602] Storage and analysis of inquiry data

[0603] The server stores user inquiries and their responses in a database. This data can be analyzed to identify trends and key issues. For example, if the same type of error occurs frequently with a particular home appliance, a report can be created to suggest a fundamental solution to the error to the manufacturer. This report is generated monthly or quarterly and provided to the manufacturer.

[0604] Report creation and delivery

[0605] Based on the results of the data analysis, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and suggestions for improvement. The reports are provided to the virtual store manager and the manufacturer, and are used to improve products and customer support quality.

[0606] Examples and prompts

[0607] For example, if a user enters "My refrigerator isn't cooling," the app will call the generative model and automatically generate answers such as, "Please check that the power is coming in properly. Please check that the temperature setting is correct. Please check that the vents are not blocked."

[0608] Prompt Sentence Examples

[0609] User Question: My refrigerator isn't cooling. What should I do?

[0610]

[0611] Generated Answer: If your refrigerator isn't cooling, try these steps first:

[0612] 1. Check if the power is supplied properly.

[0613] 2. Check that the temperature setting is appropriate.

[0614] 3. Check if the ventilation holes are blocked.

[0615] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0616] Step 1:

[0617] Users access the virtual store using their smartphones and log in by entering their account information. After successful login, a chat interface is displayed. Here, users can enter questions about household appliances or electronic devices (e.g., "My refrigerator isn't cooling"). The entered information is then sent to the server.

[0618] Input: User question (text format)

[0619] Output: A query is sent to the server

[0620] Step 2:

[0621] The server receives the question sent by the user and calls a generative AI model (e.g., OpenAI's text-davinci-003) to analyze the received question.

[0622] Input: User's question (in text format)

[0623] Output: The generative AI model is invoked

[0624] Step 3:

[0625] The generative AI model analyzes the content of the inquiry and generates the optimal answer. In this process, it generates a solution to the user's question based on what it has learned in advance from instruction manuals, error code lists, etc.

[0626] Input: User's question (in text format)

[0627] Output: Answers from the model (text format)

[0628] Step 4:

[0629] The server sends the answer obtained from the generative AI model to the user's smartphone device. The answer is sent in a standard format such as JSON.

[0630] Input: Generated answer (text format)

[0631] Output: The answer is sent to the user's device.

[0632] Step 5:

[0633] The terminal displays the answer received from the server in the chat interface, allowing the user to refer to it and follow specific steps to resolve the problem. If the user has further questions, they can also make additional inquiries through the same interface.

[0634] Input: Response from the server (text format)

[0635] Output: The answer is displayed to the user

[0636] Step 6:

[0637] The server stores the user's query and the generative model's response in a database. The stored data is managed in database format for later analysis.

[0638] Input: User queries and model responses (database format)

[0639] Output: Saved to the database

[0640] Step 7:

[0641] The server periodically analyzes the stored data from the database and generates a report, which includes statistical information on inquiries, frequently occurring problems, and improvement suggestions, etc. The generated report is provided to the manufacturer and the virtual store manager.

[0642] Input: query data stored in a database and generated answers

[0643] Output: Periodic reports (document format)

[0644] Prompt Sentence Examples

[0645] When a user types "The refrigerator is not cooling," the server sends the following prompt to the generative AI model:

[0646] User Question: My refrigerator isn't cooling. What should I do?

[0647] The generated answer looks like this:

[0648] If your refrigerator isn't cooling, try these steps first:

[0649] 1. Check if the power is supplied properly.

[0650] 2. Check that the temperature setting is appropriate.

[0651] 3. Check if the ventilation holes are blocked.

[0652]

[0653] 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.

[0654] The present invention is a user support system for handling home appliances and devices that utilizes a generative model and an emotion engine. This system recognizes emotions when a user makes an inquiry in chat format and provides optimal answers based on the results. Specific embodiments of the present invention are described below.

[0655] User Actions

[0656] Users access the login screen using a device such as a smartphone or PC and enter their account information. Once they have successfully logged in, a chat interface will appear. Users can use this interface to enter questions about home appliances and devices. The emotion engine will then recognize emotions from the user's text input and reflect that information in the next inquiry.

[0657] Server Processing

[0658] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model trained in advance from user manuals, error code lists, etc. Next, the emotion engine recognizes emotions from the user's text and adjusts the output response based on those emotions.

[0659] For example, in response to a query such as "XYZ manufacturer ABC123 refrigerator is not cooling," if the emotion engine recognizes emotions such as "anxiety" or "impatience" from the user's text, it will adjust the tone of the response to be more polite and reassuring: "If your refrigerator is not cooling, please try the following steps first: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the vents are not blocked. If you have any concerns, please contact us at any time for additional support."

[0660] Terminal handling

[0661] The device displays the response received from the server in a chat interface, allowing the user to take steps to resolve the issue and, if necessary, enter further questions for follow-up responses.

[0662] Storage and analysis of inquiry data

[0663] The server stores user inquiries, responses, and sentiment data in a database. This data can then be analyzed later to identify trends and key issues. For example, if the same type of error occurs frequently on a particular model, a solution can be proposed to the manufacturer to address the issue.

[0664] Use of Emotional Data

[0665] The server uses the emotional data recognized by the emotion engine and reflects it when creating reports. Based on the emotional data, it identifies areas where users are particularly dissatisfied and areas where support needs improvement, and provides feedback to manufacturers to improve end-user satisfaction.

[0666] Report creation and delivery

[0667] Based on the analysis results, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and improvement suggestions based on emotional data, and are provided to manufacturers. This information helps manufacturers improve their products and customer support quality.

[0668] The system of this invention allows users to enjoy the convenience of quickly resolving problems, and manufacturers can obtain data to improve the efficiency of customer inquiries and improve their products. As a specific example, when this system was used to handle a refrigerator error, the user was able to resolve the problem in just a few minutes. Furthermore, the manufacturer improved the refrigerator design based on the inquiry data and emotion data, and the occurrence rate of the same error was significantly reduced in new products.

[0669] As such, the present invention is a system that offers great benefits to both users and manufacturers, and its implementation can significantly improve the user experience of home appliances and devices.

[0670] The processing flow will be explained below.

[0671] Step 1: Log in

[0672] The device displays a login screen and the user enters their account information (username and password).

[0673] The user enters their login information and presses the submit button.

[0674] Step 2: Authentication

[0675] The server receives the login information sent from the terminal.

[0676] The server checks the account information against the database and performs authentication.

[0677] If the authentication is successful, the server generates session information and sends it to the terminal. If the authentication fails, it sends an error message to the terminal.

[0678] Step 3: Displaying the chat interface

[0679] The terminal receives the authentication result from the server, and if the authentication is successful, displays the chat interface.

[0680] Users type questions about home appliances and devices into the chat box.

[0681] Step 4: Receiving an inquiry

[0682] The server receives the user's inquiry sent from the device, which includes the manufacturer name, model number, and error details.

[0683] Step 5: Recognize emotions

[0684] The server passes the received query text to the emotion engine.

[0685] The emotion engine analyzes the user's emotions from the content of the inquiry.

[0686] The server receives the analysis results from the emotion engine and performs the next process based on the results.

[0687] Step 6: Analyzing the inquiry

[0688] The server invokes the generative model to analyze the query content, taking into account the results of the emotion engine.

[0689] The generative model extracts relevant information from pre-trained instruction manuals and generates answers that take the user's emotions into consideration.

[0690] Step 7: Generate and refine answers

[0691] The server then adjusts the tone and content of the generated response based on the emotion indicated by the emotion engine. For example, if the user is feeling anxious, the server will create a reassuring response.

[0692] The server sends the adjusted response to the terminal.

[0693] Step 8: View and review your answers

[0694] The terminal displays the response received from the server on the chat interface.

[0695] The user reviews the displayed answer and takes steps, if necessary, to resolve the problem.

[0696] If the user has further questions, they can type them again in the chat box and submit.

[0697] Step 9: Save the inquiry data

[0698] The server stores the user's inquiries, responses, and emotional data in a database.

[0699] Step 10: Compile data and generate reports

[0700] The server periodically analyzes the accumulated data and compiles information such as inquiry trends, major errors, and user sentiment.

[0701] The server creates a report based on the analysis results and provides it to the manufacturer on a monthly or quarterly basis.

[0702] This series of processes allows users to quickly resolve problems with home appliances and devices, and manufacturers can obtain data to improve the efficiency of customer inquiries and improve their products. The introduction of an emotion engine makes it possible to provide support that takes into account the user's psychological state, thereby improving user satisfaction.

[0703] Example 2

[0704] 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."

[0705] User support for modern home appliances and devices requires prompt and appropriate responses to inquiries. It is particularly important to consider the user's feelings in addition to resolving their problems. Conventional systems often provide uniform answers that ignore the user's feelings, resulting in low user satisfaction and inefficient inquiry handling. Another issue is the inability to utilize accumulated inquiry data to improve products.

[0706] 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.

[0707] In this invention, the server includes means for automatically generating responses to user inquiries by learning from instruction manuals using a generative model; means for saving inquiry data and emotion data and analyzing the inquiry content and emotion; means for creating a report based on the analysis results and emotion data and providing suggestions for product improvement; and means for adjusting the response by analyzing the user's emotion. This enables the provision of flexible responses that correspond to the user's emotion, improving the efficiency of inquiry responses and user satisfaction. Furthermore, utilizing the accumulated data also contributes to continuous product improvement.

[0708] A "generative model" is an algorithm that uses machine learning techniques to learn patterns from large amounts of data and adaptively respond to and generate new data.

[0709] "Instruction Document" means a document that describes how to use a product and provides troubleshooting information.

[0710] "User" means a person who uses a household appliance or device and seeks support.

[0711] "Inquiry Data" means information relating to user questions, problem reports, etc.

[0712] "Emotion data" is emotional information analyzed from a user's text input.

[0713] "Analysis" is the process of analyzing received data and extracting meaning and patterns.

[0714] A "report" is a document prepared based on the analysis results, and includes suggestions for product improvement.

[0715] "Product Improvement" means a change or addition to a product that improves its quality or performance.

[0716] "Automatic generation" means that the system automatically generates answers or documents without human intervention.

[0717] "Analyzing user emotions" is the process of using emotion recognition technology to identify emotions from a user's text and tailor responses accordingly.

[0718] The present invention is a user support system that utilizes a generative model and an emotion engine. This system accepts user inquiries about how to use home appliances and devices in a chat format, analyzes emotion data, and provides optimal answers. A specific embodiment of the present invention is described below.

[0719] Overall system configuration

[0720] The system consists of the following main components:

[0721] 1. User device (smartphone or PC)

[0722] 2. Server (Cloud server or dedicated server)

[0723] 3. Database (storing inquiry data and emotion data)

[0724] 4. Generative AI Models

[0725] 5. Emotion Engine

[0726] User Actions

[0727] Users access the login screen via a dedicated application or web browser using a device such as a smartphone or PC. After entering their account information, a chat interface is displayed once they have successfully logged in. Users can use this interface to enter questions about their home appliances and devices.

[0728] For example, if a user makes an inquiry such as "The ABC123 refrigerator from XYZ manufacturer is not cooling," they enter their question in the text box and click the send button. The emotion engine then recognizes the emotion from the user's text and reflects that information in the next inquiry.

[0729] Server Processing

[0730] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model that has been trained in advance from user manuals, error code lists, etc. Using reinforcement learning and deep learning techniques, it analyzes the meaning of the inquiry and identifies the problem.

[0731] Next, an emotion engine recognizes specific emotions (e.g., "anxiety" or "impatience") from the user's text. This emotion data is passed to a generative AI model, which takes this into account when generating the best answer.

[0732] Examples of concrete examples and prompts

[0733] For example, if a user asks, "My XYZ manufacturer ABC123 refrigerator isn't cooling. What should I do?" the prompt text would be as follows:

[0734] Example prompt:

[0735] "A user asks, 'My XYZ brand ABC123 refrigerator isn't cooling. What should I do?' The user's emotions seem to include anxiety. Generate a response with appropriate solutions and a reassuring tone."

[0736] Based on this prompt, the generative AI model generates the following answer:

[0737] "If your refrigerator isn't cooling, please try the following steps first: 1. Check that the power is properly supplied. 2. Check that the temperature setting is correct. 3. Check that the vents are not blocked. If you have any concerns, please contact us at any time for additional support."

[0738] Terminal handling

[0739] The device displays the response received from the server in the chat interface, where the user can refer to the response, follow up with the instructions, and enter further questions as needed to follow up.

[0740] Storage and analysis of inquiry and sentiment data

[0741] The server stores the user's inquiries, generated responses, and sentiment data in a database. The accumulated data is later analyzed and used to identify inquiry trends and key issues. For example, if the same type of error occurs frequently on a specific model, a solution to the underlying problem can be proposed to the manufacturer.

[0742] Report creation and delivery

[0743] Based on the analysis results, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and improvement suggestions based on sentiment data, and are provided to manufacturers. This information helps manufacturers improve their products and customer support quality.

[0744] The above is a specific embodiment of the present invention. This system allows users to quickly solve problems and manufacturers to obtain data for efficient response to inquiries and product improvement.

[0745] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0746] Understood. Now, I will explain the processing flow of this system's program by dividing it into processing steps below.

[0747] Step 1:

[0748] Users access the login screen using their smartphone or PC and enter their account information (user ID and password). The device then sends this authentication information to the server. The server compares the received authentication information with a database, and if authentication is successful, displays a chat interface to the user.

[0749] Input: User ID, Password

[0750] Output: Login successful message, chat interface displayed

[0751] Specific operation: The user enters their ID and password into a dedicated app or web browser, and the device sends this information to the server for authentication.

[0752] Step 2:

[0753] The user uses the chat interface to input their inquiry. For example, they might type "The ABC123 refrigerator is not cooling" into the text box and click the send button. The device then sends this inquiry to the server.

[0754] Input: Inquiry content (text)

[0755] Output: Sending query data to the server

[0756] Specific operation: The user enters a question into the chat interface and clicks the send button. The device sends this text to the server.

[0757] Step 3:

[0758] The server inputs the query data into the generative model to analyze the received query. The generative model analyzes the data based on the data it has learned in advance, identifies the problem, and generates a solution.

[0759] Input: Inquiry details

[0760] Output: Analysis results (identification of problems and solutions)

[0761] Specific operation: The server inputs data into the generative model to analyze the query, and the generative model identifies the problem and generates a solution.

[0762] Step 4:

[0763] The server passes the analysis results (problem identification and solution method) from the generative model and the query content to the emotion engine, which recognizes the user's emotions (anxiety, anger, etc.). The emotion engine extracts emotion data from the input text and returns it to the server.

[0764] Input: Inquiry details, analysis results

[0765] Output: Emotion data

[0766] Specific operation: The server passes the analysis results and query content to the emotion engine, which then recognizes the user's emotion and returns the data to the server.

[0767] Step 5:

[0768] The server uses the analysis results of the generative model and the recognition results of the emotion engine to have the generative AI model generate the optimal answer. The generative AI model then generates an appropriate answer for the user based on the prompt sentence.

[0769] For example, a prompt might read: "The user asked, 'My ABC123 refrigerator isn't cooling. What should I do?' The user's emotions seem to include anxiety. Please generate a response with appropriate solutions and a reassuring tone."

[0770] Input: prompt sentence, emotion data, analysis results

[0771] Output: The generated answer

[0772] Specific operation: The server inputs the prompt sentence into the generative AI model and obtains the generated answer.

[0773] Step 6:

[0774] The server sends the generated response to the terminal.

[0775] Input: Generated Answer

[0776] Output: Sending response data to the device

[0777] Specific operation: The server packages the generated response in a message format and sends it to the terminal.

[0778] Step 7:

[0779] The terminal displays the response received from the server on the chat interface, and the user refers to the response and performs the instructed procedure.

[0780] Input: Generated Answer

[0781] Output: Displayed in the chat interface

[0782] Specific operation: The device displays the received response in the chat window in real time, and the user follows the guided steps.

[0783] Step 8:

[0784] The server stores the query content, generated answers, and emotion data in a database.

[0785] Input: Enquiry, generated answer, sentiment data

[0786] Output: Store in database

[0787] Specific operation: The server compiles these data and writes them to the database.

[0788] Step 9:

[0789] The server analyzes the accumulated inquiry data and sentiment data to identify inquiry trends and key issues.

[0790] Input: Accumulated inquiry data, emotion data

[0791] Output: Analysis results (inquiry trends and issues)

[0792] What happens: The server uses data analytics tools to analyze the data and gain insights.

[0793] Step 10:

[0794] The server creates a report based on the analysis results and provides it to the manufacturer, including statistical information on inquiries, frequently occurring problems, and improvement suggestions based on emotional data.

[0795] Input: Analysis results

[0796] Output: Report

[0797] Specific operation: The server organizes the analysis results, automatically generates reports on a regular basis, and sends them to the manufacturer's representative.

[0798] (Application example 2)

[0799] 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."

[0800] Modern user support systems are required to respond to user inquiries quickly and accurately, but current systems often lack consideration for user emotions. Furthermore, mechanisms for analyzing user inquiry data and reflecting the results in product improvements are often inadequate. As a result, issues remain in improving user satisfaction and providing feedback for product improvement. The present invention provides technology to address these issues.

[0801] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for learning from instruction manuals using a generative model and automatically generating responses to user inquiries, means for saving inquiry data and analyzing the content of the inquiry, means for creating a report based on the analysis results and providing suggestions for product improvement, means for analyzing the user's emotions using an emotion recognition engine and adjusting the tone and content of the response, and means for saving the emotion data and later analyzing it for use in service improvement. This makes it possible to provide support that reflects the user's emotions and to realize product improvements through precise analysis of the content of the inquiry.

[0802] A "generative model" is an algorithm that automatically generates answers to user inquiries based on pre-trained data.

[0803] An "instruction manual" is a document that describes how to use a product, its functions, troubleshooting methods, etc., and serves as a guide for users to use the product correctly.

[0804] "User" means an individual or organization that uses the System to make a product inquiry.

[0805] An "answer" is information or instructions provided in response to a user's inquiry that is generated by the server to resolve the problem.

[0806] An "emotion recognition engine" is software or an algorithm that analyzes emotions from a user's text input and takes appropriate action based on the results.

[0807] "Inquiry Data" means data submitted by you containing information relating to your question or problem.

[0808] "Analysis results" are the insights and findings obtained after analyzing inquiry data, which are used to create reports and improve products.

[0809] A "report" is a document that summarizes the results of the analysis and includes suggestions for product improvement and trend analysis.

[0810] "Product improvement" refers to activities aimed at improving the quality and performance of a product based on the analysis of user feedback and inquiry data.

[0811] "Tone" refers to the way the answer is expressed and the atmosphere it conveys, and is adjusted to convey a sense of politeness and security.

[0812] "Emotional data" refers to data containing the user's emotional information analyzed by the emotion recognition engine, and is used to improve the service.

[0813] "Service improvement" refers to the activity of taking specific measures and making adjustments to improve the quality of user support based on emotional data and inquiry data.

[0814] The present invention is a customer support system for an online shopping site that uses a generative model and an emotion recognition engine to provide responses to user inquiries that take emotion into consideration. Specific embodiments of the present invention are described below.

[0815] System Overview

[0816] The system mainly consists of the following elements:

[0817] 1. Generative model: Learns from the instruction manual and automatically generates answers to user inquiries.

[0818] 2. Emotion Recognition Engine: Analyzes emotions from user text input and adjusts the tone and content of responses.

[0819] 3. Data storage and analysis: User inquiry data and sentiment data are stored and later analyzed for use in improving services.

[0820] Program processing

[0821] Emotion Recognition and Answer Generation

[0822] The server first receives a query from the user, typically in chat format and saved as the user's text data. The emotion recognition engine analyzes the text data and identifies the user's emotions (e.g., anxiety, frustration, joy, etc.). Based on the identified emotions, the server builds prompts for the generative model.

[0823] Examples of prompts are:

[0824] The user is concerned. Please answer these questions politely: How do I return a recent purchase? The return deadline may have passed.

[0825] The results of the emotion recognition engine are used to select an appropriate prompt and send it to a generative model, which then uses the generative model (e.g., OpenAI's API) to generate an answer, whose tone and content take the user's emotions into account.

[0826] Data storage and analysis

[0827] The server stores user inquiry data, response data, and emotion data in a database. This stored data is periodically analyzed and a report is generated. The report includes inquiry trends, frequently occurring problems, and improvement suggestions based on the emotion data. This allows manufacturers to improve their products and the quality of user support.

[0828] Specific examples

[0829] If a user asks a question like "How do I return an item?" and the emotion recognition engine detects "anxiety," the prompt will be generated as follows:

[0830] The user is concerned. Please answer these questions politely: How do I return a recent purchase? The return deadline may have passed.

[0831] Based on this prompt, the generative model generates a polite and reassuring answer, such as, "We'll explain how to return the item. First, the return deadline may have passed, but we'll help you with the detailed process, so don't worry."

[0832] This allows users to receive support that takes their emotions into consideration, and their inquiries are responded to quickly and appropriately, resulting in improved user satisfaction and more efficient inquiry response.

[0833] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0834] Step 1:

[0835] A user accesses a customer support application using a smartphone and inputs an inquiry. For example, the user sends an inquiry in text format, such as "How do I return a product?" This text is sent to the server as input data.

[0836] Step 2:

[0837] The server receives the text data sent by the user and sends it to the emotion recognition engine. This emotion recognition engine analyzes the text data and identifies the user's emotion. The input is the user's text data, and the output is the identified emotion information (e.g., anxiety, irritation, etc.).

[0838] Step 3:

[0839] The server constructs a prompt for the generative model based on the emotional information obtained from the emotion recognition engine. The input is the emotional information and the user's inquiry, and the output is a prompt that reflects the emotion. For example, if the user is feeling "anxious," a prompt such as "The user is feeling anxious. Please answer the following questions politely: [User's inquiry]" is generated.

[0840] Step 4:

[0841] The server sends the generated prompt text to the generative AI model, which generates an answer. The input is the prompt text, and the output is an answer text that takes the user's sentiment into account. The generative AI model generates an appropriate answer based on the prompt. For example, it might generate an answer such as, "We will guide you through the return process. First, the return deadline may have passed, but please rest assured that we will support you with the detailed procedures."

[0842] Step 5:

[0843] The server sends the generated answer text to the user's smartphone and displays it on the chat interface. The input is the generated answer text, and the output is the answer displayed on the user's smartphone.

[0844] Step 6:

[0845] The server stores the user's query data, emotion data, and generated response data in a database. The input is this data, and the output is a saved database entry. This accumulates the data in a form that can be analyzed later.

[0846] Step 7:

[0847] The server periodically analyzes the accumulated inquiry data and emotion data and generates a report. The input is the data stored in the database, and the output is the analysis results and a report. This report includes inquiry trends, frequently occurring problems, and improvement suggestions based on the emotion data.

[0848] Step 8:

[0849] The server sends the generated report to the product improvement team or person in charge. The input is the report and the output is the data sent to the person in charge. This allows the manufacturer to improve the quality of their products and user support.

[0850] The above steps will enable fast and appropriate customer support that takes user emotions into consideration.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] [Third embodiment]

[0855] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0856] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0857] 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).

[0858] 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.

[0859] 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.

[0860] 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).

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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."

[0867] The present invention is a user support system for handling home appliances and devices that utilizes generative models. This system allows users to make inquiries in a chat format and quickly obtain information needed to solve problems. Specific embodiments of the present invention are described below.

[0868] User Actions

[0869] Users access the login screen using a device such as a smartphone or PC and enter their account information. After successful login, a chat interface appears. Users use this interface to input questions about home appliances and devices. For example, they might input a question like, "My XYZ manufacturer's ABC123 refrigerator isn't cooling."

[0870] Server Processing

[0871] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model that has been trained in advance from instruction manuals, error code lists, etc. From the analysis results, it generates the optimal answer to the user's question and sends this in chat format to the device. For example, it generates an answer that includes specific steps such as, "If your refrigerator is not cooling, first try the following steps: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked."

[0872] Terminal handling

[0873] The device displays the response received from the server in a chat interface, allowing the user to take steps to resolve the issue and, if necessary, enter further questions for follow-up responses.

[0874] Storage and analysis of inquiry data

[0875] The server stores user inquiries and their responses in a database. This data can then be analyzed later to identify trends and key issues. For example, if the same type of error occurs frequently on a particular model, a solution can be proposed to the manufacturer to fundamentally resolve the issue.

[0876] Report creation and delivery

[0877] Based on the analysis results, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and suggestions for improvement, and are provided to the manufacturer. This information helps the manufacturer improve their products and the quality of their customer support.

[0878] The system of the present invention allows users to enjoy the convenience of quickly resolving problems, and allows manufacturers to obtain data for more efficient response to inquiries and product improvement. As a specific example, when this system was used to handle a refrigerator error, the user was able to resolve the problem in just a few minutes. Furthermore, the manufacturer improved the refrigerator design based on the inquiry data, and the occurrence rate of the same error was significantly reduced in new products.

[0879] As such, the present invention is a system that offers great benefits to both users and manufacturers, and its implementation can significantly improve the user experience of home appliances and devices.

[0880] The processing flow will be explained below.

[0881] Step 1: Log in

[0882] The device displays a login screen and the user enters their account information (username and password).

[0883] The user enters their login information and presses the submit button.

[0884] Step 2: Authentication

[0885] The server receives the login information sent from the terminal.

[0886] The server checks the account information against the database and performs authentication.

[0887] If the authentication is successful, the server generates session information and sends it to the terminal. If the authentication fails, it sends an error message to the terminal.

[0888] Step 3: Displaying the chat interface

[0889] The terminal receives the authentication result from the server, and if the authentication is successful, displays the chat interface.

[0890] Users type questions about home appliances and devices into the chat box.

[0891] Step 4: Receiving and analyzing inquiries

[0892] The server receives the user's inquiry sent from the device, which includes the manufacturer name, model number, and error details.

[0893] The server invokes the generative model to analyze the received query.

[0894] The generative model extracts relevant information from pre-trained instruction manuals and generates the appropriate answer.

[0895] Step 5: Generate and submit your response

[0896] The server organizes the answers received from the generative model and converts them into a user-friendly format.

[0897] The server sends the generated response to the terminal.

[0898] Step 6: View and review your answers

[0899] The terminal displays the response received from the server on the chat interface.

[0900] The user reviews the displayed answer and takes steps, if necessary, to resolve the problem.

[0901] If the user has further questions, they can type them again in the chat box and submit.

[0902] Step 7: Save the inquiry data

[0903] The server stores the user's inquiries and their responses in a database.

[0904] Step 8: Compile data and generate reports

[0905] The server periodically analyzes the accumulated data and compiles information such as inquiry trends and major errors.

[0906] The server creates a report based on the analysis results and provides it to the manufacturer on a monthly or quarterly basis.

[0907] This series of processes allows users to quickly resolve problems with home appliances and devices, and manufacturers to obtain data to respond to inquiries more efficiently and improve their products.

[0908] Example 1

[0909] 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."

[0910] It is difficult to quickly and efficiently answer user questions and resolve issues regarding home appliances and devices, and there is a lack of effective ways to utilize the data obtained during the inquiry process. As a result, it takes time for users to receive appropriate support, and manufacturers also face challenges in improving their products and streamlining the support process.

[0911] 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.

[0912] In this invention, the server includes means for learning from instruction manuals using a generative model and automatically generating responses to user inquiries, means for a user to access a chat interface using a terminal and log in by entering account information, means for inputting a question into the chat interface after logging in and sending it, means for the server to analyze the user's inquiry using the generative model, generate a response, and send it to the terminal, means for the terminal to display the response received from the server on the chat interface and the user to confirm it, means for saving inquiry data and analyzing the content of the inquiry, and means for creating a report based on the analysis results and providing suggestions for product improvement. This allows users to receive quick and accurate support, and enables manufacturers to use the accumulated data to improve their products and streamline their support processes.

[0913] A "generative model" is a mathematical model that uses machine learning algorithms to learn from large amounts of data and generate new data.

[0914] An "instruction manual" is a document that contains information about how to use, set up, and troubleshoot an appliance or device.

[0915] "Inquiry Data" refers to text data regarding questions or problems submitted by users.

[0916] "Chat interface" refers to a user interface that allows a user to communicate with the system in a two-way manner in text format.

[0917] "User" refers to a general consumer or individual who uses this system to receive support for home appliances or devices.

[0918] "Terminal" refers to an information processing device such as a smartphone, PC, or tablet, which is used by a user to access the system.

[0919] A "server" is a computer system that receives data sent by users and performs multiple functions, such as analyzing it using generative models, generating answers, storing data, and creating reports.

[0920] "Login" is the authentication process by which a user enters their account information and begins using the system.

[0921] An "answer" refers to the solution or information provided as a result of the generative model analyzing the user's query.

[0922] A "report" is a document that compiles accumulated inquiry data and analysis results, and is provided to manufacturers to improve their products and the quality of their support processes.

[0923] "Product improvement" refers to efforts to improve the design and functionality of home appliances and devices based on user feedback and inquiry analysis results.

[0924] "Means" is a broad concept that refers to methods, techniques, and devices for realizing a specific function or process.

[0925] This invention is a user support system for home appliances and devices that uses a generative AI model. Its main purpose is to provide fast and effective support by automatically generating answers to user inquiries and storing and analyzing inquiry data.

[0926] Hardware and software used

[0927] Terminal: Information processing device used by the user, such as a smartphone, PC, or tablet.

[0928] Server: A computer system that receives data, analyzes it using a generative AI model, generates answers, stores and analyzes inquiry data, and creates reports.

[0929] Generative AI model: A machine learning algorithm trained from home appliance and device instruction manuals, error code lists, etc. (e.g., OpenAI GPT-4).

[0930] Program processing description

[0931] User Actions

[0932] The user accesses the system's login screen using a device such as a smartphone or PC. By entering their account information (username, password), the user is authenticated to the system. After authentication, the user enters an inquiry through the chat interface. An example of a prompt that the user enters at this time is, "My XYZ manufacturer ABC123 refrigerator is not cooling. What should I do?"

[0933] Server Processing

[0934] The server receives inquiries sent by users. A generative AI model is used to analyze the content of these inquiries. The generative AI model learns from home appliance instruction manuals and error code lists, and generates the optimal answer based on the user's question. For example, if the inquiry is "My refrigerator isn't cooling," the generated answer will include specific steps such as "If your refrigerator isn't cooling, try the following steps: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked."

[0935] The generated answer is sent from the server to the user's device. The server also stores the query and its answer in a database. This stored data is later used to analyze query trends and identify key issues.

[0936] Terminal handling

[0937] The user's device receives the response from the server and displays it in the chat interface. The user can refer to this information to take steps to resolve the issue, and can also enter a new question for further support if necessary.

[0938] Specific examples

[0939] Example of user action: The user types into the chat interface, "My XYZ manufacturer ABC123 refrigerator isn't cooling. What should I do?" and presses the send button.

[0940] Example of server operation: The server sends a query to the generation AI model, generating an answer such as "If the refrigerator is not cooling, try the following steps: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked." and sending it to the device.

[0941] Example of device behavior: The device displays the generated answer in a chat interface, and the user follows the steps to solve the problem.

[0942] This system allows users to receive fast and accurate support, and manufacturers can use the accumulated data to improve their products and streamline their support processes.

[0943] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0944] Step 1:

[0945] User login and access to the chat interface

[0946] The user accesses the system's login screen using a device (smartphone, PC, etc.). They are authenticated to the system by entering their account information (username, password) on the login screen. If login is successful, the system displays a chat interface to the user.

[0947] Input: Account information (username, password)

[0948] Output: Authentication success / failure, chat interface displayed

[0949] Specific behavior: The user opens a browser or app, accesses the specified URL, enters their account information, and clicks the "Login" button.

[0950] Step 2:

[0951] User inquiries

[0952] Users enter specific inquiries about home appliances and devices into the chat interface and press the send button.

[0953] Input: Text of the inquiry (e.g., "My refrigerator, model ABC123, made by XYZ, is not cooling. What should I do?")

[0954] Output: Sends query data to the server

[0955] Specific operation: The user enters the inquiry content into the chat interface and clicks the "Send" button.

[0956] Step 3:

[0957] Receiving and analyzing inquiries on the server

[0958] The server receives inquiries sent by users. The received text data is sent to a generative AI model, which analyzes the content. The generative AI model is trained from instruction manuals and error code lists.

[0959] Input: Enquiry data

[0960] Output: Analysis results (understanding of query content)

[0961] Specific operation: The server receives the user's query and passes it to the generative AI model to begin analysis.

[0962] Step 4:

[0963] Generating optimal answers on the server

[0964] The generative AI model generates the best possible answer based on the analyzed query, which includes specific instructions and steps.

[0965] Input: Analysis results

[0966] Output: Best answer (text data)

[0967] Specific behavior: The generative AI model generates a specific answer such as, "If your refrigerator is not cooling, try the following steps: 1. Check that the power is supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked."

[0968] Step 5:

[0969] Sending a response from the server to the user's device

[0970] The server then sends the generated response to the user's terminal.

[0971] Input: Best answer (text data)

[0972] Output: Sending response data to the terminal

[0973] Specific operation: The server formats the generated answer and sends it to the user's terminal according to the communication protocol.

[0974] Step 6:

[0975] Display of answers on the device and user responses

[0976] The user's device displays the response received from the server in a chat interface, where the user can review it and try to resolve the issue by following the steps provided.

[0977] Input: Response data

[0978] Output: The response displayed in the chat interface

[0979] Specific operation: The device displays the received response in the chat interface, and the user confirms its content.

[0980] Step 7:

[0981] Storing and post-processing inquiry data

[0982] The server stores the received queries and their responses in a database, which will be used for future analysis and statistics.

[0983] Input: Inquiry data and response data

[0984] Output: Saved database entries

[0985] Specific operation: The server saves the query and response in a database.

[0986] Step 8:

[0987] Regular reporting and provision

[0988] The server periodically analyzes the stored data and generates reports containing inquiry statistics, common problems, and suggestions for improvement. The reports are then provided to the manufacturer.

[0989] Input: Saved data

[0990] Output: Report

[0991] Specific operation: The server analyzes the stored data, generates periodic reports, and provides them to the manufacturer.

[0992] (Application example 1)

[0993] 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."

[0994] With conventional user support systems, it has been difficult for users to quickly obtain appropriate solutions when problems arise with home appliances or electronic devices. Furthermore, manufacturers have limited means to efficiently collect and analyze user inquiry data and use it to improve their products. Virtual stores, in particular, require a system that can provide immediate and accurate support.

[0995] 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.

[0996] In this invention, the server includes means for learning from instruction manuals using a generative model and automatically generating answers to user inquiries, means for saving inquiry data and analyzing the inquiry content, means for creating reports based on the analysis results and providing suggestions for product improvement, means for users to receive support for household appliances and electronic devices in a virtual store, and means for implementing a chatbot function via smartphone to provide quick answers to user questions. This allows users to solve problems in a short time and enables manufacturers to use the collected data to improve their products.

[0997] A "generative model" is an artificial intelligence technology that learns from large amounts of data and automatically generates answers to user inquiries.

[0998] An "instruction manual" is a document that contains detailed instructions on how to use and troubleshoot a household appliance or electronic device.

[0999] "User Inquiry" means a question or problem report submitted by a User seeking support.

[1000] "Auto-generation" is the process of programmatically creating answers or suggestions using artificial intelligence models.

[1001] "Inquiry Data" means records of questions or problems received from users.

[1002] "Analysis of inquiry content" is the process of analyzing received inquiry data and identifying problems and causes.

[1003] A "report" is a document summarizing inquiry data and analysis results, and is intended to be provided to manufacturers.

[1004] A "product improvement proposal" is a specific proposal for improving the performance or quality of a product based on the analysis results of the inquiry data.

[1005] A "virtual store" is a virtual store that sells products and provides services such as customer support over the Internet.

[1006] "Household electrical appliances" refer to electrical equipment used daily in the home.

[1007] An "electronic device" is a device that uses electronic technology to process and communicate information.

[1008] The "chatbot function" is a program that uses artificial intelligence to automatically respond to user input.

[1009] A "smartphone" is a mobile phone that has multiple functions and is capable of running applications.

[1010] The present invention is a system for users to receive support for household appliances and electronic devices in a virtual store. The system uses a generative model to learn from instruction manuals and automatically generate answers to user inquiries. It also stores and analyzes inquiry data to provide reports on product improvements. Specific embodiments of the system are described below.

[1011] User Actions

[1012] Users access the support section of the virtual store using their smartphones. They enter their account information on the login screen, and once logged in, a chat interface appears. Users use this interface to enter questions about their home appliances or electronic devices, for example, "My refrigerator isn't cooling."

[1013] Server Processing

[1014] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model that has been trained in advance from user manuals, error code lists, etc. The generative AI model (e.g., OpenAI's text-davinci-003) is used to generate the optimal answer to the user's question. The generated answer is then sent to the smartphone device in chat format.

[1015] Terminal handling

[1016] The smartphone displays the response received from the server in the chat interface. The user can refer to this and take steps to resolve the problem. For example, in response to a query such as "My refrigerator isn't cooling," the smartphone displays specific steps to improve the situation, such as "Please check that the power is being supplied properly. Please check that the temperature setting is appropriate. Please check that the vents are not blocked." If the user has further questions, they can continue to follow up through the chat interface.

[1017] Storage and analysis of inquiry data

[1018] The server stores user inquiries and their responses in a database. This data can be analyzed to identify trends and key issues. For example, if the same type of error occurs frequently with a particular home appliance, a report can be created to suggest a fundamental solution to the error to the manufacturer. This report is generated monthly or quarterly and provided to the manufacturer.

[1019] Report creation and delivery

[1020] Based on the results of the data analysis, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and suggestions for improvement. The reports are provided to the virtual store manager and the manufacturer, and are used to improve products and customer support quality.

[1021] Examples and prompts

[1022] For example, if a user enters "My refrigerator isn't cooling," the app will call the generative model and automatically generate answers such as, "Please check that the power is coming in properly. Please check that the temperature setting is correct. Please check that the vents are not blocked."

[1023] Prompt Sentence Examples

[1024] User Question: My refrigerator isn't cooling. What should I do?

[1025]

[1026] Generated Answer: If your refrigerator isn't cooling, try these steps first:

[1027] 1. Check if the power is supplied properly.

[1028] 2. Check that the temperature setting is appropriate.

[1029] 3. Check if the ventilation holes are blocked.

[1030] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1031] Step 1:

[1032] Users access the virtual store using their smartphones and log in by entering their account information. After successful login, a chat interface is displayed. Here, users can enter questions about household appliances or electronic devices (e.g., "My refrigerator isn't cooling"). The entered information is then sent to the server.

[1033] Input: User question (text format)

[1034] Output: A query is sent to the server

[1035] Step 2:

[1036] The server receives the question sent by the user and calls a generative AI model (e.g., OpenAI's text-davinci-003) to analyze the received question.

[1037] Input: User's question (in text format)

[1038] Output: The generative AI model is invoked

[1039] Step 3:

[1040] The generative AI model analyzes the content of the inquiry and generates the optimal answer. In this process, it generates a solution to the user's question based on what it has learned in advance from instruction manuals, error code lists, etc.

[1041] Input: User's question (in text format)

[1042] Output: Answers from the model (text format)

[1043] Step 4:

[1044] The server sends the answer obtained from the generative AI model to the user's smartphone device. The answer is sent in a standard format such as JSON.

[1045] Input: Generated answer (text format)

[1046] Output: The answer is sent to the user's device.

[1047] Step 5:

[1048] The terminal displays the answer received from the server in the chat interface, allowing the user to refer to it and follow specific steps to resolve the problem. If the user has further questions, they can also make additional inquiries through the same interface.

[1049] Input: Response from the server (text format)

[1050] Output: The answer is displayed to the user

[1051] Step 6:

[1052] The server stores the user's query and the generative model's response in a database. The stored data is managed in database format for later analysis.

[1053] Input: User queries and model responses (database format)

[1054] Output: Saved to the database

[1055] Step 7:

[1056] The server periodically analyzes the stored data from the database and generates a report, which includes statistical information on inquiries, frequently occurring problems, and improvement suggestions, etc. The generated report is provided to the manufacturer and the virtual store manager.

[1057] Input: query data stored in a database and generated answers

[1058] Output: Periodic reports (document format)

[1059] Prompt Sentence Examples

[1060] When a user types "The refrigerator is not cooling," the server sends the following prompt to the generative AI model:

[1061] User Question: My refrigerator isn't cooling. What should I do?

[1062] The generated answer looks like this:

[1063] If your refrigerator isn't cooling, try these steps first:

[1064] 1. Check if the power is supplied properly.

[1065] 2. Check that the temperature setting is appropriate.

[1066] 3. Check if the ventilation holes are blocked.

[1067]

[1068] 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.

[1069] The present invention is a user support system for handling home appliances and devices that utilizes a generative model and an emotion engine. This system recognizes emotions when a user makes an inquiry in chat format and provides optimal answers based on the results. Specific embodiments of the present invention are described below.

[1070] User Actions

[1071] Users access the login screen using a device such as a smartphone or PC and enter their account information. Once they have successfully logged in, a chat interface will appear. Users can use this interface to enter questions about home appliances and devices. The emotion engine will then recognize emotions from the user's text input and reflect that information in the next inquiry.

[1072] Server Processing

[1073] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model trained in advance from user manuals, error code lists, etc. Next, the emotion engine recognizes emotions from the user's text and adjusts the output response based on those emotions.

[1074] For example, in response to a query such as "XYZ manufacturer ABC123 refrigerator is not cooling," if the emotion engine recognizes emotions such as "anxiety" or "impatience" from the user's text, it will adjust the tone of the response to be more polite and reassuring: "If your refrigerator is not cooling, please try the following steps first: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the vents are not blocked. If you have any concerns, please contact us at any time for additional support."

[1075] Terminal handling

[1076] The device displays the response received from the server in a chat interface, allowing the user to take steps to resolve the issue and, if necessary, enter further questions for follow-up responses.

[1077] Storage and analysis of inquiry data

[1078] The server stores user inquiries, responses, and sentiment data in a database. This data can then be analyzed later to identify trends and key issues. For example, if the same type of error occurs frequently on a particular model, a solution can be proposed to the manufacturer to address the issue.

[1079] Use of Emotional Data

[1080] The server uses the emotional data recognized by the emotion engine and reflects it when creating reports. Based on the emotional data, it identifies areas where users are particularly dissatisfied and areas where support needs improvement, and provides feedback to manufacturers to improve end-user satisfaction.

[1081] Report creation and delivery

[1082] Based on the analysis results, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and improvement suggestions based on emotional data, and are provided to manufacturers. This information helps manufacturers improve their products and customer support quality.

[1083] The system of this invention allows users to enjoy the convenience of quickly resolving problems, and manufacturers can obtain data to improve the efficiency of customer inquiries and improve their products. As a specific example, when this system was used to handle a refrigerator error, the user was able to resolve the problem in just a few minutes. Furthermore, the manufacturer improved the refrigerator design based on the inquiry data and emotion data, and the occurrence rate of the same error was significantly reduced in new products.

[1084] As such, the present invention is a system that offers great benefits to both users and manufacturers, and its implementation can significantly improve the user experience of home appliances and devices.

[1085] The processing flow will be explained below.

[1086] Step 1: Log in

[1087] The device displays a login screen and the user enters their account information (username and password).

[1088] The user enters their login information and presses the submit button.

[1089] Step 2: Authentication

[1090] The server receives the login information sent from the terminal.

[1091] The server checks the account information against the database and performs authentication.

[1092] If the authentication is successful, the server generates session information and sends it to the terminal. If the authentication fails, it sends an error message to the terminal.

[1093] Step 3: Displaying the chat interface

[1094] The terminal receives the authentication result from the server, and if the authentication is successful, displays the chat interface.

[1095] Users type questions about home appliances and devices into the chat box.

[1096] Step 4: Receiving an inquiry

[1097] The server receives the user's inquiry sent from the device, which includes the manufacturer name, model number, and error details.

[1098] Step 5: Recognize emotions

[1099] The server passes the received query text to the emotion engine.

[1100] The emotion engine analyzes the user's emotions from the content of the inquiry.

[1101] The server receives the analysis results from the emotion engine and performs the next process based on the results.

[1102] Step 6: Analyzing the inquiry

[1103] The server invokes the generative model to analyze the query content, taking into account the results of the emotion engine.

[1104] The generative model extracts relevant information from pre-trained instruction manuals and generates answers that take the user's emotions into consideration.

[1105] Step 7: Generate and refine answers

[1106] The server then adjusts the tone and content of the generated response based on the emotion indicated by the emotion engine. For example, if the user is feeling anxious, the server will create a reassuring response.

[1107] The server sends the adjusted response to the terminal.

[1108] Step 8: View and review your answers

[1109] The terminal displays the response received from the server on the chat interface.

[1110] The user reviews the displayed answer and takes steps, if necessary, to resolve the problem.

[1111] If the user has further questions, they can type them again in the chat box and submit.

[1112] Step 9: Save the inquiry data

[1113] The server stores the user's inquiries, responses, and emotional data in a database.

[1114] Step 10: Compile data and generate reports

[1115] The server periodically analyzes the accumulated data and compiles information such as inquiry trends, major errors, and user sentiment.

[1116] The server creates a report based on the analysis results and provides it to the manufacturer on a monthly or quarterly basis.

[1117] This series of processes allows users to quickly resolve problems with home appliances and devices, and manufacturers can obtain data to improve the efficiency of customer inquiries and improve their products. The introduction of an emotion engine makes it possible to provide support that takes into account the user's psychological state, thereby improving user satisfaction.

[1118] Example 2

[1119] 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."

[1120] User support for modern home appliances and devices requires prompt and appropriate responses to inquiries. It is particularly important to consider the user's feelings in addition to resolving their problems. Conventional systems often provide uniform answers that ignore the user's feelings, resulting in low user satisfaction and inefficient inquiry handling. Another issue is the inability to utilize accumulated inquiry data to improve products.

[1121] 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.

[1122] In this invention, the server includes means for automatically generating responses to user inquiries by learning from instruction manuals using a generative model; means for saving inquiry data and emotion data and analyzing the inquiry content and emotion; means for creating a report based on the analysis results and emotion data and providing suggestions for product improvement; and means for adjusting the response by analyzing the user's emotion. This enables the provision of flexible responses that correspond to the user's emotion, improving the efficiency of inquiry responses and user satisfaction. Furthermore, utilizing the accumulated data also contributes to continuous product improvement.

[1123] A "generative model" is an algorithm that uses machine learning techniques to learn patterns from large amounts of data and adaptively respond to and generate new data.

[1124] "Instruction Document" means a document that describes how to use a product and provides troubleshooting information.

[1125] "User" means a person who uses a household appliance or device and seeks support.

[1126] "Inquiry Data" means information relating to user questions, problem reports, etc.

[1127] "Emotion data" is emotional information analyzed from a user's text input.

[1128] "Analysis" is the process of analyzing received data and extracting meaning and patterns.

[1129] A "report" is a document prepared based on the analysis results, and includes suggestions for product improvement.

[1130] "Product Improvement" means a change or addition to a product that improves its quality or performance.

[1131] "Automatic generation" means that the system automatically generates answers or documents without human intervention.

[1132] "Analyzing user emotions" is the process of using emotion recognition technology to identify emotions from a user's text and tailor responses accordingly.

[1133] The present invention is a user support system that utilizes a generative model and an emotion engine. This system accepts user inquiries about how to use home appliances and devices in a chat format, analyzes emotion data, and provides optimal answers. A specific embodiment of the present invention is described below.

[1134] Overall system configuration

[1135] The system consists of the following main components:

[1136] 1. User device (smartphone or PC)

[1137] 2. Server (Cloud server or dedicated server)

[1138] 3. Database (storing inquiry data and emotion data)

[1139] 4. Generative AI Models

[1140] 5. Emotion Engine

[1141] User Actions

[1142] Users access the login screen via a dedicated application or web browser using a device such as a smartphone or PC. After entering their account information, a chat interface is displayed once they have successfully logged in. Users can use this interface to enter questions about their home appliances and devices.

[1143] For example, if a user makes an inquiry such as "The ABC123 refrigerator from XYZ manufacturer is not cooling," they enter their question in the text box and click the send button. The emotion engine then recognizes the emotion from the user's text and reflects that information in the next inquiry.

[1144] Server Processing

[1145] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model that has been trained in advance from user manuals, error code lists, etc. Using reinforcement learning and deep learning techniques, it analyzes the meaning of the inquiry and identifies the problem.

[1146] Next, an emotion engine recognizes specific emotions (e.g., "anxiety" or "impatience") from the user's text. This emotion data is passed to a generative AI model, which takes this into account when generating the best answer.

[1147] Examples of concrete examples and prompts

[1148] For example, if a user asks, "My XYZ manufacturer ABC123 refrigerator isn't cooling. What should I do?" the prompt text would be as follows:

[1149] Example prompt:

[1150] "A user asks, 'My XYZ brand ABC123 refrigerator isn't cooling. What should I do?' The user's emotions seem to include anxiety. Generate a response with appropriate solutions and a reassuring tone."

[1151] Based on this prompt, the generative AI model generates the following answer:

[1152] "If your refrigerator isn't cooling, please try the following steps first: 1. Check that the power is properly supplied. 2. Check that the temperature setting is correct. 3. Check that the vents are not blocked. If you have any concerns, please contact us at any time for additional support."

[1153] Terminal handling

[1154] The device displays the response received from the server in the chat interface, where the user can refer to the response, follow up with the instructions, and enter further questions as needed to follow up.

[1155] Storage and analysis of inquiry and sentiment data

[1156] The server stores the user's inquiries, generated responses, and sentiment data in a database. The accumulated data is later analyzed and used to identify inquiry trends and key issues. For example, if the same type of error occurs frequently on a specific model, a solution to the underlying problem can be proposed to the manufacturer.

[1157] Report creation and delivery

[1158] Based on the analysis results, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and improvement suggestions based on sentiment data, and are provided to manufacturers. This information helps manufacturers improve their products and customer support quality.

[1159] The above is a specific embodiment of the present invention. This system allows users to quickly solve problems and manufacturers to obtain data for efficient response to inquiries and product improvement.

[1160] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1161] Understood. Now, I will explain the processing flow of this system's program by dividing it into processing steps below.

[1162] Step 1:

[1163] Users access the login screen using their smartphone or PC and enter their account information (user ID and password). The device then sends this authentication information to the server. The server compares the received authentication information with a database, and if authentication is successful, displays a chat interface to the user.

[1164] Input: User ID, Password

[1165] Output: Login successful message, chat interface displayed

[1166] Specific operation: The user enters their ID and password into a dedicated app or web browser, and the device sends this information to the server for authentication.

[1167] Step 2:

[1168] The user uses the chat interface to input their inquiry. For example, they might type "The ABC123 refrigerator is not cooling" into the text box and click the send button. The device then sends this inquiry to the server.

[1169] Input: Inquiry content (text)

[1170] Output: Sending query data to the server

[1171] Specific operation: The user enters a question into the chat interface and clicks the send button. The device sends this text to the server.

[1172] Step 3:

[1173] The server inputs the query data into the generative model to analyze the received query. The generative model analyzes the data based on the data it has learned in advance, identifies the problem, and generates a solution.

[1174] Input: Inquiry details

[1175] Output: Analysis results (identification of problems and solutions)

[1176] Specific operation: The server inputs data into the generative model to analyze the query, and the generative model identifies the problem and generates a solution.

[1177] Step 4:

[1178] The server passes the analysis results (problem identification and solution method) from the generative model and the query content to the emotion engine, which recognizes the user's emotions (anxiety, anger, etc.). The emotion engine extracts emotion data from the input text and returns it to the server.

[1179] Input: Inquiry details, analysis results

[1180] Output: Emotion data

[1181] Specific operation: The server passes the analysis results and query content to the emotion engine, which then recognizes the user's emotion and returns the data to the server.

[1182] Step 5:

[1183] The server uses the analysis results of the generative model and the recognition results of the emotion engine to have the generative AI model generate the optimal answer. The generative AI model then generates an appropriate answer for the user based on the prompt sentence.

[1184] For example, a prompt might read: "The user asked, 'My ABC123 refrigerator isn't cooling. What should I do?' The user's emotions seem to include anxiety. Please generate a response with appropriate solutions and a reassuring tone."

[1185] Input: prompt sentence, emotion data, analysis results

[1186] Output: The generated answer

[1187] Specific operation: The server inputs the prompt sentence into the generative AI model and obtains the generated answer.

[1188] Step 6:

[1189] The server sends the generated response to the terminal.

[1190] Input: Generated Answer

[1191] Output: Sending response data to the device

[1192] Specific operation: The server packages the generated response in a message format and sends it to the terminal.

[1193] Step 7:

[1194] The terminal displays the response received from the server on the chat interface, and the user refers to the response and performs the instructed procedure.

[1195] Input: Generated Answer

[1196] Output: Displayed in the chat interface

[1197] Specific operation: The device displays the received response in the chat window in real time, and the user follows the guided steps.

[1198] Step 8:

[1199] The server stores the query content, generated answers, and emotion data in a database.

[1200] Input: Enquiry, generated answer, sentiment data

[1201] Output: Store in database

[1202] Specific operation: The server compiles these data and writes them to the database.

[1203] Step 9:

[1204] The server analyzes the accumulated inquiry data and sentiment data to identify inquiry trends and key issues.

[1205] Input: Accumulated inquiry data, emotion data

[1206] Output: Analysis results (inquiry trends and issues)

[1207] What happens: The server uses data analytics tools to analyze the data and gain insights.

[1208] Step 10:

[1209] The server creates a report based on the analysis results and provides it to the manufacturer, including statistical information on inquiries, frequently occurring problems, and improvement suggestions based on emotional data.

[1210] Input: Analysis results

[1211] Output: Report

[1212] Specific operation: The server organizes the analysis results, automatically generates reports on a regular basis, and sends them to the manufacturer's representative.

[1213] (Application example 2)

[1214] 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."

[1215] Modern user support systems are required to respond to user inquiries quickly and accurately, but current systems often lack consideration for user emotions. Furthermore, mechanisms for analyzing user inquiry data and reflecting the results in product improvements are often inadequate. As a result, issues remain in improving user satisfaction and providing feedback for product improvement. The present invention provides technology to address these issues.

[1216] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for learning from instruction manuals using a generative model and automatically generating responses to user inquiries, means for saving inquiry data and analyzing the content of the inquiry, means for creating a report based on the analysis results and providing suggestions for product improvement, means for analyzing the user's emotions using an emotion recognition engine and adjusting the tone and content of the response, and means for saving the emotion data and later analyzing it for use in service improvement. This makes it possible to provide support that reflects the user's emotions and to realize product improvements through precise analysis of the content of the inquiry.

[1217] A "generative model" is an algorithm that automatically generates answers to user inquiries based on pre-trained data.

[1218] An "instruction manual" is a document that describes how to use a product, its functions, troubleshooting methods, etc., and serves as a guide for users to use the product correctly.

[1219] "User" means an individual or organization that uses the System to make a product inquiry.

[1220] An "answer" is information or instructions provided in response to a user's inquiry that is generated by the server to resolve the problem.

[1221] An "emotion recognition engine" is software or an algorithm that analyzes emotions from a user's text input and takes appropriate action based on the results.

[1222] "Inquiry Data" means data submitted by you containing information relating to your question or problem.

[1223] "Analysis results" are the insights and findings obtained after analyzing inquiry data, which are used to create reports and improve products.

[1224] A "report" is a document that summarizes the results of the analysis and includes suggestions for product improvement and trend analysis.

[1225] "Product improvement" refers to activities aimed at improving the quality and performance of a product based on the analysis of user feedback and inquiry data.

[1226] "Tone" refers to the way the answer is expressed and the atmosphere it conveys, and is adjusted to convey a sense of politeness and security.

[1227] "Emotional data" refers to data containing the user's emotional information analyzed by the emotion recognition engine, and is used to improve the service.

[1228] "Service improvement" refers to the activity of taking specific measures and making adjustments to improve the quality of user support based on emotional data and inquiry data.

[1229] The present invention is a customer support system for an online shopping site that uses a generative model and an emotion recognition engine to provide responses to user inquiries that take emotion into consideration. Specific embodiments of the present invention are described below.

[1230] System Overview

[1231] The system mainly consists of the following elements:

[1232] 1. Generative model: Learns from the instruction manual and automatically generates answers to user inquiries.

[1233] 2. Emotion Recognition Engine: Analyzes emotions from user text input and adjusts the tone and content of responses.

[1234] 3. Data storage and analysis: User inquiry data and sentiment data are stored and later analyzed for use in improving services.

[1235] Program processing

[1236] Emotion Recognition and Answer Generation

[1237] The server first receives a query from the user, typically in chat format and saved as the user's text data. The emotion recognition engine analyzes the text data and identifies the user's emotions (e.g., anxiety, frustration, joy, etc.). Based on the identified emotions, the server builds prompts for the generative model.

[1238] Examples of prompts are:

[1239] The user is concerned. Please answer these questions politely: How do I return a recent purchase? The return deadline may have passed.

[1240] The results of the emotion recognition engine are used to select an appropriate prompt and send it to a generative model, which then uses the generative model (e.g., OpenAI's API) to generate an answer, whose tone and content take the user's emotions into account.

[1241] Data storage and analysis

[1242] The server stores user inquiry data, response data, and emotion data in a database. This stored data is periodically analyzed and a report is generated. The report includes inquiry trends, frequently occurring problems, and improvement suggestions based on the emotion data. This allows manufacturers to improve their products and the quality of user support.

[1243] Specific examples

[1244] If a user asks a question like "How do I return an item?" and the emotion recognition engine detects "anxiety," the prompt will be generated as follows:

[1245] The user is concerned. Please answer these questions politely: How do I return a recent purchase? The return deadline may have passed.

[1246] Based on this prompt, the generative model generates a polite and reassuring answer, such as, "We'll explain how to return the item. First, the return deadline may have passed, but we'll help you with the detailed process, so don't worry."

[1247] This allows users to receive support that takes their emotions into consideration, and their inquiries are responded to quickly and appropriately, resulting in improved user satisfaction and more efficient inquiry response.

[1248] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1249] Step 1:

[1250] A user accesses a customer support application using a smartphone and inputs an inquiry. For example, the user sends an inquiry in text format, such as "How do I return a product?" This text is sent to the server as input data.

[1251] Step 2:

[1252] The server receives the text data sent by the user and sends it to the emotion recognition engine. This emotion recognition engine analyzes the text data and identifies the user's emotion. The input is the user's text data, and the output is the identified emotion information (e.g., anxiety, irritation, etc.).

[1253] Step 3:

[1254] The server constructs a prompt for the generative model based on the emotional information obtained from the emotion recognition engine. The input is the emotional information and the user's inquiry, and the output is a prompt that reflects the emotion. For example, if the user is feeling "anxious," a prompt such as "The user is feeling anxious. Please answer the following questions politely: [User's inquiry]" is generated.

[1255] Step 4:

[1256] The server sends the generated prompt text to the generative AI model, which generates an answer. The input is the prompt text, and the output is an answer text that takes the user's sentiment into account. The generative AI model generates an appropriate answer based on the prompt. For example, it might generate an answer such as, "We will guide you through the return process. First, the return deadline may have passed, but please rest assured that we will support you with the detailed procedures."

[1257] Step 5:

[1258] The server sends the generated answer text to the user's smartphone and displays it on the chat interface. The input is the generated answer text, and the output is the answer displayed on the user's smartphone.

[1259] Step 6:

[1260] The server stores the user's query data, emotion data, and generated response data in a database. The input is this data, and the output is a saved database entry. This accumulates the data in a form that can be analyzed later.

[1261] Step 7:

[1262] The server periodically analyzes the accumulated inquiry data and emotion data and generates a report. The input is the data stored in the database, and the output is the analysis results and a report. This report includes inquiry trends, frequently occurring problems, and improvement suggestions based on the emotion data.

[1263] Step 8:

[1264] The server sends the generated report to the product improvement team or person in charge. The input is the report and the output is the data sent to the person in charge. This allows the manufacturer to improve the quality of their products and user support.

[1265] The above steps will enable fast and appropriate customer support that takes user emotions into consideration.

[1266] 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.

[1267] 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.

[1268] 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.

[1269] [Fourth embodiment]

[1270] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1271] 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.

[1272] 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).

[1273] 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.

[1274] 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.

[1275] 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).

[1276] 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.

[1277] 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.

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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."

[1283] The present invention is a user support system for handling home appliances and devices that utilizes generative models. This system allows users to make inquiries in a chat format and quickly obtain information needed to solve problems. Specific embodiments of the present invention are described below.

[1284] User Actions

[1285] Users access the login screen using a device such as a smartphone or PC and enter their account information. After successful login, a chat interface appears. Users use this interface to input questions about home appliances and devices. For example, they might input a question like, "My XYZ manufacturer's ABC123 refrigerator isn't cooling."

[1286] Server Processing

[1287] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model that has been trained in advance from instruction manuals, error code lists, etc. From the analysis results, it generates the optimal answer to the user's question and sends this in chat format to the device. For example, it generates an answer that includes specific steps such as, "If your refrigerator is not cooling, first try the following steps: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked."

[1288] Terminal handling

[1289] The device displays the response received from the server in a chat interface, allowing the user to take steps to resolve the issue and, if necessary, enter further questions for follow-up responses.

[1290] Storage and analysis of inquiry data

[1291] The server stores user inquiries and their responses in a database. This data can then be analyzed later to identify trends and key issues. For example, if the same type of error occurs frequently on a particular model, a solution can be proposed to the manufacturer to fundamentally resolve the issue.

[1292] Report creation and delivery

[1293] Based on the analysis results, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and suggestions for improvement, and are provided to the manufacturer. This information helps the manufacturer improve their products and the quality of their customer support.

[1294] The system of the present invention allows users to enjoy the convenience of quickly resolving problems, and allows manufacturers to obtain data for more efficient response to inquiries and product improvement. As a specific example, when this system was used to handle a refrigerator error, the user was able to resolve the problem in just a few minutes. Furthermore, the manufacturer improved the refrigerator design based on the inquiry data, and the occurrence rate of the same error was significantly reduced in new products.

[1295] As such, the present invention is a system that offers great benefits to both users and manufacturers, and its implementation can significantly improve the user experience of home appliances and devices.

[1296] The processing flow will be explained below.

[1297] Step 1: Log in

[1298] The device displays a login screen and the user enters their account information (username and password).

[1299] The user enters their login information and presses the submit button.

[1300] Step 2: Authentication

[1301] The server receives the login information sent from the terminal.

[1302] The server checks the account information against the database and performs authentication.

[1303] If the authentication is successful, the server generates session information and sends it to the terminal. If the authentication fails, it sends an error message to the terminal.

[1304] Step 3: Displaying the chat interface

[1305] The terminal receives the authentication result from the server, and if the authentication is successful, displays the chat interface.

[1306] Users type questions about home appliances and devices into the chat box.

[1307] Step 4: Receiving and analyzing inquiries

[1308] The server receives the user's inquiry sent from the device, which includes the manufacturer name, model number, and error details.

[1309] The server invokes the generative model to analyze the received query.

[1310] The generative model extracts relevant information from pre-trained instruction manuals and generates the appropriate answer.

[1311] Step 5: Generate and submit your response

[1312] The server organizes the answers received from the generative model and converts them into a user-friendly format.

[1313] The server sends the generated response to the terminal.

[1314] Step 6: View and review your answers

[1315] The terminal displays the response received from the server on the chat interface.

[1316] The user reviews the displayed answer and takes steps, if necessary, to resolve the problem.

[1317] If the user has further questions, they can type them again in the chat box and submit.

[1318] Step 7: Save the inquiry data

[1319] The server stores the user's inquiries and their responses in a database.

[1320] Step 8: Compile data and generate reports

[1321] The server periodically analyzes the accumulated data and compiles information such as inquiry trends and major errors.

[1322] The server creates a report based on the analysis results and provides it to the manufacturer on a monthly or quarterly basis.

[1323] This series of processes allows users to quickly resolve problems with home appliances and devices, and manufacturers to obtain data to respond to inquiries more efficiently and improve their products.

[1324] Example 1

[1325] 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."

[1326] It is difficult to quickly and efficiently answer user questions and resolve issues regarding home appliances and devices, and there is a lack of effective ways to utilize the data obtained during the inquiry process. As a result, it takes time for users to receive appropriate support, and manufacturers also face challenges in improving their products and streamlining the support process.

[1327] 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.

[1328] In this invention, the server includes means for learning from instruction manuals using a generative model and automatically generating responses to user inquiries, means for a user to access a chat interface using a terminal and log in by entering account information, means for inputting a question into the chat interface after logging in and sending it, means for the server to analyze the user's inquiry using the generative model, generate a response, and send it to the terminal, means for the terminal to display the response received from the server on the chat interface and the user to confirm it, means for saving inquiry data and analyzing the content of the inquiry, and means for creating a report based on the analysis results and providing suggestions for product improvement. This allows users to receive quick and accurate support, and enables manufacturers to use the accumulated data to improve their products and streamline their support processes.

[1329] A "generative model" is a mathematical model that uses machine learning algorithms to learn from large amounts of data and generate new data.

[1330] An "instruction manual" is a document that contains information about how to use, set up, and troubleshoot an appliance or device.

[1331] "Inquiry Data" refers to text data regarding questions or problems submitted by users.

[1332] "Chat interface" refers to a user interface that allows a user to communicate with the system in a two-way manner in text format.

[1333] "User" refers to a general consumer or individual who uses this system to receive support for home appliances or devices.

[1334] "Terminal" refers to an information processing device such as a smartphone, PC, or tablet, which is used by a user to access the system.

[1335] A "server" is a computer system that receives data sent by users and performs multiple functions, such as analyzing it using generative models, generating answers, storing data, and creating reports.

[1336] "Login" is the authentication process by which a user enters their account information and begins using the system.

[1337] An "answer" refers to the solution or information provided as a result of the generative model analyzing the user's query.

[1338] A "report" is a document that compiles accumulated inquiry data and analysis results, and is provided to manufacturers to improve their products and the quality of their support processes.

[1339] "Product improvement" refers to efforts to improve the design and functionality of home appliances and devices based on user feedback and inquiry analysis results.

[1340] "Means" is a broad concept that refers to methods, techniques, and devices for realizing a specific function or process.

[1341] This invention is a user support system for home appliances and devices that uses a generative AI model. Its main purpose is to provide fast and effective support by automatically generating answers to user inquiries and storing and analyzing inquiry data.

[1342] Hardware and software used

[1343] Terminal: Information processing device used by the user, such as a smartphone, PC, or tablet.

[1344] Server: A computer system that receives data, analyzes it using a generative AI model, generates answers, stores and analyzes inquiry data, and creates reports.

[1345] Generative AI model: A machine learning algorithm trained from home appliance and device instruction manuals, error code lists, etc. (e.g., OpenAI GPT-4).

[1346] Program processing description

[1347] User Actions

[1348] The user accesses the system's login screen using a device such as a smartphone or PC. By entering their account information (username, password), the user is authenticated to the system. After authentication, the user enters an inquiry through the chat interface. An example of a prompt that the user enters at this time is, "My XYZ manufacturer ABC123 refrigerator is not cooling. What should I do?"

[1349] Server Processing

[1350] The server receives inquiries sent by users. A generative AI model is used to analyze the content of these inquiries. The generative AI model learns from home appliance instruction manuals and error code lists, and generates the optimal answer based on the user's question. For example, if the inquiry is "My refrigerator isn't cooling," the generated answer will include specific steps such as "If your refrigerator isn't cooling, try the following steps: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked."

[1351] The generated answer is sent from the server to the user's device. The server also stores the query and its answer in a database. This stored data is later used to analyze query trends and identify key issues.

[1352] Terminal handling

[1353] The user's device receives the response from the server and displays it in the chat interface. The user can refer to this information to take steps to resolve the issue, and can also enter a new question for further support if necessary.

[1354] Specific examples

[1355] Example of user action: The user types into the chat interface, "My XYZ manufacturer ABC123 refrigerator isn't cooling. What should I do?" and presses the send button.

[1356] Example of server operation: The server sends a query to the generation AI model, generating an answer such as "If the refrigerator is not cooling, try the following steps: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked." and sending it to the device.

[1357] Example of device behavior: The device displays the generated answer in a chat interface, and the user follows the steps to solve the problem.

[1358] This system allows users to receive fast and accurate support, and manufacturers can use the accumulated data to improve their products and streamline their support processes.

[1359] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1360] Step 1:

[1361] User login and access to the chat interface

[1362] The user accesses the system's login screen using a device (smartphone, PC, etc.). They are authenticated to the system by entering their account information (username, password) on the login screen. If login is successful, the system displays a chat interface to the user.

[1363] Input: Account information (username, password)

[1364] Output: Authentication success / failure, chat interface displayed

[1365] Specific behavior: The user opens a browser or app, accesses the specified URL, enters their account information, and clicks the "Login" button.

[1366] Step 2:

[1367] User inquiries

[1368] Users enter specific inquiries about home appliances and devices into the chat interface and press the send button.

[1369] Input: Text of the inquiry (e.g., "My refrigerator, model ABC123, made by XYZ, is not cooling. What should I do?")

[1370] Output: Sends query data to the server

[1371] Specific operation: The user enters the inquiry content into the chat interface and clicks the "Send" button.

[1372] Step 3:

[1373] Receiving and analyzing inquiries on the server

[1374] The server receives inquiries sent by users. The received text data is sent to a generative AI model, which analyzes the content. The generative AI model is trained from instruction manuals and error code lists.

[1375] Input: Enquiry data

[1376] Output: Analysis results (understanding of query content)

[1377] Specific operation: The server receives the user's query and passes it to the generative AI model to begin analysis.

[1378] Step 4:

[1379] Generating optimal answers on the server

[1380] The generative AI model generates the best possible answer based on the analyzed query, which includes specific instructions and steps.

[1381] Input: Analysis results

[1382] Output: Best answer (text data)

[1383] Specific behavior: The generative AI model generates a specific answer such as, "If your refrigerator is not cooling, try the following steps: 1. Check that the power is supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the air vents are not blocked."

[1384] Step 5:

[1385] Sending a response from the server to the user's device

[1386] The server then sends the generated response to the user's terminal.

[1387] Input: Best answer (text data)

[1388] Output: Sending response data to the terminal

[1389] Specific operation: The server formats the generated answer and sends it to the user's terminal according to the communication protocol.

[1390] Step 6:

[1391] Display of answers on the device and user responses

[1392] The user's device displays the response received from the server in a chat interface, where the user can review it and try to resolve the issue by following the steps provided.

[1393] Input: Response data

[1394] Output: The response displayed in the chat interface

[1395] Specific operation: The device displays the received response in the chat interface, and the user confirms its content.

[1396] Step 7:

[1397] Storing and post-processing inquiry data

[1398] The server stores the received queries and their responses in a database, which will be used for future analysis and statistics.

[1399] Input: Inquiry data and response data

[1400] Output: Saved database entries

[1401] Specific operation: The server saves the query and response in a database.

[1402] Step 8:

[1403] Regular reporting and provision

[1404] The server periodically analyzes the stored data and generates reports containing inquiry statistics, common problems, and suggestions for improvement. The reports are then provided to the manufacturer.

[1405] Input: Saved data

[1406] Output: Report

[1407] Specific operation: The server analyzes the stored data, generates periodic reports, and provides them to the manufacturer.

[1408] (Application example 1)

[1409] 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."

[1410] With conventional user support systems, it has been difficult for users to quickly obtain appropriate solutions when problems arise with home appliances or electronic devices. Furthermore, manufacturers have limited means to efficiently collect and analyze user inquiry data and use it to improve their products. Virtual stores, in particular, require a system that can provide immediate and accurate support.

[1411] 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.

[1412] In this invention, the server includes means for learning from instruction manuals using a generative model and automatically generating answers to user inquiries, means for saving inquiry data and analyzing the inquiry content, means for creating reports based on the analysis results and providing suggestions for product improvement, means for users to receive support for household appliances and electronic devices in a virtual store, and means for implementing a chatbot function via smartphone to provide quick answers to user questions. This allows users to solve problems in a short time and enables manufacturers to use the collected data to improve their products.

[1413] A "generative model" is an artificial intelligence technology that learns from large amounts of data and automatically generates answers to user inquiries.

[1414] An "instruction manual" is a document that contains detailed instructions on how to use and troubleshoot a household appliance or electronic device.

[1415] "User Inquiry" means a question or problem report submitted by a User seeking support.

[1416] "Auto-generation" is the process of programmatically creating answers or suggestions using artificial intelligence models.

[1417] "Inquiry Data" means records of questions or problems received from users.

[1418] "Analysis of inquiry content" is the process of analyzing received inquiry data and identifying problems and causes.

[1419] A "report" is a document summarizing inquiry data and analysis results, and is intended to be provided to manufacturers.

[1420] A "product improvement proposal" is a specific proposal for improving the performance or quality of a product based on the analysis results of the inquiry data.

[1421] A "virtual store" is a virtual store that sells products and provides services such as customer support over the Internet.

[1422] "Household electrical appliances" refer to electrical equipment used daily in the home.

[1423] An "electronic device" is a device that uses electronic technology to process and communicate information.

[1424] The "chatbot function" is a program that uses artificial intelligence to automatically respond to user input.

[1425] A "smartphone" is a mobile phone that has multiple functions and is capable of running applications.

[1426] The present invention is a system for users to receive support for household appliances and electronic devices in a virtual store. The system uses a generative model to learn from instruction manuals and automatically generate answers to user inquiries. It also stores and analyzes inquiry data to provide reports on product improvements. Specific embodiments of the system are described below.

[1427] User Actions

[1428] Users access the support section of the virtual store using their smartphones. They enter their account information on the login screen, and once logged in, a chat interface appears. Users use this interface to enter questions about their home appliances or electronic devices, for example, "My refrigerator isn't cooling."

[1429] Server Processing

[1430] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model that has been trained in advance from user manuals, error code lists, etc. The generative AI model (e.g., OpenAI's text-davinci-003) is used to generate the optimal answer to the user's question. The generated answer is then sent to the smartphone device in chat format.

[1431] Terminal handling

[1432] The smartphone displays the response received from the server in the chat interface. The user can refer to this and take steps to resolve the problem. For example, in response to a query such as "My refrigerator isn't cooling," the smartphone displays specific steps to improve the situation, such as "Please check that the power is being supplied properly. Please check that the temperature setting is appropriate. Please check that the vents are not blocked." If the user has further questions, they can continue to follow up through the chat interface.

[1433] Storage and analysis of inquiry data

[1434] The server stores user inquiries and their responses in a database. This data can be analyzed to identify trends and key issues. For example, if the same type of error occurs frequently with a particular home appliance, a report can be created to suggest a fundamental solution to the error to the manufacturer. This report is generated monthly or quarterly and provided to the manufacturer.

[1435] Report creation and delivery

[1436] Based on the results of the data analysis, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and suggestions for improvement. The reports are provided to the virtual store manager and the manufacturer, and are used to improve products and customer support quality.

[1437] Examples and prompts

[1438] For example, if a user enters "My refrigerator isn't cooling," the app will call the generative model and automatically generate answers such as, "Please check that the power is coming in properly. Please check that the temperature setting is correct. Please check that the vents are not blocked."

[1439] Prompt Sentence Examples

[1440] User Question: My refrigerator isn't cooling. What should I do?

[1441]

[1442] Generated Answer: If your refrigerator isn't cooling, try these steps first:

[1443] 1. Check if the power is supplied properly.

[1444] 2. Check that the temperature setting is appropriate.

[1445] 3. Check if the ventilation holes are blocked.

[1446] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1447] Step 1:

[1448] Users access the virtual store using their smartphones and log in by entering their account information. After successful login, a chat interface is displayed. Here, users can enter questions about household appliances or electronic devices (e.g., "My refrigerator isn't cooling"). The entered information is then sent to the server.

[1449] Input: User question (text format)

[1450] Output: A query is sent to the server

[1451] Step 2:

[1452] The server receives the question sent by the user and calls a generative AI model (e.g., OpenAI's text-davinci-003) to analyze the received question.

[1453] Input: User's question (in text format)

[1454] Output: The generative AI model is invoked

[1455] Step 3:

[1456] The generative AI model analyzes the content of the inquiry and generates the optimal answer. In this process, it generates a solution to the user's question based on what it has learned in advance from instruction manuals, error code lists, etc.

[1457] Input: User's question (in text format)

[1458] Output: Answers from the model (text format)

[1459] Step 4:

[1460] The server sends the answer obtained from the generative AI model to the user's smartphone device. The answer is sent in a standard format such as JSON.

[1461] Input: Generated answer (text format)

[1462] Output: The answer is sent to the user's device.

[1463] Step 5:

[1464] The terminal displays the answer received from the server in the chat interface, allowing the user to refer to it and follow specific steps to resolve the problem. If the user has further questions, they can also make additional inquiries through the same interface.

[1465] Input: Response from the server (text format)

[1466] Output: The answer is displayed to the user

[1467] Step 6:

[1468] The server stores the user's query and the generative model's response in a database. The stored data is managed in database format for later analysis.

[1469] Input: User queries and model responses (database format)

[1470] Output: Saved to the database

[1471] Step 7:

[1472] The server periodically analyzes the stored data from the database and generates a report, which includes statistical information on inquiries, frequently occurring problems, and improvement suggestions, etc. The generated report is provided to the manufacturer and the virtual store manager.

[1473] Input: query data stored in a database and generated answers

[1474] Output: Periodic reports (document format)

[1475] Prompt Sentence Examples

[1476] When a user types "The refrigerator is not cooling," the server sends the following prompt to the generative AI model:

[1477] User Question: My refrigerator isn't cooling. What should I do?

[1478] The generated answer looks like this:

[1479] If your refrigerator isn't cooling, try these steps first:

[1480] 1. Check if the power is supplied properly.

[1481] 2. Check that the temperature setting is appropriate.

[1482] 3. Check if the ventilation holes are blocked.

[1483]

[1484] 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.

[1485] The present invention is a user support system for handling home appliances and devices that utilizes a generative model and an emotion engine. This system recognizes emotions when a user makes an inquiry in chat format and provides optimal answers based on the results. Specific embodiments of the present invention are described below.

[1486] User Actions

[1487] Users access the login screen using a device such as a smartphone or PC and enter their account information. Once they have successfully logged in, a chat interface will appear. Users can use this interface to enter questions about home appliances and devices. The emotion engine will then recognize emotions from the user's text input and reflect that information in the next inquiry.

[1488] Server Processing

[1489] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model trained in advance from user manuals, error code lists, etc. Next, the emotion engine recognizes emotions from the user's text and adjusts the output response based on those emotions.

[1490] For example, in response to a query such as "XYZ manufacturer ABC123 refrigerator is not cooling," if the emotion engine recognizes emotions such as "anxiety" or "impatience" from the user's text, it will adjust the tone of the response to be more polite and reassuring: "If your refrigerator is not cooling, please try the following steps first: 1. Check that the power is being supplied properly. 2. Check that the temperature setting is appropriate. 3. Check that the vents are not blocked. If you have any concerns, please contact us at any time for additional support."

[1491] Terminal handling

[1492] The device displays the response received from the server in a chat interface, allowing the user to take steps to resolve the issue and, if necessary, enter further questions for follow-up responses.

[1493] Storage and analysis of inquiry data

[1494] The server stores user inquiries, responses, and sentiment data in a database. This data can then be analyzed later to identify trends and key issues. For example, if the same type of error occurs frequently on a particular model, a solution can be proposed to the manufacturer to address the issue.

[1495] Use of Emotional Data

[1496] The server uses the emotional data recognized by the emotion engine and reflects it when creating reports. Based on the emotional data, it identifies areas where users are particularly dissatisfied and areas where support needs improvement, and provides feedback to manufacturers to improve end-user satisfaction.

[1497] Report creation and delivery

[1498] Based on the analysis results, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and improvement suggestions based on emotional data, and are provided to manufacturers. This information helps manufacturers improve their products and customer support quality.

[1499] The system of this invention allows users to enjoy the convenience of quickly resolving problems, and manufacturers can obtain data to improve the efficiency of customer inquiries and improve their products. As a specific example, when this system was used to handle a refrigerator error, the user was able to resolve the problem in just a few minutes. Furthermore, the manufacturer improved the refrigerator design based on the inquiry data and emotion data, and the occurrence rate of the same error was significantly reduced in new products.

[1500] As such, the present invention is a system that offers great benefits to both users and manufacturers, and its implementation can significantly improve the user experience of home appliances and devices.

[1501] The processing flow will be explained below.

[1502] Step 1: Log in

[1503] The device displays a login screen and the user enters their account information (username and password).

[1504] The user enters their login information and presses the submit button.

[1505] Step 2: Authentication

[1506] The server receives the login information sent from the terminal.

[1507] The server checks the account information against the database and performs authentication.

[1508] If the authentication is successful, the server generates session information and sends it to the terminal. If the authentication fails, it sends an error message to the terminal.

[1509] Step 3: Displaying the chat interface

[1510] The terminal receives the authentication result from the server, and if the authentication is successful, displays the chat interface.

[1511] Users type questions about home appliances and devices into the chat box.

[1512] Step 4: Receiving an inquiry

[1513] The server receives the user's inquiry sent from the device, which includes the manufacturer name, model number, and error details.

[1514] Step 5: Recognize emotions

[1515] The server passes the received query text to the emotion engine.

[1516] The emotion engine analyzes the user's emotions from the content of the inquiry.

[1517] The server receives the analysis results from the emotion engine and performs the next process based on the results.

[1518] Step 6: Analyzing the inquiry

[1519] The server invokes the generative model to analyze the query content, taking into account the results of the emotion engine.

[1520] The generative model extracts relevant information from pre-trained instruction manuals and generates answers that take the user's emotions into consideration.

[1521] Step 7: Generate and refine answers

[1522] The server then adjusts the tone and content of the generated response based on the emotion indicated by the emotion engine. For example, if the user is feeling anxious, the server will create a reassuring response.

[1523] The server sends the adjusted response to the terminal.

[1524] Step 8: View and review your answers

[1525] The terminal displays the response received from the server on the chat interface.

[1526] The user reviews the displayed answer and takes steps, if necessary, to resolve the problem.

[1527] If the user has further questions, they can type them again in the chat box and submit.

[1528] Step 9: Save the inquiry data

[1529] The server stores the user's inquiries, responses, and emotional data in a database.

[1530] Step 10: Compile data and generate reports

[1531] The server periodically analyzes the accumulated data and compiles information such as inquiry trends, major errors, and user sentiment.

[1532] The server creates a report based on the analysis results and provides it to the manufacturer on a monthly or quarterly basis.

[1533] This series of processes allows users to quickly resolve problems with home appliances and devices, and manufacturers can obtain data to improve the efficiency of customer inquiries and improve their products. The introduction of an emotion engine makes it possible to provide support that takes into account the user's psychological state, thereby improving user satisfaction.

[1534] Example 2

[1535] 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."

[1536] User support for modern home appliances and devices requires prompt and appropriate responses to inquiries. It is particularly important to consider the user's feelings in addition to resolving their problems. Conventional systems often provide uniform answers that ignore the user's feelings, resulting in low user satisfaction and inefficient inquiry handling. Another issue is the inability to utilize accumulated inquiry data to improve products.

[1537] 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.

[1538] In this invention, the server includes means for automatically generating responses to user inquiries by learning from instruction manuals using a generative model; means for saving inquiry data and emotion data and analyzing the inquiry content and emotion; means for creating a report based on the analysis results and emotion data and providing suggestions for product improvement; and means for adjusting the response by analyzing the user's emotion. This enables the provision of flexible responses that correspond to the user's emotion, improving the efficiency of inquiry responses and user satisfaction. Furthermore, utilizing the accumulated data also contributes to continuous product improvement.

[1539] A "generative model" is an algorithm that uses machine learning techniques to learn patterns from large amounts of data and adaptively respond to and generate new data.

[1540] "Instruction Document" means a document that describes how to use a product and provides troubleshooting information.

[1541] "User" means a person who uses a household appliance or device and seeks support.

[1542] "Inquiry Data" means information relating to user questions, problem reports, etc.

[1543] "Emotion data" is emotional information analyzed from a user's text input.

[1544] "Analysis" is the process of analyzing received data and extracting meaning and patterns.

[1545] A "report" is a document prepared based on the analysis results, and includes suggestions for product improvement.

[1546] "Product Improvement" means a change or addition to a product that improves its quality or performance.

[1547] "Automatic generation" means that the system automatically generates answers or documents without human intervention.

[1548] "Analyzing user emotions" is the process of using emotion recognition technology to identify emotions from a user's text and tailor responses accordingly.

[1549] The present invention is a user support system that utilizes a generative model and an emotion engine. This system accepts user inquiries about how to use home appliances and devices in a chat format, analyzes emotion data, and provides optimal answers. A specific embodiment of the present invention is described below.

[1550] Overall system configuration

[1551] The system consists of the following main components:

[1552] 1. User device (smartphone or PC)

[1553] 2. Server (Cloud server or dedicated server)

[1554] 3. Database (storing inquiry data and emotion data)

[1555] 4. Generative AI Models

[1556] 5. Emotion Engine

[1557] User Actions

[1558] Users access the login screen via a dedicated application or web browser using a device such as a smartphone or PC. After entering their account information, a chat interface is displayed once they have successfully logged in. Users can use this interface to enter questions about their home appliances and devices.

[1559] For example, if a user makes an inquiry such as "The ABC123 refrigerator from XYZ manufacturer is not cooling," they enter their question in the text box and click the send button. The emotion engine then recognizes the emotion from the user's text and reflects that information in the next inquiry.

[1560] Server Processing

[1561] The server receives inquiries sent by users. To analyze the content of these inquiries, it uses a generative model that has been trained in advance from user manuals, error code lists, etc. Using reinforcement learning and deep learning techniques, it analyzes the meaning of the inquiry and identifies the problem.

[1562] Next, an emotion engine recognizes specific emotions (e.g., "anxiety" or "impatience") from the user's text. This emotion data is passed to a generative AI model, which takes this into account when generating the best answer.

[1563] Examples of concrete examples and prompts

[1564] For example, if a user asks, "My XYZ manufacturer ABC123 refrigerator isn't cooling. What should I do?" the prompt text would be as follows:

[1565] Example prompt:

[1566] "A user asks, 'My XYZ brand ABC123 refrigerator isn't cooling. What should I do?' The user's emotions seem to include anxiety. Generate a response with appropriate solutions and a reassuring tone."

[1567] Based on this prompt, the generative AI model generates the following answer:

[1568] "If your refrigerator isn't cooling, please try the following steps first: 1. Check that the power is properly supplied. 2. Check that the temperature setting is correct. 3. Check that the vents are not blocked. If you have any concerns, please contact us at any time for additional support."

[1569] Terminal handling

[1570] The device displays the response received from the server in the chat interface, where the user can refer to the response, follow up with the instructions, and enter further questions as needed to follow up.

[1571] Storage and analysis of inquiry and sentiment data

[1572] The server stores the user's inquiries, generated responses, and sentiment data in a database. The accumulated data is later analyzed and used to identify inquiry trends and key issues. For example, if the same type of error occurs frequently on a specific model, a solution to the underlying problem can be proposed to the manufacturer.

[1573] Report creation and delivery

[1574] Based on the analysis results, the server periodically creates reports, which include statistical information on inquiries, frequently occurring problems, and improvement suggestions based on sentiment data, and are provided to manufacturers. This information helps manufacturers improve their products and customer support quality.

[1575] The above is a specific embodiment of the present invention. This system allows users to quickly solve problems and manufacturers to obtain data for efficient response to inquiries and product improvement.

[1576] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1577] Understood. Now, I will explain the processing flow of this system's program by dividing it into processing steps below.

[1578] Step 1:

[1579] Users access the login screen using their smartphone or PC and enter their account information (user ID and password). The device then sends this authentication information to the server. The server compares the received authentication information with a database, and if authentication is successful, displays a chat interface to the user.

[1580] Input: User ID, Password

[1581] Output: Login successful message, chat interface displayed

[1582] Specific operation: The user enters their ID and password into a dedicated app or web browser, and the device sends this information to the server for authentication.

[1583] Step 2:

[1584] The user uses the chat interface to input their inquiry. For example, they might type "The ABC123 refrigerator is not cooling" into the text box and click the send button. The device then sends this inquiry to the server.

[1585] Input: Inquiry content (text)

[1586] Output: Sending query data to the server

[1587] Specific operation: The user enters a question into the chat interface and clicks the send button. The device sends this text to the server.

[1588] Step 3:

[1589] The server inputs the query data into the generative model to analyze the received query. The generative model analyzes the data based on the data it has learned in advance, identifies the problem, and generates a solution.

[1590] Input: Inquiry details

[1591] Output: Analysis results (identification of problems and solutions)

[1592] Specific operation: The server inputs data into the generative model to analyze the query, and the generative model identifies the problem and generates a solution.

[1593] Step 4:

[1594] The server passes the analysis results (problem identification and solution method) from the generative model and the query content to the emotion engine, which recognizes the user's emotions (anxiety, anger, etc.). The emotion engine extracts emotion data from the input text and returns it to the server.

[1595] Input: Inquiry details, analysis results

[1596] Output: Emotion data

[1597] Specific operation: The server passes the analysis results and query content to the emotion engine, which then recognizes the user's emotion and returns the data to the server.

[1598] Step 5:

[1599] The server uses the analysis results of the generative model and the recognition results of the emotion engine to have the generative AI model generate the optimal answer. The generative AI model then generates an appropriate answer for the user based on the prompt sentence.

[1600] For example, a prompt might read: "The user asked, 'My ABC123 refrigerator isn't cooling. What should I do?' The user's emotions seem to include anxiety. Please generate a response with appropriate solutions and a reassuring tone."

[1601] Input: prompt sentence, emotion data, analysis results

[1602] Output: The generated answer

[1603] Specific operation: The server inputs the prompt sentence into the generative AI model and obtains the generated answer.

[1604] Step 6:

[1605] The server sends the generated response to the terminal.

[1606] Input: Generated Answer

[1607] Output: Sending response data to the device

[1608] Specific operation: The server packages the generated response in a message format and sends it to the terminal.

[1609] Step 7:

[1610] The terminal displays the response received from the server on the chat interface, and the user refers to the response and performs the instructed procedure.

[1611] Input: Generated Answer

[1612] Output: Displayed in the chat interface

[1613] Specific operation: The device displays the received response in the chat window in real time, and the user follows the guided steps.

[1614] Step 8:

[1615] The server stores the query content, generated answers, and emotion data in a database.

[1616] Input: Enquiry, generated answer, sentiment data

[1617] Output: Store in database

[1618] Specific operation: The server compiles these data and writes them to the database.

[1619] Step 9:

[1620] The server analyzes the accumulated inquiry data and sentiment data to identify inquiry trends and key issues.

[1621] Input: Accumulated inquiry data, emotion data

[1622] Output: Analysis results (inquiry trends and issues)

[1623] What happens: The server uses data analytics tools to analyze the data and gain insights.

[1624] Step 10:

[1625] The server creates a report based on the analysis results and provides it to the manufacturer, including statistical information on inquiries, frequently occurring problems, and improvement suggestions based on emotional data.

[1626] Input: Analysis results

[1627] Output: Report

[1628] Specific operation: The server organizes the analysis results, automatically generates reports on a regular basis, and sends them to the manufacturer's representative.

[1629] (Application example 2)

[1630] 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."

[1631] Modern user support systems are required to respond to user inquiries quickly and accurately, but current systems often lack consideration for user emotions. Furthermore, mechanisms for analyzing user inquiry data and reflecting the results in product improvements are often inadequate. As a result, issues remain in improving user satisfaction and providing feedback for product improvement. The present invention provides technology to address these issues.

[1632] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for learning from instruction manuals using a generative model and automatically generating responses to user inquiries, means for saving inquiry data and analyzing the content of the inquiry, means for creating a report based on the analysis results and providing suggestions for product improvement, means for analyzing the user's emotions using an emotion recognition engine and adjusting the tone and content of the response, and means for saving the emotion data and later analyzing it for use in service improvement. This makes it possible to provide support that reflects the user's emotions and to realize product improvements through precise analysis of the content of the inquiry.

[1633] A "generative model" is an algorithm that automatically generates answers to user inquiries based on pre-trained data.

[1634] An "instruction manual" is a document that describes how to use a product, its functions, troubleshooting methods, etc., and serves as a guide for users to use the product correctly.

[1635] "User" means an individual or organization that uses the System to make a product inquiry.

[1636] An "answer" is information or instructions provided in response to a user's inquiry that is generated by the server to resolve the problem.

[1637] An "emotion recognition engine" is software or an algorithm that analyzes emotions from a user's text input and takes appropriate action based on the results.

[1638] "Inquiry Data" means data submitted by you containing information relating to your question or problem.

[1639] "Analysis results" are the insights and findings obtained after analyzing inquiry data, which are used to create reports and improve products.

[1640] A "report" is a document that summarizes the results of the analysis and includes suggestions for product improvement and trend analysis.

[1641] "Product improvement" refers to activities aimed at improving the quality and performance of a product based on the analysis of user feedback and inquiry data.

[1642] "Tone" refers to the way the answer is expressed and the atmosphere it conveys, and is adjusted to convey a sense of politeness and security.

[1643] "Emotional data" refers to data containing the user's emotional information analyzed by the emotion recognition engine, and is used to improve the service.

[1644] "Service improvement" refers to the activity of taking specific measures and making adjustments to improve the quality of user support based on emotional data and inquiry data.

[1645] The present invention is a customer support system for an online shopping site that uses a generative model and an emotion recognition engine to provide responses to user inquiries that take emotion into consideration. Specific embodiments of the present invention are described below.

[1646] System Overview

[1647] The system mainly consists of the following elements:

[1648] 1. Generative model: Learns from the instruction manual and automatically generates answers to user inquiries.

[1649] 2. Emotion Recognition Engine: Analyzes emotions from user text input and adjusts the tone and content of responses.

[1650] 3. Data storage and analysis: User inquiry data and sentiment data are stored and later analyzed for use in improving services.

[1651] Program processing

[1652] Emotion Recognition and Answer Generation

[1653] The server first receives a query from the user, typically in chat format and saved as the user's text data. The emotion recognition engine analyzes the text data and identifies the user's emotions (e.g., anxiety, frustration, joy, etc.). Based on the identified emotions, the server builds prompts for the generative model.

[1654] Examples of prompts are:

[1655] The user is concerned. Please answer these questions politely: How do I return a recent purchase? The return deadline may have passed.

[1656] The results of the emotion recognition engine are used to select an appropriate prompt and send it to a generative model, which then uses the generative model (e.g., OpenAI's API) to generate an answer, whose tone and content take the user's emotions into account.

[1657] Data storage and analysis

[1658] The server stores user inquiry data, response data, and emotion data in a database. This stored data is periodically analyzed and a report is generated. The report includes inquiry trends, frequently occurring problems, and improvement suggestions based on the emotion data. This allows manufacturers to improve their products and the quality of user support.

[1659] Specific examples

[1660] If a user asks a question like "How do I return an item?" and the emotion recognition engine detects "anxiety," the prompt will be generated as follows:

[1661] The user is concerned. Please answer these questions politely: How do I return a recent purchase? The return deadline may have passed.

[1662] Based on this prompt, the generative model generates a polite and reassuring answer, such as, "We'll explain how to return the item. First, the return deadline may have passed, but we'll help you with the detailed process, so don't worry."

[1663] This allows users to receive support that takes their emotions into consideration, and their inquiries are responded to quickly and appropriately, resulting in improved user satisfaction and more efficient inquiry response.

[1664] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1665] Step 1:

[1666] A user accesses a customer support application using a smartphone and inputs an inquiry. For example, the user sends an inquiry in text format, such as "How do I return a product?" This text is sent to the server as input data.

[1667] Step 2:

[1668] The server receives the text data sent by the user and sends it to the emotion recognition engine. This emotion recognition engine analyzes the text data and identifies the user's emotion. The input is the user's text data, and the output is the identified emotion information (e.g., anxiety, irritation, etc.).

[1669] Step 3:

[1670] The server constructs a prompt for the generative model based on the emotional information obtained from the emotion recognition engine. The input is the emotional information and the user's inquiry, and the output is a prompt that reflects the emotion. For example, if the user is feeling "anxious," a prompt such as "The user is feeling anxious. Please answer the following questions politely: [User's inquiry]" is generated.

[1671] Step 4:

[1672] The server sends the generated prompt text to the generative AI model, which generates an answer. The input is the prompt text, and the output is an answer text that takes the user's sentiment into account. The generative AI model generates an appropriate answer based on the prompt. For example, it might generate an answer such as, "We will guide you through the return process. First, the return deadline may have passed, but please rest assured that we will support you with the detailed procedures."

[1673] Step 5:

[1674] The server sends the generated answer text to the user's smartphone and displays it on the chat interface. The input is the generated answer text, and the output is the answer displayed on the user's smartphone.

[1675] Step 6:

[1676] The server stores the user's query data, emotion data, and generated response data in a database. The input is this data, and the output is a saved database entry. This accumulates the data in a form that can be analyzed later.

[1677] Step 7:

[1678] The server periodically analyzes the accumulated inquiry data and emotion data and generates a report. The input is the data stored in the database, and the output is the analysis results and a report. This report includes inquiry trends, frequently occurring problems, and improvement suggestions based on the emotion data.

[1679] Step 8:

[1680] The server sends the generated report to the product improvement team or person in charge. The input is the report and the output is the data sent to the person in charge. This allows the manufacturer to improve the quality of their products and user support.

[1681] The above steps will enable fast and appropriate customer support that takes user emotions into consideration.

[1682] 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.

[1683] 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.

[1684] 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.

[1685] 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.

[1686] 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.

[1687] 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.

[1688] 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).

[1689] 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.

[1690] 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."

[1691] 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.

[1692] 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).

[1693] 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.

[1694] 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.

[1695] 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.

[1696] 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.

[1697] 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.

[1698] 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.

[1699] 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.

[1700] 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.

[1701] 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.

[1702] 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.

[1703] The following is further disclosed regarding the above embodiment.

[1704] (Claim 1)

[1705] A means for automatically generating answers to user inquiries by learning from instruction manuals using a generative model;

[1706] means for storing inquiry data and analyzing the inquiry content;

[1707] A means to create reports based on the analysis results and provide suggestions for product improvement;

[1708] A system including:

[1709] (Claim 2)

[1710] 2. The system according to claim 1, further comprising a means for a user to make inquiries in chat format and receive responses.

[1711] (Claim 3)

[1712] 10. The system of claim 1, further comprising means for managing data for each product and providing monthly or quarterly reports to manufacturers.

[1713] "Example 1"

[1714] (Claim 1)

[1715] A means for automatically generating answers to user inquiries by learning from instruction manuals using a generative model;

[1716] A means for a user to access the chat interface using a device and enter account information to log in;

[1717] After logging in, you can type and send questions in the chat interface.

[1718] A means for the server to analyze the user's inquiry using the generative model, generate an answer, and send it to the terminal;

[1719] A means for displaying the response received by the terminal from the server on a chat interface so that the user can confirm it;

[1720] means for storing inquiry data and analyzing the inquiry content;

[1721] A means to create reports based on the analysis results and provide suggestions for product improvement;

[1722] A system including:

[1723] (Claim 2)

[1724] 2. The system according to claim 1, further comprising a means for a user to make inquiries in chat format and receive responses.

[1725] (Claim 3)

[1726] 10. The system of claim 1, further comprising means for managing data for each product and providing monthly or quarterly reports to manufacturers.

[1727] "Application Example 1"

[1728] (Claim 1)

[1729] A means for automatically generating answers to user inquiries by learning from instruction manuals using a generative model;

[1730] means for storing inquiry data and analyzing the inquiry content;

[1731] A means to create reports based on the analysis results and provide suggestions for product improvement;

[1732] A means for users to get support for their consumer electronics and electronic devices within the virtual store;

[1733] A chatbot function can be implemented via smartphones to provide quick answers to user questions,

[1734] A system including:

[1735] (Claim 2)

[1736] 2. The system according to claim 1, further comprising a means for a user to make inquiries in chat format and receive responses.

[1737] (Claim 3)

[1738] 10. The system of claim 1, further comprising means for managing data for each product and providing periodic reports to manufacturers.

[1739] "Example 2: Combining Emotion Engines"

[1740] (Claim 1)

[1741] A means for automatically generating answers to user inquiries by learning from instruction manuals using a generative model;

[1742] A means for storing inquiry data and emotion data and analyzing the inquiry content and emotion;

[1743] a means for generating a report based on the analysis results and sentiment data and providing suggestions for product improvement;

[1744] A means of adjusting responses by analyzing user sentiment;

[1745] A system including:

[1746] (Claim 2)

[1747] 2. The system according to claim 1, further comprising a means for a user to make inquiries in chat format and receive responses.

[1748] (Claim 3)

[1749] 2. The system according to claim 1, further comprising means for managing data for each product and providing periodic reports to manufacturers.

[1750] "Application example 2 when combining emotion engines"

[1751] (Claim 1)

[1752] A means for automatically generating answers to user inquiries by learning from instruction manuals using a generative model;

[1753] means for storing inquiry data and analyzing the inquiry content;

[1754] A means to create reports based on the analysis results and provide suggestions for product improvement;

[1755] An emotion recognition engine analyzes the user's emotions and adjusts the tone and content of the response.

[1756] A means to store emotional data and later analyze it for use in improving services,

[1757] A system including:

[1758] (Claim 2)

[1759] 2. The system according to claim 1, further comprising a means for a user to make inquiries in chat format and receive responses.

[1760] (Claim 3)

[1761] 10. The system of claim 1, further comprising means for managing data by product and providing reports by institution. [Explanation of symbols]

[1762] 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 automatically generating answers to user inquiries by learning from instruction manuals using a generative model; means for storing inquiry data and analyzing the inquiry content; A means to create reports based on the analysis results and provide suggestions for product improvement; A system including:

2. 2. The system according to claim 1, further comprising a means for a user to make inquiries in a chat format and receive responses.

3. 2. The system according to claim 1, further comprising means for managing data for each product and providing a report to the manufacturer monthly or quarterly.

Images