System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving an inquiry from a user through a chat interface; natural language processing means for analyzing the received inquiry and specifying information on a related device; means for acquiring a corresponding instruction manual from a database based on the specified information and generating an answer to the inquiry; means for notifying the user of the generated answer; means for aggregating all inquiry contents from the user and generating statistical data; and means for creating a report based on the statistical data and providing the report to a manufacturer.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] Today, many home appliances and devices have complex functions, and their instruction manuals contain detailed and varied information. This makes it difficult for users to quickly find solutions to specific problems or errors. This also leads to an increase in call center inquiries and rising customer support costs. Furthermore, manufacturers lack effective ways to collect and analyze user feedback and use it to improve their products and add new features. [Means for solving the problem]

[0005] This invention provides a system that receives inquiries from users via a chat interface and analyzes them using natural language processing to identify relevant equipment information. Based on the identified information, it retrieves instruction manuals from a database and generates optimal answers to provide to users. It also records and aggregates all inquiries in a database to generate statistical data. Reports based on the generated statistical data can be created and provided to manufacturers, helping them improve products and develop new features. This system allows users to solve problems efficiently, and manufacturers to reduce customer support costs and obtain information useful for product development.

[0006] "User" refers to an individual who uses the system to ask questions about the handling of a home appliance or device.

[0007] "Chat interface" refers to a communication means through which users can enter questions in text form and receive answers.

[0008] "Natural language processing means" refers to technology for analyzing user questions and identifying related device information and error details.

[0009] "Database" refers to a system for recording and storing instruction manuals and inquiries from users.

[0010] "Instruction Manual" refers to a document that describes how to use a particular appliance or device and how to troubleshoot errors.

[0011] The "answer generation means" refers to a function that refers to an instruction manual from a database based on information identified by the natural language processing means and generates an optimal answer for the user.

[0012] "Answer notification means" refers to a communication means for delivering the generated answer to the user.

[0013] "Inquiry content" refers to questions about the handling of home appliances and devices that users ask through the system.

[0014] "Statistical data" refers to data obtained by compiling and analyzing inquiries from all users.

[0015] "Means of creating a 'report' and providing it to manufacturers" refers to the process of compiling information for product improvement and new function development based on statistical data and providing it to manufacturers.

[0016] "Manufacturer" refers to a company that designs, manufactures, and sells home appliances and devices. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] The present invention relates to a system that accepts inquiries about home appliances and devices in a chat format, analyzes the user's question, and provides the most appropriate answer. This system is implemented in the following way.

[0039] First, a user accesses the chat interface using a terminal. The user makes an inquiry by entering a question in the text box and pressing the send button. For example, a specific question can be entered, such as "Please tell me about the error code E23 on the XYZ refrigerator."

[0040] Next, the server receives the user's inquiry and analyzes it using natural language processing means, which extracts information such as "XYZ refrigerator" and "error code E23" from the question and identifies the relevant device information and error content.

[0041] The server accesses the database based on the identified information and searches for the corresponding instruction manual. The database returns the corresponding instruction manual, and extracts the solution to the error code E23 from it. For example, if the solution for the error code E23 is "indicates poor cooling, check the power supply, and clean the filter," an answer is generated based on this information.

[0042] The generated answer is sent from the server to the user's device, and the user receives the answer through a chat interface, specifically displaying the message "Error code E23 indicates poor cooling. Please check the power supply and clean the filter."

[0043] In addition, the server records all user inquiries in a database. The recorded data is periodically compiled and analyzed as statistical data. Reports are created based on this statistical data and provided to manufacturers. This allows manufacturers to effectively obtain feedback necessary for product improvement and the addition of new features.

[0044] For example, if many users inquire about a common error code, the solution to that error code will be improved and the relevant section of the instruction manual will be revised. In this way, the system of the present invention provides an environment in which users can solve problems efficiently, helping manufacturers improve the quality of their products while reducing the burden on customer support.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] A user accesses the chat interface using a terminal, enters a question in the text box, and presses the send button, which sends the user's inquiry from the terminal to the server.

[0048] Step 2:

[0049] The server receives an inquiry from a user and passes the inquiry content to the natural language processing means, which analyzes the received inquiry content and extracts the corresponding device type and error code.

[0050] Step 3:

[0051] The natural language processing means identifies the "device type (e.g., XYZ refrigerator)" and "error code (e.g., E23)" as analysis results and returns them to the server. The server then accesses the database based on this information.

[0052] Step 4:

[0053] The server retrieves the instruction manual data for the target device from the database. For example, it searches for "XYZ refrigerator instruction manual" and retrieves related information.

[0054] Step 5:

[0055] The server extracts the solution corresponding to the identified error code (e.g., E23) from the instruction manual data acquired. For example, if the solution to error code E23 is "indicates poor cooling, check the power supply, and clean the filter," this information is extracted.

[0056] Step 6:

[0057] Based on the information extracted by the server, the optimal response to the inquiry is generated, for example, "Error code E23 indicates poor cooling. Check the power supply and clean the filter."

[0058] Step 7:

[0059] The server sends the generated answer to the terminal and notifies the user, who can then check the answer in the chat interface again via the terminal.

[0060] Step 8:

[0061] The server records all user inquiries in a database and periodically compiles and analyzes them. It creates reports based on the compiled statistical data and provides them to manufacturers. The manufacturers use the reports to improve their products and develop new features.

[0062] The above is a specific processing flow of the system of the present invention.

[0063] Example 1

[0064] 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."

[0065] Today's consumers increasingly use a wide variety of home appliances and devices, and want to quickly resolve any problems or errors they encounter with these products. However, referring to instruction manuals one by one is time-consuming, and finding the appropriate solution can be difficult, especially for specialized issues like error codes. Manufacturers also need to efficiently process user inquiries and collect data to help improve and enhance their products. Current systems do not adequately meet these needs, causing inconvenience to both users and manufacturers.

[0066] 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.

[0067] In this invention, the server includes means for receiving inquiries from users via a chat interface, natural language processing means for analyzing the received inquiries and identifying information on related devices, and means for retrieving the relevant instruction manual from a database based on the identified information and generating an answer to the inquiry. This allows users to quickly and accurately find solutions to their problems, and enables manufacturers to utilize the question history to improve product quality and streamline customer support.

[0068] A "user" is an individual or corporation that uses the system to make inquiries about home appliances and devices.

[0069] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0070] A "chat interface" is a text-based interaction tool that allows users to enter questions and interact with the system.

[0071] A "server" is a computer system that receives queries from users, analyzes them, and generates and sends appropriate responses.

[0072] "Natural language processing means" is a technology for analyzing received text data and understanding the content of the user's question.

[0073] A "database" is a system for centrally managing data such as instruction manuals and past inquiry history for home appliances and devices.

[0074] An "instruction manual" is a document that describes how to use a home appliance or device, the meaning of error codes, troubleshooting, etc.

[0075] A "means for generating an answer" is a means for creating an appropriate response to a user's question.

[0076] The "notification means" is a means for transmitting the generated answer to the user's terminal.

[0077] "Statistical data" refers to data analyzed based on the collected inquiries from users.

[0078] "Report" means a report prepared based on statistical data and provided to a manufacturer.

[0079] "Manufacturers" are companies that make appliances and devices.

[0080] The present invention is a system that allows users to make inquiries about home appliances and devices, and provides quick and accurate answers through a chat interface. This system operates by combining terminals, servers, databases, and natural language processing technology.

[0081] First, a user accesses the chat interface using a device (e.g., computer, smartphone, or tablet). Here, the user enters a question in the text box and clicks the send button. For example, the user might enter, "Can you tell me about error code E23 on my XYZ refrigerator?"

[0082] The server receives the query sent by the user and analyzes it using natural language processing technology. Specific software used is Google Cloud Natural Language API and IBM Watson Natural Language Understanding. Through this analysis, the server extracts important keywords from the text (e.g., "XYZ refrigerator" or "error code E23").

[0083] The server then queries a database based on these keywords to retrieve the relevant instruction manual. The database uses MySQL or MongoDB, and searches the instruction manual for a solution to the corresponding error code. For example, if the solution to error code E23 is "indicates poor cooling, check the power supply, and clean the filter," the server generates an answer based on this information.

[0084] The generated response is sent from the server to the user's device and displayed in the chat interface, specifically saying, "Error code E23 indicates poor cooling. Please check the power supply and clean the filter."

[0085] In addition, the server records all user inquiries in a database. This data is periodically aggregated and analyzed using statistical analysis software in Python or R. A report is generated based on the analysis results and provided to the manufacturer. This allows the manufacturer to obtain feedback needed to improve the quality of their products and add new features.

[0086] Examples of specific prompts are:

[0087] Example user input:

[0088] "What can I do about error code E23 on the XYZ refrigerator?"

[0089] Example server response:

[0090] "Error code E23 indicates poor cooling. Check the power supply and clean the filters."

[0091] Example prompt for a generative AI model:

[0092] "A user is asking, 'What can I do about error code E23 on my XYZ refrigerator?' Generate the best answer possible. The answer should include specific solutions (e.g., check the power supply and clean the filter)."

[0093] In this way, the system of the present invention provides an environment in which users can efficiently solve problems, and helps manufacturers improve the quality of their products while reducing the burden of customer support.

[0094] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0095] Step 1:

[0096] The user inputs a question into the terminal and sends it.

[0097] Specifically, the user types a question into the text box of the chat interface, such as "Can you tell me about error code E23 on the XYZ refrigerator?", and then presses the send button.

[0098] Input: User question (e.g. "What can I do about error code E23 on my XYZ refrigerator?")

[0099] Output: Submitted question data

[0100] Step 2:

[0101] The server receives the query.

[0102] The server receives the data sent by the user and adds it to a processing queue, at which point the received data is stored in text format.

[0103] Input: Submitted question data

[0104] Output: Question data added to the processing queue

[0105] Step 3:

[0106] The server analyzes the query using natural language processing (NLP) techniques.

[0107] Specifically, the server analyzes the input text using Google Cloud Natural Language API, IBM Watson Natural Language Understanding, etc. The server then performs entity recognition and extracts keywords such as "XYZ refrigerator" and "error code E23."

[0108] Input: Question data retrieved from the processing queue

[0109] Output: Analysis results (keywords: "XYZ refrigerator", "error code E23")

[0110] Step 4:

[0111] The server searches the database based on the keywords.

[0112] The server uses the extracted keywords to query a database, for example, using MySQL or MongoDB to search for the corresponding instruction manual and extract the relevant information.

[0113] Input: Keywords from the analysis results ("XYZ refrigerator", "Error code E23")

[0114] Output: Data from the relevant instruction manual

[0115] Step 5:

[0116] The server retrieves the relevant solutions and generates an answer.

[0117] The server identifies a solution to the error code E23 based on the contents of the instruction manual retrieved from the database. For example, it generates a response such as, "Error code E23 indicates poor cooling. Check the power supply and clean the filter."

[0118] Input: Instruction manual data

[0119] Output: Generated response (e.g. "Error code E23 indicates poor cooling. Check the power supply and clean the filters.")

[0120] Step 6:

[0121] The server sends the generated answer to the user's terminal.

[0122] The server sends the generated reply to the user's terminal and displays it on the chat interface.

[0123] Input: Generated answer

[0124] Output: Answer displayed on the user's terminal

[0125] Step 7:

[0126] The server records the inquiry in a database.

[0127] The server stores all queries in a database, making them available for future analysis and reference.

[0128] Input: Processed question and answer data

[0129] Output: Records stored in the database

[0130] Step 8:

[0131] The server aggregates and analyzes the data and creates reports for manufacturers.

[0132] The server periodically aggregates the recorded data and analyzes it using statistical analysis software such as Python or R. Based on the results of this analysis, a report is created and provided to the manufacturer.

[0133] Input: Query history stored in the database

[0134] Output: Report for manufacturer

[0135] (Application example 1)

[0136] 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."

[0137] There is a problem in that it is difficult to quickly provide appropriate solutions to abnormalities and problems that occur during the operation of machines and robots used in factories. In particular, if on-site workers and engineers cannot find a solution immediately, production efficiency may decrease, resulting in wasted time and costs.

[0138] 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.

[0139] In this invention, the server includes: means for receiving inquiries from users through a chat interface; natural language processing means for analyzing the received inquiries and identifying information on related equipment; means for retrieving the relevant instruction manual from a database based on the identified information and generating an answer to the inquiry; means for notifying the user of the generated answer; means for aggregating all inquiries from users and generating statistical data; means for creating a report based on the statistical data and providing it to the manufacturer; and means for receiving inquiries regarding abnormalities or problems with machines in the manufacturing process and using a generative AI model to provide appropriate maintenance procedures. This enables users to efficiently troubleshoot and maintain machines and robots used in factories.

[0140] A "chat interface" is an interactive interface for users to submit text-based inquiries.

[0141] "Natural language processing means" is a technology that analyzes text data from users and understands and processes human language.

[0142] A "database" is a system for organizing, storing, and searching specific information.

[0143] A "query answer generator" is a mechanism that generates an answer to a user's question based on information retrieved from a database.

[0144] A "generative AI model" is a model that uses artificial intelligence technology to generate and analyze data and provide appropriate answers and responses.

[0145] "Statistical data" refers to data obtained as a result of compiling and analyzing inquiries from users.

[0146] "Report" means a summary of information based on statistical data and provided to a manufacturer.

[0147] "Machine abnormalities and problems" refers to conditions or problems in which machines or robots used in the manufacturing process do not function properly.

[0148] "Maintenance procedures" are specific operating methods for checking the correct operation of machines and robots and making any necessary adjustments or repairs.

[0149] "Manufacturer" means a company or organization that designs and produces equipment or systems involved in the manufacturing process.

[0150] The present invention is a system that accepts inquiries about the operation and maintenance of machines and robots in manufacturing processes in a chat format, analyzes the user's question, and provides the most appropriate answer. This system is implemented in the following way.

[0151] Users access a chat interface installed in the factory using a device such as a smartphone or tablet. Through this chat interface, users make inquiries by entering a question in a text box and pressing the send button. For example, users can enter specific questions such as, "Please tell me about the XYZ robot's error code E45" or "My robot is stuck and won't move. What should I do?"

[0152] Next, the server receives the user's inquiry and analyzes it using natural language processing means, which extracts information such as "XYZ robot" and "error code E45" from the question and identifies the relevant device information and error content.

[0153] Based on the identified information, the server searches the database for the corresponding instruction manual. The database returns relevant information, and from that information, it extracts solutions to error code E45 and robot maintenance procedures. For example, detailed information including steps such as "check the power supply unit" is provided as a solution to error code E45.

[0154] The generated answer is sent from the server to the user's device, and the user receives the answer through a chat interface, specifically displaying the message "Error code E45 indicates a problem with the power supply unit. Please check the power supply unit."

[0155] In addition, the server records all user inquiries in a database. The recorded data is periodically aggregated and analyzed as statistical data using a generative AI model. A report is created based on this statistical data and provided to the manufacturer. This allows the manufacturer to effectively obtain the feedback needed to improve their products and add new features.

[0156] For example:

[0157] Example prompt sentence:

[0158] "Please tell me about the XYZ robot error code E45."

[0159] "My robot is stuck and won't move, what should I do?"

[0160] "Please tell me the maintenance procedure for the picking robot."

[0161] Hardware used: smartphone, tablet

[0162] Software used: OpenAI API, Flask

[0163] This allows factory workers and engineers to troubleshoot robots and machinery quickly and efficiently, significantly improving production efficiency.

[0164] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0165] Step 1:

[0166] A user accesses the chat interface using a device (smartphone or tablet) and enters a question. For example, they might enter, "Please tell me about the XYZ robot error code E45." The input data is in text format, and once the input is complete, it is sent to the server by pressing the send button.

[0167] Step 2:

[0168] The server receives queries from users. The received queries are saved as text data. Specifically, the server receives an HTTP request and extracts its payload (the query content). The input data is the user's question text, which is passed to the server's analysis module.

[0169] Step 3:

[0170] The server analyzes the query using natural language processing. Specifically, an NLP (Natural Language Processing) model extracts information such as "XYZ robot" or "error code E45" from the text data. In this step, the input data is the user's question text, and the output data is the extracted important keywords.

[0171] Step 4:

[0172] The server searches the database based on the extracted keywords, generates a database search query, and retrieves information about related instruction manuals and error codes. The input data is the extracted keywords, and the output data is the corresponding information in the instruction manual.

[0173] Step 5:

[0174] The server generates an answer to the query based on the retrieved information. In this step, a generative AI model is used to provide a specific solution to the error code E45. The input data is the information retrieved from the database, and the output data is the answer text to be presented to the user. For example, the generated answer might be, "Error code E45 indicates a problem with the power supply unit. Please check the power supply unit."

[0175] Step 6:

[0176] The generated answer is sent from the server to the user's device. Specifically, the answer text is displayed in the chat interface as an HTTP response. The input data is the generated answer text, and the output data is the answer displayed on the user's device.

[0177] Step 7:

[0178] The server records all user inquiries in a database. The recorded data is later aggregated and analyzed using a generative AI model. The input data is all inquiries, and the output data is statistical data and analysis results.

[0179] Step 8:

[0180] The server creates a report based on the statistical data and provides it to the manufacturer. The report includes common problems, their solutions, and improvements. The input data is the statistical data, and the output data is a document in the form of a report.

[0181] 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.

[0182] The present invention relates to a system that combines an emotion engine that recognizes user emotions, and provides a system that accepts inquiries about home appliances and device usage in a chat format, analyzes the user's question, and provides the most appropriate answer. This system is implemented in the following way.

[0183] First, a user accesses the chat interface using a terminal. The user makes an inquiry by entering a question in the text box and pressing the send button. For example, the user can enter a specific question such as, "Please tell me about the error code E23 on the XYZ refrigerator."

[0184] Next, the server receives the user's inquiry and passes the inquiry to the natural language processing means. The natural language processing means analyzes the question and extracts the corresponding device information and error code. The extracted information includes the "device type (e.g., XYZ refrigerator)" and the "error code (e.g., E23)."

[0185] The server then uses an emotion engine to analyze the emotion from the user's question. The emotion engine identifies the emotion from the user's text and returns that information to the server. For example, if the user uses the phrase "I'm very troubled," the emotion engine identifies emotions such as "confusion" and "anxiety."

[0186] The server adjusts the expression of the answer to the user based on the identified emotional information. For example, if the user is in trouble, the server generates an answer using more polite and reassuring expressions.

[0187] The server accesses the database based on the emotion information and analysis results to retrieve the corresponding instruction manual data. The instruction manual data returned from the database contains solutions to the error code E23, such as "indicates poor cooling, check the power supply, and clean the filter."

[0188] The server generates a response that takes the user's feelings into consideration based on the information it has acquired, such as "Error code E23 indicates poor cooling. Please rest assured. Check the power supply and clean the filter."

[0189] The generated answer is sent from the server to the device and notified to the user, who can then check the answer through the chat interface on the device.

[0190] Furthermore, the server records all inquiries and emotional information from users in a database. The recorded data is periodically compiled and analyzed as statistical data. Reports are created based on this statistical data and provided to manufacturers. Furthermore, by analyzing the emotional information as well, it becomes possible to improve products and review support systems based on user emotions.

[0191] For example, if many users express feelings of "confusion" or "anxiety" about a particular error code, a detailed explanation of the solution to that error code will be provided, and the relevant section of the instruction manual will be enhanced. In this way, the system of the present invention provides an environment where users can solve problems efficiently and with peace of mind, and manufacturers can use this information to improve the quality of their products based on user emotions while reducing the burden of customer support.

[0192] The processing flow will be explained below.

[0193] Step 1:

[0194] A user accesses the chat interface using a terminal, enters a question in the text box, and presses the send button. This sends the user's inquiry from the terminal to the server. For example, a specific question might be entered, such as "What can I do about error code E23 on the XYZ refrigerator?"

[0195] Step 2:

[0196] The server receives a user's inquiry and passes the inquiry to the natural language processing means, which analyzes the inquiry and extracts the corresponding device type (e.g., XYZ refrigerator) and error code (e.g., E23).

[0197] Step 3:

[0198] The server sends the query to the emotion engine based on the analyzed device type and error code information to identify the user's emotion. The emotion engine identifies emotions such as "confusion" or "anxiety" from the text and returns that information to the server.

[0199] Step 4:

[0200] The server receives the emotion information returned by the emotion engine and adjusts the wording of the response based on the user's emotion. For example, if the user is "confused," it decides to use a more polite and reassuring wording.

[0201] Step 5:

[0202] Next, the server accesses the database to retrieve the relevant instruction manual based on the parsed device information and error code. For example, the server searches for "XYZ refrigerator instruction manual" and retrieves the relevant information.

[0203] Step 6:

[0204] The server extracts a solution for the identified error code E23 from the instruction manual data it has acquired. For example, if the solution for error code E23 is described as "indicates poor cooling, check the power supply, and clean the filter," it extracts this information.

[0205] Step 7:

[0206] The server generates an optimal answer based on the extracted solution and the user's sentiment information identified earlier, for example, "Error code E23 indicates poor cooling. Please rest assured. Check the power supply and clean the filter."

[0207] Step 8:

[0208] The server sends the generated answer to the user's terminal and notifies the user, who can then check the answer in a chat interface on the terminal.

[0209] Step 9:

[0210] The server records all user inquiries and emotional information in a database, and periodically compiles and analyzes them. The server creates a report based on the statistical data and emotional information compiled and provides it to the manufacturer.

[0211] The above is the specific processing flow of the invention that combines an emotion engine that recognizes and responds to user emotions.

[0212] Example 2

[0213] 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."

[0214] Conventional inquiry systems can provide appropriate answers to user inquiries, but they are unable to respond in a way that takes the user's emotions into consideration. As a result, if the user feels anxious or confused, appropriate support cannot be provided, resulting in a decrease in user satisfaction. Furthermore, there is an insufficient mechanism for aggregating inquiry content to generate statistical data that can be used to improve product quality.

[0215] 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.

[0216] In this invention, the server includes means for receiving inquiries from users through a chat interface, natural language processing means for analyzing the received inquiries and identifying information on related devices, means for retrieving the relevant instruction manual from a database based on the identified information and generating an answer to the inquiry, emotion analysis means for analyzing the user's emotions, means for adjusting the expression of the answer based on the results of the emotion analysis, means for notifying the user of the generated answer, means for aggregating all inquiries and emotion information from users and generating statistical data, and means for creating reports based on the statistical data and providing them to manufacturers. This makes it possible to provide appropriate answers that take user emotions into consideration, thereby increasing user satisfaction and helping to improve products and support systems.

[0217] A "user" is a user who makes an inquiry through the chat interface of this system.

[0218] A "chat interface" is an interface that allows users to input and send inquiries in text format.

[0219] A "server" is a computing device that receives queries from users, analyzes them, and generates and notifies them of responses.

[0220] The "natural language processing means" is a processing means for analyzing the content of an inquiry received from a user and extracting related information.

[0221] The "emotion analysis means" is a means for identifying emotions from the user's text and analyzing that information.

[0222] A "database" is a collection of information that stores inquiry details, related equipment information, instruction manuals, etc.

[0223] An "instruction manual" is a document that describes how to use a device and how to deal with error codes.

[0224] The "answer generation means" is a means for generating an answer to be provided to the user based on the analyzed information.

[0225] The "notification means" is a means for sending the generated answer to the user and notifying him / her.

[0226] "Emotion information" is emotion data analyzed from the content of the user's inquiry.

[0227] The "aggregation means" is a means for aggregating all inquiries and emotional information from users and generating statistical data.

[0228] "Statistical data" is data that has been compiled and analyzed to reveal trends and patterns.

[0229] "Report" means a report prepared based on the generated statistical data and provided to the manufacturer.

[0230] "Manufacturer" is the company that makes the equipment you use and receives information for improvements.

[0231] This invention relates to a system that combines an emotion analysis engine that recognizes user emotions, accepts inquiries about home appliances and device usage in chat format, analyzes the user's question, and provides the most appropriate answer. This system communicates between a server, a terminal, and the user, and uses the following hardware and software:

[0232] Hardware and Software

[0233] 1. Server

[0234] Hardware: High-performance servers installed in a data center

[0235] Software: Natural Language Processing (NLP) libraries (e.g., SpaCy, NLTK), sentiment analysis engines (e.g., IBM Watson, Google Cloud Natural Language API), database management systems (e.g., MySQL, PostgreSQL)

[0236] 2. Terminal

[0237] Hardware: Your laptops, desktops, and smartphones

[0238] Software: Web browser or dedicated application

[0239] 3. Network

[0240] Internet connection: Communications infrastructure that provides high-speed and stable internet connection

[0241] System operation procedure

[0242] The system is implemented in the following way.

[0243] 1. A user accesses the chat interface using a device, types a specific question into the text box, for example, "What can I do about error code E23 on my XYZ refrigerator?", and presses the send button.

[0244] 2. The server receives the query message sent by the user and passes it to natural language processing (NLP) software, at which point the server uses NLP libraries to parse the text data and extract key information such as the device type (e.g., XYZ refrigerator) and the error code (e.g., E23).

[0245] 3. The server uses a sentiment analysis engine to identify emotions from the text provided by the user. For example, if the user types a phrase like "I'm very worried," the sentiment analysis engine will identify emotions like "confused" or "anxious," and send this information back to the server.

[0246] 4. Based on the analyzed emotion information and the results of natural language processing, the server accesses the database and retrieves the relevant instruction manual data, such as "indicates poor cooling, check the power supply, and clean the filter" that describes specific solutions.

[0247] 5. The server generates a response that takes into account the user's emotional information. For example, it generates a response such as "Error code E23 indicates poor cooling. Please be reassured. Check the power supply and clean the filter." and adjusts the expression to take the user's emotional information into account.

[0248] 6. The server sends the generated answer to the user's device, and the user confirms the answer through the chat interface.

[0249] 7. The server records all user inquiries and sentiment information in a database, periodically aggregates them to generate statistical data, and then creates reports based on the statistical data and provides them to manufacturers, allowing them to obtain useful information for improving their products and support systems.

[0250] Examples and prompts

[0251] The user types and sends the following into the chat on their device: "Can you tell me about the error code E23 on my XYZ refrigerator? I'm having a lot of trouble." The server receives this query and uses natural language processing software to extract "XYZ refrigerator" and "E23." The server then uses a sentiment analysis engine to identify the emotion "confused." Based on this information, the server retrieves "solutions to E23" from a database and generates an answer that takes the user's emotions into consideration. For example, the server might generate an answer like, "Error code E23 indicates poor cooling. Please rest assured. Check the power and clean the filter." The server then sends the generated answer to the device, where the user can view it in the chat interface. The server records all data in a database for later statistical analysis.

[0252] This system provides an environment where users can solve problems efficiently and with peace of mind, and helps manufacturers improve the quality of their products based on user sentiment while reducing the burden on customer support.

[0253] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0254] Step 1:

[0255] A user accesses the chat interface using a device. For example, he opens an application on a smartphone or PC, types "Please tell me about the error code E23 on the XYZ refrigerator" in the chat box, and presses the send button. This input generates the user's inquiry, which is sent to the server as text data.

[0256] Step 2:

[0257] The server receives a query message from a user. The received data (textual query content) is added to the processing queue. Specifically, the received data is temporarily stored and sent to the next processing step. In this case, the input is the user's query text, and the output is the query data waiting to be parsed.

[0258] Step 3:

[0259] The server passes the received query message to natural language processing software. In this process, an NLP library (e.g., SpaCy or NLTK) is used to extract "device type" and "error code" from the text data. Specifically, "XYZ refrigerator" and "E23" are extracted from the text "Please tell me about error code E23 for XYZ refrigerator." The input is the user's text data, and the output is the extracted key information (device type and error code).

[0260] Step 4:

[0261] The server uses a sentiment analysis engine to identify emotions from the user's text. For example, if the text contains the phrase "I'm very worried," the sentiment analysis engine (e.g., IBM Watson or Google Cloud Natural Language API) will identify emotions such as "confused" or "anxious." The input is the user's text data, and the output is the analyzed emotional information.

[0262] Step 5:

[0263] The server accesses the database based on the analysis results and retrieves the relevant instruction manual data. Specifically, it executes a database query to retrieve a solution such as "Error code E23 indicates poor cooling; check the power supply and clean the filter." The input is the analyzed key information (device type and error code), and the output is the relevant instruction manual data.

[0264] Step 6:

[0265] The server generates a response that takes the user's emotions into consideration. Specifically, based on the analyzed emotional information, it creates a polite response such as, "Error code E23 indicates poor cooling. Please rest assured. Check the power supply and clean the filter." The input is the acquired instruction manual data and emotional information, and the output is an optimized response.

[0266] Step 7:

[0267] The server sends the generated answer to the user's device. Specifically, this answer is delivered to the user through the chat interface. The input is the generated answer, and the output is a notification sent to the user's device.

[0268] Step 8:

[0269] The user checks the reply sent from the server through the chat interface on their device. The user reads the reply and takes specific action. In this step, the user displays the reply they received and takes action based on the information.

[0270] Step 9:

[0271] The server records all user inquiries and emotional information in a database. The input is all inquiry data and emotional information, and the output is records stored in the database. These records are periodically aggregated and analyzed as statistical data, and reports are generated.

[0272] Step 10:

[0273] The server creates a report based on the generated statistical data and provides it to the manufacturer, which then obtains information that is useful for improving the product and reviewing the support system. The input is statistical data, and the output is a report provided to the manufacturer.

[0274] (Application example 2)

[0275] 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."

[0276] Conventional inquiry response systems provide mechanical answers without considering the user's feelings, which often leaves users unable to resolve their problems with peace of mind. Furthermore, manufacturers have been limited in their ability to improve customer satisfaction because they have not reviewed their support systems or improved their products based on user feelings.

[0277] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving an inquiry from a user through a chat interface; natural language processing means for analyzing the received inquiry and identifying information about related devices; means for retrieving the relevant instruction manual from a database based on the identified information and generating a response to the inquiry; means for notifying the user of the generated response; means for analyzing the user's emotions using an emotion recognition model and adjusting the expression of the response based on the emotions; means for aggregating all inquiry contents and emotional information from users and generating statistical data; and means for creating a report based on the statistical data and providing it to the manufacturer. This makes it possible to provide an answer that takes user emotions into consideration, allowing users to solve problems with peace of mind and also enabling manufacturers to improve their products and review their support systems based on user emotional information.

[0278] "User" refers to a person who uses the system to make an inquiry.

[0279] "Inquiry" refers to a question or request entered by a user through the chat interface regarding the handling of a home appliance or device.

[0280] "Chat interface" refers to a communication method that allows users to type and submit questions in a text box.

[0281] "Analysis" refers to analyzing the content of the received inquiry and understanding the meaning and elements of the question.

[0282] "Natural language processing means" refers to technical means for analyzing the content of a user's inquiry and identifying relevant information.

[0283] A "database" refers to an information storage device for storing information such as equipment instruction manuals and solutions to error codes.

[0284] An "emotion recognition model" refers to the algorithms or software used to identify emotions from a user's text.

[0285] "Answer" refers to a solution or instruction provided to the user based on the analyzed information.

[0286] "Notification" refers to the act of sending the generated answer to the user.

[0287] "Statistical data" refers to data that has been compiled and analyzed based on inquiries and their emotional information obtained from multiple users.

[0288] "Report" means a report prepared based on statistical data and provided to a manufacturer.

[0289] "Manufacturer" refers to the company or entity that provides the product to the user.

[0290] This invention relates to a smartphone application called "Smart Shopping Assistant" that supports shopping in brick-and-mortar stores. The following describes a system that specifically realizes this "Smart Shopping Assistant."

[0291] Users access the chat interface on the application using their smartphones. They make inquiries by entering a question in the text box and pressing the send button. For example, they can enter a specific question such as, "I don't know how to use this washing machine."

[0292] The server receives inquiries from users and passes the contents of those inquiries to a natural language processing means. The natural language processing means analyzes the content of the question and extracts corresponding product information and operation instructions. This is done using Python and NLTK (Natural Language Toolkit). The analyzed information includes the type of product and operation instructions.

[0293] Next, the server uses an emotion recognition model to analyze the emotion from the user's question. For emotion recognition, the Hugging Face emotion recognition model is used. For example, if a user uses the phrase "I'm very troubled," the emotion recognition model identifies emotions such as "confusion" or "anxiety." The emotion recognition model identifies the emotion from the text and returns that information to the server.

[0294] The server adjusts the wording of the response to the user based on the identified emotional information. For example, if the user is in trouble, it generates an answer using more polite and reassuring language. Based on the emotional information and analysis results, the server accesses a database to obtain relevant product information and operation instructions. The database stores product instruction manuals and FAQs. The information returned from this database is compiled by the answer generation means in a format appropriate for the user.

[0295] For example, a response such as "This washing machine is easy to operate. First, press the power button, select a program, and then press the start button" is generated. The generated response is sent from the server to the device and notified to the user. The user can check the response through the chat interface on their smartphone.

[0296] Furthermore, the server records all user inquiries and emotional information in a database. The recorded data is periodically compiled and analyzed as statistical data. Reports are created based on this statistical data and provided to manufacturers. Furthermore, by analyzing the emotional information as well, it is possible to improve products and review support systems based on user emotions.

[0297] For example, if many users express feelings of "confusion" or "anxiety" about a particular operation, the system will provide an explanation of that operation or strengthen the relevant section of the instruction manual. In this way, the system of the present invention provides an environment where users can solve problems efficiently and with peace of mind, and manufacturers can use this information to improve the quality of their products based on user feelings while reducing the burden on customer support.

[0298] Specific examples

[0299] If a user types a question like "My vacuum cleaner isn't working, what should I do?", the server can use an emotion recognition model to identify the user's emotion as "confused" and generate a polite and reassuring response based on that. An example prompt would look like this:

[0300] plaintext

[0301] "User input: 'My vacuum cleaner isn't working, what should I do?' Identify the sentiment and generate the best answer."

[0302] The generated answer will notify the user in the form of "Don't worry. Here are some possible reasons why your vacuum cleaner isn't working: Make sure the power cord is securely connected..."

[0303] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0304] Step 1:

[0305] The user uses a terminal to access the chat interface of the smart shopping assistant and inputs a question. The input is the user's question (e.g., "I don't know how to use this washing machine.") This question is sent to the server.

[0306] Step 2:

[0307] The server passes the received question to a natural language processing tool and analyzes the inquiry. Specifically, it uses Python and NLTK to tokenize the question and extract nouns and proper nouns. The input is the user's question, and the output is information such as the type of device and how to operate it.

[0308] Step 3:

[0309] The server uses an emotion recognition model to analyze the emotion from the user's question. Specifically, it uses the Hugging Face emotion recognition model to analyze the text and identify the user's emotion (e.g., "confused" or "anxious"). The input is the user's question, and the output is the user's emotional information.

[0310] Step 4:

[0311] The server generates a response appropriate for the user based on the emotional information and the results of natural language processing. Specifically, it creates responses using expressions that take the user's emotions into consideration. For example, if the user is confused, it uses polite expressions such as "Don't worry." Emotional information and device information are input, and a polite and reassuring response is output.

[0312] Step 5:

[0313] The server accesses the database to obtain relevant product information and operating instructions. Specifically, it searches the database for product instruction manuals and FAQs and extracts the necessary information. The input is device information, and the output is the relevant instruction manual and operating instructions.

[0314] Step 6:

[0315] The server generates a final answer and notifies the user. The generated answer is sent to the user's device, where the user can confirm it through the chat interface. The generated answer is the input, and the notified answer is the output.

[0316] Step 7:

[0317] The server records all inquiry content and emotion information in a database. Specifically, it periodically aggregates the inquiry content and emotion information to generate statistical data. All inquiry content and emotion information are input, and statistical data is obtained as output.

[0318] Step 8:

[0319] The server creates a report based on the statistical data and provides it to the manufacturer. Specifically, it compiles the data analysis results into a report format so that the manufacturer can improve their product and review their support system based on user sentiment information. The input is statistical data, and the output is a report that is provided to the manufacturer.

[0320] 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.

[0321] 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.

[0322] 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.

[0323] [Second embodiment]

[0324] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0325] 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.

[0326] 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).

[0327] 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.

[0328] 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.

[0329] 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).

[0330] 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.

[0331] 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.

[0332] 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.

[0333] 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.

[0334] 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.

[0335] 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."

[0336] The present invention relates to a system that accepts inquiries about home appliances and devices in a chat format, analyzes the user's question, and provides the most appropriate answer. This system is implemented in the following way.

[0337] First, a user accesses the chat interface using a terminal. The user makes an inquiry by entering a question in the text box and pressing the send button. For example, a specific question can be entered, such as "Please tell me about the error code E23 on the XYZ refrigerator."

[0338] Next, the server receives the user's inquiry and analyzes it using natural language processing means, which extracts information such as "XYZ refrigerator" and "error code E23" from the question and identifies the relevant device information and error content.

[0339] The server accesses the database based on the identified information and searches for the corresponding instruction manual. The database returns the corresponding instruction manual, and extracts the solution to the error code E23 from it. For example, if the solution for the error code E23 is "indicates poor cooling, check the power supply, and clean the filter," an answer is generated based on this information.

[0340] The generated answer is sent from the server to the user's device, and the user receives the answer through a chat interface, specifically displaying the message "Error code E23 indicates poor cooling. Please check the power supply and clean the filter."

[0341] In addition, the server records all user inquiries in a database. The recorded data is periodically compiled and analyzed as statistical data. Reports are created based on this statistical data and provided to manufacturers. This allows manufacturers to effectively obtain feedback necessary for product improvement and the addition of new features.

[0342] For example, if many users inquire about a common error code, the solution to that error code will be improved and the relevant section of the instruction manual will be revised. In this way, the system of the present invention provides an environment in which users can solve problems efficiently, helping manufacturers improve the quality of their products while reducing the burden on customer support.

[0343] The processing flow will be explained below.

[0344] Step 1:

[0345] A user accesses the chat interface using a terminal, enters a question in the text box, and presses the send button, which sends the user's inquiry from the terminal to the server.

[0346] Step 2:

[0347] The server receives an inquiry from a user and passes the inquiry content to the natural language processing means, which analyzes the received inquiry content and extracts the corresponding device type and error code.

[0348] Step 3:

[0349] The natural language processing means identifies the "device type (e.g., XYZ refrigerator)" and "error code (e.g., E23)" as analysis results and returns them to the server. The server then accesses the database based on this information.

[0350] Step 4:

[0351] The server retrieves the instruction manual data for the target device from the database. For example, it searches for "XYZ refrigerator instruction manual" and retrieves related information.

[0352] Step 5:

[0353] The server extracts the solution corresponding to the identified error code (e.g., E23) from the instruction manual data acquired. For example, if the solution to error code E23 is "indicates poor cooling, check the power supply, and clean the filter," this information is extracted.

[0354] Step 6:

[0355] Based on the information extracted by the server, the optimal response to the inquiry is generated, for example, "Error code E23 indicates poor cooling. Check the power supply and clean the filter."

[0356] Step 7:

[0357] The server sends the generated answer to the terminal and notifies the user, who can then check the answer in the chat interface again via the terminal.

[0358] Step 8:

[0359] The server records all user inquiries in a database and periodically compiles and analyzes them. It creates reports based on the compiled statistical data and provides them to manufacturers. The manufacturers use the reports to improve their products and develop new features.

[0360] The above is a specific processing flow of the system of the present invention.

[0361] Example 1

[0362] 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."

[0363] Today's consumers increasingly use a wide variety of home appliances and devices, and want to quickly resolve any problems or errors they encounter with these products. However, referring to instruction manuals one by one is time-consuming, and finding the appropriate solution can be difficult, especially for specialized issues like error codes. Manufacturers also need to efficiently process user inquiries and collect data to help improve and enhance their products. Current systems do not adequately meet these needs, causing inconvenience to both users and manufacturers.

[0364] 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.

[0365] In this invention, the server includes means for receiving inquiries from users via a chat interface, natural language processing means for analyzing the received inquiries and identifying information on related devices, and means for retrieving the relevant instruction manual from a database based on the identified information and generating an answer to the inquiry. This allows users to quickly and accurately find solutions to their problems, and enables manufacturers to utilize the question history to improve product quality and streamline customer support.

[0366] A "user" is an individual or corporation that uses the system to make inquiries about home appliances and devices.

[0367] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0368] A "chat interface" is a text-based interaction tool that allows users to enter questions and interact with the system.

[0369] A "server" is a computer system that receives queries from users, analyzes them, and generates and sends appropriate responses.

[0370] "Natural language processing means" is a technology for analyzing received text data and understanding the content of the user's question.

[0371] A "database" is a system for centrally managing data such as instruction manuals and past inquiry history for home appliances and devices.

[0372] An "instruction manual" is a document that describes how to use a home appliance or device, the meaning of error codes, troubleshooting, etc.

[0373] A "means for generating an answer" is a means for creating an appropriate response to a user's question.

[0374] The "notification means" is a means for transmitting the generated answer to the user's terminal.

[0375] "Statistical data" refers to data analyzed based on the collected inquiries from users.

[0376] "Report" means a report prepared based on statistical data and provided to a manufacturer.

[0377] "Manufacturers" are companies that make appliances and devices.

[0378] The present invention is a system that allows users to make inquiries about home appliances and devices, and provides quick and accurate answers through a chat interface. This system operates by combining terminals, servers, databases, and natural language processing technology.

[0379] First, a user accesses the chat interface using a device (e.g., computer, smartphone, or tablet). Here, the user enters a question in the text box and clicks the send button. For example, the user might enter, "Can you tell me about error code E23 on my XYZ refrigerator?"

[0380] The server receives the query sent by the user and analyzes it using natural language processing technology. Specific software used is Google Cloud Natural Language API and IBM Watson Natural Language Understanding. Through this analysis, the server extracts important keywords from the text (e.g., "XYZ refrigerator" or "error code E23").

[0381] The server then queries a database based on these keywords to retrieve the relevant instruction manual. The database uses MySQL or MongoDB, and searches the instruction manual for a solution to the corresponding error code. For example, if the solution to error code E23 is "indicates poor cooling, check the power supply, and clean the filter," the server generates an answer based on this information.

[0382] The generated response is sent from the server to the user's device and displayed in the chat interface, specifically saying, "Error code E23 indicates poor cooling. Please check the power supply and clean the filter."

[0383] In addition, the server records all user inquiries in a database. This data is periodically aggregated and analyzed using statistical analysis software in Python or R. A report is generated based on the analysis results and provided to the manufacturer. This allows the manufacturer to obtain feedback needed to improve the quality of their products and add new features.

[0384] Examples of specific prompts are:

[0385] Example user input:

[0386] "What can I do about error code E23 on the XYZ refrigerator?"

[0387] Example server response:

[0388] "Error code E23 indicates poor cooling. Check the power supply and clean the filters."

[0389] Example prompt for a generative AI model:

[0390] "A user is asking, 'What can I do about error code E23 on my XYZ refrigerator?' Generate the best answer possible. The answer should include specific solutions (e.g., check the power supply and clean the filter)."

[0391] In this way, the system of the present invention provides an environment in which users can efficiently solve problems, and helps manufacturers improve the quality of their products while reducing the burden of customer support.

[0392] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0393] Step 1:

[0394] The user inputs a question into the terminal and sends it.

[0395] Specifically, the user types a question into the text box of the chat interface, such as "Can you tell me about error code E23 on the XYZ refrigerator?", and then presses the send button.

[0396] Input: User question (e.g. "What can I do about error code E23 on my XYZ refrigerator?")

[0397] Output: Submitted question data

[0398] Step 2:

[0399] The server receives the query.

[0400] The server receives the data sent by the user and adds it to a processing queue, at which point the received data is stored in text format.

[0401] Input: Submitted question data

[0402] Output: Question data added to the processing queue

[0403] Step 3:

[0404] The server analyzes the query using natural language processing (NLP) techniques.

[0405] Specifically, the server analyzes the input text using Google Cloud Natural Language API, IBM Watson Natural Language Understanding, etc. The server then performs entity recognition and extracts keywords such as "XYZ refrigerator" and "error code E23."

[0406] Input: Question data retrieved from the processing queue

[0407] Output: Analysis results (keywords: "XYZ refrigerator", "error code E23")

[0408] Step 4:

[0409] The server searches the database based on the keywords.

[0410] The server uses the extracted keywords to query a database, for example, using MySQL or MongoDB to search for the corresponding instruction manual and extract the relevant information.

[0411] Input: Keywords from the analysis results ("XYZ refrigerator", "Error code E23")

[0412] Output: Data from the relevant instruction manual

[0413] Step 5:

[0414] The server retrieves the relevant solutions and generates an answer.

[0415] The server identifies a solution to the error code E23 based on the contents of the instruction manual retrieved from the database. For example, it generates a response such as, "Error code E23 indicates poor cooling. Check the power supply and clean the filter."

[0416] Input: Instruction manual data

[0417] Output: Generated response (e.g. "Error code E23 indicates poor cooling. Check the power supply and clean the filters.")

[0418] Step 6:

[0419] The server sends the generated answer to the user's terminal.

[0420] The server sends the generated reply to the user's terminal and displays it on the chat interface.

[0421] Input: Generated answer

[0422] Output: Answer displayed on the user's terminal

[0423] Step 7:

[0424] The server records the inquiry in a database.

[0425] The server stores all queries in a database, making them available for future analysis and reference.

[0426] Input: Processed question and answer data

[0427] Output: Records stored in the database

[0428] Step 8:

[0429] The server aggregates and analyzes the data and creates reports for manufacturers.

[0430] The server periodically aggregates the recorded data and analyzes it using statistical analysis software such as Python or R. Based on the results of this analysis, a report is created and provided to the manufacturer.

[0431] Input: Query history stored in the database

[0432] Output: Report for manufacturer

[0433] (Application example 1)

[0434] 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."

[0435] There is a problem in that it is difficult to quickly provide appropriate solutions to abnormalities and problems that occur during the operation of machines and robots used in factories. In particular, if on-site workers and engineers cannot find a solution immediately, production efficiency may decrease, resulting in wasted time and costs.

[0436] 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.

[0437] In this invention, the server includes: means for receiving inquiries from users through a chat interface; natural language processing means for analyzing the received inquiries and identifying information on related equipment; means for retrieving the relevant instruction manual from a database based on the identified information and generating an answer to the inquiry; means for notifying the user of the generated answer; means for aggregating all inquiries from users and generating statistical data; means for creating a report based on the statistical data and providing it to the manufacturer; and means for receiving inquiries regarding abnormalities or problems with machines in the manufacturing process and using a generative AI model to provide appropriate maintenance procedures. This enables users to efficiently troubleshoot and maintain machines and robots used in factories.

[0438] A "chat interface" is an interactive interface for users to submit text-based inquiries.

[0439] "Natural language processing means" is a technology that analyzes text data from users and understands and processes human language.

[0440] A "database" is a system for organizing, storing, and searching specific information.

[0441] A "query answer generator" is a mechanism that generates an answer to a user's question based on information retrieved from a database.

[0442] A "generative AI model" is a model that uses artificial intelligence technology to generate and analyze data and provide appropriate answers and responses.

[0443] "Statistical data" refers to data obtained as a result of compiling and analyzing inquiries from users.

[0444] "Report" means a summary of information based on statistical data and provided to a manufacturer.

[0445] "Machine abnormalities and problems" refers to conditions or problems in which machines or robots used in the manufacturing process do not function properly.

[0446] "Maintenance procedures" are specific operating methods for checking the correct operation of machines and robots and making any necessary adjustments or repairs.

[0447] "Manufacturer" means a company or organization that designs and produces equipment or systems involved in the manufacturing process.

[0448] The present invention is a system that accepts inquiries about the operation and maintenance of machines and robots in manufacturing processes in a chat format, analyzes the user's question, and provides the most appropriate answer. This system is implemented in the following way.

[0449] Users access a chat interface installed in the factory using a device such as a smartphone or tablet. Through this chat interface, users make inquiries by entering a question in a text box and pressing the send button. For example, users can enter specific questions such as, "Please tell me about the XYZ robot's error code E45" or "My robot is stuck and won't move. What should I do?"

[0450] Next, the server receives the user's inquiry and analyzes it using natural language processing means, which extracts information such as "XYZ robot" and "error code E45" from the question and identifies the relevant device information and error content.

[0451] Based on the identified information, the server searches the database for the corresponding instruction manual. The database returns relevant information, and from that information, it extracts solutions to error code E45 and robot maintenance procedures. For example, detailed information including steps such as "check the power supply unit" is provided as a solution to error code E45.

[0452] The generated answer is sent from the server to the user's device, and the user receives the answer through a chat interface, specifically displaying the message "Error code E45 indicates a problem with the power supply unit. Please check the power supply unit."

[0453] In addition, the server records all user inquiries in a database. The recorded data is periodically aggregated and analyzed as statistical data using a generative AI model. A report is created based on this statistical data and provided to the manufacturer. This allows the manufacturer to effectively obtain the feedback needed to improve their products and add new features.

[0454] For example:

[0455] Example prompt sentence:

[0456] "Please tell me about the XYZ robot error code E45."

[0457] "My robot is stuck and won't move, what should I do?"

[0458] "Please tell me the maintenance procedure for the picking robot."

[0459] Hardware used: smartphone, tablet

[0460] Software used: OpenAI API, Flask

[0461] This allows factory workers and engineers to troubleshoot robots and machinery quickly and efficiently, significantly improving production efficiency.

[0462] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0463] Step 1:

[0464] A user accesses the chat interface using a device (smartphone or tablet) and enters a question. For example, they might enter, "Please tell me about the XYZ robot error code E45." The input data is in text format, and once the input is complete, it is sent to the server by pressing the send button.

[0465] Step 2:

[0466] The server receives queries from users. The received queries are saved as text data. Specifically, the server receives an HTTP request and extracts its payload (the query content). The input data is the user's question text, which is passed to the server's analysis module.

[0467] Step 3:

[0468] The server analyzes the query using natural language processing. Specifically, an NLP (Natural Language Processing) model extracts information such as "XYZ robot" or "error code E45" from the text data. In this step, the input data is the user's question text, and the output data is the extracted important keywords.

[0469] Step 4:

[0470] The server searches the database based on the extracted keywords, generates a database search query, and retrieves information about related instruction manuals and error codes. The input data is the extracted keywords, and the output data is the corresponding information in the instruction manual.

[0471] Step 5:

[0472] The server generates an answer to the query based on the retrieved information. In this step, a generative AI model is used to provide a specific solution to the error code E45. The input data is the information retrieved from the database, and the output data is the answer text to be presented to the user. For example, the generated answer might be, "Error code E45 indicates a problem with the power supply unit. Please check the power supply unit."

[0473] Step 6:

[0474] The generated answer is sent from the server to the user's device. Specifically, the answer text is displayed in the chat interface as an HTTP response. The input data is the generated answer text, and the output data is the answer displayed on the user's device.

[0475] Step 7:

[0476] The server records all user inquiries in a database. The recorded data is later aggregated and analyzed using a generative AI model. The input data is all inquiries, and the output data is statistical data and analysis results.

[0477] Step 8:

[0478] The server creates a report based on the statistical data and provides it to the manufacturer. The report includes common problems, their solutions, and improvements. The input data is the statistical data, and the output data is a document in the form of a report.

[0479] 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.

[0480] The present invention relates to a system that combines an emotion engine that recognizes user emotions, and provides a system that accepts inquiries about home appliances and device usage in a chat format, analyzes the user's question, and provides the most appropriate answer. This system is implemented in the following way.

[0481] First, a user accesses the chat interface using a terminal. The user makes an inquiry by entering a question in the text box and pressing the send button. For example, the user can enter a specific question such as, "Please tell me about the error code E23 on the XYZ refrigerator."

[0482] Next, the server receives the user's inquiry and passes the inquiry to the natural language processing means. The natural language processing means analyzes the question and extracts the corresponding device information and error code. The extracted information includes the "device type (e.g., XYZ refrigerator)" and the "error code (e.g., E23)."

[0483] The server then uses an emotion engine to analyze the emotion from the user's question. The emotion engine identifies the emotion from the user's text and returns that information to the server. For example, if the user uses the phrase "I'm very troubled," the emotion engine identifies emotions such as "confusion" and "anxiety."

[0484] The server adjusts the expression of the answer to the user based on the identified emotional information. For example, if the user is in trouble, the server generates an answer using more polite and reassuring expressions.

[0485] The server accesses the database based on the emotion information and analysis results to retrieve the corresponding instruction manual data. The instruction manual data returned from the database contains solutions to the error code E23, such as "indicates poor cooling, check the power supply, and clean the filter."

[0486] The server generates a response that takes the user's feelings into consideration based on the information it has acquired, such as "Error code E23 indicates poor cooling. Please rest assured. Check the power supply and clean the filter."

[0487] The generated answer is sent from the server to the device and notified to the user, who can then check the answer through the chat interface on the device.

[0488] Furthermore, the server records all inquiries and emotional information from users in a database. The recorded data is periodically compiled and analyzed as statistical data. Reports are created based on this statistical data and provided to manufacturers. Furthermore, by analyzing the emotional information as well, it becomes possible to improve products and review support systems based on user emotions.

[0489] For example, if many users express feelings of "confusion" or "anxiety" about a particular error code, a detailed explanation of the solution to that error code will be provided, and the relevant section of the instruction manual will be enhanced. In this way, the system of the present invention provides an environment where users can solve problems efficiently and with peace of mind, and manufacturers can use this information to improve the quality of their products based on user emotions while reducing the burden of customer support.

[0490] The processing flow will be explained below.

[0491] Step 1:

[0492] A user accesses the chat interface using a terminal, enters a question in the text box, and presses the send button. This sends the user's inquiry from the terminal to the server. For example, a specific question might be entered, such as "What can I do about error code E23 on the XYZ refrigerator?"

[0493] Step 2:

[0494] The server receives a user's inquiry and passes the inquiry to the natural language processing means, which analyzes the inquiry and extracts the corresponding device type (e.g., XYZ refrigerator) and error code (e.g., E23).

[0495] Step 3:

[0496] The server sends the query to the emotion engine based on the analyzed device type and error code information to identify the user's emotion. The emotion engine identifies emotions such as "confusion" or "anxiety" from the text and returns that information to the server.

[0497] Step 4:

[0498] The server receives the emotion information returned by the emotion engine and adjusts the wording of the response based on the user's emotion. For example, if the user is "confused," it decides to use a more polite and reassuring wording.

[0499] Step 5:

[0500] Next, the server accesses the database to retrieve the relevant instruction manual based on the parsed device information and error code. For example, the server searches for "XYZ refrigerator instruction manual" and retrieves the relevant information.

[0501] Step 6:

[0502] The server extracts a solution for the identified error code E23 from the instruction manual data it has acquired. For example, if the solution for error code E23 is described as "indicates poor cooling, check the power supply, and clean the filter," it extracts this information.

[0503] Step 7:

[0504] The server generates an optimal answer based on the extracted solution and the user's sentiment information identified earlier, for example, "Error code E23 indicates poor cooling. Please rest assured. Check the power supply and clean the filter."

[0505] Step 8:

[0506] The server sends the generated answer to the user's terminal and notifies the user, who can then check the answer in a chat interface on the terminal.

[0507] Step 9:

[0508] The server records all user inquiries and emotional information in a database, and periodically compiles and analyzes them. The server creates a report based on the statistical data and emotional information compiled and provides it to the manufacturer.

[0509] The above is the specific processing flow of the invention that combines an emotion engine that recognizes and responds to user emotions.

[0510] Example 2

[0511] 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."

[0512] Conventional inquiry systems can provide appropriate answers to user inquiries, but they are unable to respond in a way that takes the user's emotions into consideration. As a result, if the user feels anxious or confused, appropriate support cannot be provided, resulting in a decrease in user satisfaction. Furthermore, there is an insufficient mechanism for aggregating inquiry content to generate statistical data that can be used to improve product quality.

[0513] 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.

[0514] In this invention, the server includes means for receiving inquiries from users through a chat interface, natural language processing means for analyzing the received inquiries and identifying information on related devices, means for retrieving the relevant instruction manual from a database based on the identified information and generating an answer to the inquiry, emotion analysis means for analyzing the user's emotions, means for adjusting the expression of the answer based on the results of the emotion analysis, means for notifying the user of the generated answer, means for aggregating all inquiries and emotion information from users and generating statistical data, and means for creating reports based on the statistical data and providing them to manufacturers. This makes it possible to provide appropriate answers that take user emotions into consideration, thereby increasing user satisfaction and helping to improve products and support systems.

[0515] A "user" is a user who makes an inquiry through the chat interface of this system.

[0516] A "chat interface" is an interface that allows users to input and send inquiries in text format.

[0517] A "server" is a computing device that receives queries from users, analyzes them, and generates and notifies them of responses.

[0518] The "natural language processing means" is a processing means for analyzing the content of an inquiry received from a user and extracting related information.

[0519] The "emotion analysis means" is a means for identifying emotions from the user's text and analyzing that information.

[0520] A "database" is a collection of information that stores inquiry details, related equipment information, instruction manuals, etc.

[0521] An "instruction manual" is a document that describes how to use a device and how to deal with error codes.

[0522] The "answer generation means" is a means for generating an answer to be provided to the user based on the analyzed information.

[0523] The "notification means" is a means for sending the generated answer to the user and notifying him / her.

[0524] "Emotion information" is emotion data analyzed from the content of the user's inquiry.

[0525] The "aggregation means" is a means for aggregating all inquiries and emotional information from users and generating statistical data.

[0526] "Statistical data" is data that has been compiled and analyzed to reveal trends and patterns.

[0527] "Report" means a report prepared based on the generated statistical data and provided to the manufacturer.

[0528] "Manufacturer" is the company that makes the equipment you use and receives information for improvements.

[0529] This invention relates to a system that combines an emotion analysis engine that recognizes user emotions, accepts inquiries about home appliances and device usage in chat format, analyzes the user's question, and provides the most appropriate answer. This system communicates between a server, a terminal, and the user, and uses the following hardware and software:

[0530] Hardware and Software

[0531] 1. Server

[0532] Hardware: High-performance servers installed in a data center

[0533] Software: Natural Language Processing (NLP) libraries (e.g., SpaCy, NLTK), sentiment analysis engines (e.g., IBM Watson, Google Cloud Natural Language API), database management systems (e.g., MySQL, PostgreSQL)

[0534] 2. Terminal

[0535] Hardware: Your laptops, desktops, and smartphones

[0536] Software: Web browser or dedicated application

[0537] 3. Network

[0538] Internet connection: Communications infrastructure that provides high-speed and stable internet connection

[0539] System operation procedure

[0540] The system is implemented in the following way.

[0541] 1. A user accesses the chat interface using a device, types a specific question into the text box, for example, "What can I do about error code E23 on my XYZ refrigerator?", and presses the send button.

[0542] 2. The server receives the query message sent by the user and passes it to natural language processing (NLP) software, at which point the server uses NLP libraries to parse the text data and extract key information such as the device type (e.g., XYZ refrigerator) and the error code (e.g., E23).

[0543] 3. The server uses a sentiment analysis engine to identify emotions from the text provided by the user. For example, if the user types a phrase like "I'm very worried," the sentiment analysis engine will identify emotions like "confused" or "anxious," and send this information back to the server.

[0544] 4. Based on the analyzed emotion information and the results of natural language processing, the server accesses the database and retrieves the relevant instruction manual data, such as "indicates poor cooling, check the power supply, and clean the filter" that describes specific solutions.

[0545] 5. The server generates a response that takes into account the user's emotional information. For example, it generates a response such as "Error code E23 indicates poor cooling. Please be reassured. Check the power supply and clean the filter." and adjusts the expression to take the user's emotional information into account.

[0546] 6. The server sends the generated answer to the user's device, and the user confirms the answer through the chat interface.

[0547] 7. The server records all user inquiries and sentiment information in a database, periodically aggregates them to generate statistical data, and then creates reports based on the statistical data and provides them to manufacturers, allowing them to obtain useful information for improving their products and support systems.

[0548] Examples and prompts

[0549] The user types and sends the following into the chat on their device: "Can you tell me about the error code E23 on my XYZ refrigerator? I'm having a lot of trouble." The server receives this query and uses natural language processing software to extract "XYZ refrigerator" and "E23." The server then uses a sentiment analysis engine to identify the emotion "confused." Based on this information, the server retrieves "solutions to E23" from a database and generates an answer that takes the user's emotions into consideration. For example, the server might generate an answer like, "Error code E23 indicates poor cooling. Please rest assured. Check the power and clean the filter." The server then sends the generated answer to the device, where the user can view it in the chat interface. The server records all data in a database for later statistical analysis.

[0550] This system provides an environment where users can solve problems efficiently and with peace of mind, and helps manufacturers improve the quality of their products based on user sentiment while reducing the burden on customer support.

[0551] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0552] Step 1:

[0553] A user accesses the chat interface using a device. For example, he opens an application on a smartphone or PC, types "Please tell me about the error code E23 on the XYZ refrigerator" in the chat box, and presses the send button. This input generates the user's inquiry, which is sent to the server as text data.

[0554] Step 2:

[0555] The server receives a query message from a user. The received data (textual query content) is added to the processing queue. Specifically, the received data is temporarily stored and sent to the next processing step. In this case, the input is the user's query text, and the output is the query data waiting to be parsed.

[0556] Step 3:

[0557] The server passes the received query message to natural language processing software. In this process, an NLP library (e.g., SpaCy or NLTK) is used to extract "device type" and "error code" from the text data. Specifically, "XYZ refrigerator" and "E23" are extracted from the text "Please tell me about error code E23 for XYZ refrigerator." The input is the user's text data, and the output is the extracted key information (device type and error code).

[0558] Step 4:

[0559] The server uses a sentiment analysis engine to identify emotions from the user's text. For example, if the text contains the phrase "I'm very worried," the sentiment analysis engine (e.g., IBM Watson or Google Cloud Natural Language API) will identify emotions such as "confused" or "anxious." The input is the user's text data, and the output is the analyzed emotional information.

[0560] Step 5:

[0561] The server accesses the database based on the analysis results and retrieves the relevant instruction manual data. Specifically, it executes a database query to retrieve a solution such as "Error code E23 indicates poor cooling; check the power supply and clean the filter." The input is the analyzed key information (device type and error code), and the output is the relevant instruction manual data.

[0562] Step 6:

[0563] The server generates a response that takes the user's emotions into consideration. Specifically, based on the analyzed emotional information, it creates a polite response such as, "Error code E23 indicates poor cooling. Please rest assured. Check the power supply and clean the filter." The input is the acquired instruction manual data and emotional information, and the output is an optimized response.

[0564] Step 7:

[0565] The server sends the generated answer to the user's device. Specifically, this answer is delivered to the user through the chat interface. The input is the generated answer, and the output is a notification sent to the user's device.

[0566] Step 8:

[0567] The user checks the reply sent from the server through the chat interface on their device. The user reads the reply and takes specific action. In this step, the user displays the reply they received and takes action based on the information.

[0568] Step 9:

[0569] The server records all user inquiries and emotional information in a database. The input is all inquiry data and emotional information, and the output is records stored in the database. These records are periodically aggregated and analyzed as statistical data, and reports are generated.

[0570] Step 10:

[0571] The server creates a report based on the generated statistical data and provides it to the manufacturer, which then obtains information that is useful for improving the product and reviewing the support system. The input is statistical data, and the output is a report provided to the manufacturer.

[0572] (Application example 2)

[0573] 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."

[0574] Conventional inquiry response systems provide mechanical answers without considering the user's feelings, which often leaves users unable to resolve their problems with peace of mind. Furthermore, manufacturers have been limited in their ability to improve customer satisfaction because they have not reviewed their support systems or improved their products based on user feelings.

[0575] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving an inquiry from a user through a chat interface; natural language processing means for analyzing the received inquiry and identifying information about related devices; means for retrieving the relevant instruction manual from a database based on the identified information and generating a response to the inquiry; means for notifying the user of the generated response; means for analyzing the user's emotions using an emotion recognition model and adjusting the expression of the response based on the emotions; means for aggregating all inquiry contents and emotional information from users and generating statistical data; and means for creating a report based on the statistical data and providing it to the manufacturer. This makes it possible to provide an answer that takes user emotions into consideration, allowing users to solve problems with peace of mind and also enabling manufacturers to improve their products and review their support systems based on user emotional information.

[0576] "User" refers to a person who uses the system to make an inquiry.

[0577] "Inquiry" refers to a question or request entered by a user through the chat interface regarding the handling of a home appliance or device.

[0578] "Chat interface" refers to a communication method that allows users to type and submit questions in a text box.

[0579] "Analysis" refers to analyzing the content of the received inquiry and understanding the meaning and elements of the question.

[0580] "Natural language processing means" refers to technical means for analyzing the content of a user's inquiry and identifying relevant information.

[0581] A "database" refers to an information storage device for storing information such as equipment instruction manuals and solutions to error codes.

[0582] An "emotion recognition model" refers to the algorithms or software used to identify emotions from a user's text.

[0583] "Answer" refers to a solution or instruction provided to the user based on the analyzed information.

[0584] "Notification" refers to the act of sending the generated answer to the user.

[0585] "Statistical data" refers to data that has been compiled and analyzed based on inquiries and their emotional information obtained from multiple users.

[0586] "Report" means a report prepared based on statistical data and provided to a manufacturer.

[0587] "Manufacturer" refers to the company or entity that provides the product to the user.

[0588] This invention relates to a smartphone application called "Smart Shopping Assistant" that supports shopping in brick-and-mortar stores. The following describes a system that specifically realizes this "Smart Shopping Assistant."

[0589] Users access the chat interface on the application using their smartphones. They make inquiries by entering a question in the text box and pressing the send button. For example, they can enter a specific question such as, "I don't know how to use this washing machine."

[0590] The server receives inquiries from users and passes the contents of those inquiries to a natural language processing means. The natural language processing means analyzes the content of the question and extracts corresponding product information and operation instructions. This is done using Python and NLTK (Natural Language Toolkit). The analyzed information includes the type of product and operation instructions.

[0591] Next, the server uses an emotion recognition model to analyze the emotion from the user's question. For emotion recognition, the Hugging Face emotion recognition model is used. For example, if a user uses the phrase "I'm very troubled," the emotion recognition model identifies emotions such as "confusion" or "anxiety." The emotion recognition model identifies the emotion from the text and returns that information to the server.

[0592] The server adjusts the wording of the response to the user based on the identified emotional information. For example, if the user is in trouble, it generates an answer using more polite and reassuring language. Based on the emotional information and analysis results, the server accesses a database to obtain relevant product information and operation instructions. The database stores product instruction manuals and FAQs. The information returned from this database is compiled by the answer generation means in a format appropriate for the user.

[0593] For example, a response such as "This washing machine is easy to operate. First, press the power button, select a program, and then press the start button" is generated. The generated response is sent from the server to the device and notified to the user. The user can check the response through the chat interface on their smartphone.

[0594] Furthermore, the server records all user inquiries and emotional information in a database. The recorded data is periodically compiled and analyzed as statistical data. Reports are created based on this statistical data and provided to manufacturers. Furthermore, by analyzing the emotional information as well, it is possible to improve products and review support systems based on user emotions.

[0595] For example, if many users express feelings of "confusion" or "anxiety" about a particular operation, the system will provide an explanation of that operation or strengthen the relevant section of the instruction manual. In this way, the system of the present invention provides an environment where users can solve problems efficiently and with peace of mind, and manufacturers can use this information to improve the quality of their products based on user feelings while reducing the burden on customer support.

[0596] Specific examples

[0597] If a user types a question like "My vacuum cleaner isn't working, what should I do?", the server can use an emotion recognition model to identify the user's emotion as "confused" and generate a polite and reassuring response based on that. An example prompt would look like this:

[0598] plaintext

[0599] "User input: 'My vacuum cleaner isn't working, what should I do?' Identify the sentiment and generate the best answer."

[0600] The generated answer will notify the user in the form of "Don't worry. Here are some possible reasons why your vacuum cleaner isn't working: Make sure the power cord is securely connected..."

[0601] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0602] Step 1:

[0603] The user uses a terminal to access the chat interface of the smart shopping assistant and inputs a question. The input is the user's question (e.g., "I don't know how to use this washing machine.") This question is sent to the server.

[0604] Step 2:

[0605] The server passes the received question to a natural language processing tool and analyzes the inquiry. Specifically, it uses Python and NLTK to tokenize the question and extract nouns and proper nouns. The input is the user's question, and the output is information such as the type of device and how to operate it.

[0606] Step 3:

[0607] The server uses an emotion recognition model to analyze the emotion from the user's question. Specifically, it uses the Hugging Face emotion recognition model to analyze the text and identify the user's emotion (e.g., "confused" or "anxious"). The input is the user's question, and the output is the user's emotional information.

[0608] Step 4:

[0609] The server generates a response appropriate for the user based on the emotional information and the results of natural language processing. Specifically, it creates responses using expressions that take the user's emotions into consideration. For example, if the user is confused, it uses polite expressions such as "Don't worry." Emotional information and device information are input, and a polite and reassuring response is output.

[0610] Step 5:

[0611] The server accesses the database to obtain relevant product information and operating instructions. Specifically, it searches the database for product instruction manuals and FAQs and extracts the necessary information. The input is device information, and the output is the relevant instruction manual and operating instructions.

[0612] Step 6:

[0613] The server generates a final answer and notifies the user. The generated answer is sent to the user's device, where the user can confirm it through the chat interface. The generated answer is the input, and the notified answer is the output.

[0614] Step 7:

[0615] The server records all inquiry content and emotion information in a database. Specifically, it periodically aggregates the inquiry content and emotion information to generate statistical data. All inquiry content and emotion information are input, and statistical data is obtained as output.

[0616] Step 8:

[0617] The server creates a report based on the statistical data and provides it to the manufacturer. Specifically, it compiles the data analysis results into a report format so that the manufacturer can improve their product and review their support system based on user sentiment information. The input is statistical data, and the output is a report that is provided to the manufacturer.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] [Third embodiment]

[0622] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0623] 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.

[0624] 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).

[0625] 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.

[0626] 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.

[0627] 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).

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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."

[0634] The present invention relates to a system that accepts inquiries about home appliances and devices in a chat format, analyzes the user's question, and provides the most appropriate answer. This system is implemented in the following way.

[0635] First, a user accesses the chat interface using a terminal. The user makes an inquiry by entering a question in the text box and pressing the send button. For example, a specific question can be entered, such as "Please tell me about the error code E23 on the XYZ refrigerator."

[0636] Next, the server receives the user's inquiry and analyzes it using natural language processing means, which extracts information such as "XYZ refrigerator" and "error code E23" from the question and identifies the relevant device information and error content.

[0637] The server accesses the database based on the identified information and searches for the corresponding instruction manual. The database returns the corresponding instruction manual, and extracts the solution to the error code E23 from it. For example, if the solution for the error code E23 is "indicates poor cooling, check the power supply, and clean the filter," an answer is generated based on this information.

[0638] The generated answer is sent from the server to the user's device, and the user receives the answer through a chat interface, specifically displaying the message "Error code E23 indicates poor cooling. Please check the power supply and clean the filter."

[0639] In addition, the server records all user inquiries in a database. The recorded data is periodically compiled and analyzed as statistical data. Reports are created based on this statistical data and provided to manufacturers. This allows manufacturers to effectively obtain feedback necessary for product improvement and the addition of new features.

[0640] For example, if many users inquire about a common error code, the solution to that error code will be improved and the relevant section of the instruction manual will be revised. In this way, the system of the present invention provides an environment in which users can solve problems efficiently, helping manufacturers improve the quality of their products while reducing the burden on customer support.

[0641] The processing flow will be explained below.

[0642] Step 1:

[0643] A user accesses the chat interface using a terminal, enters a question in the text box, and presses the send button, which sends the user's inquiry from the terminal to the server.

[0644] Step 2:

[0645] The server receives an inquiry from a user and passes the inquiry content to the natural language processing means, which analyzes the received inquiry content and extracts the corresponding device type and error code.

[0646] Step 3:

[0647] The natural language processing means identifies the "device type (e.g., XYZ refrigerator)" and "error code (e.g., E23)" as analysis results and returns them to the server. The server then accesses the database based on this information.

[0648] Step 4:

[0649] The server retrieves the instruction manual data for the target device from the database. For example, it searches for "XYZ refrigerator instruction manual" and retrieves related information.

[0650] Step 5:

[0651] The server extracts the solution corresponding to the identified error code (e.g., E23) from the instruction manual data acquired. For example, if the solution to error code E23 is "indicates poor cooling, check the power supply, and clean the filter," this information is extracted.

[0652] Step 6:

[0653] Based on the information extracted by the server, the optimal response to the inquiry is generated, for example, "Error code E23 indicates poor cooling. Check the power supply and clean the filter."

[0654] Step 7:

[0655] The server sends the generated answer to the terminal and notifies the user, who can then check the answer in the chat interface again via the terminal.

[0656] Step 8:

[0657] The server records all user inquiries in a database and periodically compiles and analyzes them. It creates reports based on the compiled statistical data and provides them to manufacturers. The manufacturers use the reports to improve their products and develop new features.

[0658] The above is a specific processing flow of the system of the present invention.

[0659] Example 1

[0660] 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."

[0661] Today's consumers increasingly use a wide variety of home appliances and devices, and want to quickly resolve any problems or errors they encounter with these products. However, referring to instruction manuals one by one is time-consuming, and finding the appropriate solution can be difficult, especially for specialized issues like error codes. Manufacturers also need to efficiently process user inquiries and collect data to help improve and enhance their products. Current systems do not adequately meet these needs, causing inconvenience to both users and manufacturers.

[0662] 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.

[0663] In this invention, the server includes means for receiving inquiries from users via a chat interface, natural language processing means for analyzing the received inquiries and identifying information on related devices, and means for retrieving the relevant instruction manual from a database based on the identified information and generating an answer to the inquiry. This allows users to quickly and accurately find solutions to their problems, and enables manufacturers to utilize the question history to improve product quality and streamline customer support.

[0664] A "user" is an individual or corporation that uses the system to make inquiries about home appliances and devices.

[0665] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0666] A "chat interface" is a text-based interaction tool that allows users to enter questions and interact with the system.

[0667] A "server" is a computer system that receives queries from users, analyzes them, and generates and sends appropriate responses.

[0668] "Natural language processing means" is a technology for analyzing received text data and understanding the content of the user's question.

[0669] A "database" is a system for centrally managing data such as instruction manuals and past inquiry history for home appliances and devices.

[0670] An "instruction manual" is a document that describes how to use a home appliance or device, the meaning of error codes, troubleshooting, etc.

[0671] A "means for generating an answer" is a means for creating an appropriate response to a user's question.

[0672] The "notification means" is a means for transmitting the generated answer to the user's terminal.

[0673] "Statistical data" refers to data analyzed based on the collected inquiries from users.

[0674] "Report" means a report prepared based on statistical data and provided to a manufacturer.

[0675] "Manufacturers" are companies that make appliances and devices.

[0676] The present invention is a system that allows users to make inquiries about home appliances and devices, and provides quick and accurate answers through a chat interface. This system operates by combining terminals, servers, databases, and natural language processing technology.

[0677] First, a user accesses the chat interface using a device (e.g., computer, smartphone, or tablet). Here, the user enters a question in the text box and clicks the send button. For example, the user might enter, "Can you tell me about error code E23 on my XYZ refrigerator?"

[0678] The server receives the query sent by the user and analyzes it using natural language processing technology. Specific software used is Google Cloud Natural Language API and IBM Watson Natural Language Understanding. Through this analysis, the server extracts important keywords from the text (e.g., "XYZ refrigerator" or "error code E23").

[0679] The server then queries a database based on these keywords to retrieve the relevant instruction manual. The database uses MySQL or MongoDB, and searches the instruction manual for a solution to the corresponding error code. For example, if the solution to error code E23 is "indicates poor cooling, check the power supply, and clean the filter," the server generates an answer based on this information.

[0680] The generated response is sent from the server to the user's device and displayed in the chat interface, specifically saying, "Error code E23 indicates poor cooling. Please check the power supply and clean the filter."

[0681] In addition, the server records all user inquiries in a database. This data is periodically aggregated and analyzed using statistical analysis software in Python or R. A report is generated based on the analysis results and provided to the manufacturer. This allows the manufacturer to obtain feedback needed to improve the quality of their products and add new features.

[0682] Examples of specific prompts are:

[0683] Example user input:

[0684] "What can I do about error code E23 on the XYZ refrigerator?"

[0685] Example server response:

[0686] "Error code E23 indicates poor cooling. Check the power supply and clean the filters."

[0687] Example prompt for a generative AI model:

[0688] "A user is asking, 'What can I do about error code E23 on my XYZ refrigerator?' Generate the best answer possible. The answer should include specific solutions (e.g., check the power supply and clean the filter)."

[0689] In this way, the system of the present invention provides an environment in which users can efficiently solve problems, and helps manufacturers improve the quality of their products while reducing the burden of customer support.

[0690] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0691] Step 1:

[0692] The user inputs a question into the terminal and sends it.

[0693] Specifically, the user types a question into the text box of the chat interface, such as "Can you tell me about error code E23 on the XYZ refrigerator?", and then presses the send button.

[0694] Input: User question (e.g. "What can I do about error code E23 on my XYZ refrigerator?")

[0695] Output: Submitted question data

[0696] Step 2:

[0697] The server receives the query.

[0698] The server receives the data sent by the user and adds it to a processing queue, at which point the received data is stored in text format.

[0699] Input: Submitted question data

[0700] Output: Question data added to the processing queue

[0701] Step 3:

[0702] The server analyzes the query using natural language processing (NLP) techniques.

[0703] Specifically, the server analyzes the input text using Google Cloud Natural Language API, IBM Watson Natural Language Understanding, etc. The server then performs entity recognition and extracts keywords such as "XYZ refrigerator" and "error code E23."

[0704] Input: Question data retrieved from the processing queue

[0705] Output: Analysis results (keywords: "XYZ refrigerator", "error code E23")

[0706] Step 4:

[0707] The server searches the database based on the keywords.

[0708] The server uses the extracted keywords to query a database, for example, using MySQL or MongoDB to search for the corresponding instruction manual and extract the relevant information.

[0709] Input: Keywords from the analysis results ("XYZ refrigerator", "Error code E23")

[0710] Output: Data from the relevant instruction manual

[0711] Step 5:

[0712] The server retrieves the relevant solutions and generates an answer.

[0713] The server identifies a solution to the error code E23 based on the contents of the instruction manual retrieved from the database. For example, it generates a response such as, "Error code E23 indicates poor cooling. Check the power supply and clean the filter."

[0714] Input: Instruction manual data

[0715] Output: Generated response (e.g. "Error code E23 indicates poor cooling. Check the power supply and clean the filters.")

[0716] Step 6:

[0717] The server sends the generated answer to the user's terminal.

[0718] The server sends the generated reply to the user's terminal and displays it on the chat interface.

[0719] Input: Generated answer

[0720] Output: Answer displayed on the user's terminal

[0721] Step 7:

[0722] The server records the inquiry in a database.

[0723] The server stores all queries in a database, making them available for future analysis and reference.

[0724] Input: Processed question and answer data

[0725] Output: Records stored in the database

[0726] Step 8:

[0727] The server aggregates and analyzes the data and creates reports for manufacturers.

[0728] The server periodically aggregates the recorded data and analyzes it using statistical analysis software such as Python or R. Based on the results of this analysis, a report is created and provided to the manufacturer.

[0729] Input: Query history stored in the database

[0730] Output: Report for manufacturer

[0731] (Application example 1)

[0732] 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."

[0733] There is a problem in that it is difficult to quickly provide appropriate solutions to abnormalities and problems that occur during the operation of machines and robots used in factories. In particular, if on-site workers and engineers cannot find a solution immediately, production efficiency may decrease, resulting in wasted time and costs.

[0734] 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.

[0735] In this invention, the server includes: means for receiving inquiries from users through a chat interface; natural language processing means for analyzing the received inquiries and identifying information on related equipment; means for retrieving the relevant instruction manual from a database based on the identified information and generating an answer to the inquiry; means for notifying the user of the generated answer; means for aggregating all inquiries from users and generating statistical data; means for creating a report based on the statistical data and providing it to the manufacturer; and means for receiving inquiries regarding abnormalities or problems with machines in the manufacturing process and using a generative AI model to provide appropriate maintenance procedures. This enables users to efficiently troubleshoot and maintain machines and robots used in factories.

[0736] A "chat interface" is an interactive interface for users to submit text-based inquiries.

[0737] "Natural language processing means" is a technology that analyzes text data from users and understands and processes human language.

[0738] A "database" is a system for organizing, storing, and searching specific information.

[0739] A "query answer generator" is a mechanism that generates an answer to a user's question based on information retrieved from a database.

[0740] A "generative AI model" is a model that uses artificial intelligence technology to generate and analyze data and provide appropriate answers and responses.

[0741] "Statistical data" refers to data obtained as a result of compiling and analyzing inquiries from users.

[0742] "Report" means a summary of information based on statistical data and provided to a manufacturer.

[0743] "Machine abnormalities and problems" refers to conditions or problems in which machines or robots used in the manufacturing process do not function properly.

[0744] "Maintenance procedures" are specific operating methods for checking the correct operation of machines and robots and making any necessary adjustments or repairs.

[0745] "Manufacturer" means a company or organization that designs and produces equipment or systems involved in the manufacturing process.

[0746] The present invention is a system that accepts inquiries about the operation and maintenance of machines and robots in manufacturing processes in a chat format, analyzes the user's question, and provides the most appropriate answer. This system is implemented in the following way.

[0747] Users access a chat interface installed in the factory using a device such as a smartphone or tablet. Through this chat interface, users make inquiries by entering a question in a text box and pressing the send button. For example, users can enter specific questions such as, "Please tell me about the XYZ robot's error code E45" or "My robot is stuck and won't move. What should I do?"

[0748] Next, the server receives the user's inquiry and analyzes it using natural language processing means, which extracts information such as "XYZ robot" and "error code E45" from the question and identifies the relevant device information and error content.

[0749] Based on the identified information, the server searches the database for the corresponding instruction manual. The database returns relevant information, and from that information, it extracts solutions to error code E45 and robot maintenance procedures. For example, detailed information including steps such as "check the power supply unit" is provided as a solution to error code E45.

[0750] The generated answer is sent from the server to the user's device, and the user receives the answer through a chat interface, specifically displaying the message "Error code E45 indicates a problem with the power supply unit. Please check the power supply unit."

[0751] In addition, the server records all user inquiries in a database. The recorded data is periodically aggregated and analyzed as statistical data using a generative AI model. A report is created based on this statistical data and provided to the manufacturer. This allows the manufacturer to effectively obtain the feedback needed to improve their products and add new features.

[0752] For example:

[0753] Example prompt sentence:

[0754] "Please tell me about the XYZ robot error code E45."

[0755] "My robot is stuck and won't move, what should I do?"

[0756] "Please tell me the maintenance procedure for the picking robot."

[0757] Hardware used: smartphone, tablet

[0758] Software used: OpenAI API, Flask

[0759] This allows factory workers and engineers to troubleshoot robots and machinery quickly and efficiently, significantly improving production efficiency.

[0760] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0761] Step 1:

[0762] A user accesses the chat interface using a device (smartphone or tablet) and enters a question. For example, they might enter, "Please tell me about the XYZ robot error code E45." The input data is in text format, and once the input is complete, it is sent to the server by pressing the send button.

[0763] Step 2:

[0764] The server receives queries from users. The received queries are saved as text data. Specifically, the server receives an HTTP request and extracts its payload (the query content). The input data is the user's question text, which is passed to the server's analysis module.

[0765] Step 3:

[0766] The server analyzes the query using natural language processing. Specifically, an NLP (Natural Language Processing) model extracts information such as "XYZ robot" or "error code E45" from the text data. In this step, the input data is the user's question text, and the output data is the extracted important keywords.

[0767] Step 4:

[0768] The server searches the database based on the extracted keywords, generates a database search query, and retrieves information about related instruction manuals and error codes. The input data is the extracted keywords, and the output data is the corresponding information in the instruction manual.

[0769] Step 5:

[0770] The server generates an answer to the query based on the retrieved information. In this step, a generative AI model is used to provide a specific solution to the error code E45. The input data is the information retrieved from the database, and the output data is the answer text to be presented to the user. For example, the generated answer might be, "Error code E45 indicates a problem with the power supply unit. Please check the power supply unit."

[0771] Step 6:

[0772] The generated answer is sent from the server to the user's device. Specifically, the answer text is displayed in the chat interface as an HTTP response. The input data is the generated answer text, and the output data is the answer displayed on the user's device.

[0773] Step 7:

[0774] The server records all user inquiries in a database. The recorded data is later aggregated and analyzed using a generative AI model. The input data is all inquiries, and the output data is statistical data and analysis results.

[0775] Step 8:

[0776] The server creates a report based on the statistical data and provides it to the manufacturer. The report includes common problems, their solutions, and improvements. The input data is the statistical data, and the output data is a document in the form of a report.

[0777] 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.

[0778] The present invention relates to a system that combines an emotion engine that recognizes user emotions, and provides a system that accepts inquiries about home appliances and device usage in a chat format, analyzes the user's question, and provides the most appropriate answer. This system is implemented in the following way.

[0779] First, a user accesses the chat interface using a terminal. The user makes an inquiry by entering a question in the text box and pressing the send button. For example, the user can enter a specific question such as, "Please tell me about the error code E23 on the XYZ refrigerator."

[0780] Next, the server receives the user's inquiry and passes the inquiry to the natural language processing means. The natural language processing means analyzes the question and extracts the corresponding device information and error code. The extracted information includes the "device type (e.g., XYZ refrigerator)" and the "error code (e.g., E23)."

[0781] The server then uses an emotion engine to analyze the emotion from the user's question. The emotion engine identifies the emotion from the user's text and returns that information to the server. For example, if the user uses the phrase "I'm very troubled," the emotion engine identifies emotions such as "confusion" and "anxiety."

[0782] The server adjusts the expression of the answer to the user based on the identified emotional information. For example, if the user is in trouble, the server generates an answer using more polite and reassuring expressions.

[0783] The server accesses the database based on the emotion information and analysis results to retrieve the corresponding instruction manual data. The instruction manual data returned from the database contains solutions to the error code E23, such as "indicates poor cooling, check the power supply, and clean the filter."

[0784] The server generates a response that takes the user's feelings into consideration based on the information it has acquired, such as "Error code E23 indicates poor cooling. Please rest assured. Check the power supply and clean the filter."

[0785] The generated answer is sent from the server to the device and notified to the user, who can then check the answer through the chat interface on the device.

[0786] Furthermore, the server records all inquiries and emotional information from users in a database. The recorded data is periodically compiled and analyzed as statistical data. Reports are created based on this statistical data and provided to manufacturers. Furthermore, by analyzing the emotional information as well, it becomes possible to improve products and review support systems based on user emotions.

[0787] For example, if many users express feelings of "confusion" or "anxiety" about a particular error code, a detailed explanation of the solution to that error code will be provided, and the relevant section of the instruction manual will be enhanced. In this way, the system of the present invention provides an environment where users can solve problems efficiently and with peace of mind, and manufacturers can use this information to improve the quality of their products based on user emotions while reducing the burden of customer support.

[0788] The processing flow will be explained below.

[0789] Step 1:

[0790] A user accesses the chat interface using a terminal, enters a question in the text box, and presses the send button. This sends the user's inquiry from the terminal to the server. For example, a specific question might be entered, such as "What can I do about error code E23 on the XYZ refrigerator?"

[0791] Step 2:

[0792] The server receives a user's inquiry and passes the inquiry to the natural language processing means, which analyzes the inquiry and extracts the corresponding device type (e.g., XYZ refrigerator) and error code (e.g., E23).

[0793] Step 3:

[0794] The server sends the query to the emotion engine based on the analyzed device type and error code information to identify the user's emotion. The emotion engine identifies emotions such as "confusion" or "anxiety" from the text and returns that information to the server.

[0795] Step 4:

[0796] The server receives the emotion information returned by the emotion engine and adjusts the wording of the response based on the user's emotion. For example, if the user is "confused," it decides to use a more polite and reassuring wording.

[0797] Step 5:

[0798] Next, the server accesses the database to retrieve the relevant instruction manual based on the parsed device information and error code. For example, the server searches for "XYZ refrigerator instruction manual" and retrieves the relevant information.

[0799] Step 6:

[0800] The server extracts a solution for the identified error code E23 from the instruction manual data it has acquired. For example, if the solution for error code E23 is described as "indicates poor cooling, check the power supply, and clean the filter," it extracts this information.

[0801] Step 7:

[0802] The server generates an optimal answer based on the extracted solution and the user's sentiment information identified earlier, for example, "Error code E23 indicates poor cooling. Please rest assured. Check the power supply and clean the filter."

[0803] Step 8:

[0804] The server sends the generated answer to the user's terminal and notifies the user, who can then check the answer in a chat interface on the terminal.

[0805] Step 9:

[0806] The server records all user inquiries and emotional information in a database, and periodically compiles and analyzes them. The server creates a report based on the statistical data and emotional information compiled and provides it to the manufacturer.

[0807] The above is the specific processing flow of the invention that combines an emotion engine that recognizes and responds to user emotions.

[0808] Example 2

[0809] 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."

[0810] Conventional inquiry systems can provide appropriate answers to user inquiries, but they are unable to respond in a way that takes the user's emotions into consideration. As a result, if the user feels anxious or confused, appropriate support cannot be provided, resulting in a decrease in user satisfaction. Furthermore, there is an insufficient mechanism for aggregating inquiry content to generate statistical data that can be used to improve product quality.

[0811] 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.

[0812] In this invention, the server includes means for receiving inquiries from users through a chat interface, natural language processing means for analyzing the received inquiries and identifying information on related devices, means for retrieving the relevant instruction manual from a database based on the identified information and generating an answer to the inquiry, emotion analysis means for analyzing the user's emotions, means for adjusting the expression of the answer based on the results of the emotion analysis, means for notifying the user of the generated answer, means for aggregating all inquiries and emotion information from users and generating statistical data, and means for creating reports based on the statistical data and providing them to manufacturers. This makes it possible to provide appropriate answers that take user emotions into consideration, thereby increasing user satisfaction and helping to improve products and support systems.

[0813] A "user" is a user who makes an inquiry through the chat interface of this system.

[0814] A "chat interface" is an interface that allows users to input and send inquiries in text format.

[0815] A "server" is a computing device that receives queries from users, analyzes them, and generates and notifies them of responses.

[0816] The "natural language processing means" is a processing means for analyzing the content of an inquiry received from a user and extracting related information.

[0817] The "emotion analysis means" is a means for identifying emotions from the user's text and analyzing that information.

[0818] A "database" is a collection of information that stores inquiry details, related equipment information, instruction manuals, etc.

[0819] An "instruction manual" is a document that describes how to use a device and how to deal with error codes.

[0820] The "answer generation means" is a means for generating an answer to be provided to the user based on the analyzed information.

[0821] The "notification means" is a means for sending the generated answer to the user and notifying him / her.

[0822] "Emotion information" is emotion data analyzed from the content of the user's inquiry.

[0823] The "aggregation means" is a means for aggregating all inquiries and emotional information from users and generating statistical data.

[0824] "Statistical data" is data that has been compiled and analyzed to reveal trends and patterns.

[0825] "Report" means a report prepared based on the generated statistical data and provided to the manufacturer.

[0826] "Manufacturer" is the company that makes the equipment you use and receives information for improvements.

[0827] This invention relates to a system that combines an emotion analysis engine that recognizes user emotions, accepts inquiries about home appliances and device usage in chat format, analyzes the user's question, and provides the most appropriate answer. This system communicates between a server, a terminal, and the user, and uses the following hardware and software:

[0828] Hardware and Software

[0829] 1. Server

[0830] Hardware: High-performance servers installed in a data center

[0831] Software: Natural Language Processing (NLP) libraries (e.g., SpaCy, NLTK), sentiment analysis engines (e.g., IBM Watson, Google Cloud Natural Language API), database management systems (e.g., MySQL, PostgreSQL)

[0832] 2. Terminal

[0833] Hardware: Your laptops, desktops, and smartphones

[0834] Software: Web browser or dedicated application

[0835] 3. Network

[0836] Internet connection: Communications infrastructure that provides high-speed and stable internet connection

[0837] System operation procedure

[0838] The system is implemented in the following way.

[0839] 1. A user accesses the chat interface using a device, types a specific question into the text box, for example, "What can I do about error code E23 on my XYZ refrigerator?", and presses the send button.

[0840] 2. The server receives the query message sent by the user and passes it to natural language processing (NLP) software, at which point the server uses NLP libraries to parse the text data and extract key information such as the device type (e.g., XYZ refrigerator) and the error code (e.g., E23).

[0841] 3. The server uses a sentiment analysis engine to identify emotions from the text provided by the user. For example, if the user types a phrase like "I'm very worried," the sentiment analysis engine will identify emotions like "confused" or "anxious," and send this information back to the server.

[0842] 4. Based on the analyzed emotion information and the results of natural language processing, the server accesses the database and retrieves the relevant instruction manual data, such as "indicates poor cooling, check the power supply, and clean the filter" that describes specific solutions.

[0843] 5. The server generates a response that takes into account the user's emotional information. For example, it generates a response such as "Error code E23 indicates poor cooling. Please be reassured. Check the power supply and clean the filter." and adjusts the expression to take the user's emotional information into account.

[0844] 6. The server sends the generated answer to the user's device, and the user confirms the answer through the chat interface.

[0845] 7. The server records all user inquiries and sentiment information in a database, periodically aggregates them to generate statistical data, and then creates reports based on the statistical data and provides them to manufacturers, allowing them to obtain useful information for improving their products and support systems.

[0846] Examples and prompts

[0847] The user types and sends the following into the chat on their device: "Can you tell me about the error code E23 on my XYZ refrigerator? I'm having a lot of trouble." The server receives this query and uses natural language processing software to extract "XYZ refrigerator" and "E23." The server then uses a sentiment analysis engine to identify the emotion "confused." Based on this information, the server retrieves "solutions to E23" from a database and generates an answer that takes the user's emotions into consideration. For example, the server might generate an answer like, "Error code E23 indicates poor cooling. Please rest assured. Check the power and clean the filter." The server then sends the generated answer to the device, where the user can view it in the chat interface. The server records all data in a database for later statistical analysis.

[0848] This system provides an environment where users can solve problems efficiently and with peace of mind, and helps manufacturers improve the quality of their products based on user sentiment while reducing the burden on customer support.

[0849] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0850] Step 1:

[0851] A user accesses the chat interface using a device. For example, he opens an application on a smartphone or PC, types "Please tell me about the error code E23 on the XYZ refrigerator" in the chat box, and presses the send button. This input generates the user's inquiry, which is sent to the server as text data.

[0852] Step 2:

[0853] The server receives a query message from a user. The received data (textual query content) is added to the processing queue. Specifically, the received data is temporarily stored and sent to the next processing step. In this case, the input is the user's query text, and the output is the query data waiting to be parsed.

[0854] Step 3:

[0855] The server passes the received query message to natural language processing software. In this process, an NLP library (e.g., SpaCy or NLTK) is used to extract "device type" and "error code" from the text data. Specifically, "XYZ refrigerator" and "E23" are extracted from the text "Please tell me about error code E23 for XYZ refrigerator." The input is the user's text data, and the output is the extracted key information (device type and error code).

[0856] Step 4:

[0857] The server uses a sentiment analysis engine to identify emotions from the user's text. For example, if the text contains the phrase "I'm very worried," the sentiment analysis engine (e.g., IBM Watson or Google Cloud Natural Language API) will identify emotions such as "confused" or "anxious." The input is the user's text data, and the output is the analyzed emotional information.

[0858] Step 5:

[0859] The server accesses the database based on the analysis results and retrieves the relevant instruction manual data. Specifically, it executes a database query to retrieve a solution such as "Error code E23 indicates poor cooling; check the power supply and clean the filter." The input is the analyzed key information (device type and error code), and the output is the relevant instruction manual data.

[0860] Step 6:

[0861] The server generates a response that takes the user's emotions into consideration. Specifically, based on the analyzed emotional information, it creates a polite response such as, "Error code E23 indicates poor cooling. Please rest assured. Check the power supply and clean the filter." The input is the acquired instruction manual data and emotional information, and the output is an optimized response.

[0862] Step 7:

[0863] The server sends the generated answer to the user's device. Specifically, this answer is delivered to the user through the chat interface. The input is the generated answer, and the output is a notification sent to the user's device.

[0864] Step 8:

[0865] The user checks the reply sent from the server through the chat interface on their device. The user reads the reply and takes specific action. In this step, the user displays the reply they received and takes action based on the information.

[0866] Step 9:

[0867] The server records all user inquiries and emotional information in a database. The input is all inquiry data and emotional information, and the output is records stored in the database. These records are periodically aggregated and analyzed as statistical data, and reports are generated.

[0868] Step 10:

[0869] The server creates a report based on the generated statistical data and provides it to the manufacturer, which then obtains information that is useful for improving the product and reviewing the support system. The input is statistical data, and the output is a report provided to the manufacturer.

[0870] (Application example 2)

[0871] 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."

[0872] Conventional inquiry response systems provide mechanical answers without considering the user's feelings, which often leaves users unable to resolve their problems with peace of mind. Furthermore, manufacturers have been limited in their ability to improve customer satisfaction because they have not reviewed their support systems or improved their products based on user feelings.

[0873] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving an inquiry from a user through a chat interface; natural language processing means for analyzing the received inquiry and identifying information about related devices; means for retrieving the relevant instruction manual from a database based on the identified information and generating a response to the inquiry; means for notifying the user of the generated response; means for analyzing the user's emotions using an emotion recognition model and adjusting the expression of the response based on the emotions; means for aggregating all inquiry contents and emotional information from users and generating statistical data; and means for creating a report based on the statistical data and providing it to the manufacturer. This makes it possible to provide an answer that takes user emotions into consideration, allowing users to solve problems with peace of mind and also enabling manufacturers to improve their products and review their support systems based on user emotional information.

[0874] "User" refers to a person who uses the system to make an inquiry.

[0875] "Inquiry" refers to a question or request entered by a user through the chat interface regarding the handling of a home appliance or device.

[0876] "Chat interface" refers to a communication method that allows users to type and submit questions in a text box.

[0877] "Analysis" refers to analyzing the content of the received inquiry and understanding the meaning and elements of the question.

[0878] "Natural language processing means" refers to technical means for analyzing the content of a user's inquiry and identifying relevant information.

[0879] A "database" refers to an information storage device for storing information such as equipment instruction manuals and solutions to error codes.

[0880] An "emotion recognition model" refers to the algorithms or software used to identify emotions from a user's text.

[0881] "Answer" refers to a solution or instruction provided to the user based on the analyzed information.

[0882] "Notification" refers to the act of sending the generated answer to the user.

[0883] "Statistical data" refers to data that has been compiled and analyzed based on inquiries and their emotional information obtained from multiple users.

[0884] "Report" means a report prepared based on statistical data and provided to a manufacturer.

[0885] "Manufacturer" refers to the company or entity that provides the product to the user.

[0886] This invention relates to a smartphone application called "Smart Shopping Assistant" that supports shopping in brick-and-mortar stores. The following describes a system that specifically realizes this "Smart Shopping Assistant."

[0887] Users access the chat interface on the application using their smartphones. They make inquiries by entering a question in the text box and pressing the send button. For example, they can enter a specific question such as, "I don't know how to use this washing machine."

[0888] The server receives inquiries from users and passes the contents of those inquiries to a natural language processing means. The natural language processing means analyzes the content of the question and extracts corresponding product information and operation instructions. This is done using Python and NLTK (Natural Language Toolkit). The analyzed information includes the type of product and operation instructions.

[0889] Next, the server uses an emotion recognition model to analyze the emotion from the user's question. For emotion recognition, the Hugging Face emotion recognition model is used. For example, if a user uses the phrase "I'm very troubled," the emotion recognition model identifies emotions such as "confusion" or "anxiety." The emotion recognition model identifies the emotion from the text and returns that information to the server.

[0890] The server adjusts the wording of the response to the user based on the identified emotional information. For example, if the user is in trouble, it generates an answer using more polite and reassuring language. Based on the emotional information and analysis results, the server accesses a database to obtain relevant product information and operation instructions. The database stores product instruction manuals and FAQs. The information returned from this database is compiled by the answer generation means in a format appropriate for the user.

[0891] For example, a response such as "This washing machine is easy to operate. First, press the power button, select a program, and then press the start button" is generated. The generated response is sent from the server to the device and notified to the user. The user can check the response through the chat interface on their smartphone.

[0892] Furthermore, the server records all user inquiries and emotional information in a database. The recorded data is periodically compiled and analyzed as statistical data. Reports are created based on this statistical data and provided to manufacturers. Furthermore, by analyzing the emotional information as well, it is possible to improve products and review support systems based on user emotions.

[0893] For example, if many users express feelings of "confusion" or "anxiety" about a particular operation, the system will provide an explanation of that operation or strengthen the relevant section of the instruction manual. In this way, the system of the present invention provides an environment where users can solve problems efficiently and with peace of mind, and manufacturers can use this information to improve the quality of their products based on user feelings while reducing the burden on customer support.

[0894] Specific examples

[0895] If a user types a question like "My vacuum cleaner isn't working, what should I do?", the server can use an emotion recognition model to identify the user's emotion as "confused" and generate a polite and reassuring response based on that. An example prompt would look like this:

[0896] plaintext

[0897] "User input: 'My vacuum cleaner isn't working, what should I do?' Identify the sentiment and generate the best answer."

[0898] The generated answer will notify the user in the form of "Don't worry. Here are some possible reasons why your vacuum cleaner isn't working: Make sure the power cord is securely connected..."

[0899] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0900] Step 1:

[0901] The user uses a terminal to access the chat interface of the smart shopping assistant and inputs a question. The input is the user's question (e.g., "I don't know how to use this washing machine.") This question is sent to the server.

[0902] Step 2:

[0903] The server passes the received question to a natural language processing tool and analyzes the inquiry. Specifically, it uses Python and NLTK to tokenize the question and extract nouns and proper nouns. The input is the user's question, and the output is information such as the type of device and how to operate it.

[0904] Step 3:

[0905] The server uses an emotion recognition model to analyze the emotion from the user's question. Specifically, it uses the Hugging Face emotion recognition model to analyze the text and identify the user's emotion (e.g., "confused" or "anxious"). The input is the user's question, and the output is the user's emotional information.

[0906] Step 4:

[0907] The server generates a response appropriate for the user based on the emotional information and the results of natural language processing. Specifically, it creates responses using expressions that take the user's emotions into consideration. For example, if the user is confused, it uses polite expressions such as "Don't worry." Emotional information and device information are input, and a polite and reassuring response is output.

[0908] Step 5:

[0909] The server accesses the database to obtain relevant product information and operating instructions. Specifically, it searches the database for product instruction manuals and FAQs and extracts the necessary information. The input is device information, and the output is the relevant instruction manual and operating instructions.

[0910] Step 6:

[0911] The server generates a final answer and notifies the user. The generated answer is sent to the user's device, where the user can confirm it through the chat interface. The generated answer is the input, and the notified answer is the output.

[0912] Step 7:

[0913] The server records all inquiry content and emotion information in a database. Specifically, it periodically aggregates the inquiry content and emotion information to generate statistical data. All inquiry content and emotion information are input, and statistical data is obtained as output.

[0914] Step 8:

[0915] The server creates a report based on the statistical data and provides it to the manufacturer. Specifically, it compiles the data analysis results into a report format so that the manufacturer can improve their product and review their support system based on user sentiment information. The input is statistical data, and the output is a report that is provided to the manufacturer.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] [Fourth embodiment]

[0920] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0921] 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.

[0922] 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).

[0923] 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.

[0924] 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.

[0925] 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).

[0926] 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.

[0927] 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.

[0928] 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.

[0929] 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.

[0930] 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.

[0931] 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.

[0932] 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."

[0933] The present invention relates to a system that accepts inquiries about home appliances and devices in a chat format, analyzes the user's question, and provides the most appropriate answer. This system is implemented in the following way.

[0934] First, a user accesses the chat interface using a terminal. The user makes an inquiry by entering a question in the text box and pressing the send button. For example, a specific question can be entered, such as "Please tell me about the error code E23 on the XYZ refrigerator."

[0935] Next, the server receives the user's inquiry and analyzes it using natural language processing means, which extracts information such as "XYZ refrigerator" and "error code E23" from the question and identifies the relevant device information and error content.

[0936] The server accesses the database based on the identified information and searches for the corresponding instruction manual. The database returns the corresponding instruction manual, and extracts the solution to the error code E23 from it. For example, if the solution for the error code E23 is "indicates poor cooling, check the power supply, and clean the filter," an answer is generated based on this information.

[0937] The generated answer is sent from the server to the user's device, and the user receives the answer through a chat interface, specifically displaying the message "Error code E23 indicates poor cooling. Please check the power supply and clean the filter."

[0938] In addition, the server records all user inquiries in a database. The recorded data is periodically compiled and analyzed as statistical data. Reports are created based on this statistical data and provided to manufacturers. This allows manufacturers to effectively obtain feedback necessary for product improvement and the addition of new features.

[0939] For example, if many users inquire about a common error code, the solution to that error code will be improved and the relevant section of the instruction manual will be revised. In this way, the system of the present invention provides an environment in which users can solve problems efficiently, helping manufacturers improve the quality of their products while reducing the burden on customer support.

[0940] The processing flow will be explained below.

[0941] Step 1:

[0942] A user accesses the chat interface using a terminal, enters a question in the text box, and presses the send button, which sends the user's inquiry from the terminal to the server.

[0943] Step 2:

[0944] The server receives an inquiry from a user and passes the inquiry content to the natural language processing means, which analyzes the received inquiry content and extracts the corresponding device type and error code.

[0945] Step 3:

[0946] The natural language processing means identifies the "device type (e.g., XYZ refrigerator)" and "error code (e.g., E23)" as analysis results and returns them to the server. The server then accesses the database based on this information.

[0947] Step 4:

[0948] The server retrieves the instruction manual data for the target device from the database. For example, it searches for "XYZ refrigerator instruction manual" and retrieves related information.

[0949] Step 5:

[0950] The server extracts the solution corresponding to the identified error code (e.g., E23) from the instruction manual data acquired. For example, if the solution to error code E23 is "indicates poor cooling, check the power supply, and clean the filter," this information is extracted.

[0951] Step 6:

[0952] Based on the information extracted by the server, the optimal response to the inquiry is generated, for example, "Error code E23 indicates poor cooling. Check the power supply and clean the filter."

[0953] Step 7:

[0954] The server sends the generated answer to the terminal and notifies the user, who can then check the answer in the chat interface again via the terminal.

[0955] Step 8:

[0956] The server records all user inquiries in a database and periodically compiles and analyzes them. It creates reports based on the compiled statistical data and provides them to manufacturers. The manufacturers use the reports to improve their products and develop new features.

[0957] The above is a specific processing flow of the system of the present invention.

[0958] Example 1

[0959] 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."

[0960] Today's consumers increasingly use a wide variety of home appliances and devices, and want to quickly resolve any problems or errors they encounter with these products. However, referring to instruction manuals one by one is time-consuming, and finding the appropriate solution can be difficult, especially for specialized issues like error codes. Manufacturers also need to efficiently process user inquiries and collect data to help improve and enhance their products. Current systems do not adequately meet these needs, causing inconvenience to both users and manufacturers.

[0961] 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.

[0962] In this invention, the server includes means for receiving inquiries from users via a chat interface, natural language processing means for analyzing the received inquiries and identifying information on related devices, and means for retrieving the relevant instruction manual from a database based on the identified information and generating an answer to the inquiry. This allows users to quickly and accurately find solutions to their problems, and enables manufacturers to utilize the question history to improve product quality and streamline customer support.

[0963] A "user" is an individual or corporation that uses the system to make inquiries about home appliances and devices.

[0964] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0965] A "chat interface" is a text-based interaction tool that allows users to enter questions and interact with the system.

[0966] A "server" is a computer system that receives queries from users, analyzes them, and generates and sends appropriate responses.

[0967] "Natural language processing means" is a technology for analyzing received text data and understanding the content of the user's question.

[0968] A "database" is a system for centrally managing data such as instruction manuals and past inquiry history for home appliances and devices.

[0969] An "instruction manual" is a document that describes how to use a home appliance or device, the meaning of error codes, troubleshooting, etc.

[0970] A "means for generating an answer" is a means for creating an appropriate response to a user's question.

[0971] The "notification means" is a means for transmitting the generated answer to the user's terminal.

[0972] "Statistical data" refers to data analyzed based on the collected inquiries from users.

[0973] "Report" means a report prepared based on statistical data and provided to a manufacturer.

[0974] "Manufacturers" are companies that make appliances and devices.

[0975] The present invention is a system that allows users to make inquiries about home appliances and devices, and provides quick and accurate answers through a chat interface. This system operates by combining terminals, servers, databases, and natural language processing technology.

[0976] First, a user accesses the chat interface using a device (e.g., computer, smartphone, or tablet). Here, the user enters a question in the text box and clicks the send button. For example, the user might enter, "Can you tell me about error code E23 on my XYZ refrigerator?"

[0977] The server receives the query sent by the user and analyzes it using natural language processing technology. Specific software used is Google Cloud Natural Language API and IBM Watson Natural Language Understanding. Through this analysis, the server extracts important keywords from the text (e.g., "XYZ refrigerator" or "error code E23").

[0978] The server then queries a database based on these keywords to retrieve the relevant instruction manual. The database uses MySQL or MongoDB, and searches the instruction manual for a solution to the corresponding error code. For example, if the solution to error code E23 is "indicates poor cooling, check the power supply, and clean the filter," the server generates an answer based on this information.

[0979] The generated response is sent from the server to the user's device and displayed in the chat interface, specifically saying, "Error code E23 indicates poor cooling. Please check the power supply and clean the filter."

[0980] In addition, the server records all user inquiries in a database. This data is periodically aggregated and analyzed using statistical analysis software in Python or R. A report is generated based on the analysis results and provided to the manufacturer. This allows the manufacturer to obtain feedback needed to improve the quality of their products and add new features.

[0981] Examples of specific prompts are:

[0982] Example user input:

[0983] "What can I do about error code E23 on the XYZ refrigerator?"

[0984] Example server response:

[0985] "Error code E23 indicates poor cooling. Check the power supply and clean the filters."

[0986] Example prompt for a generative AI model:

[0987] "A user is asking, 'What can I do about error code E23 on my XYZ refrigerator?' Generate the best answer possible. The answer should include specific solutions (e.g., check the power supply and clean the filter)."

[0988] In this way, the system of the present invention provides an environment in which users can efficiently solve problems, and helps manufacturers improve the quality of their products while reducing the burden of customer support.

[0989] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0990] Step 1:

[0991] The user inputs a question into the terminal and sends it.

[0992] Specifically, the user types a question into the text box of the chat interface, such as "Can you tell me about error code E23 on the XYZ refrigerator?", and then presses the send button.

[0993] Input: User question (e.g. "What can I do about error code E23 on my XYZ refrigerator?")

[0994] Output: Submitted question data

[0995] Step 2:

[0996] The server receives the query.

[0997] The server receives the data sent by the user and adds it to a processing queue, at which point the received data is stored in text format.

[0998] Input: Submitted question data

[0999] Output: Question data added to the processing queue

[1000] Step 3:

[1001] The server analyzes the query using natural language processing (NLP) techniques.

[1002] Specifically, the server analyzes the input text using Google Cloud Natural Language API, IBM Watson Natural Language Understanding, etc. The server then performs entity recognition and extracts keywords such as "XYZ refrigerator" and "error code E23."

[1003] Input: Question data retrieved from the processing queue

[1004] Output: Analysis results (keywords: "XYZ refrigerator", "error code E23")

[1005] Step 4:

[1006] The server searches the database based on the keywords.

[1007] The server uses the extracted keywords to query a database, for example, using MySQL or MongoDB to search for the corresponding instruction manual and extract the relevant information.

[1008] Input: Keywords from the analysis results ("XYZ refrigerator", "Error code E23")

[1009] Output: Data from the relevant instruction manual

[1010] Step 5:

[1011] The server retrieves the relevant solutions and generates an answer.

[1012] The server identifies a solution to the error code E23 based on the contents of the instruction manual retrieved from the database. For example, it generates a response such as, "Error code E23 indicates poor cooling. Check the power supply and clean the filter."

[1013] Input: Instruction manual data

[1014] Output: Generated response (e.g. "Error code E23 indicates poor cooling. Check the power supply and clean the filters.")

[1015] Step 6:

[1016] The server sends the generated answer to the user's terminal.

[1017] The server sends the generated reply to the user's terminal and displays it on the chat interface.

[1018] Input: Generated answer

[1019] Output: Answer displayed on the user's terminal

[1020] Step 7:

[1021] The server records the inquiry in a database.

[1022] The server stores all queries in a database, making them available for future analysis and reference.

[1023] Input: Processed question and answer data

[1024] Output: Records stored in the database

[1025] Step 8:

[1026] The server aggregates and analyzes the data and creates reports for manufacturers.

[1027] The server periodically aggregates the recorded data and analyzes it using statistical analysis software such as Python or R. Based on the results of this analysis, a report is created and provided to the manufacturer.

[1028] Input: Query history stored in the database

[1029] Output: Report for manufacturer

[1030] (Application example 1)

[1031] 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."

[1032] There is a problem in that it is difficult to quickly provide appropriate solutions to abnormalities and problems that occur during the operation of machines and robots used in factories. In particular, if on-site workers and engineers cannot find a solution immediately, production efficiency may decrease, resulting in wasted time and costs.

[1033] 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.

[1034] In this invention, the server includes: means for receiving inquiries from users through a chat interface; natural language processing means for analyzing the received inquiries and identifying information on related equipment; means for retrieving the relevant instruction manual from a database based on the identified information and generating an answer to the inquiry; means for notifying the user of the generated answer; means for aggregating all inquiries from users and generating statistical data; means for creating a report based on the statistical data and providing it to the manufacturer; and means for receiving inquiries regarding abnormalities or problems with machines in the manufacturing process and using a generative AI model to provide appropriate maintenance procedures. This enables users to efficiently troubleshoot and maintain machines and robots used in factories.

[1035] A "chat interface" is an interactive interface for users to submit text-based inquiries.

[1036] "Natural language processing means" is a technology that analyzes text data from users and understands and processes human language.

[1037] A "database" is a system for organizing, storing, and searching specific information.

[1038] A "query answer generator" is a mechanism that generates an answer to a user's question based on information retrieved from a database.

[1039] A "generative AI model" is a model that uses artificial intelligence technology to generate and analyze data and provide appropriate answers and responses.

[1040] "Statistical data" refers to data obtained as a result of compiling and analyzing inquiries from users.

[1041] "Report" means a summary of information based on statistical data and provided to a manufacturer.

[1042] "Machine abnormalities and problems" refers to conditions or problems in which machines or robots used in the manufacturing process do not function properly.

[1043] "Maintenance procedures" are specific operating methods for checking the correct operation of machines and robots and making any necessary adjustments or repairs.

[1044] "Manufacturer" means a company or organization that designs and produces equipment or systems involved in the manufacturing process.

[1045] The present invention is a system that accepts inquiries about the operation and maintenance of machines and robots in manufacturing processes in a chat format, analyzes the user's question, and provides the most appropriate answer. This system is implemented in the following way.

[1046] Users access a chat interface installed in the factory using a device such as a smartphone or tablet. Through this chat interface, users make inquiries by entering a question in a text box and pressing the send button. For example, users can enter specific questions such as, "Please tell me about the XYZ robot's error code E45" or "My robot is stuck and won't move. What should I do?"

[1047] Next, the server receives the user's inquiry and analyzes it using natural language processing means, which extracts information such as "XYZ robot" and "error code E45" from the question and identifies the relevant device information and error content.

[1048] Based on the identified information, the server searches the database for the corresponding instruction manual. The database returns relevant information, and from that information, it extracts solutions to error code E45 and robot maintenance procedures. For example, detailed information including steps such as "check the power supply unit" is provided as a solution to error code E45.

[1049] The generated answer is sent from the server to the user's device, and the user receives the answer through a chat interface, specifically displaying the message "Error code E45 indicates a problem with the power supply unit. Please check the power supply unit."

[1050] In addition, the server records all user inquiries in a database. The recorded data is periodically aggregated and analyzed as statistical data using a generative AI model. A report is created based on this statistical data and provided to the manufacturer. This allows the manufacturer to effectively obtain the feedback needed to improve their products and add new features.

[1051] For example:

[1052] Example prompt sentence:

[1053] "Please tell me about the XYZ robot error code E45."

[1054] "My robot is stuck and won't move, what should I do?"

[1055] "Please tell me the maintenance procedure for the picking robot."

[1056] Hardware used: smartphone, tablet

[1057] Software used: OpenAI API, Flask

[1058] This allows factory workers and engineers to troubleshoot robots and machinery quickly and efficiently, significantly improving production efficiency.

[1059] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1060] Step 1:

[1061] A user accesses the chat interface using a device (smartphone or tablet) and enters a question. For example, they might enter, "Please tell me about the XYZ robot error code E45." The input data is in text format, and once the input is complete, it is sent to the server by pressing the send button.

[1062] Step 2:

[1063] The server receives queries from users. The received queries are saved as text data. Specifically, the server receives an HTTP request and extracts its payload (the query content). The input data is the user's question text, which is passed to the server's analysis module.

[1064] Step 3:

[1065] The server analyzes the query using natural language processing. Specifically, an NLP (Natural Language Processing) model extracts information such as "XYZ robot" or "error code E45" from the text data. In this step, the input data is the user's question text, and the output data is the extracted important keywords.

[1066] Step 4:

[1067] The server searches the database based on the extracted keywords, generates a database search query, and retrieves information about related instruction manuals and error codes. The input data is the extracted keywords, and the output data is the corresponding information in the instruction manual.

[1068] Step 5:

[1069] The server generates an answer to the query based on the retrieved information. In this step, a generative AI model is used to provide a specific solution to the error code E45. The input data is the information retrieved from the database, and the output data is the answer text to be presented to the user. For example, the generated answer might be, "Error code E45 indicates a problem with the power supply unit. Please check the power supply unit."

[1070] Step 6:

[1071] The generated answer is sent from the server to the user's device. Specifically, the answer text is displayed in the chat interface as an HTTP response. The input data is the generated answer text, and the output data is the answer displayed on the user's device.

[1072] Step 7:

[1073] The server records all user inquiries in a database. The recorded data is later aggregated and analyzed using a generative AI model. The input data is all inquiries, and the output data is statistical data and analysis results.

[1074] Step 8:

[1075] The server creates a report based on the statistical data and provides it to the manufacturer. The report includes common problems, their solutions, and improvements. The input data is the statistical data, and the output data is a document in the form of a report.

[1076] 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.

[1077] The present invention relates to a system that combines an emotion engine that recognizes user emotions, and provides a system that accepts inquiries about home appliances and device usage in a chat format, analyzes the user's question, and provides the most appropriate answer. This system is implemented in the following way.

[1078] First, a user accesses the chat interface using a terminal. The user makes an inquiry by entering a question in the text box and pressing the send button. For example, the user can enter a specific question such as, "Please tell me about the error code E23 on the XYZ refrigerator."

[1079] Next, the server receives the user's inquiry and passes the inquiry to the natural language processing means. The natural language processing means analyzes the question and extracts the corresponding device information and error code. The extracted information includes the "device type (e.g., XYZ refrigerator)" and the "error code (e.g., E23)."

[1080] The server then uses an emotion engine to analyze the emotion from the user's question. The emotion engine identifies the emotion from the user's text and returns that information to the server. For example, if the user uses the phrase "I'm very troubled," the emotion engine identifies emotions such as "confusion" and "anxiety."

[1081] The server adjusts the expression of the answer to the user based on the identified emotional information. For example, if the user is in trouble, the server generates an answer using more polite and reassuring expressions.

[1082] The server accesses the database based on the emotion information and analysis results to retrieve the corresponding instruction manual data. The instruction manual data returned from the database contains solutions to the error code E23, such as "indicates poor cooling, check the power supply, and clean the filter."

[1083] The server generates a response that takes the user's feelings into consideration based on the information it has acquired, such as "Error code E23 indicates poor cooling. Please rest assured. Check the power supply and clean the filter."

[1084] The generated answer is sent from the server to the device and notified to the user, who can then check the answer through the chat interface on the device.

[1085] Furthermore, the server records all inquiries and emotional information from users in a database. The recorded data is periodically compiled and analyzed as statistical data. Reports are created based on this statistical data and provided to manufacturers. Furthermore, by analyzing the emotional information as well, it becomes possible to improve products and review support systems based on user emotions.

[1086] For example, if many users express feelings of "confusion" or "anxiety" about a particular error code, a detailed explanation of the solution to that error code will be provided, and the relevant section of the instruction manual will be enhanced. In this way, the system of the present invention provides an environment where users can solve problems efficiently and with peace of mind, and manufacturers can use this information to improve the quality of their products based on user emotions while reducing the burden of customer support.

[1087] The processing flow will be explained below.

[1088] Step 1:

[1089] A user accesses the chat interface using a terminal, enters a question in the text box, and presses the send button. This sends the user's inquiry from the terminal to the server. For example, a specific question might be entered, such as "What can I do about error code E23 on the XYZ refrigerator?"

[1090] Step 2:

[1091] The server receives a user's inquiry and passes the inquiry to the natural language processing means, which analyzes the inquiry and extracts the corresponding device type (e.g., XYZ refrigerator) and error code (e.g., E23).

[1092] Step 3:

[1093] The server sends the query to the emotion engine based on the analyzed device type and error code information to identify the user's emotion. The emotion engine identifies emotions such as "confusion" or "anxiety" from the text and returns that information to the server.

[1094] Step 4:

[1095] The server receives the emotion information returned by the emotion engine and adjusts the wording of the response based on the user's emotion. For example, if the user is "confused," it decides to use a more polite and reassuring wording.

[1096] Step 5:

[1097] Next, the server accesses the database to retrieve the relevant instruction manual based on the parsed device information and error code. For example, the server searches for "XYZ refrigerator instruction manual" and retrieves the relevant information.

[1098] Step 6:

[1099] The server extracts a solution for the identified error code E23 from the instruction manual data it has acquired. For example, if the solution for error code E23 is described as "indicates poor cooling, check the power supply, and clean the filter," it extracts this information.

[1100] Step 7:

[1101] The server generates an optimal answer based on the extracted solution and the user's sentiment information identified earlier, for example, "Error code E23 indicates poor cooling. Please rest assured. Check the power supply and clean the filter."

[1102] Step 8:

[1103] The server sends the generated answer to the user's terminal and notifies the user, who can then check the answer in a chat interface on the terminal.

[1104] Step 9:

[1105] The server records all user inquiries and emotional information in a database, and periodically compiles and analyzes them. The server creates a report based on the statistical data and emotional information compiled and provides it to the manufacturer.

[1106] The above is the specific processing flow of the invention that combines an emotion engine that recognizes and responds to user emotions.

[1107] Example 2

[1108] 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."

[1109] Conventional inquiry systems can provide appropriate answers to user inquiries, but they are unable to respond in a way that takes the user's emotions into consideration. As a result, if the user feels anxious or confused, appropriate support cannot be provided, resulting in a decrease in user satisfaction. Furthermore, there is an insufficient mechanism for aggregating inquiry content to generate statistical data that can be used to improve product quality.

[1110] 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.

[1111] In this invention, the server includes means for receiving inquiries from users through a chat interface, natural language processing means for analyzing the received inquiries and identifying information on related devices, means for retrieving the relevant instruction manual from a database based on the identified information and generating an answer to the inquiry, emotion analysis means for analyzing the user's emotions, means for adjusting the expression of the answer based on the results of the emotion analysis, means for notifying the user of the generated answer, means for aggregating all inquiries and emotion information from users and generating statistical data, and means for creating reports based on the statistical data and providing them to manufacturers. This makes it possible to provide appropriate answers that take user emotions into consideration, thereby increasing user satisfaction and helping to improve products and support systems.

[1112] A "user" is a user who makes an inquiry through the chat interface of this system.

[1113] A "chat interface" is an interface that allows users to input and send inquiries in text format.

[1114] A "server" is a computing device that receives queries from users, analyzes them, and generates and notifies them of responses.

[1115] The "natural language processing means" is a processing means for analyzing the content of an inquiry received from a user and extracting related information.

[1116] The "emotion analysis means" is a means for identifying emotions from the user's text and analyzing that information.

[1117] A "database" is a collection of information that stores inquiry details, related equipment information, instruction manuals, etc.

[1118] An "instruction manual" is a document that describes how to use a device and how to deal with error codes.

[1119] The "answer generation means" is a means for generating an answer to be provided to the user based on the analyzed information.

[1120] The "notification means" is a means for sending the generated answer to the user and notifying him / her.

[1121] "Emotion information" is emotion data analyzed from the content of the user's inquiry.

[1122] The "aggregation means" is a means for aggregating all inquiries and emotional information from users and generating statistical data.

[1123] "Statistical data" is data that has been compiled and analyzed to reveal trends and patterns.

[1124] "Report" means a report prepared based on the generated statistical data and provided to the manufacturer.

[1125] "Manufacturer" is the company that makes the equipment you use and receives information for improvements.

[1126] This invention relates to a system that combines an emotion analysis engine that recognizes user emotions, accepts inquiries about home appliances and device usage in chat format, analyzes the user's question, and provides the most appropriate answer. This system communicates between a server, a terminal, and the user, and uses the following hardware and software:

[1127] Hardware and Software

[1128] 1. Server

[1129] Hardware: High-performance servers installed in a data center

[1130] Software: Natural Language Processing (NLP) libraries (e.g., SpaCy, NLTK), sentiment analysis engines (e.g., IBM Watson, Google Cloud Natural Language API), database management systems (e.g., MySQL, PostgreSQL)

[1131] 2. Terminal

[1132] Hardware: Your laptops, desktops, and smartphones

[1133] Software: Web browser or dedicated application

[1134] 3. Network

[1135] Internet connection: Communications infrastructure that provides high-speed and stable internet connection

[1136] System operation procedure

[1137] The system is implemented in the following way.

[1138] 1. A user accesses the chat interface using a device, types a specific question into the text box, for example, "What can I do about error code E23 on my XYZ refrigerator?", and presses the send button.

[1139] 2. The server receives the query message sent by the user and passes it to natural language processing (NLP) software, at which point the server uses NLP libraries to parse the text data and extract key information such as the device type (e.g., XYZ refrigerator) and the error code (e.g., E23).

[1140] 3. The server uses a sentiment analysis engine to identify emotions from the text provided by the user. For example, if the user types a phrase like "I'm very worried," the sentiment analysis engine will identify emotions like "confused" or "anxious," and send this information back to the server.

[1141] 4. Based on the analyzed emotion information and the results of natural language processing, the server accesses the database and retrieves the relevant instruction manual data, such as "indicates poor cooling, check the power supply, and clean the filter" that describes specific solutions.

[1142] 5. The server generates a response that takes into account the user's emotional information. For example, it generates a response such as "Error code E23 indicates poor cooling. Please be reassured. Check the power supply and clean the filter." and adjusts the expression to take the user's emotional information into account.

[1143] 6. The server sends the generated answer to the user's device, and the user confirms the answer through the chat interface.

[1144] 7. The server records all user inquiries and sentiment information in a database, periodically aggregates them to generate statistical data, and then creates reports based on the statistical data and provides them to manufacturers, allowing them to obtain useful information for improving their products and support systems.

[1145] Examples and prompts

[1146] The user types and sends the following into the chat on their device: "Can you tell me about the error code E23 on my XYZ refrigerator? I'm having a lot of trouble." The server receives this query and uses natural language processing software to extract "XYZ refrigerator" and "E23." The server then uses a sentiment analysis engine to identify the emotion "confused." Based on this information, the server retrieves "solutions to E23" from a database and generates an answer that takes the user's emotions into consideration. For example, the server might generate an answer like, "Error code E23 indicates poor cooling. Please rest assured. Check the power and clean the filter." The server then sends the generated answer to the device, where the user can view it in the chat interface. The server records all data in a database for later statistical analysis.

[1147] This system provides an environment where users can solve problems efficiently and with peace of mind, and helps manufacturers improve the quality of their products based on user sentiment while reducing the burden on customer support.

[1148] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1149] Step 1:

[1150] A user accesses the chat interface using a device. For example, he opens an application on a smartphone or PC, types "Please tell me about the error code E23 on the XYZ refrigerator" in the chat box, and presses the send button. This input generates the user's inquiry, which is sent to the server as text data.

[1151] Step 2:

[1152] The server receives a query message from a user. The received data (textual query content) is added to the processing queue. Specifically, the received data is temporarily stored and sent to the next processing step. In this case, the input is the user's query text, and the output is the query data waiting to be parsed.

[1153] Step 3:

[1154] The server passes the received query message to natural language processing software. In this process, an NLP library (e.g., SpaCy or NLTK) is used to extract "device type" and "error code" from the text data. Specifically, "XYZ refrigerator" and "E23" are extracted from the text "Please tell me about error code E23 for XYZ refrigerator." The input is the user's text data, and the output is the extracted key information (device type and error code).

[1155] Step 4:

[1156] The server uses a sentiment analysis engine to identify emotions from the user's text. For example, if the text contains the phrase "I'm very worried," the sentiment analysis engine (e.g., IBM Watson or Google Cloud Natural Language API) will identify emotions such as "confused" or "anxious." The input is the user's text data, and the output is the analyzed emotional information.

[1157] Step 5:

[1158] The server accesses the database based on the analysis results and retrieves the relevant instruction manual data. Specifically, it executes a database query to retrieve a solution such as "Error code E23 indicates poor cooling; check the power supply and clean the filter." The input is the analyzed key information (device type and error code), and the output is the relevant instruction manual data.

[1159] Step 6:

[1160] The server generates a response that takes the user's emotions into consideration. Specifically, based on the analyzed emotional information, it creates a polite response such as, "Error code E23 indicates poor cooling. Please rest assured. Check the power supply and clean the filter." The input is the acquired instruction manual data and emotional information, and the output is an optimized response.

[1161] Step 7:

[1162] The server sends the generated answer to the user's device. Specifically, this answer is delivered to the user through the chat interface. The input is the generated answer, and the output is a notification sent to the user's device.

[1163] Step 8:

[1164] The user checks the reply sent from the server through the chat interface on their device. The user reads the reply and takes specific action. In this step, the user displays the reply they received and takes action based on the information.

[1165] Step 9:

[1166] The server records all user inquiries and emotional information in a database. The input is all inquiry data and emotional information, and the output is records stored in the database. These records are periodically aggregated and analyzed as statistical data, and reports are generated.

[1167] Step 10:

[1168] The server creates a report based on the generated statistical data and provides it to the manufacturer, which then obtains information that is useful for improving the product and reviewing the support system. The input is statistical data, and the output is a report provided to the manufacturer.

[1169] (Application example 2)

[1170] 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."

[1171] Conventional inquiry response systems provide mechanical answers without considering the user's feelings, which often leaves users unable to resolve their problems with peace of mind. Furthermore, manufacturers have been limited in their ability to improve customer satisfaction because they have not reviewed their support systems or improved their products based on user feelings.

[1172] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving an inquiry from a user through a chat interface; natural language processing means for analyzing the received inquiry and identifying information about related devices; means for retrieving the relevant instruction manual from a database based on the identified information and generating a response to the inquiry; means for notifying the user of the generated response; means for analyzing the user's emotions using an emotion recognition model and adjusting the expression of the response based on the emotions; means for aggregating all inquiry contents and emotional information from users and generating statistical data; and means for creating a report based on the statistical data and providing it to the manufacturer. This makes it possible to provide an answer that takes user emotions into consideration, allowing users to solve problems with peace of mind and also enabling manufacturers to improve their products and review their support systems based on user emotional information.

[1173] "User" refers to a person who uses the system to make an inquiry.

[1174] "Inquiry" refers to a question or request entered by a user through the chat interface regarding the handling of a home appliance or device.

[1175] "Chat interface" refers to a communication method that allows users to type and submit questions in a text box.

[1176] "Analysis" refers to analyzing the content of the received inquiry and understanding the meaning and elements of the question.

[1177] "Natural language processing means" refers to technical means for analyzing the content of a user's inquiry and identifying relevant information.

[1178] A "database" refers to an information storage device for storing information such as equipment instruction manuals and solutions to error codes.

[1179] An "emotion recognition model" refers to the algorithms or software used to identify emotions from a user's text.

[1180] "Answer" refers to a solution or instruction provided to the user based on the analyzed information.

[1181] "Notification" refers to the act of sending the generated answer to the user.

[1182] "Statistical data" refers to data that has been compiled and analyzed based on inquiries and their emotional information obtained from multiple users.

[1183] "Report" means a report prepared based on statistical data and provided to a manufacturer.

[1184] "Manufacturer" refers to the company or entity that provides the product to the user.

[1185] This invention relates to a smartphone application called "Smart Shopping Assistant" that supports shopping in brick-and-mortar stores. The following describes a system that specifically realizes this "Smart Shopping Assistant."

[1186] Users access the chat interface on the application using their smartphones. They make inquiries by entering a question in the text box and pressing the send button. For example, they can enter a specific question such as, "I don't know how to use this washing machine."

[1187] The server receives inquiries from users and passes the contents of those inquiries to a natural language processing means. The natural language processing means analyzes the content of the question and extracts corresponding product information and operation instructions. This is done using Python and NLTK (Natural Language Toolkit). The analyzed information includes the type of product and operation instructions.

[1188] Next, the server uses an emotion recognition model to analyze the emotion from the user's question. For emotion recognition, the Hugging Face emotion recognition model is used. For example, if a user uses the phrase "I'm very troubled," the emotion recognition model identifies emotions such as "confusion" or "anxiety." The emotion recognition model identifies the emotion from the text and returns that information to the server.

[1189] The server adjusts the wording of the response to the user based on the identified emotional information. For example, if the user is in trouble, it generates an answer using more polite and reassuring language. Based on the emotional information and analysis results, the server accesses a database to obtain relevant product information and operation instructions. The database stores product instruction manuals and FAQs. The information returned from this database is compiled by the answer generation means in a format appropriate for the user.

[1190] For example, a response such as "This washing machine is easy to operate. First, press the power button, select a program, and then press the start button" is generated. The generated response is sent from the server to the device and notified to the user. The user can check the response through the chat interface on their smartphone.

[1191] Furthermore, the server records all user inquiries and emotional information in a database. The recorded data is periodically compiled and analyzed as statistical data. Reports are created based on this statistical data and provided to manufacturers. Furthermore, by analyzing the emotional information as well, it is possible to improve products and review support systems based on user emotions.

[1192] For example, if many users express feelings of "confusion" or "anxiety" about a particular operation, the system will provide an explanation of that operation or strengthen the relevant section of the instruction manual. In this way, the system of the present invention provides an environment where users can solve problems efficiently and with peace of mind, and manufacturers can use this information to improve the quality of their products based on user feelings while reducing the burden on customer support.

[1193] Specific examples

[1194] If a user types a question like "My vacuum cleaner isn't working, what should I do?", the server can use an emotion recognition model to identify the user's emotion as "confused" and generate a polite and reassuring response based on that. An example prompt would look like this:

[1195] plaintext

[1196] "User input: 'My vacuum cleaner isn't working, what should I do?' Identify the sentiment and generate the best answer."

[1197] The generated answer will notify the user in the form of "Don't worry. Here are some possible reasons why your vacuum cleaner isn't working: Make sure the power cord is securely connected..."

[1198] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1199] Step 1:

[1200] The user uses a terminal to access the chat interface of the smart shopping assistant and inputs a question. The input is the user's question (e.g., "I don't know how to use this washing machine.") This question is sent to the server.

[1201] Step 2:

[1202] The server passes the received question to a natural language processing tool and analyzes the inquiry. Specifically, it uses Python and NLTK to tokenize the question and extract nouns and proper nouns. The input is the user's question, and the output is information such as the type of device and how to operate it.

[1203] Step 3:

[1204] The server uses an emotion recognition model to analyze the emotion from the user's question. Specifically, it uses the Hugging Face emotion recognition model to analyze the text and identify the user's emotion (e.g., "confused" or "anxious"). The input is the user's question, and the output is the user's emotional information.

[1205] Step 4:

[1206] The server generates a response appropriate for the user based on the emotional information and the results of natural language processing. Specifically, it creates responses using expressions that take the user's emotions into consideration. For example, if the user is confused, it uses polite expressions such as "Don't worry." Emotional information and device information are input, and a polite and reassuring response is output.

[1207] Step 5:

[1208] The server accesses the database to obtain relevant product information and operating instructions. Specifically, it searches the database for product instruction manuals and FAQs and extracts the necessary information. The input is device information, and the output is the relevant instruction manual and operating instructions.

[1209] Step 6:

[1210] The server generates a final answer and notifies the user. The generated answer is sent to the user's device, where the user can confirm it through the chat interface. The generated answer is the input, and the notified answer is the output.

[1211] Step 7:

[1212] The server records all inquiry content and emotion information in a database. Specifically, it periodically aggregates the inquiry content and emotion information to generate statistical data. All inquiry content and emotion information are input, and statistical data is obtained as output.

[1213] Step 8:

[1214] The server creates a report based on the statistical data and provides it to the manufacturer. Specifically, it compiles the data analysis results into a report format so that the manufacturer can improve their product and review their support system based on user sentiment information. The input is statistical data, and the output is a report that is provided to the manufacturer.

[1215] 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.

[1216] 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.

[1217] 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.

[1218] 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.

[1219] FIG. 9 illustrates 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 behaviors 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.

[1220] 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.

[1221] 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).

[1222] 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.

[1223] 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."

[1224] 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.

[1225] 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).

[1226] 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.

[1227] 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.

[1228] 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.

[1229] 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.

[1230] 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.

[1231] 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.

[1232] 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.

[1233] 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.

[1234] 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.

[1235] 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.

[1236] The following is further disclosed regarding the above embodiment.

[1237] (Claim 1)

[1238] means for receiving inquiries from users through a chat interface;

[1239] natural language processing means for analyzing the received query and identifying relevant device information;

[1240] A means for retrieving a corresponding instruction manual from a database based on the identified information and generating a response to the inquiry;

[1241] means for notifying the user of the generated answer;

[1242] means for aggregating all inquiries from users and generating statistical data;

[1243] A means to create reports based on statistical data and provide them to manufacturers,

[1244] A system including:

[1245] (Claim 2)

[1246] 2. The system according to claim 1, wherein the natural language processing means identifies the type of device and an error code.

[1247] (Claim 3)

[1248] 10. The system of claim 1, further comprising a database for recording and analyzing user inquiries via the chat interface.

[1249] "Example 1"

[1250] (Claim 1)

[1251] means for receiving inquiries from users through a chat interface;

[1252] natural language processing means for analyzing the received query and identifying relevant device information;

[1253] A means for retrieving a corresponding instruction manual from a database based on the identified information and generating a response to the inquiry;

[1254] means for notifying the generated answer to the user's terminal;

[1255] means for aggregating all inquiries from users and generating statistical data;

[1256] A means for generating reports based on the generated statistical data and providing them to manufacturers;

[1257] A system including:

[1258] (Claim 2)

[1259] 2. The system of claim 1, wherein the natural language processing means identifies the type of device and a fault code.

[1260] (Claim 3)

[1261] 10. The system of claim 1, further comprising a database for recording and analyzing user inquiries via the chat interface.

[1262] "Application Example 1"

[1263] (Claim 1)

[1264] means for receiving inquiries from users through a chat interface;

[1265] natural language processing means for analyzing the received query and identifying relevant device information;

[1266] A means for retrieving a corresponding instruction manual from a database based on the identified information and generating a response to the inquiry;

[1267] means for notifying the user of the generated answer;

[1268] means for aggregating all inquiries from users and generating statistical data;

[1269] A means to generate reports based on statistical data and provide them to manufacturers;

[1270] A means for using a generative AI model to receive inquiries about machine anomalies and problems in the manufacturing process and provide appropriate maintenance procedures;

[1271] A system including:

[1272] (Claim 2)

[1273] 2. The system according to claim 1, wherein the natural language processing means identifies the type of device and an error code.

[1274] (Claim 3)

[1275] 10. The system of claim 1, further comprising a database for recording and analyzing user inquiries via the chat interface.

[1276] "Example 2: Combining Emotion Engines"

[1277] (Claim 1)

[1278] means for receiving inquiries from users through a chat interface;

[1279] natural language processing means for analyzing the received query and identifying relevant device information;

[1280] A means for retrieving a corresponding instruction manual from a database based on the identified information and generating a response to the inquiry;

[1281] emotion analysis means for analyzing the emotions of a user;

[1282] a means for adjusting the wording of the response based on the results of the sentiment analysis;

[1283] means for notifying the user of the generated answer;

[1284] A means for aggregating all inquiries and emotional information from users to generate statistical data;

[1285] A means to generate reports based on statistical data and provide them to manufacturers;

[1286] A system including:

[1287] (Claim 2)

[1288] 2. The system according to claim 1, wherein the natural language processing means identifies the type of device and the error code, and further identifies the user's emotions.

[1289] (Claim 3)

[1290] 10. The system of claim 1, further comprising a database for recording and analyzing user inquiries and emotional information via the chat interface.

[1291] "Application example 2 when combining emotion engines"

[1292] (Claim 1)

[1293] means for receiving inquiries from users through a chat interface;

[1294] natural language processing means for analyzing the received query and identifying relevant device information;

[1295] A means for retrieving a corresponding instruction manual from a database based on the identified information and generating a response to the inquiry;

[1296] means for notifying the user of the generated answer;

[1297] means for analyzing a user's emotion using an emotion recognition model and adjusting the expression of the answer based on the emotion;

[1298] A means for aggregating all inquiries and emotional information from users to generate statistical data;

[1299] A means to generate reports based on statistical data and provide them to manufacturers;

[1300] A system including:

[1301] (Claim 2)

[1302] 2. The system according to claim 1, wherein the natural language processing means identifies the type of device and an error code.

[1303] (Claim 3)

[1304] 10. The system of claim 1, further comprising a database for recording and analyzing user inquiries and user emotional information via a chat interface. [Explanation of symbols]

[1305] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving inquiries from users through a chat interface; natural language processing means for analyzing the received query and identifying relevant device information; A means for retrieving a corresponding instruction manual from a database based on the identified information and generating a response to the inquiry; means for notifying the user of the generated answer; means for aggregating all inquiries from users and generating statistical data; A means to create reports based on statistical data and provide them to manufacturers, A system including:

2. 2. The system according to claim 1, wherein the natural language processing means identifies the type of device and an error code.

3. 10. The system of claim 1, further comprising a database for recording and analyzing inquiries from users via the chat interface.

Images