System

Abstract

A system is provided.SOLUTION: A system, comprising: a question receiving means for providing an appropriate answer to a question from a user in an online community platform using a generative artificial intelligence model; a generating means for sending a question content to the generative artificial intelligence model and generating an answer; and an answer outputting means for displaying the generated answer to the user.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] Online communities are places where many members participate and a wide variety of topics and issues are discussed. However, when users have questions or concerns, it can be difficult to obtain a prompt and appropriate answer. It is also not easy to organize the information scattered throughout the community and provide useful information to users. Furthermore, if discussions are not actively held, the appeal of the community and members' motivation to participate can decline. The purpose of the present invention is to solve these problems. [Means for solving the problem]

[0005] The present invention provides a system for supporting the operation of an online community platform using a generative artificial intelligence model. The system described in claim 1 includes a question receiving means, a generating means, and an answer output means for receiving a question from a user, transmitting the question to a generative artificial intelligence model, generating an appropriate answer, and displaying it to the user. The system described in claim 2 includes a search receiving means, an analyzing means, and an information display means for analyzing past posts and related materials in the community and providing useful information based on the user's search keywords. The system described in claim 3 further includes a new topic generating means, a topic notification means, and a comment notification means for generating a new topic using a generative artificial intelligence model, notifying the user, and receiving user comments and notifying other users, in order to stimulate discussion within the community. This improves the efficiency of online community operation and enhances user convenience.

[0006] A "generative artificial intelligence model" is a type of artificial intelligence equipped with algorithms that analyze past data and trends and generate new information and answers.

[0007] An "online community platform" is an internet service that allows multiple users to participate and discuss and share information on various topics.

[0008] The "question receiving means" is a technical means for receiving questions posted by users.

[0009] "Generation means" refers to the technical means for analyzing the received question and generating an appropriate answer.

[0010] "Answer output means" refers to a technical means for displaying the generated answer to the user.

[0011] "Search receiving means" refers to the technical means for receiving search keywords entered by the user.

[0012] "Analysis means" refers to a technical means of using a generative artificial intelligence model to analyze past posts and related materials within a community and collect relevant information.

[0013] "Information display means" refers to a technical means for organizing the analyzed information and displaying it to the user.

[0014] "New topic generation means" refers to a technical means for generating new topics or questions using a generative artificial intelligence model.

[0015] "Topic notification means" refers to a technical means for notifying users of new topics that have been created.

[0016] "Comment notification means" refers to a technical means for receiving a user's comment and notifying other users of it. [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] This invention is a system that utilizes generative artificial intelligence models to support the operation of an online community platform. This system realizes functions such as providing answers to questions, organizing and providing useful information, and promoting discussions.

[0039] Answers to questions

[0040] Processing Flow

[0041] 1. A user logs into an online community platform and posts a question, for example, "What is the difference between a for loop and a while loop in Python?"

[0042] 2. The terminal sends the user's input data to the server.

[0043] 3. The server passes the question to the generative AI model and requests it to generate an answer.

[0044] 4. The generative AI model analyzes the question and generates an appropriate answer. For example, the generative AI model might generate, "For loops are used to repeat a set number of times, and while loops are used to repeat while a condition is true."

[0045] 5. The server sends the generated response to the device.

[0046] 6. The device displays the answer to the user.

[0047] Providing useful information

[0048] Processing Flow

[0049] 1. A user searches for information on a specific topic, for example, typing in "helpful articles on data science."

[0050] 2. The device sends the search keywords to the server.

[0051] 3. The server passes the search keywords to the generative AI model and requests it to collect related information.

[0052] 4. The generative AI model analyzes past posts and materials and lists relevant information. For example, the generative AI model finds articles like "Data Science Introduction Articles" and "Data Analysis Basics with Python."

[0053] 5. The server sends the organized information list to the terminal.

[0054] 6. The terminal displays the information list to the user.

[0055] Facilitating discussion

[0056] Processing Flow

[0057] 1. The server periodically uses a generative artificial intelligence model to generate new topics and questions, such as "What are the technology trends for next month?"

[0058] 2. The server sends the generated topic to the terminal and notifies the user.

[0059] 3. The device displays the new topic to the user.

[0060] 4. A user posts a comment on a new topic, for example, "Advances in AI and machine learning are attracting attention."

[0061] 5. The device sends the comment to the server.

[0062] 6. The server receives the comment and notifies the other users' terminals.

[0063] 7. Other users join the discussion, making it more lively.

[0064] By implementing this system, it is possible to improve the efficiency of online community management and enhance user convenience. By using a generative AI model, it is possible to provide quick and accurate answers to questions, organize information within the community, provide useful information, and stimulate discussions.

[0065] The processing flow will be explained below.

[0066] Answers to questions

[0067] Processing Flow

[0068] Step 1:

[0069] A user logs in to an online community platform, enters "What is the difference between a for loop and a while loop in Python?" in the question posting interface, and presses the "Submit" button.

[0070] Step 2:

[0071] The terminal sends the entered question to the server.

[0072] Step 3:

[0073] The server passes the received question to the API of the generative artificial intelligence model and sends a request to generate an answer.

[0074] Step 4:

[0075] A generative AI model analyzes the question and generates an appropriate answer based on past discussions and a knowledge base (e.g., "A for loop is used to repeat something a set number of times, while a while loop is used to repeat something while a condition is true").

[0076] Step 5:

[0077] The generative artificial intelligence model returns the generated answer to the server.

[0078] Step 6:

[0079] The server sends the received response to the terminal.

[0080] Step 7:

[0081] The terminal displays the answer to the user.

[0082] Providing useful information

[0083] Processing Flow

[0084] Step 1:

[0085] A user types "helpful articles about data science" into the search interface of an online community platform and presses the "Search" button.

[0086] Step 2:

[0087] The terminal transmits the entered search keyword to the server.

[0088] Step 3:

[0089] The server passes the received search keywords to the API of the generative artificial intelligence model and sends a request to collect related information.

[0090] Step 4:

[0091] A generative artificial intelligence model analyzes your search keywords and lists relevant past posts and resources (e.g., "Data Science Introduction Articles" or "Data Analysis Basics with Python").

[0092] Step 5:

[0093] The generative artificial intelligence model sends the collected information back to the server.

[0094] Step 6:

[0095] The server organizes the received information list and sends it to the terminal.

[0096] Step 7:

[0097] The terminal displays the information list to the user.

[0098] Facilitating discussion

[0099] Processing Flow

[0100] Step 1:

[0101] The server periodically calls the API of the generative artificial intelligence model, requesting the generation of new topics and questions.

[0102] Step 2:

[0103] A generative artificial intelligence model analyzes past community posts and trends to generate interesting new topics and questions (e.g., "What are the technology trends next month?").

[0104] Step 3:

[0105] The generative artificial intelligence model returns the generated topics to the server.

[0106] Step 4:

[0107] The server sends the received topic to the terminal and notifies the user.

[0108] Step 5:

[0109] The device displays new topic notifications to the user.

[0110] Step 6:

[0111] A user posts a comment on a new topic saying, "Advances in AI and machine learning are attracting attention."

[0112] Step 7:

[0113] The terminal transmits the user's comments to the server.

[0114] Step 8:

[0115] The server notifies the terminals of other users of the received comments.

[0116] Step 9:

[0117] Join discussions based on notifications received by other users.

[0118] This will stimulate activity in the online community and promote information sharing among users.

[0119] Example 1

[0120] 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."

[0121] In online community management, there is a lack of means to provide quick and accurate answers to users' questions and solve problems that users are struggling with. Additionally, there is a lack of mechanisms to provide useful information on specific topics, making it difficult for users to efficiently obtain the information they need. Furthermore, it is difficult to stimulate discussions, and there is a need for means to maintain the vitality of the community.

[0122] 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.

[0123] In this invention, the server includes a question receiving means for users to log in to the online community platform and post questions, a data transmitting means for transmitting user input data to the server, an answer generating means for transmitting the received question content to the generative artificial intelligence model and generating an appropriate answer, and an answer output means for transmitting the generated answer to the terminal and displaying it to the user. This enables prompt and accurate answers to user questions. Furthermore, the server includes a search receiving means for users to search for information on a specific topic, a data transmitting means for transmitting search keywords to the server and requesting the generative artificial intelligence model to collect related information, an information searching means for analyzing related information using the generative artificial intelligence model and listing the information, and an information display means for transmitting the information list to the terminal and displaying it to the user, thereby enabling users to efficiently obtain the information they need. Furthermore, the server includes a new topic generating means for periodically generating new topics and questions, a topic notification means for transmitting the generated topics to the terminal and notifying the user, a comment transmitting means for receiving user comments and transmitting them to the server, and a comment notification means for notifying other users of the comments, thereby promoting community discussions.

[0124] The "question receiving means" is a means by which a user logs in to the online community platform and posts a question.

[0125] The "data transmission means" is a means for transmitting the data input by the user to the server.

[0126] The "answer generation means" is a means for transmitting the received question content to a generative artificial intelligence model and generating an appropriate answer.

[0127] The "answer output means" is a means for transmitting the generated answer to the terminal and displaying it to the user.

[0128] A "search receiving means" is a means by which a user searches for information on a particular topic.

[0129] "Information search means" refers to a means for analyzing related information using a generative artificial intelligence model and listing the information.

[0130] The "information display means" is a means for transmitting the information list to the terminal and displaying it to the user.

[0131] A "new topic generation means" is a means for periodically generating new topics and questions.

[0132] The "topic notification means" is a means for transmitting the generated topic to the terminal and notifying the user.

[0133] The "comment sending means" is a means for receiving user comments and sending them to the server.

[0134] The "comment notification means" is a means for notifying other users of a comment.

[0135] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes user questions and search keywords, and generates and collects appropriate answers and related information.

[0136] This invention is a system that uses a generative artificial intelligence model to support the operation of an online community platform. This system has functions such as providing answers to questions, organizing and providing useful information, and facilitating discussions.

[0137] The main hardware components of this system include a server, a terminal, and a user input device. The software used includes a generative AI model (e.g., a model known as a general generative AI model) and an API for data transmission.

[0138] First, a user logs into an online community platform. The user uses an interface to input a question or search keyword. For example, a user might post a question such as "What is the difference between a for loop and a while loop in Python?" This input is sent from the terminal to the server.

[0139] Next, the server receives the user's input data and passes it to a generative AI model. This model analyzes the question and generates an appropriate answer. For example, it might generate an answer such as, "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true." This answer is then sent from the server to the device and displayed to the user.

[0140] Additionally, when a user searches for information on a specific topic, for example, by typing "useful articles on data science," these search keywords are also sent to the server. The server passes the keywords to the generative AI model, requesting it to collect related information. The generative AI model analyzes past posts and materials and lists related information, such as "introductory articles on data science" or "basics of data analysis using Python." This list of information is then sent via the server to the device and displayed to the user.

[0141] Furthermore, to stimulate discussion, the server periodically generates new topics and questions. For example, a topic such as "What will be the technology trends next month?" is generated. This topic is sent to the device and notified to the user. Users can then post comments in response, for example, "Advances in AI and machine learning are attracting attention." These comments are then sent to the server and notified to other users, further stimulating discussion.

[0142] To understand how this system works, consider the following example prompt:

[0143] "Please explain in detail the difference between for loops and while loops in Python."

[0144] "Can you recommend some useful articles on the basics of data science?"

[0145] "I want to discuss the latest technology trends, so please generate new topics."

[0146] By inputting prompts like the ones above into the generative AI model, we can understand specifically how the system will provide answers and information. This system is designed to improve the efficiency of online community management and enhance user convenience.

[0147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0148] Answers to questions

[0149] Step 1:

[0150] A user logs in to an online community platform and posts a question. For example, they type, "What is the difference between a for loop and a while loop in Python?" This input is registered on the device as question data.

[0151] Step 2:

[0152] The terminal sends the question data to the server. The entered question data is sent to the server via an HTTP request. The format of the sent data is the question content in text format.

[0153] Step 3:

[0154] The server receives the question data and sends a request to the generative AI model. The input question data is analyzed, and the data format is converted into a format that the generative AI model can accept before being sent to the model. As the generative AI model, for example, a widely used general generative artificial intelligence model can be used.

[0155] Step 4:

[0156] The generative AI model analyzes the question and generates an appropriate answer. It analyzes the input question and generates answer data in text format based on past data and the scene. For example, it generates an answer such as, "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true."

[0157] Step 5:

[0158] The server receives the generated answer and sends it to the device. The text-format answer data returned from the generative AI model is converted into an appropriate output format (e.g., JSON format) before being sent to the device.

[0159] Step 6:

[0160] The device displays the answer to the user. It parses the received JSON data and displays it on the screen in a user-friendly format. Specifically, the display area on the browser displays the message, "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true."

[0161] Providing useful information

[0162] Step 1:

[0163] A user searches for information on a specific topic, for example, by typing "useful articles about data science." This input is registered as search data on the device.

[0164] Step 2:

[0165] The terminal sends the search keywords to the server. The entered search data is sent to the server via an HTTP request. The data sent is in the form of the search keywords in text format.

[0166] Step 3:

[0167] The server receives the search keywords and sends a request to the generative AI model. The server analyzes the input search data, converts the data format into a format that the generative AI model can accept, and then sends it to the model.

[0168] Step 4:

[0169] The generative AI model analyzes keywords and lists related information. Based on the keywords entered, it references past posts and materials to generate related information (a list of information in text format). For example, it finds information such as "Introductory articles on data science" and "The basics of data analysis using Python."

[0170] Step 5:

[0171] The server sends the organized information list to the device. The text-format information list returned by the generative AI model is converted into an appropriate output format (e.g., JSON format) and then sent to the device.

[0172] Step 6:

[0173] The device displays a list of information to the user. It parses the received JSON data and displays it on the screen in a user-friendly format. Specifically, it displays links such as "Introductory articles on data science" and "Basics of data analysis using Python."

[0174] Facilitating discussion

[0175] Step 1:

[0176] The server periodically generates new topics and questions, for example, "What are the technology trends next month?" using a generative AI model.

[0177] Step 2:

[0178] The server sends the generated topics to the terminal. The topic data generated by the generative AI model is converted into an appropriate output format (e.g., JSON format) and then sent to the terminal.

[0179] Step 3:

[0180] The device displays the new topic to the user. It parses the received JSON data and displays it as a new topic to the user. Specifically, the browser displays "New Topic: What are the technology trends for next month?"

[0181] Step 4:

[0182] A user posts a comment on a new topic. For example, they write, "The progress of AI and machine learning is attracting attention." This comment is registered on the device as comment data.

[0183] Step 5:

[0184] The device sends the comment to the server. The entered comment data is sent to the server via an HTTP request.

[0185] Step 6:

[0186] The server receives the comment and notifies the other user's device. The server converts the received comment data into an appropriate output format (for example, JSON format) and sends it to the other user's device.

[0187] Step 7:

[0188] Other users can participate in the discussion. Check the comment notifications you receive and post new comments to stimulate the discussion. For example, you could reply, "I agree. The field of deep learning is particularly advanced."

[0189] (Application example 1)

[0190] 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."

[0191] Currently, in many factories, it often takes a long time for workers to find solutions to technical questions or problems. Furthermore, workers must check multiple materials and documents to find the information they need, which is inefficient. Furthermore, a lack of real-time discussion and knowledge sharing on-site hinders information sharing and technological improvement. To solve these problems, a system is needed in which factory robots themselves can answer workers' questions, provide necessary information, and facilitate discussion.

[0192] 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.

[0193] In this invention, the server includes a question receiving means for using a generative artificial intelligence model to provide appropriate answers to questions from users on the online community platform, a generating means for sending the content of the question to the generative artificial intelligence model and generating an answer, an answer output means for displaying the generated answer to the user, a worker question receiving means for receiving questions from workers in a system incorporated in a factory robot, a robot display means for displaying the answer on a robot operation panel, a search receiving means for analyzing past posts and related materials in the online community and providing useful information to users, and a search engine for sending search keywords to the generative artificial intelligence model and collecting related information. The system includes an analysis means, an information display means for organizing the collected information and displaying it to the user, a worker information search means for allowing factory workers to search for useful information related to a specific technology, a robot information display means for displaying information on a robot operation panel, a new topic generation means for promoting discussions within an online community using a generative artificial intelligence model, a topic notification means for notifying users of the generated topics, a comment notification means for receiving user comments and notifying other users, a discussion topic generation means for promoting discussions among factory workers, and a robot comment display means for displaying comments on the robot operation panel. This enables workers to obtain answers to technical questions in real time and quickly search for and share necessary information, while also stimulating discussions on site, enabling efficient problem solving and knowledge sharing.

[0194] A "generative artificial intelligence model" is an artificial intelligence technology for generating natural language text based on input data.

[0195] An "online community platform" is a digital service that allows users to interact and share information over the Internet.

[0196] The "question receiving means" is an interface for receiving questions from users.

[0197] "Generation means" is a process for analyzing the content of a question and generating an appropriate answer using a generative artificial intelligence model.

[0198] The "answer output means" is an interface for displaying the generated answer to the user.

[0199] A "factory robot" is an industrial machine that is programmed to perform automated tasks.

[0200] The "means for receiving questions from workers" is an interface that allows the robot to receive technical questions from factory workers.

[0201] The "robot display means" is an interface for displaying data on the robot's operation panel.

[0202] The "search receiving means" is an interface that allows users to input search keywords and topics.

[0203] "Analysis means" refers to the process of analyzing input data using a generative artificial intelligence model and collecting relevant information.

[0204] The "information display means" is an interface for organizing collected information and displaying it to the user.

[0205] The "worker information search means" is an interface that allows factory workers to search for specific techniques or information.

[0206] A "discussion topic generator" is a process that generates new topics to facilitate discussion.

[0207] The "topic notification means" is an interface for notifying users of generated discussion topics.

[0208] The "comment notification means" is an interface for notifying other users of comments posted by a user.

[0209] The "robot comment display means" is an interface for displaying comments on the robot's operation panel.

[0210] This invention is a system that utilizes a generative artificial intelligence model to support factory workers. This system realizes functions such as providing answers to questions, organizing and providing useful information, and facilitating discussions.

[0211] Specifically, the following processing is performed.

[0212] The server uses the generative artificial intelligence model to provide appropriate answers to questions from factory workers. The worker inputs a question through the robot operation panel, and the data is sent to the server through a question receiving means. On the server, the generative artificial intelligence model analyzes the question and generates an appropriate answer. The generated answer is displayed on the robot operation panel through an answer output means. As a specific example, when a worker asks, "How do I troubleshoot signal analysis?", the generative artificial intelligence model responds, "To identify the root cause of the problem, first observe the signal waveform using an oscilloscope. If an abnormal pattern is found, analyze that part in more detail. Adjust the filter if necessary and check the signal regularity."

[0213] The server also provides useful materials when factory workers search for specific technologies or information. When a worker enters search keywords, the data is sent to the server through a search receiving means. On the server, a generative AI model analyzes past posts and related materials, collecting and organizing related information. The collected information is displayed on the robot operation panel through an information display means. For example, if a worker searches for "the latest methods for optimizing automation processes," the generative AI model will list "overviews of the latest research" and "concrete application examples" and provide them to the worker.

[0214] Furthermore, the server generates new topics and notifies comments to promote discussions among factory workers. New discussion topics are periodically generated by a new topic generation means and notified to workers via a topic notification means. Workers enter comments on the notified topics, and these comments are notified to other workers via the comment notification means. This process stimulates the exchange of opinions on-site and promotes problem solving and technological improvement. For example, if a topic such as "What are the technological trends for next month?" is generated and a worker comments, "Advances in AI and machine learning are attracting attention," other workers are notified and a discussion begins.

[0215] The specific implementation of this system utilizes OpenAI's GPT-3 API, which displays answers, information, and comments on the factory robot's operation panel. Workers can enter questions and comments on topics through the robot's operation panel, enabling real-time answers, information search, and discussion.

[0216] Examples of prompt sentences include:

[0217] Example 1:

[0218] "Question from a factory worker: How do I troubleshoot signal analysis?"

[0219] "Specific answer provided: To identify the root cause of the problem, first observe the signal waveform using an oscilloscope. If an abnormal pattern is found, analyze that area further. Adjust the filter as needed to check for signal regularity."

[0220] Example 2:

[0221] "Topic request from a factory worker: What are the latest techniques for optimizing automated processes?"

[0222] "Specific information provided: Provide workers with an overview of the latest research and a list of specific applications."

[0223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0224] Step 1:

[0225] A user uses the operation panel of a factory robot to input technical questions, information searches, and discussion topics. For example, the user inputs a question such as "How do I troubleshoot signal analysis?" The user's input data is sent to the server through the worker question receiving means.

[0226] Step 2:

[0227] The server uses a question receiving means to pass the question data sent by the user to the generative AI model and request that it generate an answer.The server then analyzes the input question and sends it as a prompt to the API of the generative AI model.

[0228] Step 3:

[0229] The generative AI model generates an appropriate answer based on the prompt. For example, it might generate an answer such as, "Use an oscilloscope to observe the signal waveform." The model generates answer data as natural language text by referencing past knowledge bases and case studies.

[0230] Step 4:

[0231] The server receives the answer from the generative artificial intelligence model using the generating means. The received answer data is passed directly to the answer output means, where it is processed to be displayed on the robot operation panel.

[0232] Step 5:

[0233] The terminal displays the generated answer on the user's operation panel through the answer output means, and the user can check the generated answer on the robot's operation panel and follow the specific instructions.

[0234] Step 6:

[0235] When a user searches for a specific technology or information, the user inputs search keywords using the operation panel. The search keywords are sent to the server through the search receiving means. For example, a user searches for "latest methods for optimizing automated processes."

[0236] Step 7:

[0237] The server uses the search receiving means to send search keywords to the generative artificial intelligence model and request the collection of related information. The generative artificial intelligence model analyzes related materials based on the input keywords and lists useful information.

[0238] Step 8:

[0239] The generative artificial intelligence model generates related information and transmits it to the server, which uses the information display means to organize the received related information and convert it into a display format.

[0240] Step 9:

[0241] The terminal displays the collected useful information on the operation panel through the information display means, allowing the user to check the necessary information and use it in their work.

[0242] Step 10:

[0243] The server periodically generates new discussion topics using the new topic generation means, and the generated topics are notified to users via the topic notification means.

[0244] Step 11:

[0245] A user inputs a comment on a new topic and sends it to the server via the operation panel. The input comment is notified to other users via the comment notification means.

[0246] Step 12:

[0247] The server notifies all users of comments, promoting discussion. Users can check other users' comments through the operation panel, exchange opinions, and share information.

[0248] 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.

[0249] This invention is a system that supports the operation of an online community platform by combining a generative AI model and an emotion engine. This system provides answers to questions, organizes and provides useful information, and promotes discussions, realizing interactions that respond to the user's emotional state.

[0250] Answering questions with emotion recognition

[0251] Processing Flow

[0252] 1. A user logs in to an online community platform, enters "What is the difference between a for loop and a while loop in Python?" in the question posting interface, and presses the "Submit" button.

[0253] 2. The device sends the entered question to the server.

[0254] 3. The server analyzes the user's emotional state using the emotion engine along with the content of the user's question.

[0255] 4. The server passes the question and the user's emotional state to the generative AI model and sends a request to generate an answer.

[0256] 5. A generative AI model analyzes the question and generates an appropriate answer with a tone and content that reflects the user's emotional state (e.g., "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true.").

[0257] 6. The server sends the generated response to the device.

[0258] 7. The device displays the answer to the user.

[0259] Providing useful information with emotion recognition

[0260] Processing Flow

[0261] 1. A user types "useful articles about data science" into the search interface of an online community platform and presses the "Search" button.

[0262] 2. The device sends the entered search keywords to the server.

[0263] 3. The server analyzes the user's emotional state using an emotion engine along with the received search keywords.

[0264] 4. The server passes the search keywords and the user's emotional state to the generative AI model and sends a request to collect related information.

[0265] 5. A generative AI model analyzes search keywords and lists relevant information with priority and display content based on the user's emotional state (e.g., "Introductory articles on data science" or "Basics of data analysis using Python").

[0266] 6. The server sends the organized information list to the terminal.

[0267] 7. The terminal displays the information list to the user.

[0268] Facilitating discussions with emotion awareness

[0269] Processing Flow

[0270] 1. The server periodically calls the API of the generative artificial intelligence model to request the generation of new topics and questions.

[0271] 2. Generative AI models analyze past community posts and trends to generate interesting new topics and questions (e.g., "What are the technology trends next month?").

[0272] 3. For topics generated by the generative AI model, an emotion engine is used to tailor feedback and responses according to the user's emotional state.

[0273] 4. The server sends the generated topic to the terminal and notifies the user.

[0274] 5. The device displays a new topic notification to the user.

[0275] 6. A user posts a comment on a new topic saying, "Advances in AI and machine learning are attracting attention."

[0276] 7. The device sends the user's comments to the server, and the emotion engine analyzes the user's emotional state.

[0277] 8. The server notifies other users of the received comments and emotional state.

[0278] 9. Other users can join the discussion based on the notifications they receive, further stimulating the discussion.

[0279] In this way, inventions that combine emotion engines will make online community management even more user-friendly, enabling more appropriate and personalized interactions. By providing answers, organizing information, and promoting discussions in accordance with the user's emotional state, the community will become more attractive and people willing to participate will increase.

[0280] The processing flow will be explained below.

[0281] Answering questions with emotion recognition

[0282] Processing Flow

[0283] Step 1:

[0284] A user logs in to an online community platform, enters "What is the difference between a for loop and a while loop in Python?" in the question posting interface, and presses the "Submit" button.

[0285] Step 2:

[0286] The terminal sends the entered question to the server.

[0287] Step 3:

[0288] The server receives the question and uses an emotion engine to analyze the user's emotional state, thereby determining the emotion (e.g., excitement, annoyance, confusion, etc.) at the time the user submits the question.

[0289] Step 4:

[0290] The server passes the question and the user's emotional state to a generative AI model and sends a request to generate an answer.

[0291] Step 5:

[0292] The generative AI model analyzes the question and the user's emotional state to generate an answer with the appropriate tone and content. For example, if the user is confused, the generated answer will be more polite and detailed.

[0293] Step 6:

[0294] The server receives the generated response and transmits it to the terminal.

[0295] Step 7:

[0296] The terminal displays the answer to the user.

[0297] Providing useful information with emotion recognition

[0298] Processing Flow

[0299] Step 1:

[0300] A user types "helpful articles about data science" into the search interface of an online community platform and presses the "Search" button.

[0301] Step 2:

[0302] The terminal transmits the entered search keyword to the server.

[0303] Step 3:

[0304] The server receives the search keywords and uses an emotion engine to analyze the user's emotional state, thereby determining the type of information the user is currently interested in and their emotions (e.g., excitement, curiosity, professional interest, etc.).

[0305] Step 4:

[0306] The server passes the search keywords and emotional state to a generative artificial intelligence model and sends a request to collect related information.

[0307] Step 5:

[0308] A generative artificial intelligence model analyzes search keywords and emotional state to generate a list of information with adjusted priorities and content (e.g., "Introductory articles on data science" or "Basics of data analysis using Python").

[0309] Step 6:

[0310] The server receives the generated information list and transmits it to the terminal.

[0311] Step 7:

[0312] The terminal displays the information list to the user.

[0313] Facilitating discussions with emotion awareness

[0314] Processing Flow

[0315] Step 1:

[0316] The server periodically calls the API of the generative artificial intelligence model, requesting the generation of new topics and questions.

[0317] Step 2:

[0318] A generative artificial intelligence model analyzes past community posts and trends to generate interesting new topics and questions (e.g., "What are the technology trends next month?").

[0319] Step 3:

[0320] A server receives the generated topics, analyzes the user's emotional state using an emotion engine, and generates emotional feedback related to the topics.

[0321] Step 4:

[0322] The server sends the generated topic and emotional feedback to the terminal and notifies the user.

[0323] Step 5:

[0324] The device displays new topic notifications to the user.

[0325] Step 6:

[0326] A user posts a comment on a new topic saying, "Advances in AI and machine learning are attracting attention."

[0327] Step 7:

[0328] The device sends the user's comments to the server, and the emotion engine analyzes the user's emotional state.

[0329] Step 8:

[0330] The server notifies the received comments and emotional states to the terminals of other users.

[0331] Step 9:

[0332] Other users can join the discussion based on the notifications they receive, further stimulating the discussion.

[0333] By using the above processing flow, the system of the present invention combined with the emotion engine can provide appropriate and personalized interactions according to the user's emotional state.

[0334] Example 2

[0335] 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."

[0336] In online community platforms, it is important to provide quick and appropriate answers to users' diverse questions, effectively present useful information when users search, and stimulate discussions. However, conventional systems lack interactions that take into account the user's emotional state, which has led to issues such as reduced user satisfaction and community activity.

[0337] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a question receiving means for receiving a question from a user, an answer generating means for analyzing the question content and the user's emotional state and transmitting the content to a generative AI model to generate an answer, and an answer output means for displaying the generated answer to the user. This makes it possible to provide an answer according to the user's emotional state.

[0338] The server includes a search receiving means for receiving search keywords from a user and analyzing the user's emotional state, an information collecting means for transmitting the search keywords and the user's emotional state to a generative artificial intelligence model and collecting related information, and an information display means for organizing the collected information and displaying it to the user, thereby making it possible to provide useful information according to the user's emotional state.

[0339] The server includes a new topic generation means for generating new discussion topics using a generative artificial intelligence model, a topic notification means for notifying users of the generated topics, and a comment notification means for receiving comments posted by users and notifying other users of the comments, thereby enabling the promotion of discussions.

[0340] The "question receiving means" is a function or device for receiving questions from users.

[0341] "Answer generation means" refers to a function or device that analyzes the question content and the user's emotional state, and sends the results to a generative artificial intelligence model to generate an answer.

[0342] The "answer output means" refers to a function or device for displaying the generated answer to the user.

[0343] The "search receiving means" is a function or device for receiving search keywords from a user and analyzing the user's emotional state.

[0344] "Information collection means" refers to a function or device for sending search keywords and the user's emotional state to a generative artificial intelligence model and collecting related information.

[0345] "Information display means" refers to a function or device for organizing collected information and displaying it to the user.

[0346] "New topic generation means" refers to a function or device for generating new discussion topics using a generative artificial intelligence model.

[0347] The "topic notification means" is a function or device for notifying users of the generated topic.

[0348] The "comment notification means" is a function or device for receiving comments posted by a user and notifying other users of the comments.

[0349] This invention is a management support system for an online community platform that combines a generative AI model and an emotion engine. This system answers questions with emotion recognition, provides useful information, and promotes discussion.

[0350] Functions and technologies used

[0351] Providing answers to questions

[0352] When a user logs in to an online community platform and submits a question, the terminal sends the question data to a server. The server then analyzes the user's emotional state using an emotion engine along with the received question content. In this case, the emotion engine uses what is commonly known as an emotion analysis API (e.g., an emotion analysis tool or emotion analysis technology).

[0353] The server then passes the question and the user's emotional state to a generative AI model (commonly known as an AI model) and sends a request to generate an answer. For example, a generative AI model. This generative AI model analyzes the question and generates an appropriate answer with a tone and content that matches the user's emotional state. This generated answer is then sent back from the server to the device, where it is displayed to the user.

[0354] Examples:

[0355] User Question: "What is the difference between a for loop and a while loop in Python?"

[0356] Example prompt: "The user asks, 'What is the difference between a for loop and a while loop in Python?' and their emotional state is curious. Please generate a kind and concise answer."

[0357] Providing useful information

[0358] When a user enters and submits a search keyword, the device sends the search keyword to the server. The server then uses an emotion engine to analyze the user's emotional state along with the received search keyword. The analysis uses a generically named emotion analysis API.

[0359] The server then passes the search keywords and the user's emotional state to a generative AI model and sends a request to collect related information. The generative AI model analyzes the search keywords and lists related information with priority and display content according to the user's emotional state. The organized information list is then sent back from the server to the device, where it is displayed to the user.

[0360] Examples:

[0361] User search keywords: "helpful articles about data science"

[0362] Example prompt: "A user has searched for 'helpful articles about data science' and is in an excited emotional state. Please provide a list of articles that are easy to understand and aimed at beginners."

[0363] Facilitating discussion

[0364] The server periodically calls the API of the generative AI model to request the generation of new topics and questions. The generative AI model analyzes past community posts and trends to generate interesting new topics and questions. It then uses an emotion engine to adjust the feedback and response content for the generated topics, which the server then sends to the device and notifies the user.

[0365] When a user posts a comment on a new topic, the device sends the comment to the server, where the emotion engine analyzes the user's emotional state. The server then notifies other users of the received comment and emotional state, stimulating discussions.

[0366] Examples:

[0367] New discussion topic: "What are the technology trends for next month?"

[0368] Example prompt: "Generate new discussion topics based on trends across the community. Topics that many users find entertaining and exciting."

[0369] In this way, systems that utilize emotion understanding can realize user-friendly designs for managing online communities. From selecting topics to providing content and answers, it is possible to provide optimal interactions according to the user's emotional state.

[0370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0371] Answering questions with emotion recognition

[0372] Step 1:

[0373] A user logs into an online community platform, enters a question, and presses the "Submit" button.

[0374] How it works: A user accesses the question form using a browser or a dedicated app, enters "What is the difference between a for loop and a while loop in Python?", and clicks the submit button.

[0375] Input: Text data of the question

[0376] Output: Instructions to submit a question

[0377] Step 2:

[0378] The terminal transmits the input question data to the server.

[0379] How it works: The device sends the question entered by the user to the server as an HTTP request, which includes the user ID and the question.

[0380] Input: HTTP request data (user ID, question)

[0381] Output: The request sent to the server

[0382] Step 3:

[0383] The server uses an emotion engine to analyze the question content and the user's emotional state.

[0384] How it works: The server sends the question content as an API request to the emotion engine, and analyzes the returned emotion data. The emotion engine uses the generic name emotion analysis API.

[0385] Input: Text data of the question

[0386] Output: Emotional information (e.g. curious, confused)

[0387] Step 4:

[0388] The server sends the question and the user's emotional state to the generative AI model and sends a request to generate an answer.

[0389] Operation: The server generates a prompt containing the question and emotion data for the API of the generative AI model, and sends an API request.

[0390] Input: Question content, emotion data

[0391] Output: Answer generation request

[0392] Step 5:

[0393] A generative AI model analyzes the question and generates an answer with a tone and content that reflects the user's emotional state.

[0394] How it works: The model parses the prompt and generates an appropriate answer, which is returned to the server as an API response.

[0395] Input: Prompt sentence (question content, emotion data)

[0396] Output: The generated answer

[0397] Step 6:

[0398] The server sends the generated response to the terminal.

[0399] How it works: The server sends a response containing the generated answer to the device as an HTTP request.

[0400] Input: Generated answer

[0401] Output: Sending response data

[0402] Step 7:

[0403] The terminal displays the answer to the user.

[0404] Operation: The device displays the received response data on the screen, providing visual feedback to the user.

[0405] Input: Response data

[0406] Output: Update the screen display

[0407] Providing useful information with emotion recognition

[0408] Step 1:

[0409] A user enters keywords into the search interface of an online community platform and presses the "Search" button.

[0410] What happens: A user enters "helpful articles about data science" into the search form and clicks the search button.

[0411] Input: Search keyword text data

[0412] Output: Search submission instructions

[0413] Step 2:

[0414] The terminal transmits the entered search keyword to the server.

[0415] How it works: The device sends the search keyword to the server as an HTTP request. The request includes the user ID and the search keyword.

[0416] Input: HTTP request data (user ID, search keywords)

[0417] Output: The request sent to the server

[0418] Step 3:

[0419] The server analyzes the received search keywords and the user's emotional state using an emotion engine.

[0420] How it works: The server sends search keywords as API requests to the emotion engine and analyzes the returned emotion data.

[0421] Input: Search keyword text data

[0422] Output: Emotional information (e.g., excited, relaxed)

[0423] Step 4:

[0424] The server sends the search keywords and the user's emotional state to a generative artificial intelligence model and sends a request to collect related information.

[0425] How it works: The server generates a prompt containing search keywords and emotion data for the API of the generative AI model and sends an API request.

[0426] Input: Search keywords, emotion data

[0427] Output: Information collection request

[0428] Step 5:

[0429] A generative artificial intelligence model analyzes search keywords and lists relevant information based on priority and content.

[0430] How it works: The model parses the prompt, gathers the appropriate information, and generates a list, which is returned to the server as an API response.

[0431] Input: Prompt sentence (search keywords, emotion data)

[0432] Output: Generated information list

[0433] Step 6:

[0434] The server transmits the generated information list to the terminal.

[0435] Operation: The server sends a response containing the generated information list to the terminal as an HTTP request.

[0436] Input: Generated information list

[0437] Output: Sending a list of information

[0438] Step 7:

[0439] The terminal displays the information list to the user.

[0440] Operation: The device displays the received information list on the screen, providing visual feedback to the user.

[0441] Input: Information List

[0442] Output: Update the screen display

[0443] Facilitating discussions with emotion awareness

[0444] Step 1:

[0445] The server periodically calls the API of the generative artificial intelligence model, requesting the generation of new topics and questions.

[0446] How it works: The server sets up a periodic job and calls the API of the generative AI model at specific time intervals.

[0447] Input: Trigger signal for periodic job

[0448] Output: New topic creation request

[0449] Step 2:

[0450] A generative artificial intelligence model analyzes past community posts and trends to generate interesting new topics and questions.

[0451] How it works: The model analyzes historical data and generates new topics, which are then returned to the server as API responses.

[0452] Input: Prompt text (past posting data, trend information)

[0453] Output: Generated topics

[0454] Step 3:

[0455] The generative artificial intelligence model uses an emotion engine to analyze the user's emotional state and adjust the feedback depending on the topic.

[0456] How it works: For each topic, sentiment analysis is performed to tailor feedback based on the user's past sentiment data.

[0457] Input: Generated topics

[0458] Output: Sentiment analysis feedback

[0459] Step 4:

[0460] The server sends the generated topic to the terminal and notifies the user.

[0461] Operation: The server sends the generated topic to the terminal as a notification message.

[0462] Input: Generated topics

[0463] Output: Topic notification data

[0464] Step 5:

[0465] The device displays new topic notifications to the user.

[0466] Behavior: The device displays a notification message in a pop-up window or in the notification bar.

[0467] Input: Topic notification data

[0468] Output: On-screen notification

[0469] Step 6:

[0470] A user enters a comment on a new topic and clicks the post button.

[0471] What happens: A user enters their opinion into the comment form and clicks the post button.

[0472] Input: Text data of comment content

[0473] Output: Instructions to send comments

[0474] Step 7:

[0475] The terminal transmits the user's comments to the server.

[0476] How it works: The device sends the user's comments as an HTTP request to the server, and the server analyzes the user's emotional state using an emotion engine.

[0477] Input: HTTP request data (user ID, comment content)

[0478] Output: Send comment data

[0479] Step 8:

[0480] The server notifies the received comments and emotional states to the terminals of other users.

[0481] How it works: The server sends notification messages to other relevant users based on the comments and emotion data.

[0482] Input: Comment content, emotion data

[0483] Output: Comment notification data

[0484] Step 9:

[0485] Other users join the discussion, making it more lively.

[0486] What happens: Other users see the notification, join the discussion, and post comments.

[0487] Enter: Comment Notification

[0488] Output: Stimulating discussion

[0489] This will create an online community management support system that utilizes emotion recognition and generative AI models. The system will provide appropriate answers according to the user's emotional state, present useful information, and promote discussion.

[0490] (Application example 2)

[0491] 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."

[0492] In online and real-world environments, it is important to provide appropriate interactions without being hindered by the emotional state of users and customers. However, existing systems do not take the emotional state of users and customers into account, which can lead to reduced satisfaction and effectiveness. In addition, providing information and promoting discussions is done uniformly without adapting to the emotional state, which creates the challenge of not being able to provide services tailored to individual needs.

[0493] The specific processing by the specific 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 a question receiving means, a generating means, an answer output means, a sentiment analysis means, and an answer adjustment means. This makes it possible to adjust answers based on the emotional state of the user or customer and provide more personalized interactions. In addition, by using an information priority adjustment means, the priority of information provided to the user can be adjusted according to the emotional state, and by using a discussion activation means, lively discussions based on sentiment analysis can be promoted.

[0494] The "question receiving means" is a system or device for receiving questions from users.

[0495] The "generation means" is a system or device that generates an answer using a generative artificial intelligence model based on the content of the received question.

[0496] The "answer output means" is a system or device for displaying or providing the generated answer to the user.

[0497] An "emotion analysis means" is a system or device for analyzing emotions using facial expressions and other data of a customer.

[0498] The "answer adjustment means" is a system or device for adjusting the tone and content of the generated answer based on the emotion data obtained by the emotion analysis means.

[0499] The "search receiving means" is a system or device for receiving search keywords from a user.

[0500] "Analysis means" refers to a system or device for sending search keywords to a generative artificial intelligence model and collecting related information.

[0501] "Information display means" refers to a system or device for organizing collected information and displaying it to the user.

[0502] The "information priority adjustment means" is a system or device for adjusting the priority of collected information in consideration of the emotional state of the user obtained by emotion analysis.

[0503] A "new topic generation means" is a system or device for generating new topics using a generative artificial intelligence model.

[0504] The "topic notification means" is a system or device for notifying users of generated topics.

[0505] The "comment notification means" is a system or device for receiving a user's comment and notifying other users of the comment.

[0506] The "discussion activation means" is a system or device for activating discussions using sentiment analysis.

[0507] This invention is a system that combines a generative artificial intelligence model and an emotion analysis engine to improve customer experience in brick-and-mortar stores. A specific example of this system is described below.

[0508] System configuration

[0509] The system comprises a question receiving means, a generating means, an answer output means, a sentiment analysis means, and an answer adjustment means.

[0510] 1. How to receive questions:

[0511] Questions from users are received through a smartphone application, which has an interface that allows users to freely input questions.

[0512] 2. Generation means:

[0513] A question is sent via an online API to a generative artificial intelligence model (e.g., GPT-4 (registered trademark)), which analyzes the question and generates an appropriate answer.

[0514] 3. Answer output means:

[0515] This is a means for displaying the generated answers to the user. The answers are displayed on the smartphone application.

[0516] 4. Emotion analysis means:

[0517] The customer's facial expressions are captured using a smartphone camera and analyzed using an emotion analysis engine (e.g., Microsoft® Azure® Emotion API), which allows the customer's current emotional state to be identified.

[0518] 5. Response adjustment method:

[0519] The responses generated by the generative AI model are adjusted based on emotional data obtained through sentiment analysis. For example, if a customer is feeling stressed, the system will provide responses in a more relaxing tone.

[0520] System Operation

[0521] This system uses the following hardware and software:

[0522] Hardware

[0523] Smartphone (iOS or ANDROID (registered trademark))

[0524] Server (Linux (registered trademark) server)

[0525] Camera (built-in camera on smartphone)

[0526] software

[0527] Emotion engine (Microsoft Azure Emotion API)

[0528] Generative AI model (using GPT-4)

[0529] App development framework (React Native)

[0530] Database (MySQL (registered trademark) or PostgreSQL)

[0531] Data processing and calculation

[0532] The data is processed and calculated as follows:

[0533] Customer facial expression data is captured by a camera and their emotional state is analyzed using an emotion analysis engine.

[0534] Based on your emotional state, the responses generated by the generative AI model are adjusted to optimize tone and content.

[0535] Specific examples

[0536] A customer types "Tell me about the latest trending products" into a smartphone app and submits it. At this time, the smartphone camera captures the customer's face and performs emotional analysis. As a result, the generative AI model generates a tone-adjusted response based on the customer's emotional state, such as "Here are the latest trending products. They have a particularly relaxing effect, making them perfect for when you're tired," and displays it on the smartphone.

[0537] Prompt Sentence Examples

[0538] User prompt: "What are the latest trending products?"

[0539] This will enable a more personalized customer experience in physical stores and improve customer satisfaction.

[0540] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0541] Step 1:

[0542] A user inputs a question into a smartphone app. For example, "What are the latest trending products?" and presses the send button. The input includes the user's question text. The device receives this question data and sends it to the server.

[0543] Step 2:

[0544] The server receives question data sent by the user. The received data includes the user's question text. The server sends this question text to a generative AI model and requests it to generate an answer.

[0545] Step 3:

[0546] A generative AI model generates an answer based on the question received from the server. The input includes the user's question text. The model analyzes the question, generates an appropriate answer text, and sends it back to the server.

[0547] Step 4:

[0548] The server receives the answer text received from the generative AI model. The received data includes the generated answer text. The server temporarily stores this answer and waits until it receives emotion data from the device.

[0549] Step 5:

[0550] The device captures the user's facial expressions using the smartphone's built-in camera and sends them to the emotion analysis engine. The input data includes facial expression images. The device receives the emotion data as the analysis result and sends it to the server.

[0551] Step 6:

[0552] The server receives the emotion data sent from the emotion analysis engine. The received data includes the user's emotional state. Based on the emotion data, the server sends a request to the generative AI model to adjust the pre-generated answer text.

[0553] Step 7:

[0554] A generative AI model adjusts the response text based on the emotion data received from the server. The input includes the stored response text and emotion data. The model adjusts the tone of the response to match the user's emotional state and sends the adjusted response text back to the server.

[0555] Step 8:

[0556] The server transmits the adjusted answer text to the terminal. The received data includes the answer text adjusted to match the emotional state.

[0557] Step 9:

[0558] The device displays the adjusted answer text to the user, who then accepts the answer displayed on the smartphone app to complete the interaction.

[0559] 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.

[0560] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0561] 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.

[0562] [Second embodiment]

[0563] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0564] 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.

[0565] 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).

[0566] 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.

[0567] 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.

[0568] 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).

[0569] 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.

[0570] 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.

[0571] 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.

[0572] 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.

[0573] 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.

[0574] 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."

[0575] This invention is a system that utilizes generative artificial intelligence models to support the operation of an online community platform. This system realizes functions such as providing answers to questions, organizing and providing useful information, and promoting discussions.

[0576] Answers to questions

[0577] Processing Flow

[0578] 1. A user logs into an online community platform and posts a question, for example, "What is the difference between a for loop and a while loop in Python?"

[0579] 2. The terminal sends the user's input data to the server.

[0580] 3. The server passes the question to the generative AI model and requests it to generate an answer.

[0581] 4. The generative AI model analyzes the question and generates an appropriate answer. For example, the generative AI model might generate, "For loops are used to repeat a set number of times, and while loops are used to repeat while a condition is true."

[0582] 5. The server sends the generated response to the device.

[0583] 6. The device displays the answer to the user.

[0584] Providing useful information

[0585] Processing Flow

[0586] 1. A user searches for information on a specific topic, for example, typing in "helpful articles on data science."

[0587] 2. The device sends the search keywords to the server.

[0588] 3. The server passes the search keywords to the generative AI model and requests it to collect related information.

[0589] 4. The generative AI model analyzes past posts and materials and lists relevant information. For example, the generative AI model finds articles like "Data Science Introduction Articles" and "Data Analysis Basics with Python."

[0590] 5. The server sends the organized information list to the terminal.

[0591] 6. The terminal displays the information list to the user.

[0592] Facilitating discussion

[0593] Processing Flow

[0594] 1. The server periodically uses a generative artificial intelligence model to generate new topics and questions, such as "What are the technology trends for next month?"

[0595] 2. The server sends the generated topic to the terminal and notifies the user.

[0596] 3. The device displays the new topic to the user.

[0597] 4. A user posts a comment on a new topic, for example, "Advances in AI and machine learning are attracting attention."

[0598] 5. The device sends the comment to the server.

[0599] 6. The server receives the comment and notifies the other users' terminals.

[0600] 7. Other users join the discussion, making it more lively.

[0601] By implementing this system, it is possible to improve the efficiency of online community management and enhance user convenience. By using a generative AI model, it is possible to provide quick and accurate answers to questions, organize information within the community, provide useful information, and stimulate discussions.

[0602] The processing flow will be explained below.

[0603] Answers to questions

[0604] Processing Flow

[0605] Step 1:

[0606] A user logs in to an online community platform, enters "What is the difference between a for loop and a while loop in Python?" in the question posting interface, and presses the "Submit" button.

[0607] Step 2:

[0608] The terminal sends the entered question to the server.

[0609] Step 3:

[0610] The server passes the received question to the API of the generative artificial intelligence model and sends a request to generate an answer.

[0611] Step 4:

[0612] A generative AI model analyzes the question and generates an appropriate answer based on past discussions and a knowledge base (e.g., "A for loop is used to repeat something a set number of times, while a while loop is used to repeat something while a condition is true").

[0613] Step 5:

[0614] The generative artificial intelligence model returns the generated answer to the server.

[0615] Step 6:

[0616] The server sends the received response to the terminal.

[0617] Step 7:

[0618] The terminal displays the answer to the user.

[0619] Providing useful information

[0620] Processing Flow

[0621] Step 1:

[0622] A user types "helpful articles about data science" into the search interface of an online community platform and presses the "Search" button.

[0623] Step 2:

[0624] The terminal transmits the entered search keyword to the server.

[0625] Step 3:

[0626] The server passes the received search keywords to the API of the generative artificial intelligence model and sends a request to collect related information.

[0627] Step 4:

[0628] A generative artificial intelligence model analyzes your search keywords and lists relevant past posts and resources (e.g., "Data Science Introduction Articles" or "Data Analysis Basics with Python").

[0629] Step 5:

[0630] The generative artificial intelligence model sends the collected information back to the server.

[0631] Step 6:

[0632] The server organizes the received information list and sends it to the terminal.

[0633] Step 7:

[0634] The terminal displays the information list to the user.

[0635] Facilitating discussion

[0636] Processing Flow

[0637] Step 1:

[0638] The server periodically calls the API of the generative artificial intelligence model, requesting the generation of new topics and questions.

[0639] Step 2:

[0640] A generative artificial intelligence model analyzes past community posts and trends to generate interesting new topics and questions (e.g., "What are the technology trends next month?").

[0641] Step 3:

[0642] The generative artificial intelligence model returns the generated topics to the server.

[0643] Step 4:

[0644] The server sends the received topic to the terminal and notifies the user.

[0645] Step 5:

[0646] The device displays new topic notifications to the user.

[0647] Step 6:

[0648] A user posts a comment on a new topic saying, "Advances in AI and machine learning are attracting attention."

[0649] Step 7:

[0650] The terminal transmits the user's comments to the server.

[0651] Step 8:

[0652] The server notifies the terminals of other users of the received comments.

[0653] Step 9:

[0654] Join discussions based on notifications received by other users.

[0655] This will stimulate activity in the online community and promote information sharing among users.

[0656] Example 1

[0657] 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."

[0658] In online community management, there is a lack of means to provide quick and accurate answers to users' questions and solve problems that users are struggling with. Additionally, there is a lack of mechanisms to provide useful information on specific topics, making it difficult for users to efficiently obtain the information they need. Furthermore, it is difficult to stimulate discussions, and there is a need for means to maintain the vitality of the community.

[0659] 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.

[0660] In this invention, the server includes a question receiving means for users to log in to the online community platform and post questions, a data transmitting means for transmitting user input data to the server, an answer generating means for transmitting the received question content to the generative artificial intelligence model and generating an appropriate answer, and an answer output means for transmitting the generated answer to the terminal and displaying it to the user. This enables prompt and accurate answers to user questions. Furthermore, the server includes a search receiving means for users to search for information on a specific topic, a data transmitting means for transmitting search keywords to the server and requesting the generative artificial intelligence model to collect related information, an information searching means for analyzing related information using the generative artificial intelligence model and listing the information, and an information display means for transmitting the information list to the terminal and displaying it to the user, thereby enabling users to efficiently obtain the information they need. Furthermore, the server includes a new topic generating means for periodically generating new topics and questions, a topic notification means for transmitting the generated topics to the terminal and notifying the user, a comment transmitting means for receiving user comments and transmitting them to the server, and a comment notification means for notifying other users of the comments, thereby promoting community discussions.

[0661] The "question receiving means" is a means by which a user logs in to the online community platform and posts a question.

[0662] The "data transmission means" is a means for transmitting the data input by the user to the server.

[0663] The "answer generation means" is a means for transmitting the received question content to a generative artificial intelligence model and generating an appropriate answer.

[0664] The "answer output means" is a means for transmitting the generated answer to the terminal and displaying it to the user.

[0665] A "search receiving means" is a means by which a user searches for information on a particular topic.

[0666] "Information search means" refers to a means for analyzing related information using a generative artificial intelligence model and listing the information.

[0667] The "information display means" is a means for transmitting the information list to the terminal and displaying it to the user.

[0668] A "new topic generation means" is a means for periodically generating new topics and questions.

[0669] The "topic notification means" is a means for transmitting the generated topic to the terminal and notifying the user.

[0670] The "comment sending means" is a means for receiving user comments and sending them to the server.

[0671] The "comment notification means" is a means for notifying other users of a comment.

[0672] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes user questions and search keywords, and generates and collects appropriate answers and related information.

[0673] This invention is a system that uses a generative artificial intelligence model to support the operation of an online community platform. This system has functions such as providing answers to questions, organizing and providing useful information, and facilitating discussions.

[0674] The main hardware components of this system include a server, a terminal, and a user input device. The software used includes a generative AI model (e.g., a model known as a general generative AI model) and an API for data transmission.

[0675] First, a user logs into an online community platform. The user uses an interface to input a question or search keyword. For example, a user might post a question such as "What is the difference between a for loop and a while loop in Python?" This input is sent from the terminal to the server.

[0676] Next, the server receives the user's input data and passes it to a generative AI model. This model analyzes the question and generates an appropriate answer. For example, it might generate an answer such as, "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true." This answer is then sent from the server to the device and displayed to the user.

[0677] Additionally, when a user searches for information on a specific topic, for example, by typing "useful articles on data science," these search keywords are also sent to the server. The server passes the keywords to the generative AI model, requesting it to collect related information. The generative AI model analyzes past posts and materials and lists related information, such as "introductory articles on data science" or "basics of data analysis using Python." This list of information is then sent via the server to the device and displayed to the user.

[0678] Furthermore, to stimulate discussion, the server periodically generates new topics and questions. For example, a topic such as "What will be the technology trends next month?" is generated. This topic is sent to the device and notified to the user. Users can then post comments in response, for example, "Advances in AI and machine learning are attracting attention." These comments are then sent to the server and notified to other users, further stimulating discussion.

[0679] To understand how this system works, consider the following example prompt:

[0680] "Please explain in detail the difference between for loops and while loops in Python."

[0681] "Can you recommend some useful articles on the basics of data science?"

[0682] "I want to discuss the latest technology trends, so please generate new topics."

[0683] By inputting prompts like the ones above into the generative AI model, we can understand specifically how the system will provide answers and information. This system is designed to improve the efficiency of online community management and enhance user convenience.

[0684] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0685] Answers to questions

[0686] Step 1:

[0687] A user logs in to an online community platform and posts a question. For example, they type, "What is the difference between a for loop and a while loop in Python?" This input is registered on the device as question data.

[0688] Step 2:

[0689] The terminal sends the question data to the server. The entered question data is sent to the server via an HTTP request. The format of the sent data is the question content in text format.

[0690] Step 3:

[0691] The server receives the question data and sends a request to the generative AI model. The input question data is analyzed, and the data format is converted into a format that the generative AI model can accept before being sent to the model. As the generative AI model, for example, a widely used general generative artificial intelligence model can be used.

[0692] Step 4:

[0693] The generative AI model analyzes the question and generates an appropriate answer. It analyzes the input question and generates answer data in text format based on past data and the scene. For example, it generates an answer such as, "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true."

[0694] Step 5:

[0695] The server receives the generated answer and sends it to the device. The text-format answer data returned from the generative AI model is converted into an appropriate output format (e.g., JSON format) before being sent to the device.

[0696] Step 6:

[0697] The device displays the answer to the user. It parses the received JSON data and displays it on the screen in a user-friendly format. Specifically, the display area on the browser displays the message, "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true."

[0698] Providing useful information

[0699] Step 1:

[0700] A user searches for information on a specific topic, for example, by typing "useful articles about data science." This input is registered as search data on the device.

[0701] Step 2:

[0702] The terminal sends the search keywords to the server. The entered search data is sent to the server via an HTTP request. The data sent is in the form of the search keywords in text format.

[0703] Step 3:

[0704] The server receives the search keywords and sends a request to the generative AI model. The server analyzes the input search data, converts the data format into a format that the generative AI model can accept, and then sends it to the model.

[0705] Step 4:

[0706] The generative AI model analyzes keywords and lists related information. Based on the keywords entered, it references past posts and materials to generate related information (a list of information in text format). For example, it finds information such as "Introductory articles on data science" and "The basics of data analysis using Python."

[0707] Step 5:

[0708] The server sends the organized information list to the device. The text-format information list returned by the generative AI model is converted into an appropriate output format (e.g., JSON format) and then sent to the device.

[0709] Step 6:

[0710] The device displays a list of information to the user. It parses the received JSON data and displays it on the screen in a user-friendly format. Specifically, it displays links such as "Introductory articles on data science" and "Basics of data analysis using Python."

[0711] Facilitating discussion

[0712] Step 1:

[0713] The server periodically generates new topics and questions, for example, "What are the technology trends next month?" using a generative AI model.

[0714] Step 2:

[0715] The server sends the generated topics to the terminal. The topic data generated by the generative AI model is converted into an appropriate output format (e.g., JSON format) and then sent to the terminal.

[0716] Step 3:

[0717] The device displays the new topic to the user. It parses the received JSON data and displays it as a new topic to the user. Specifically, the browser displays "New Topic: What are the technology trends for next month?"

[0718] Step 4:

[0719] A user posts a comment on a new topic. For example, they write, "The progress of AI and machine learning is attracting attention." This comment is registered on the device as comment data.

[0720] Step 5:

[0721] The device sends the comment to the server. The entered comment data is sent to the server via an HTTP request.

[0722] Step 6:

[0723] The server receives the comment and notifies the other user's device. The server converts the received comment data into an appropriate output format (for example, JSON format) and sends it to the other user's device.

[0724] Step 7:

[0725] Other users can participate in the discussion. Check the comment notifications you receive and post new comments to stimulate the discussion. For example, you could reply, "I agree. The field of deep learning is particularly advanced."

[0726] (Application example 1)

[0727] 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."

[0728] Currently, in many factories, it often takes a long time for workers to find solutions to technical questions or problems. Furthermore, workers must check multiple materials and documents to find the information they need, which is inefficient. Furthermore, a lack of real-time discussion and knowledge sharing on-site hinders information sharing and technological improvement. To solve these problems, a system is needed in which factory robots themselves can answer workers' questions, provide necessary information, and facilitate discussion.

[0729] 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.

[0730] In this invention, the server includes a question receiving means for using a generative artificial intelligence model to provide appropriate answers to questions from users on the online community platform, a generating means for sending the content of the question to the generative artificial intelligence model and generating an answer, an answer output means for displaying the generated answer to the user, a worker question receiving means for receiving questions from workers in a system incorporated in a factory robot, a robot display means for displaying the answer on a robot operation panel, a search receiving means for analyzing past posts and related materials in the online community and providing useful information to users, and a search engine for sending search keywords to the generative artificial intelligence model and collecting related information. The system includes an analysis means, an information display means for organizing the collected information and displaying it to the user, a worker information search means for allowing factory workers to search for useful information related to a specific technology, a robot information display means for displaying information on a robot operation panel, a new topic generation means for promoting discussions within an online community using a generative artificial intelligence model, a topic notification means for notifying users of the generated topics, a comment notification means for receiving user comments and notifying other users, a discussion topic generation means for promoting discussions among factory workers, and a robot comment display means for displaying comments on the robot operation panel. This enables workers to obtain answers to technical questions in real time and quickly search for and share necessary information, while also stimulating discussions on site, enabling efficient problem solving and knowledge sharing.

[0731] A "generative artificial intelligence model" is an artificial intelligence technology for generating natural language text based on input data.

[0732] An "online community platform" is a digital service that allows users to interact and share information over the Internet.

[0733] The "question receiving means" is an interface for receiving questions from users.

[0734] "Generation means" is a process for analyzing the content of a question and generating an appropriate answer using a generative artificial intelligence model.

[0735] The "answer output means" is an interface for displaying the generated answer to the user.

[0736] A "factory robot" is an industrial machine that is programmed to perform automated tasks.

[0737] The "means for receiving questions from workers" is an interface that allows the robot to receive technical questions from factory workers.

[0738] The "robot display means" is an interface for displaying data on the robot's operation panel.

[0739] The "search receiving means" is an interface that allows users to input search keywords and topics.

[0740] "Analysis means" refers to the process of analyzing input data using a generative artificial intelligence model and collecting relevant information.

[0741] The "information display means" is an interface for organizing collected information and displaying it to the user.

[0742] The "worker information search means" is an interface that allows factory workers to search for specific techniques or information.

[0743] A "discussion topic generator" is a process that generates new topics to facilitate discussion.

[0744] The "topic notification means" is an interface for notifying users of generated discussion topics.

[0745] The "comment notification means" is an interface for notifying other users of comments posted by a user.

[0746] The "robot comment display means" is an interface for displaying comments on the robot's operation panel.

[0747] This invention is a system that utilizes a generative artificial intelligence model to support factory workers. This system realizes functions such as providing answers to questions, organizing and providing useful information, and facilitating discussions.

[0748] Specifically, the following processing is performed.

[0749] The server uses the generative artificial intelligence model to provide appropriate answers to questions from factory workers. The worker inputs a question through the robot operation panel, and the data is sent to the server through a question receiving means. On the server, the generative artificial intelligence model analyzes the question and generates an appropriate answer. The generated answer is displayed on the robot operation panel through an answer output means. As a specific example, when a worker asks, "How do I troubleshoot signal analysis?", the generative artificial intelligence model responds, "To identify the root cause of the problem, first observe the signal waveform using an oscilloscope. If an abnormal pattern is found, analyze that part in more detail. Adjust the filter if necessary and check the signal regularity."

[0750] The server also provides useful materials when factory workers search for specific technologies or information. When a worker enters search keywords, the data is sent to the server through a search receiving means. On the server, a generative AI model analyzes past posts and related materials, collecting and organizing related information. The collected information is displayed on the robot operation panel through an information display means. For example, if a worker searches for "the latest methods for optimizing automation processes," the generative AI model will list "overviews of the latest research" and "concrete application examples" and provide them to the worker.

[0751] Furthermore, the server generates new topics and notifies comments to promote discussions among factory workers. New discussion topics are periodically generated by a new topic generation means and notified to workers via a topic notification means. Workers enter comments on the notified topics, and these comments are notified to other workers via the comment notification means. This process stimulates the exchange of opinions on-site and promotes problem solving and technological improvement. For example, if a topic such as "What are the technological trends for next month?" is generated and a worker comments, "Advances in AI and machine learning are attracting attention," other workers are notified and a discussion begins.

[0752] The specific implementation of this system utilizes OpenAI's GPT-3 API to display answers, information, and comments on the operation panel of a factory robot. Workers can enter questions and comments on topics through the robot's operation panel, enabling real-time answers, information search, and discussion.

[0753] Examples of prompt sentences include:

[0754] Example 1:

[0755] "Question from a factory worker: How do I troubleshoot signal analysis?"

[0756] "Specific answer provided: To identify the root cause of the problem, first observe the signal waveform using an oscilloscope. If an abnormal pattern is found, analyze that area further. Adjust the filter as needed to check for signal regularity."

[0757] Example 2:

[0758] "Topic request from a factory worker: What are the latest techniques for optimizing automated processes?"

[0759] "Specific information provided: Provide workers with an overview of the latest research and a list of specific applications."

[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 uses the operation panel of a factory robot to input technical questions, information searches, and discussion topics. For example, the user inputs a question such as "How do I troubleshoot signal analysis?" The user's input data is sent to the server through the worker question receiving means.

[0763] Step 2:

[0764] The server uses a question receiving means to pass the question data sent by the user to the generative AI model and request that it generate an answer.The server then analyzes the input question and sends it as a prompt to the API of the generative AI model.

[0765] Step 3:

[0766] The generative AI model generates an appropriate answer based on the prompt. For example, it might generate an answer such as, "Use an oscilloscope to observe the signal waveform." The model generates answer data as natural language text by referencing past knowledge bases and case studies.

[0767] Step 4:

[0768] The server receives the answer from the generative artificial intelligence model using the generating means. The received answer data is passed directly to the answer output means, where it is processed to be displayed on the robot operation panel.

[0769] Step 5:

[0770] The terminal displays the generated answer on the user's operation panel through the answer output means, and the user can check the generated answer on the robot's operation panel and follow the specific instructions.

[0771] Step 6:

[0772] When a user searches for a specific technology or information, the user inputs search keywords using the operation panel. The search keywords are sent to the server through the search receiving means. For example, a user searches for "latest methods for optimizing automated processes."

[0773] Step 7:

[0774] The server uses the search receiving means to send search keywords to the generative artificial intelligence model and request the collection of related information. The generative artificial intelligence model analyzes related materials based on the input keywords and lists useful information.

[0775] Step 8:

[0776] The generative artificial intelligence model generates related information and transmits it to the server, which uses the information display means to organize the received related information and convert it into a display format.

[0777] Step 9:

[0778] The terminal displays the collected useful information on the operation panel through the information display means, allowing the user to check the necessary information and use it in their work.

[0779] Step 10:

[0780] The server periodically generates new discussion topics using the new topic generation means, and the generated topics are notified to users via the topic notification means.

[0781] Step 11:

[0782] A user inputs a comment on a new topic and sends it to the server via the operation panel. The input comment is notified to other users via the comment notification means.

[0783] Step 12:

[0784] The server notifies all users of comments, promoting discussion. Users can check other users' comments through the operation panel, exchange opinions, and share information.

[0785] 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.

[0786] This invention is a system that supports the operation of an online community platform by combining a generative AI model and an emotion engine. This system provides answers to questions, organizes and provides useful information, and promotes discussions, realizing interactions that respond to the user's emotional state.

[0787] Answering questions with emotion recognition

[0788] Processing Flow

[0789] 1. A user logs in to an online community platform, enters "What is the difference between a for loop and a while loop in Python?" in the question posting interface, and presses the "Submit" button.

[0790] 2. The device sends the entered question to the server.

[0791] 3. The server analyzes the user's emotional state using the emotion engine along with the content of the user's question.

[0792] 4. The server passes the question and the user's emotional state to the generative AI model and sends a request to generate an answer.

[0793] 5. A generative AI model analyzes the question and generates an appropriate answer with a tone and content that reflects the user's emotional state (e.g., "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true.").

[0794] 6. The server sends the generated response to the device.

[0795] 7. The device displays the answer to the user.

[0796] Providing useful information with emotion recognition

[0797] Processing Flow

[0798] 1. A user types "useful articles about data science" into the search interface of an online community platform and presses the "Search" button.

[0799] 2. The device sends the entered search keywords to the server.

[0800] 3. The server analyzes the user's emotional state using an emotion engine along with the received search keywords.

[0801] 4. The server passes the search keywords and the user's emotional state to the generative AI model and sends a request to collect related information.

[0802] 5. A generative AI model analyzes search keywords and lists relevant information with priority and display content based on the user's emotional state (e.g., "Introductory articles on data science" or "Basics of data analysis using Python").

[0803] 6. The server sends the organized information list to the terminal.

[0804] 7. The terminal displays the information list to the user.

[0805] Facilitating discussions with emotion awareness

[0806] Processing Flow

[0807] 1. The server periodically calls the API of the generative artificial intelligence model to request the generation of new topics and questions.

[0808] 2. Generative AI models analyze past community posts and trends to generate interesting new topics and questions (e.g., "What are the technology trends next month?").

[0809] 3. For topics generated by the generative AI model, an emotion engine is used to tailor feedback and responses according to the user's emotional state.

[0810] 4. The server sends the generated topic to the terminal and notifies the user.

[0811] 5. The device displays a new topic notification to the user.

[0812] 6. A user posts a comment on a new topic saying, "Advances in AI and machine learning are attracting attention."

[0813] 7. The device sends the user's comments to the server, and the emotion engine analyzes the user's emotional state.

[0814] 8. The server notifies other users of the received comments and emotional state.

[0815] 9. Other users can join the discussion based on the notifications they receive, further stimulating the discussion.

[0816] In this way, inventions that combine emotion engines will make online community management even more user-friendly, enabling more appropriate and personalized interactions. By providing answers, organizing information, and promoting discussions in accordance with the user's emotional state, the community will become more attractive and people willing to participate will increase.

[0817] The processing flow will be explained below.

[0818] Answering questions with emotion recognition

[0819] Processing Flow

[0820] Step 1:

[0821] A user logs in to an online community platform, enters "What is the difference between a for loop and a while loop in Python?" in the question posting interface, and presses the "Submit" button.

[0822] Step 2:

[0823] The terminal sends the entered question to the server.

[0824] Step 3:

[0825] The server receives the question and uses an emotion engine to analyze the user's emotional state, thereby determining the emotion (e.g., excitement, annoyance, confusion, etc.) at the time the user submits the question.

[0826] Step 4:

[0827] The server passes the question and the user's emotional state to a generative AI model and sends a request to generate an answer.

[0828] Step 5:

[0829] The generative AI model analyzes the question and the user's emotional state to generate an answer with the appropriate tone and content. For example, if the user is confused, the generated answer will be more polite and detailed.

[0830] Step 6:

[0831] The server receives the generated response and transmits it to the terminal.

[0832] Step 7:

[0833] The terminal displays the answer to the user.

[0834] Providing useful information with emotion recognition

[0835] Processing Flow

[0836] Step 1:

[0837] A user types "helpful articles about data science" into the search interface of an online community platform and presses the "Search" button.

[0838] Step 2:

[0839] The terminal transmits the entered search keyword to the server.

[0840] Step 3:

[0841] The server receives the search keywords and uses an emotion engine to analyze the user's emotional state, thereby determining the type of information the user is currently interested in and their emotions (e.g., excitement, curiosity, professional interest, etc.).

[0842] Step 4:

[0843] The server passes the search keywords and emotional state to a generative artificial intelligence model and sends a request to collect related information.

[0844] Step 5:

[0845] A generative artificial intelligence model analyzes search keywords and emotional state to generate a list of information with adjusted priorities and content (e.g., "Introductory articles on data science" or "Basics of data analysis using Python").

[0846] Step 6:

[0847] The server receives the generated information list and transmits it to the terminal.

[0848] Step 7:

[0849] The terminal displays the information list to the user.

[0850] Facilitating discussions with emotion awareness

[0851] Processing Flow

[0852] Step 1:

[0853] The server periodically calls the API of the generative artificial intelligence model, requesting the generation of new topics and questions.

[0854] Step 2:

[0855] A generative artificial intelligence model analyzes past community posts and trends to generate interesting new topics and questions (e.g., "What are the technology trends next month?").

[0856] Step 3:

[0857] A server receives the generated topics, analyzes the user's emotional state using an emotion engine, and generates emotional feedback related to the topics.

[0858] Step 4:

[0859] The server sends the generated topic and emotional feedback to the terminal and notifies the user.

[0860] Step 5:

[0861] The device displays new topic notifications to the user.

[0862] Step 6:

[0863] A user posts a comment on a new topic saying, "Advances in AI and machine learning are attracting attention."

[0864] Step 7:

[0865] The device sends the user's comments to the server, and the emotion engine analyzes the user's emotional state.

[0866] Step 8:

[0867] The server notifies the received comments and emotional states to the terminals of other users.

[0868] Step 9:

[0869] Other users can join the discussion based on the notifications they receive, further stimulating the discussion.

[0870] By using the above processing flow, the system of the present invention combined with the emotion engine can provide appropriate and personalized interactions according to the user's emotional state.

[0871] Example 2

[0872] 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."

[0873] In online community platforms, it is important to provide quick and appropriate answers to users' diverse questions, effectively present useful information when users search, and stimulate discussions. However, conventional systems lack interactions that take into account the user's emotional state, which has led to issues such as reduced user satisfaction and community activity.

[0874] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a question receiving means for receiving a question from a user, an answer generating means for analyzing the question content and the user's emotional state and transmitting the content to a generative AI model to generate an answer, and an answer output means for displaying the generated answer to the user. This makes it possible to provide an answer according to the user's emotional state.

[0875] The server includes a search receiving means for receiving search keywords from a user and analyzing the user's emotional state, an information collecting means for transmitting the search keywords and the user's emotional state to a generative artificial intelligence model and collecting related information, and an information display means for organizing the collected information and displaying it to the user, thereby making it possible to provide useful information according to the user's emotional state.

[0876] The server includes a new topic generation means for generating new discussion topics using a generative artificial intelligence model, a topic notification means for notifying users of the generated topics, and a comment notification means for receiving comments posted by users and notifying other users of the comments, thereby enabling the promotion of discussions.

[0877] The "question receiving means" is a function or device for receiving questions from users.

[0878] "Answer generation means" refers to a function or device that analyzes the question content and the user's emotional state, and sends the results to a generative artificial intelligence model to generate an answer.

[0879] The "answer output means" refers to a function or device for displaying the generated answer to the user.

[0880] The "search receiving means" is a function or device for receiving search keywords from a user and analyzing the user's emotional state.

[0881] "Information collection means" refers to a function or device for sending search keywords and the user's emotional state to a generative artificial intelligence model and collecting related information.

[0882] "Information display means" refers to a function or device for organizing collected information and displaying it to the user.

[0883] "New topic generation means" refers to a function or device for generating new discussion topics using a generative artificial intelligence model.

[0884] The "topic notification means" is a function or device for notifying users of the generated topic.

[0885] The "comment notification means" is a function or device for receiving comments posted by a user and notifying other users of the comments.

[0886] This invention is a management support system for an online community platform that combines a generative AI model and an emotion engine. This system answers questions with emotion recognition, provides useful information, and promotes discussion.

[0887] Functions and technologies used

[0888] Providing answers to questions

[0889] When a user logs in to an online community platform and submits a question, the terminal sends the question data to a server. The server then analyzes the user's emotional state using an emotion engine along with the received question content. In this case, the emotion engine uses what is commonly known as an emotion analysis API (e.g., an emotion analysis tool or emotion analysis technology).

[0890] The server then passes the question and the user's emotional state to a generative AI model (commonly known as an AI model) and sends a request to generate an answer. For example, a generative AI model. This generative AI model analyzes the question and generates an appropriate answer with a tone and content that matches the user's emotional state. This generated answer is then sent back from the server to the device, where it is displayed to the user.

[0891] Examples:

[0892] User Question: "What is the difference between a for loop and a while loop in Python?"

[0893] Example prompt: "The user asks, 'What is the difference between a for loop and a while loop in Python?' and their emotional state is curious. Please generate a kind and concise answer."

[0894] Providing useful information

[0895] When a user enters and submits a search keyword, the device sends the search keyword to the server. The server then uses an emotion engine to analyze the user's emotional state along with the received search keyword. The analysis uses a generically named emotion analysis API.

[0896] The server then passes the search keywords and the user's emotional state to a generative AI model and sends a request to collect related information. The generative AI model analyzes the search keywords and lists related information with priority and display content according to the user's emotional state. The organized information list is then sent back from the server to the device, where it is displayed to the user.

[0897] Examples:

[0898] User search keywords: "helpful articles about data science"

[0899] Example prompt: "A user has searched for 'helpful articles about data science' and is in an excited emotional state. Please provide a list of articles that are easy to understand and aimed at beginners."

[0900] Facilitating discussion

[0901] The server periodically calls the API of the generative AI model to request the generation of new topics and questions. The generative AI model analyzes past community posts and trends to generate interesting new topics and questions. It then uses an emotion engine to adjust the feedback and response content for the generated topics, which the server then sends to the device and notifies the user.

[0902] When a user posts a comment on a new topic, the device sends the comment to the server, where the emotion engine analyzes the user's emotional state. The server then notifies other users of the received comment and emotional state, stimulating discussions.

[0903] Examples:

[0904] New discussion topic: "What are the technology trends for next month?"

[0905] Example prompt: "Generate new discussion topics based on trends across the community. Topics that many users find entertaining and exciting."

[0906] In this way, systems that utilize emotion understanding can realize user-friendly designs for managing online communities. From selecting topics to providing content and answers, it is possible to provide optimal interactions according to the user's emotional state.

[0907] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0908] Answering questions with emotion recognition

[0909] Step 1:

[0910] A user logs into an online community platform, enters a question, and presses the "Submit" button.

[0911] How it works: A user accesses the question form using a browser or a dedicated app, enters "What is the difference between a for loop and a while loop in Python?", and clicks the submit button.

[0912] Input: Text data of the question

[0913] Output: Instructions to submit a question

[0914] Step 2:

[0915] The terminal transmits the input question data to the server.

[0916] How it works: The device sends the question entered by the user to the server as an HTTP request, which includes the user ID and the question.

[0917] Input: HTTP request data (user ID, question)

[0918] Output: The request sent to the server

[0919] Step 3:

[0920] The server uses an emotion engine to analyze the question content and the user's emotional state.

[0921] How it works: The server sends the question content as an API request to the emotion engine, and analyzes the returned emotion data. The emotion engine uses the generic name emotion analysis API.

[0922] Input: Text data of the question

[0923] Output: Emotional information (e.g. curious, confused)

[0924] Step 4:

[0925] The server sends the question and the user's emotional state to the generative AI model and sends a request to generate an answer.

[0926] Operation: The server generates a prompt containing the question and emotion data for the API of the generative AI model, and sends an API request.

[0927] Input: Question content, emotion data

[0928] Output: Answer generation request

[0929] Step 5:

[0930] A generative AI model analyzes the question and generates an answer with a tone and content that reflects the user's emotional state.

[0931] How it works: The model parses the prompt and generates an appropriate answer, which is returned to the server as an API response.

[0932] Input: Prompt sentence (question content, emotion data)

[0933] Output: The generated answer

[0934] Step 6:

[0935] The server sends the generated response to the terminal.

[0936] How it works: The server sends a response containing the generated answer to the device as an HTTP request.

[0937] Input: Generated answer

[0938] Output: Sending response data

[0939] Step 7:

[0940] The terminal displays the answer to the user.

[0941] Operation: The device displays the received response data on the screen, providing visual feedback to the user.

[0942] Input: Response data

[0943] Output: Update the screen display

[0944] Providing useful information with emotion recognition

[0945] Step 1:

[0946] A user enters keywords into the search interface of an online community platform and presses the "Search" button.

[0947] What happens: A user enters "helpful articles about data science" into the search form and clicks the search button.

[0948] Input: Search keyword text data

[0949] Output: Search submission instructions

[0950] Step 2:

[0951] The terminal transmits the entered search keyword to the server.

[0952] How it works: The device sends the search keyword to the server as an HTTP request. The request includes the user ID and the search keyword.

[0953] Input: HTTP request data (user ID, search keywords)

[0954] Output: The request sent to the server

[0955] Step 3:

[0956] The server analyzes the received search keywords and the user's emotional state using an emotion engine.

[0957] How it works: The server sends search keywords as API requests to the emotion engine and analyzes the returned emotion data.

[0958] Input: Search keyword text data

[0959] Output: Emotional information (e.g., excited, relaxed)

[0960] Step 4:

[0961] The server sends the search keywords and the user's emotional state to a generative artificial intelligence model and sends a request to collect related information.

[0962] How it works: The server generates a prompt containing search keywords and emotion data for the API of the generative AI model and sends an API request.

[0963] Input: Search keywords, emotion data

[0964] Output: Information collection request

[0965] Step 5:

[0966] A generative artificial intelligence model analyzes search keywords and lists relevant information based on priority and content.

[0967] How it works: The model parses the prompt, gathers the appropriate information, and generates a list, which is returned to the server as an API response.

[0968] Input: Prompt sentence (search keywords, emotion data)

[0969] Output: Generated information list

[0970] Step 6:

[0971] The server transmits the generated information list to the terminal.

[0972] Operation: The server sends a response containing the generated information list to the terminal as an HTTP request.

[0973] Input: Generated information list

[0974] Output: Sending a list of information

[0975] Step 7:

[0976] The terminal displays the information list to the user.

[0977] Operation: The device displays the received information list on the screen, providing visual feedback to the user.

[0978] Input: Information List

[0979] Output: Update the screen display

[0980] Facilitating discussions with emotion awareness

[0981] Step 1:

[0982] The server periodically calls the API of the generative artificial intelligence model, requesting the generation of new topics and questions.

[0983] How it works: The server sets up a periodic job and calls the API of the generative AI model at specific time intervals.

[0984] Input: Trigger signal for periodic job

[0985] Output: New topic creation request

[0986] Step 2:

[0987] A generative artificial intelligence model analyzes past community posts and trends to generate interesting new topics and questions.

[0988] How it works: The model analyzes historical data and generates new topics, which are then returned to the server as API responses.

[0989] Input: Prompt text (past posting data, trend information)

[0990] Output: Generated topics

[0991] Step 3:

[0992] The generative artificial intelligence model uses an emotion engine to analyze the user's emotional state and adjust the feedback depending on the topic.

[0993] How it works: For each topic, sentiment analysis is performed to tailor feedback based on the user's past sentiment data.

[0994] Input: Generated topics

[0995] Output: Sentiment analysis feedback

[0996] Step 4:

[0997] The server sends the generated topic to the terminal and notifies the user.

[0998] Operation: The server sends the generated topic to the terminal as a notification message.

[0999] Input: Generated topics

[1000] Output: Topic notification data

[1001] Step 5:

[1002] The device displays new topic notifications to the user.

[1003] Behavior: The device displays a notification message in a pop-up window or in the notification bar.

[1004] Input: Topic notification data

[1005] Output: On-screen notification

[1006] Step 6:

[1007] A user enters a comment on a new topic and clicks the post button.

[1008] What happens: A user enters their opinion into the comment form and clicks the post button.

[1009] Input: Text data of comment content

[1010] Output: Instructions to send comments

[1011] Step 7:

[1012] The terminal transmits the user's comments to the server.

[1013] How it works: The device sends the user's comments as an HTTP request to the server, and the server analyzes the user's emotional state using an emotion engine.

[1014] Input: HTTP request data (user ID, comment content)

[1015] Output: Send comment data

[1016] Step 8:

[1017] The server notifies the received comments and emotional states to the terminals of other users.

[1018] How it works: The server sends notification messages to other relevant users based on the comments and emotion data.

[1019] Input: Comment content, emotion data

[1020] Output: Comment notification data

[1021] Step 9:

[1022] Other users join the discussion, making it more lively.

[1023] What happens: Other users see the notification, join the discussion, and post comments.

[1024] Enter: Comment Notification

[1025] Output: Stimulating discussion

[1026] This will create an online community management support system that utilizes emotion recognition and generative AI models. The system will provide appropriate answers according to the user's emotional state, present useful information, and promote discussion.

[1027] (Application example 2)

[1028] 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."

[1029] In online and real-world environments, it is important to provide appropriate interactions without being hindered by the emotional state of users and customers. However, existing systems do not take the emotional state of users and customers into account, which can lead to reduced satisfaction and effectiveness. In addition, providing information and promoting discussions is done uniformly without adapting to the emotional state, which creates the challenge of not being able to provide services tailored to individual needs.

[1030] The specific processing by the specific 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 a question receiving means, a generating means, an answer output means, a sentiment analysis means, and an answer adjustment means. This makes it possible to adjust answers based on the emotional state of the user or customer and provide more personalized interactions. In addition, by using an information priority adjustment means, the priority of information provided to the user can be adjusted according to the emotional state, and by using a discussion activation means, lively discussions based on sentiment analysis can be promoted.

[1031] The "question receiving means" is a system or device for receiving questions from users.

[1032] The "generation means" is a system or device that generates an answer using a generative artificial intelligence model based on the content of the received question.

[1033] The "answer output means" is a system or device for displaying or providing the generated answer to the user.

[1034] An "emotion analysis means" is a system or device for analyzing emotions using facial expressions and other data of a customer.

[1035] The "answer adjustment means" is a system or device for adjusting the tone and content of the generated answer based on the emotion data obtained by the emotion analysis means.

[1036] The "search receiving means" is a system or device for receiving search keywords from a user.

[1037] "Analysis means" refers to a system or device for sending search keywords to a generative artificial intelligence model and collecting related information.

[1038] "Information display means" refers to a system or device for organizing collected information and displaying it to the user.

[1039] The "information priority adjustment means" is a system or device for adjusting the priority of collected information in consideration of the emotional state of the user obtained by emotion analysis.

[1040] A "new topic generation means" is a system or device for generating new topics using a generative artificial intelligence model.

[1041] The "topic notification means" is a system or device for notifying users of generated topics.

[1042] The "comment notification means" is a system or device for receiving a user's comment and notifying other users of the comment.

[1043] The "discussion activation means" is a system or device for activating discussions using sentiment analysis.

[1044] This invention is a system that combines a generative artificial intelligence model and an emotion analysis engine to improve customer experience in brick-and-mortar stores. A specific example of this system is described below.

[1045] System configuration

[1046] The system comprises a question receiving means, a generating means, an answer output means, a sentiment analysis means, and an answer adjustment means.

[1047] 1. How to receive questions:

[1048] Questions from users are received through a smartphone application, which has an interface that allows users to freely input questions.

[1049] 2. Generation means:

[1050] A question is sent via an online API to a generative AI model (e.g., GPT-4), which analyzes the question and generates an appropriate answer.

[1051] 3. Answer output means:

[1052] This is a means for displaying the generated answers to the user. The answers are displayed on the smartphone application.

[1053] 4. Emotion analysis means:

[1054] Customers' facial expressions are captured using a smartphone camera and analyzed using an emotion analysis engine (for example, Microsoft Azure's Emotion API), which allows us to identify the customer's current emotional state.

[1055] 5. Response adjustment method:

[1056] The responses generated by the generative AI model are adjusted based on emotional data obtained through sentiment analysis. For example, if a customer is feeling stressed, the system will provide responses in a more relaxing tone.

[1057] System Operation

[1058] This system uses the following hardware and software:

[1059] Hardware

[1060] Smartphone (iOS or Android)

[1061] Server (Linux server)

[1062] Camera (built-in camera on smartphone)

[1063] software

[1064] Emotion engine (Microsoft Azure Emotion API)

[1065] Generative AI model (using GPT-4)

[1066] App development framework (React Native)

[1067] Database (MySQL or PostgreSQL)

[1068] Data processing and calculation

[1069] The data is processed and calculated as follows:

[1070] Customer facial expression data is captured by a camera and their emotional state is analyzed using an emotion analysis engine.

[1071] Based on your emotional state, the responses generated by the generative AI model are adjusted to optimize tone and content.

[1072] Specific examples

[1073] A customer types "Tell me about the latest trending products" into a smartphone app and submits it. At this time, the smartphone camera captures the customer's face and performs emotional analysis. As a result, the generative AI model generates a tone-adjusted response based on the customer's emotional state, such as "Here are the latest trending products. They have a particularly relaxing effect, making them perfect for when you're tired," and displays it on the smartphone.

[1074] Prompt Sentence Examples

[1075] User prompt: "What are the latest trending products?"

[1076] This will enable a more personalized customer experience in physical stores and improve customer satisfaction.

[1077] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1078] Step 1:

[1079] A user inputs a question into a smartphone app. For example, "What are the latest trending products?" and presses the send button. The input includes the user's question text. The device receives this question data and sends it to the server.

[1080] Step 2:

[1081] The server receives question data sent by the user. The received data includes the user's question text. The server sends this question text to a generative AI model and requests it to generate an answer.

[1082] Step 3:

[1083] A generative AI model generates an answer based on the question received from the server. The input includes the user's question text. The model analyzes the question, generates an appropriate answer text, and sends it back to the server.

[1084] Step 4:

[1085] The server receives the answer text received from the generative AI model. The received data includes the generated answer text. The server temporarily stores this answer and waits until it receives emotion data from the device.

[1086] Step 5:

[1087] The device captures the user's facial expressions using the smartphone's built-in camera and sends them to the emotion analysis engine. The input data includes facial expression images. The device receives the emotion data as the analysis result and sends it to the server.

[1088] Step 6:

[1089] The server receives the emotion data sent from the emotion analysis engine. The received data includes the user's emotional state. Based on the emotion data, the server sends a request to the generative AI model to adjust the pre-generated answer text.

[1090] Step 7:

[1091] A generative AI model adjusts the response text based on the emotion data received from the server. The input includes the stored response text and emotion data. The model adjusts the tone of the response to match the user's emotional state and sends the adjusted response text back to the server.

[1092] Step 8:

[1093] The server transmits the adjusted answer text to the terminal. The received data includes the answer text adjusted to match the emotional state.

[1094] Step 9:

[1095] The device displays the adjusted answer text to the user, who then accepts the answer displayed on the smartphone app to complete the interaction.

[1096] 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.

[1097] 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.

[1098] 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.

[1099] [Third embodiment]

[1100] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1101] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1102] 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).

[1103] 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.

[1104] 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.

[1105] 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).

[1106] 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.

[1107] 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.

[1108] 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.

[1109] 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.

[1110] 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.

[1111] 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."

[1112] This invention is a system that utilizes generative artificial intelligence models to support the operation of an online community platform. This system realizes functions such as providing answers to questions, organizing and providing useful information, and promoting discussions.

[1113] Answers to questions

[1114] Processing Flow

[1115] 1. A user logs into an online community platform and posts a question, for example, "What is the difference between a for loop and a while loop in Python?"

[1116] 2. The terminal sends the user's input data to the server.

[1117] 3. The server passes the question to the generative AI model and requests it to generate an answer.

[1118] 4. The generative AI model analyzes the question and generates an appropriate answer. For example, the generative AI model might generate, "For loops are used to repeat a set number of times, and while loops are used to repeat while a condition is true."

[1119] 5. The server sends the generated response to the device.

[1120] 6. The device displays the answer to the user.

[1121] Providing useful information

[1122] Processing Flow

[1123] 1. A user searches for information on a specific topic, for example, typing in "helpful articles on data science."

[1124] 2. The device sends the search keywords to the server.

[1125] 3. The server passes the search keywords to the generative AI model and requests it to collect related information.

[1126] 4. The generative AI model analyzes past posts and materials and lists relevant information. For example, the generative AI model finds articles like "Data Science Introduction Articles" and "Data Analysis Basics with Python."

[1127] 5. The server sends the organized information list to the terminal.

[1128] 6. The terminal displays the information list to the user.

[1129] Facilitating discussion

[1130] Processing Flow

[1131] 1. The server periodically uses a generative artificial intelligence model to generate new topics and questions, such as "What are the technology trends for next month?"

[1132] 2. The server sends the generated topic to the terminal and notifies the user.

[1133] 3. The device displays the new topic to the user.

[1134] 4. A user posts a comment on a new topic, for example, "Advances in AI and machine learning are attracting attention."

[1135] 5. The device sends the comment to the server.

[1136] 6. The server receives the comment and notifies the other users' terminals.

[1137] 7. Other users join the discussion, making it more lively.

[1138] By implementing this system, it is possible to improve the efficiency of online community management and enhance user convenience. By using a generative AI model, it is possible to provide quick and accurate answers to questions, organize information within the community, provide useful information, and stimulate discussions.

[1139] The processing flow will be explained below.

[1140] Answers to questions

[1141] Processing Flow

[1142] Step 1:

[1143] A user logs in to an online community platform, enters "What is the difference between a for loop and a while loop in Python?" in the question posting interface, and presses the "Submit" button.

[1144] Step 2:

[1145] The terminal sends the entered question to the server.

[1146] Step 3:

[1147] The server passes the received question to the API of the generative artificial intelligence model and sends a request to generate an answer.

[1148] Step 4:

[1149] A generative AI model analyzes the question and generates an appropriate answer based on past discussions and a knowledge base (e.g., "A for loop is used to repeat something a set number of times, while a while loop is used to repeat something while a condition is true").

[1150] Step 5:

[1151] The generative artificial intelligence model returns the generated answer to the server.

[1152] Step 6:

[1153] The server sends the received response to the terminal.

[1154] Step 7:

[1155] The terminal displays the answer to the user.

[1156] Providing useful information

[1157] Processing Flow

[1158] Step 1:

[1159] A user types "helpful articles about data science" into the search interface of an online community platform and presses the "Search" button.

[1160] Step 2:

[1161] The terminal transmits the entered search keyword to the server.

[1162] Step 3:

[1163] The server passes the received search keywords to the API of the generative artificial intelligence model and sends a request to collect related information.

[1164] Step 4:

[1165] A generative artificial intelligence model analyzes your search keywords and lists relevant past posts and resources (e.g., "Data Science Introduction Articles" or "Data Analysis Basics with Python").

[1166] Step 5:

[1167] The generative artificial intelligence model sends the collected information back to the server.

[1168] Step 6:

[1169] The server organizes the received information list and sends it to the terminal.

[1170] Step 7:

[1171] The terminal displays the information list to the user.

[1172] Facilitating discussion

[1173] Processing Flow

[1174] Step 1:

[1175] The server periodically calls the API of the generative artificial intelligence model, requesting the generation of new topics and questions.

[1176] Step 2:

[1177] A generative artificial intelligence model analyzes past community posts and trends to generate interesting new topics and questions (e.g., "What are the technology trends next month?").

[1178] Step 3:

[1179] The generative artificial intelligence model returns the generated topics to the server.

[1180] Step 4:

[1181] The server sends the received topic to the terminal and notifies the user.

[1182] Step 5:

[1183] The device displays new topic notifications to the user.

[1184] Step 6:

[1185] A user posts a comment on a new topic saying, "Advances in AI and machine learning are attracting attention."

[1186] Step 7:

[1187] The terminal transmits the user's comments to the server.

[1188] Step 8:

[1189] The server notifies the terminals of other users of the received comments.

[1190] Step 9:

[1191] Join discussions based on notifications received by other users.

[1192] This will stimulate activity in the online community and promote information sharing among users.

[1193] Example 1

[1194] 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."

[1195] In online community management, there is a lack of means to provide quick and accurate answers to users' questions and solve problems that users are struggling with. Additionally, there is a lack of mechanisms to provide useful information on specific topics, making it difficult for users to efficiently obtain the information they need. Furthermore, it is difficult to stimulate discussions, and there is a need for means to maintain the vitality of the community.

[1196] 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.

[1197] In this invention, the server includes a question receiving means for users to log in to the online community platform and post questions, a data transmitting means for transmitting user input data to the server, an answer generating means for transmitting the received question content to the generative artificial intelligence model and generating an appropriate answer, and an answer output means for transmitting the generated answer to the terminal and displaying it to the user. This enables prompt and accurate answers to user questions. Furthermore, the server includes a search receiving means for users to search for information on a specific topic, a data transmitting means for transmitting search keywords to the server and requesting the generative artificial intelligence model to collect related information, an information searching means for analyzing related information using the generative artificial intelligence model and listing the information, and an information display means for transmitting the information list to the terminal and displaying it to the user, thereby enabling users to efficiently obtain the information they need. Furthermore, the server includes a new topic generating means for periodically generating new topics and questions, a topic notification means for transmitting the generated topics to the terminal and notifying the user, a comment transmitting means for receiving user comments and transmitting them to the server, and a comment notification means for notifying other users of the comments, thereby promoting community discussions.

[1198] The "question receiving means" is a means by which a user logs in to the online community platform and posts a question.

[1199] The "data transmission means" is a means for transmitting the data input by the user to the server.

[1200] The "answer generation means" is a means for transmitting the received question content to a generative artificial intelligence model and generating an appropriate answer.

[1201] The "answer output means" is a means for transmitting the generated answer to the terminal and displaying it to the user.

[1202] A "search receiving means" is a means by which a user searches for information on a particular topic.

[1203] "Information search means" refers to a means for analyzing related information using a generative artificial intelligence model and listing the information.

[1204] The "information display means" is a means for transmitting the information list to the terminal and displaying it to the user.

[1205] A "new topic generation means" is a means for periodically generating new topics and questions.

[1206] The "topic notification means" is a means for transmitting the generated topic to the terminal and notifying the user.

[1207] The "comment sending means" is a means for receiving user comments and sending them to the server.

[1208] The "comment notification means" is a means for notifying other users of a comment.

[1209] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes user questions and search keywords, and generates and collects appropriate answers and related information.

[1210] This invention is a system that uses a generative artificial intelligence model to support the operation of an online community platform. This system has functions such as providing answers to questions, organizing and providing useful information, and facilitating discussions.

[1211] The main hardware components of this system include a server, a terminal, and a user input device. The software used includes a generative AI model (e.g., a model known as a general generative AI model) and an API for data transmission.

[1212] First, a user logs into an online community platform. The user uses an interface to input a question or search keyword. For example, a user might post a question such as "What is the difference between a for loop and a while loop in Python?" This input is sent from the terminal to the server.

[1213] Next, the server receives the user's input data and passes it to a generative AI model. This model analyzes the question and generates an appropriate answer. For example, it might generate an answer such as, "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true." This answer is then sent from the server to the device and displayed to the user.

[1214] Additionally, when a user searches for information on a specific topic, for example, by typing "useful articles on data science," these search keywords are also sent to the server. The server passes the keywords to the generative AI model, requesting it to collect related information. The generative AI model analyzes past posts and materials and lists related information, such as "introductory articles on data science" or "basics of data analysis using Python." This list of information is then sent via the server to the device and displayed to the user.

[1215] Furthermore, to stimulate discussion, the server periodically generates new topics and questions. For example, a topic such as "What will be the technology trends next month?" is generated. This topic is sent to the device and notified to the user. Users can then post comments in response, for example, "Advances in AI and machine learning are attracting attention." These comments are then sent to the server and notified to other users, further stimulating discussion.

[1216] To understand how this system works, consider the following example prompt:

[1217] "Please explain in detail the difference between for loops and while loops in Python."

[1218] "Can you recommend some useful articles on the basics of data science?"

[1219] "I want to discuss the latest technology trends, so please generate new topics."

[1220] By inputting prompts like the ones above into the generative AI model, we can understand specifically how the system will provide answers and information. This system is designed to improve the efficiency of online community management and enhance user convenience.

[1221] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1222] Answers to questions

[1223] Step 1:

[1224] A user logs in to an online community platform and posts a question. For example, they type, "What is the difference between a for loop and a while loop in Python?" This input is registered on the device as question data.

[1225] Step 2:

[1226] The terminal sends the question data to the server. The entered question data is sent to the server via an HTTP request. The format of the sent data is the question content in text format.

[1227] Step 3:

[1228] The server receives the question data and sends a request to the generative AI model. The input question data is analyzed, and the data format is converted into a format that the generative AI model can accept before being sent to the model. As the generative AI model, for example, a widely used general generative artificial intelligence model can be used.

[1229] Step 4:

[1230] The generative AI model analyzes the question and generates an appropriate answer. It analyzes the input question and generates answer data in text format based on past data and the scene. For example, it generates an answer such as, "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true."

[1231] Step 5:

[1232] The server receives the generated answer and sends it to the device. The text-format answer data returned from the generative AI model is converted into an appropriate output format (e.g., JSON format) before being sent to the device.

[1233] Step 6:

[1234] The device displays the answer to the user. It parses the received JSON data and displays it on the screen in a user-friendly format. Specifically, the display area on the browser displays the message, "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true."

[1235] Providing useful information

[1236] Step 1:

[1237] A user searches for information on a specific topic, for example, by typing "useful articles about data science." This input is registered as search data on the device.

[1238] Step 2:

[1239] The terminal sends the search keywords to the server. The entered search data is sent to the server via an HTTP request. The data sent is in the form of the search keywords in text format.

[1240] Step 3:

[1241] The server receives the search keywords and sends a request to the generative AI model. The server analyzes the input search data, converts the data format into a format that the generative AI model can accept, and then sends it to the model.

[1242] Step 4:

[1243] The generative AI model analyzes keywords and lists related information. Based on the keywords entered, it references past posts and materials to generate related information (a list of information in text format). For example, it finds information such as "Introductory articles on data science" and "The basics of data analysis using Python."

[1244] Step 5:

[1245] The server sends the organized information list to the device. The text-format information list returned by the generative AI model is converted into an appropriate output format (e.g., JSON format) and then sent to the device.

[1246] Step 6:

[1247] The device displays a list of information to the user. It parses the received JSON data and displays it on the screen in a user-friendly format. Specifically, it displays links such as "Introductory articles on data science" and "Basics of data analysis using Python."

[1248] Facilitating discussion

[1249] Step 1:

[1250] The server periodically generates new topics and questions, for example, "What are the technology trends next month?" using a generative AI model.

[1251] Step 2:

[1252] The server sends the generated topics to the terminal. The topic data generated by the generative AI model is converted into an appropriate output format (e.g., JSON format) and then sent to the terminal.

[1253] Step 3:

[1254] The device displays the new topic to the user. It parses the received JSON data and displays it as a new topic to the user. Specifically, the browser displays "New Topic: What are the technology trends for next month?"

[1255] Step 4:

[1256] A user posts a comment on a new topic. For example, they write, "The progress of AI and machine learning is attracting attention." This comment is registered on the device as comment data.

[1257] Step 5:

[1258] The device sends the comment to the server. The entered comment data is sent to the server via an HTTP request.

[1259] Step 6:

[1260] The server receives the comment and notifies the other user's device. The server converts the received comment data into an appropriate output format (for example, JSON format) and sends it to the other user's device.

[1261] Step 7:

[1262] Other users can participate in the discussion. Check the comment notifications you receive and post new comments to stimulate the discussion. For example, you could reply, "I agree. The field of deep learning is particularly advanced."

[1263] (Application example 1)

[1264] 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."

[1265] Currently, in many factories, it often takes a long time for workers to find solutions to technical questions or problems. Furthermore, workers must check multiple materials and documents to find the information they need, which is inefficient. Furthermore, a lack of real-time discussion and knowledge sharing on-site hinders information sharing and technological improvement. To solve these problems, a system is needed in which factory robots themselves can answer workers' questions, provide necessary information, and facilitate discussion.

[1266] 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.

[1267] In this invention, the server includes a question receiving means for using a generative artificial intelligence model to provide appropriate answers to questions from users on the online community platform, a generating means for sending the content of the question to the generative artificial intelligence model and generating an answer, an answer output means for displaying the generated answer to the user, a worker question receiving means for receiving questions from workers in a system incorporated in a factory robot, a robot display means for displaying the answer on a robot operation panel, a search receiving means for analyzing past posts and related materials in the online community and providing useful information to users, and a search engine for sending search keywords to the generative artificial intelligence model and collecting related information. The system includes an analysis means, an information display means for organizing the collected information and displaying it to the user, a worker information search means for allowing factory workers to search for useful information related to a specific technology, a robot information display means for displaying information on a robot operation panel, a new topic generation means for promoting discussions within an online community using a generative artificial intelligence model, a topic notification means for notifying users of the generated topics, a comment notification means for receiving user comments and notifying other users, a discussion topic generation means for promoting discussions among factory workers, and a robot comment display means for displaying comments on the robot operation panel. This enables workers to obtain answers to technical questions in real time and quickly search for and share necessary information, while also stimulating discussions on site, enabling efficient problem solving and knowledge sharing.

[1268] A "generative artificial intelligence model" is an artificial intelligence technology for generating natural language text based on input data.

[1269] An "online community platform" is a digital service that allows users to interact and share information over the Internet.

[1270] The "question receiving means" is an interface for receiving questions from users.

[1271] "Generation means" is a process for analyzing the content of a question and generating an appropriate answer using a generative artificial intelligence model.

[1272] The "answer output means" is an interface for displaying the generated answer to the user.

[1273] A "factory robot" is an industrial machine that is programmed to perform automated tasks.

[1274] The "means for receiving questions from workers" is an interface that allows the robot to receive technical questions from factory workers.

[1275] The "robot display means" is an interface for displaying data on the robot's operation panel.

[1276] The "search receiving means" is an interface that allows users to input search keywords and topics.

[1277] "Analysis means" refers to the process of analyzing input data using a generative artificial intelligence model and collecting relevant information.

[1278] The "information display means" is an interface for organizing collected information and displaying it to the user.

[1279] The "worker information search means" is an interface that allows factory workers to search for specific techniques or information.

[1280] A "discussion topic generator" is a process that generates new topics to facilitate discussion.

[1281] The "topic notification means" is an interface for notifying users of generated discussion topics.

[1282] The "comment notification means" is an interface for notifying other users of comments posted by a user.

[1283] The "robot comment display means" is an interface for displaying comments on the robot's operation panel.

[1284] This invention is a system that utilizes a generative artificial intelligence model to support factory workers. This system realizes functions such as providing answers to questions, organizing and providing useful information, and facilitating discussions.

[1285] Specifically, the following processing is performed.

[1286] The server uses the generative artificial intelligence model to provide appropriate answers to questions from factory workers. The worker inputs a question through the robot operation panel, and the data is sent to the server through a question receiving means. On the server, the generative artificial intelligence model analyzes the question and generates an appropriate answer. The generated answer is displayed on the robot operation panel through an answer output means. As a specific example, when a worker asks, "How do I troubleshoot signal analysis?", the generative artificial intelligence model responds, "To identify the root cause of the problem, first observe the signal waveform using an oscilloscope. If an abnormal pattern is found, analyze that part in more detail. Adjust the filter if necessary and check the signal regularity."

[1287] The server also provides useful materials when factory workers search for specific technologies or information. When a worker enters search keywords, the data is sent to the server through a search receiving means. On the server, a generative AI model analyzes past posts and related materials, collecting and organizing related information. The collected information is displayed on the robot operation panel through an information display means. For example, if a worker searches for "the latest methods for optimizing automation processes," the generative AI model will list "overviews of the latest research" and "concrete application examples" and provide them to the worker.

[1288] Furthermore, the server generates new topics and notifies comments to promote discussions among factory workers. New discussion topics are periodically generated by a new topic generation means and notified to workers via a topic notification means. Workers enter comments on the notified topics, and these comments are notified to other workers via the comment notification means. This process stimulates the exchange of opinions on-site and promotes problem solving and technological improvement. For example, if a topic such as "What are the technological trends for next month?" is generated and a worker comments, "Advances in AI and machine learning are attracting attention," other workers are notified and a discussion begins.

[1289] The specific implementation of this system utilizes OpenAI's GPT-3 API to display answers, information, and comments on the operation panel of a factory robot. Workers can enter questions and comments on topics through the robot's operation panel, enabling real-time answers, information search, and discussion.

[1290] Examples of prompt sentences include:

[1291] Example 1:

[1292] "Question from a factory worker: How do I troubleshoot signal analysis?"

[1293] "Specific answer provided: To identify the root cause of the problem, first observe the signal waveform using an oscilloscope. If an abnormal pattern is found, analyze that area further. Adjust the filter as needed to check for signal regularity."

[1294] Example 2:

[1295] "Topic request from a factory worker: What are the latest techniques for optimizing automated processes?"

[1296] "Specific information provided: Provide workers with an overview of the latest research and a list of specific applications."

[1297] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1298] Step 1:

[1299] A user uses the operation panel of a factory robot to input technical questions, information searches, and discussion topics. For example, the user inputs a question such as "How do I troubleshoot signal analysis?" The user's input data is sent to the server through the worker question receiving means.

[1300] Step 2:

[1301] The server uses a question receiving means to pass the question data sent by the user to the generative AI model and request that it generate an answer.The server then analyzes the input question and sends it as a prompt to the API of the generative AI model.

[1302] Step 3:

[1303] The generative AI model generates an appropriate answer based on the prompt. For example, it might generate an answer such as, "Use an oscilloscope to observe the signal waveform." The model generates answer data as natural language text by referencing past knowledge bases and case studies.

[1304] Step 4:

[1305] The server receives the answer from the generative artificial intelligence model using the generating means. The received answer data is passed directly to the answer output means, where it is processed to be displayed on the robot operation panel.

[1306] Step 5:

[1307] The terminal displays the generated answer on the user's operation panel through the answer output means, and the user can check the generated answer on the robot's operation panel and follow the specific instructions.

[1308] Step 6:

[1309] When a user searches for a specific technology or information, the user inputs search keywords using the operation panel. The search keywords are sent to the server through the search receiving means. For example, a user searches for "latest methods for optimizing automated processes."

[1310] Step 7:

[1311] The server uses the search receiving means to send search keywords to the generative artificial intelligence model and request the collection of related information. The generative artificial intelligence model analyzes related materials based on the input keywords and lists useful information.

[1312] Step 8:

[1313] The generative artificial intelligence model generates related information and transmits it to the server, which uses the information display means to organize the received related information and convert it into a display format.

[1314] Step 9:

[1315] The terminal displays the collected useful information on the operation panel through the information display means, allowing the user to check the necessary information and use it in their work.

[1316] Step 10:

[1317] The server periodically generates new discussion topics using the new topic generation means, and the generated topics are notified to users via the topic notification means.

[1318] Step 11:

[1319] A user inputs a comment on a new topic and sends it to the server via the operation panel. The input comment is notified to other users via the comment notification means.

[1320] Step 12:

[1321] The server notifies all users of comments, promoting discussion. Users can check other users' comments through the operation panel, exchange opinions, and share information.

[1322] 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.

[1323] This invention is a system that supports the operation of an online community platform by combining a generative AI model and an emotion engine. This system provides answers to questions, organizes and provides useful information, and promotes discussions, realizing interactions that respond to the user's emotional state.

[1324] Answering questions with emotion recognition

[1325] Processing Flow

[1326] 1. A user logs in to an online community platform, enters "What is the difference between a for loop and a while loop in Python?" in the question posting interface, and presses the "Submit" button.

[1327] 2. The device sends the entered question to the server.

[1328] 3. The server analyzes the user's emotional state using the emotion engine along with the content of the user's question.

[1329] 4. The server passes the question and the user's emotional state to the generative AI model and sends a request to generate an answer.

[1330] 5. A generative AI model analyzes the question and generates an appropriate answer with a tone and content that reflects the user's emotional state (e.g., "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true.").

[1331] 6. The server sends the generated response to the device.

[1332] 7. The device displays the answer to the user.

[1333] Providing useful information with emotion recognition

[1334] Processing Flow

[1335] 1. A user types "useful articles about data science" into the search interface of an online community platform and presses the "Search" button.

[1336] 2. The device sends the entered search keywords to the server.

[1337] 3. The server analyzes the user's emotional state using an emotion engine along with the received search keywords.

[1338] 4. The server passes the search keywords and the user's emotional state to the generative AI model and sends a request to collect related information.

[1339] 5. A generative AI model analyzes search keywords and lists relevant information with priority and display content based on the user's emotional state (e.g., "Introductory articles on data science" or "Basics of data analysis using Python").

[1340] 6. The server sends the organized information list to the terminal.

[1341] 7. The terminal displays the information list to the user.

[1342] Facilitating discussions with emotion awareness

[1343] Processing Flow

[1344] 1. The server periodically calls the API of the generative artificial intelligence model to request the generation of new topics and questions.

[1345] 2. Generative AI models analyze past community posts and trends to generate interesting new topics and questions (e.g., "What are the technology trends next month?").

[1346] 3. For topics generated by the generative AI model, an emotion engine is used to tailor feedback and responses according to the user's emotional state.

[1347] 4. The server sends the generated topic to the terminal and notifies the user.

[1348] 5. The device displays a new topic notification to the user.

[1349] 6. A user posts a comment on a new topic saying, "Advances in AI and machine learning are attracting attention."

[1350] 7. The device sends the user's comments to the server, and the emotion engine analyzes the user's emotional state.

[1351] 8. The server notifies other users of the received comments and emotional state.

[1352] 9. Other users can join the discussion based on the notifications they receive, further stimulating the discussion.

[1353] In this way, inventions that combine emotion engines will make online community management even more user-friendly, enabling more appropriate and personalized interactions. By providing answers, organizing information, and promoting discussions in accordance with the user's emotional state, the community will become more attractive and people willing to participate will increase.

[1354] The processing flow will be explained below.

[1355] Answering questions with emotion recognition

[1356] Processing Flow

[1357] Step 1:

[1358] A user logs in to an online community platform, enters "What is the difference between a for loop and a while loop in Python?" in the question posting interface, and presses the "Submit" button.

[1359] Step 2:

[1360] The terminal sends the entered question to the server.

[1361] Step 3:

[1362] The server receives the question and uses an emotion engine to analyze the user's emotional state, thereby determining the emotion (e.g., excitement, annoyance, confusion, etc.) at the time the user submits the question.

[1363] Step 4:

[1364] The server passes the question and the user's emotional state to a generative AI model and sends a request to generate an answer.

[1365] Step 5:

[1366] The generative AI model analyzes the question and the user's emotional state to generate an answer with the appropriate tone and content. For example, if the user is confused, the generated answer will be more polite and detailed.

[1367] Step 6:

[1368] The server receives the generated response and transmits it to the terminal.

[1369] Step 7:

[1370] The terminal displays the answer to the user.

[1371] Providing useful information with emotion recognition

[1372] Processing Flow

[1373] Step 1:

[1374] A user types "helpful articles about data science" into the search interface of an online community platform and presses the "Search" button.

[1375] Step 2:

[1376] The terminal transmits the entered search keyword to the server.

[1377] Step 3:

[1378] The server receives the search keywords and uses an emotion engine to analyze the user's emotional state, thereby determining the type of information the user is currently interested in and their emotions (e.g., excitement, curiosity, professional interest, etc.).

[1379] Step 4:

[1380] The server passes the search keywords and emotional state to a generative artificial intelligence model and sends a request to collect related information.

[1381] Step 5:

[1382] A generative artificial intelligence model analyzes search keywords and emotional state to generate a list of information with adjusted priorities and content (e.g., "Introductory articles on data science" or "Basics of data analysis using Python").

[1383] Step 6:

[1384] The server receives the generated information list and transmits it to the terminal.

[1385] Step 7:

[1386] The terminal displays the information list to the user.

[1387] Facilitating discussions with emotion awareness

[1388] Processing Flow

[1389] Step 1:

[1390] The server periodically calls the API of the generative artificial intelligence model, requesting the generation of new topics and questions.

[1391] Step 2:

[1392] A generative artificial intelligence model analyzes past community posts and trends to generate interesting new topics and questions (e.g., "What are the technology trends next month?").

[1393] Step 3:

[1394] A server receives the generated topics, analyzes the user's emotional state using an emotion engine, and generates emotional feedback related to the topics.

[1395] Step 4:

[1396] The server sends the generated topic and emotional feedback to the terminal and notifies the user.

[1397] Step 5:

[1398] The device displays new topic notifications to the user.

[1399] Step 6:

[1400] A user posts a comment on a new topic saying, "Advances in AI and machine learning are attracting attention."

[1401] Step 7:

[1402] The device sends the user's comments to the server, and the emotion engine analyzes the user's emotional state.

[1403] Step 8:

[1404] The server notifies the received comments and emotional states to the terminals of other users.

[1405] Step 9:

[1406] Other users can join the discussion based on the notifications they receive, further stimulating the discussion.

[1407] By using the above processing flow, the system of the present invention combined with the emotion engine can provide appropriate and personalized interactions according to the user's emotional state.

[1408] Example 2

[1409] 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."

[1410] In online community platforms, it is important to provide quick and appropriate answers to users' diverse questions, effectively present useful information when users search, and stimulate discussions. However, conventional systems lack interactions that take into account the user's emotional state, which has led to issues such as reduced user satisfaction and community activity.

[1411] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a question receiving means for receiving a question from a user, an answer generating means for analyzing the question content and the user's emotional state and transmitting the content to a generative AI model to generate an answer, and an answer output means for displaying the generated answer to the user. This makes it possible to provide an answer according to the user's emotional state.

[1412] The server includes a search receiving means for receiving search keywords from a user and analyzing the user's emotional state, an information collecting means for transmitting the search keywords and the user's emotional state to a generative artificial intelligence model and collecting related information, and an information display means for organizing the collected information and displaying it to the user, thereby making it possible to provide useful information according to the user's emotional state.

[1413] The server includes a new topic generation means for generating new discussion topics using a generative artificial intelligence model, a topic notification means for notifying users of the generated topics, and a comment notification means for receiving comments posted by users and notifying other users of the comments, thereby enabling the promotion of discussions.

[1414] The "question receiving means" is a function or device for receiving questions from users.

[1415] "Answer generation means" refers to a function or device that analyzes the question content and the user's emotional state, and sends the results to a generative artificial intelligence model to generate an answer.

[1416] The "answer output means" refers to a function or device for displaying the generated answer to the user.

[1417] The "search receiving means" is a function or device for receiving search keywords from a user and analyzing the user's emotional state.

[1418] "Information collection means" refers to a function or device for sending search keywords and the user's emotional state to a generative artificial intelligence model and collecting related information.

[1419] "Information display means" refers to a function or device for organizing collected information and displaying it to the user.

[1420] "New topic generation means" refers to a function or device for generating new discussion topics using a generative artificial intelligence model.

[1421] The "topic notification means" is a function or device for notifying users of the generated topic.

[1422] The "comment notification means" is a function or device for receiving comments posted by a user and notifying other users of the comments.

[1423] This invention is a management support system for an online community platform that combines a generative AI model and an emotion engine. This system answers questions with emotion recognition, provides useful information, and promotes discussion.

[1424] Functions and technologies used

[1425] Providing answers to questions

[1426] When a user logs in to an online community platform and submits a question, the terminal sends the question data to a server. The server then analyzes the user's emotional state using an emotion engine along with the received question content. In this case, the emotion engine uses what is commonly known as an emotion analysis API (e.g., an emotion analysis tool or emotion analysis technology).

[1427] The server then passes the question and the user's emotional state to a generative AI model (commonly known as an AI model) and sends a request to generate an answer. For example, a generative AI model. This generative AI model analyzes the question and generates an appropriate answer with a tone and content that matches the user's emotional state. This generated answer is then sent back from the server to the device, where it is displayed to the user.

[1428] Examples:

[1429] User Question: "What is the difference between a for loop and a while loop in Python?"

[1430] Example prompt: "The user asks, 'What is the difference between a for loop and a while loop in Python?' and their emotional state is curious. Please generate a kind and concise answer."

[1431] Providing useful information

[1432] When a user enters and submits a search keyword, the device sends the search keyword to the server. The server then uses an emotion engine to analyze the user's emotional state along with the received search keyword. The analysis uses a generically named emotion analysis API.

[1433] The server then passes the search keywords and the user's emotional state to a generative AI model and sends a request to collect related information. The generative AI model analyzes the search keywords and lists related information with priority and display content according to the user's emotional state. The organized information list is then sent back from the server to the device, where it is displayed to the user.

[1434] Examples:

[1435] User search keywords: "helpful articles about data science"

[1436] Example prompt: "A user has searched for 'helpful articles about data science' and is in an excited emotional state. Please provide a list of articles that are easy to understand and aimed at beginners."

[1437] Facilitating discussion

[1438] The server periodically calls the API of the generative AI model to request the generation of new topics and questions. The generative AI model analyzes past community posts and trends to generate interesting new topics and questions. It then uses an emotion engine to adjust the feedback and response content for the generated topics, which the server then sends to the device and notifies the user.

[1439] When a user posts a comment on a new topic, the device sends the comment to the server, where the emotion engine analyzes the user's emotional state. The server then notifies other users of the received comment and emotional state, stimulating discussions.

[1440] Examples:

[1441] New discussion topic: "What are the technology trends for next month?"

[1442] Example prompt: "Generate new discussion topics based on trends across the community. Topics that many users find entertaining and exciting."

[1443] In this way, systems that utilize emotion understanding can realize user-friendly designs for managing online communities. From selecting topics to providing content and answers, it is possible to provide optimal interactions according to the user's emotional state.

[1444] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1445] Answering questions with emotion recognition

[1446] Step 1:

[1447] A user logs into an online community platform, enters a question, and presses the "Submit" button.

[1448] How it works: A user accesses the question form using a browser or a dedicated app, enters "What is the difference between a for loop and a while loop in Python?", and clicks the submit button.

[1449] Input: Text data of the question

[1450] Output: Instructions to submit a question

[1451] Step 2:

[1452] The terminal transmits the input question data to the server.

[1453] How it works: The device sends the question entered by the user to the server as an HTTP request, which includes the user ID and the question.

[1454] Input: HTTP request data (user ID, question)

[1455] Output: The request sent to the server

[1456] Step 3:

[1457] The server uses an emotion engine to analyze the question content and the user's emotional state.

[1458] How it works: The server sends the question content as an API request to the emotion engine, and analyzes the returned emotion data. The emotion engine uses the generic name emotion analysis API.

[1459] Input: Text data of the question

[1460] Output: Emotional information (e.g. curious, confused)

[1461] Step 4:

[1462] The server sends the question and the user's emotional state to the generative AI model and sends a request to generate an answer.

[1463] Operation: The server generates a prompt containing the question and emotion data for the API of the generative AI model, and sends an API request.

[1464] Input: Question content, emotion data

[1465] Output: Answer generation request

[1466] Step 5:

[1467] A generative AI model analyzes the question and generates an answer with a tone and content that reflects the user's emotional state.

[1468] How it works: The model parses the prompt and generates an appropriate answer, which is returned to the server as an API response.

[1469] Input: Prompt sentence (question content, emotion data)

[1470] Output: The generated answer

[1471] Step 6:

[1472] The server sends the generated response to the terminal.

[1473] How it works: The server sends a response containing the generated answer to the device as an HTTP request.

[1474] Input: Generated answer

[1475] Output: Sending response data

[1476] Step 7:

[1477] The terminal displays the answer to the user.

[1478] Operation: The device displays the received response data on the screen, providing visual feedback to the user.

[1479] Input: Response data

[1480] Output: Update the screen display

[1481] Providing useful information with emotion recognition

[1482] Step 1:

[1483] A user enters keywords into the search interface of an online community platform and presses the "Search" button.

[1484] What happens: A user enters "helpful articles about data science" into the search form and clicks the search button.

[1485] Input: Search keyword text data

[1486] Output: Search submission instructions

[1487] Step 2:

[1488] The terminal transmits the entered search keyword to the server.

[1489] How it works: The device sends the search keyword to the server as an HTTP request. The request includes the user ID and the search keyword.

[1490] Input: HTTP request data (user ID, search keywords)

[1491] Output: The request sent to the server

[1492] Step 3:

[1493] The server analyzes the received search keywords and the user's emotional state using an emotion engine.

[1494] How it works: The server sends search keywords as API requests to the emotion engine and analyzes the returned emotion data.

[1495] Input: Search keyword text data

[1496] Output: Emotional information (e.g., excited, relaxed)

[1497] Step 4:

[1498] The server sends the search keywords and the user's emotional state to a generative artificial intelligence model and sends a request to collect related information.

[1499] How it works: The server generates a prompt containing search keywords and emotion data for the API of the generative AI model and sends an API request.

[1500] Input: Search keywords, emotion data

[1501] Output: Information collection request

[1502] Step 5:

[1503] A generative artificial intelligence model analyzes search keywords and lists relevant information based on priority and content.

[1504] How it works: The model parses the prompt, gathers the appropriate information, and generates a list, which is returned to the server as an API response.

[1505] Input: Prompt sentence (search keywords, emotion data)

[1506] Output: Generated information list

[1507] Step 6:

[1508] The server transmits the generated information list to the terminal.

[1509] Operation: The server sends a response containing the generated information list to the terminal as an HTTP request.

[1510] Input: Generated information list

[1511] Output: Sending a list of information

[1512] Step 7:

[1513] The terminal displays the information list to the user.

[1514] Operation: The device displays the received information list on the screen, providing visual feedback to the user.

[1515] Input: Information List

[1516] Output: Update the screen display

[1517] Facilitating discussions with emotion awareness

[1518] Step 1:

[1519] The server periodically calls the API of the generative artificial intelligence model, requesting the generation of new topics and questions.

[1520] How it works: The server sets up a periodic job and calls the API of the generative AI model at specific time intervals.

[1521] Input: Trigger signal for periodic job

[1522] Output: New topic creation request

[1523] Step 2:

[1524] A generative artificial intelligence model analyzes past community posts and trends to generate interesting new topics and questions.

[1525] How it works: The model analyzes historical data and generates new topics, which are then returned to the server as API responses.

[1526] Input: Prompt text (past posting data, trend information)

[1527] Output: Generated topics

[1528] Step 3:

[1529] The generative artificial intelligence model uses an emotion engine to analyze the user's emotional state and adjust the feedback depending on the topic.

[1530] How it works: For each topic, sentiment analysis is performed to tailor feedback based on the user's past sentiment data.

[1531] Input: Generated topics

[1532] Output: Sentiment analysis feedback

[1533] Step 4:

[1534] The server sends the generated topic to the terminal and notifies the user.

[1535] Operation: The server sends the generated topic to the terminal as a notification message.

[1536] Input: Generated topics

[1537] Output: Topic notification data

[1538] Step 5:

[1539] The device displays new topic notifications to the user.

[1540] Behavior: The device displays a notification message in a pop-up window or in the notification bar.

[1541] Input: Topic notification data

[1542] Output: On-screen notification

[1543] Step 6:

[1544] A user enters a comment on a new topic and clicks the post button.

[1545] What happens: A user enters their opinion into the comment form and clicks the post button.

[1546] Input: Text data of comment content

[1547] Output: Instructions to send comments

[1548] Step 7:

[1549] The terminal transmits the user's comments to the server.

[1550] How it works: The device sends the user's comments as an HTTP request to the server, and the server analyzes the user's emotional state using an emotion engine.

[1551] Input: HTTP request data (user ID, comment content)

[1552] Output: Send comment data

[1553] Step 8:

[1554] The server notifies the received comments and emotional states to the terminals of other users.

[1555] How it works: The server sends notification messages to other relevant users based on the comments and emotion data.

[1556] Input: Comment content, emotion data

[1557] Output: Comment notification data

[1558] Step 9:

[1559] Other users join the discussion, making it more lively.

[1560] What happens: Other users see the notification, join the discussion, and post comments.

[1561] Enter: Comment Notification

[1562] Output: Stimulating discussion

[1563] This will create an online community management support system that utilizes emotion recognition and generative AI models. The system will provide appropriate answers according to the user's emotional state, present useful information, and promote discussion.

[1564] (Application example 2)

[1565] 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."

[1566] In online and real-world environments, it is important to provide appropriate interactions without being hindered by the emotional state of users and customers. However, existing systems do not take the emotional state of users and customers into account, which can lead to reduced satisfaction and effectiveness. In addition, providing information and promoting discussions is done uniformly without adapting to the emotional state, which creates the challenge of not being able to provide services tailored to individual needs.

[1567] The specific processing by the specific 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 a question receiving means, a generating means, an answer output means, a sentiment analysis means, and an answer adjustment means. This makes it possible to adjust answers based on the emotional state of the user or customer and provide more personalized interactions. In addition, by using an information priority adjustment means, the priority of information provided to the user can be adjusted according to the emotional state, and by using a discussion activation means, lively discussions based on sentiment analysis can be promoted.

[1568] The "question receiving means" is a system or device for receiving questions from users.

[1569] The "generation means" is a system or device that generates an answer using a generative artificial intelligence model based on the content of the received question.

[1570] The "answer output means" is a system or device for displaying or providing the generated answer to the user.

[1571] An "emotion analysis means" is a system or device for analyzing emotions using facial expressions and other data of a customer.

[1572] The "answer adjustment means" is a system or device for adjusting the tone and content of the generated answer based on the emotion data obtained by the emotion analysis means.

[1573] The "search receiving means" is a system or device for receiving search keywords from a user.

[1574] "Analysis means" refers to a system or device for sending search keywords to a generative artificial intelligence model and collecting related information.

[1575] "Information display means" refers to a system or device for organizing collected information and displaying it to the user.

[1576] The "information priority adjustment means" is a system or device for adjusting the priority of collected information in consideration of the emotional state of the user obtained by emotion analysis.

[1577] A "new topic generation means" is a system or device for generating new topics using a generative artificial intelligence model.

[1578] The "topic notification means" is a system or device for notifying users of generated topics.

[1579] The "comment notification means" is a system or device for receiving a user's comment and notifying other users of the comment.

[1580] The "discussion activation means" is a system or device for activating discussions using sentiment analysis.

[1581] This invention is a system that combines a generative artificial intelligence model and an emotion analysis engine to improve customer experience in brick-and-mortar stores. A specific example of this system is described below.

[1582] System configuration

[1583] The system comprises a question receiving means, a generating means, an answer output means, a sentiment analysis means, and an answer adjustment means.

[1584] 1. How to receive questions:

[1585] Questions from users are received through a smartphone application, which has an interface that allows users to freely input questions.

[1586] 2. Generation means:

[1587] A question is sent via an online API to a generative AI model (e.g., GPT-4), which analyzes the question and generates an appropriate answer.

[1588] 3. Answer output means:

[1589] This is a means for displaying the generated answers to the user. The answers are displayed on the smartphone application.

[1590] 4. Emotion analysis means:

[1591] Customers' facial expressions are captured using a smartphone camera and analyzed using an emotion analysis engine (for example, Microsoft Azure's Emotion API), which allows us to identify the customer's current emotional state.

[1592] 5. Response adjustment method:

[1593] The responses generated by the generative AI model are adjusted based on emotional data obtained through sentiment analysis. For example, if a customer is feeling stressed, the system will provide responses in a more relaxing tone.

[1594] System Operation

[1595] This system uses the following hardware and software:

[1596] Hardware

[1597] Smartphone (iOS or Android)

[1598] Server (Linux server)

[1599] Camera (built-in camera on smartphone)

[1600] software

[1601] Emotion engine (Microsoft Azure Emotion API)

[1602] Generative AI model (using GPT-4)

[1603] App development framework (React Native)

[1604] Database (MySQL or PostgreSQL)

[1605] Data processing and calculation

[1606] The data is processed and calculated as follows:

[1607] Customer facial expression data is captured by a camera and their emotional state is analyzed using an emotion analysis engine.

[1608] Based on your emotional state, the responses generated by the generative AI model are adjusted to optimize tone and content.

[1609] Specific examples

[1610] A customer types "Tell me about the latest trending products" into a smartphone app and submits it. At this time, the smartphone camera captures the customer's face and performs emotional analysis. As a result, the generative AI model generates a tone-adjusted response based on the customer's emotional state, such as "Here are the latest trending products. They have a particularly relaxing effect, making them perfect for when you're tired," and displays it on the smartphone.

[1611] Prompt Sentence Examples

[1612] User prompt: "What are the latest trending products?"

[1613] This will enable a more personalized customer experience in physical stores and improve customer satisfaction.

[1614] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1615] Step 1:

[1616] A user inputs a question into a smartphone app. For example, "What are the latest trending products?" and presses the send button. The input includes the user's question text. The device receives this question data and sends it to the server.

[1617] Step 2:

[1618] The server receives question data sent by the user. The received data includes the user's question text. The server sends this question text to a generative AI model and requests it to generate an answer.

[1619] Step 3:

[1620] A generative AI model generates an answer based on the question received from the server. The input includes the user's question text. The model analyzes the question, generates an appropriate answer text, and sends it back to the server.

[1621] Step 4:

[1622] The server receives the answer text received from the generative AI model. The received data includes the generated answer text. The server temporarily stores this answer and waits until it receives emotion data from the device.

[1623] Step 5:

[1624] The device captures the user's facial expressions using the smartphone's built-in camera and sends them to the emotion analysis engine. The input data includes facial expression images. The device receives the emotion data as the analysis result and sends it to the server.

[1625] Step 6:

[1626] The server receives the emotion data sent from the emotion analysis engine. The received data includes the user's emotional state. Based on the emotion data, the server sends a request to the generative AI model to adjust the pre-generated answer text.

[1627] Step 7:

[1628] A generative AI model adjusts the response text based on the emotion data received from the server. The input includes the stored response text and emotion data. The model adjusts the tone of the response to match the user's emotional state and sends the adjusted response text back to the server.

[1629] Step 8:

[1630] The server transmits the adjusted answer text to the terminal. The received data includes the answer text adjusted to match the emotional state.

[1631] Step 9:

[1632] The device displays the adjusted answer text to the user, who then accepts the answer displayed on the smartphone app to complete the interaction.

[1633] 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.

[1634] 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.

[1635] 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.

[1636] [Fourth embodiment]

[1637] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1638] 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.

[1639] 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).

[1640] 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.

[1641] 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.

[1642] 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).

[1643] 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.

[1644] 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.

[1645] 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.

[1646] 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.

[1647] 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.

[1648] 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.

[1649] 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."

[1650] This invention is a system that utilizes generative artificial intelligence models to support the operation of an online community platform. This system realizes functions such as providing answers to questions, organizing and providing useful information, and promoting discussions.

[1651] Answers to questions

[1652] Processing Flow

[1653] 1. A user logs into an online community platform and posts a question, for example, "What is the difference between a for loop and a while loop in Python?"

[1654] 2. The terminal sends the user's input data to the server.

[1655] 3. The server passes the question to the generative AI model and requests it to generate an answer.

[1656] 4. The generative AI model analyzes the question and generates an appropriate answer. For example, the generative AI model might generate, "For loops are used to repeat a set number of times, and while loops are used to repeat while a condition is true."

[1657] 5. The server sends the generated response to the device.

[1658] 6. The device displays the answer to the user.

[1659] Providing useful information

[1660] Processing Flow

[1661] 1. A user searches for information on a specific topic, for example, typing in "helpful articles on data science."

[1662] 2. The device sends the search keywords to the server.

[1663] 3. The server passes the search keywords to the generative AI model and requests it to collect related information.

[1664] 4. The generative AI model analyzes past posts and materials and lists relevant information. For example, the generative AI model finds articles like "Data Science Introduction Articles" and "Data Analysis Basics with Python."

[1665] 5. The server sends the organized information list to the terminal.

[1666] 6. The terminal displays the information list to the user.

[1667] Facilitating discussion

[1668] Processing Flow

[1669] 1. The server periodically uses a generative artificial intelligence model to generate new topics and questions, such as "What are the technology trends for next month?"

[1670] 2. The server sends the generated topic to the terminal and notifies the user.

[1671] 3. The device displays the new topic to the user.

[1672] 4. A user posts a comment on a new topic, for example, "Advances in AI and machine learning are attracting attention."

[1673] 5. The device sends the comment to the server.

[1674] 6. The server receives the comment and notifies the other users' terminals.

[1675] 7. Other users join the discussion, making it more lively.

[1676] By implementing this system, it is possible to improve the efficiency of online community management and enhance user convenience. By using a generative AI model, it is possible to provide quick and accurate answers to questions, organize information within the community, provide useful information, and stimulate discussions.

[1677] The processing flow will be explained below.

[1678] Answers to questions

[1679] Processing Flow

[1680] Step 1:

[1681] A user logs in to an online community platform, enters "What is the difference between a for loop and a while loop in Python?" in the question posting interface, and presses the "Submit" button.

[1682] Step 2:

[1683] The terminal sends the entered question to the server.

[1684] Step 3:

[1685] The server passes the received question to the API of the generative artificial intelligence model and sends a request to generate an answer.

[1686] Step 4:

[1687] A generative AI model analyzes the question and generates an appropriate answer based on past discussions and a knowledge base (e.g., "A for loop is used to repeat something a set number of times, while a while loop is used to repeat something while a condition is true").

[1688] Step 5:

[1689] The generative artificial intelligence model returns the generated answer to the server.

[1690] Step 6:

[1691] The server sends the received response to the terminal.

[1692] Step 7:

[1693] The terminal displays the answer to the user.

[1694] Providing useful information

[1695] Processing Flow

[1696] Step 1:

[1697] A user types "helpful articles about data science" into the search interface of an online community platform and presses the "Search" button.

[1698] Step 2:

[1699] The terminal transmits the entered search keyword to the server.

[1700] Step 3:

[1701] The server passes the received search keywords to the API of the generative artificial intelligence model and sends a request to collect related information.

[1702] Step 4:

[1703] A generative artificial intelligence model analyzes your search keywords and lists relevant past posts and resources (e.g., "Data Science Introduction Articles" or "Data Analysis Basics with Python").

[1704] Step 5:

[1705] The generative artificial intelligence model sends the collected information back to the server.

[1706] Step 6:

[1707] The server organizes the received information list and sends it to the terminal.

[1708] Step 7:

[1709] The terminal displays the information list to the user.

[1710] Facilitating discussion

[1711] Processing Flow

[1712] Step 1:

[1713] The server periodically calls the API of the generative artificial intelligence model, requesting the generation of new topics and questions.

[1714] Step 2:

[1715] A generative artificial intelligence model analyzes past community posts and trends to generate interesting new topics and questions (e.g., "What are the technology trends next month?").

[1716] Step 3:

[1717] The generative artificial intelligence model returns the generated topics to the server.

[1718] Step 4:

[1719] The server sends the received topic to the terminal and notifies the user.

[1720] Step 5:

[1721] The device displays new topic notifications to the user.

[1722] Step 6:

[1723] A user posts a comment on a new topic saying, "Advances in AI and machine learning are attracting attention."

[1724] Step 7:

[1725] The terminal transmits the user's comments to the server.

[1726] Step 8:

[1727] The server notifies the terminals of other users of the received comments.

[1728] Step 9:

[1729] Join discussions based on notifications received by other users.

[1730] This will stimulate activity in the online community and promote information sharing among users.

[1731] Example 1

[1732] 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."

[1733] In online community management, there is a lack of means to provide quick and accurate answers to users' questions and solve problems that users are struggling with. Additionally, there is a lack of mechanisms to provide useful information on specific topics, making it difficult for users to efficiently obtain the information they need. Furthermore, it is difficult to stimulate discussions, and there is a need for means to maintain the vitality of the community.

[1734] 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.

[1735] In this invention, the server includes a question receiving means for users to log in to the online community platform and post questions, a data transmitting means for transmitting user input data to the server, an answer generating means for transmitting the received question content to the generative artificial intelligence model and generating an appropriate answer, and an answer output means for transmitting the generated answer to the terminal and displaying it to the user. This enables prompt and accurate answers to user questions. Furthermore, the server includes a search receiving means for users to search for information on a specific topic, a data transmitting means for transmitting search keywords to the server and requesting the generative artificial intelligence model to collect related information, an information searching means for analyzing related information using the generative artificial intelligence model and listing the information, and an information display means for transmitting the information list to the terminal and displaying it to the user, thereby enabling users to efficiently obtain the information they need. Furthermore, the server includes a new topic generating means for periodically generating new topics and questions, a topic notification means for transmitting the generated topics to the terminal and notifying the user, a comment transmitting means for receiving user comments and transmitting them to the server, and a comment notification means for notifying other users of the comments, thereby promoting community discussions.

[1736] The "question receiving means" is a means by which a user logs in to the online community platform and posts a question.

[1737] The "data transmission means" is a means for transmitting the data input by the user to the server.

[1738] The "answer generation means" is a means for transmitting the received question content to a generative artificial intelligence model and generating an appropriate answer.

[1739] The "answer output means" is a means for transmitting the generated answer to the terminal and displaying it to the user.

[1740] A "search receiving means" is a means by which a user searches for information on a particular topic.

[1741] "Information search means" refers to a means for analyzing related information using a generative artificial intelligence model and listing the information.

[1742] The "information display means" is a means for transmitting the information list to the terminal and displaying it to the user.

[1743] A "new topic generation means" is a means for periodically generating new topics and questions.

[1744] The "topic notification means" is a means for transmitting the generated topic to the terminal and notifying the user.

[1745] The "comment sending means" is a means for receiving user comments and sending them to the server.

[1746] The "comment notification means" is a means for notifying other users of a comment.

[1747] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes user questions and search keywords, and generates and collects appropriate answers and related information.

[1748] This invention is a system that uses a generative artificial intelligence model to support the operation of an online community platform. This system has functions such as providing answers to questions, organizing and providing useful information, and facilitating discussions.

[1749] The main hardware components of this system include a server, a terminal, and a user input device. The software used includes a generative AI model (e.g., a model known as a general generative AI model) and an API for data transmission.

[1750] First, a user logs into an online community platform. The user uses an interface to input a question or search keyword. For example, a user might post a question such as "What is the difference between a for loop and a while loop in Python?" This input is sent from the terminal to the server.

[1751] Next, the server receives the user's input data and passes it to a generative AI model. This model analyzes the question and generates an appropriate answer. For example, it might generate an answer such as, "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true." This answer is then sent from the server to the device and displayed to the user.

[1752] Additionally, when a user searches for information on a specific topic, for example, by typing "useful articles on data science," these search keywords are also sent to the server. The server passes the keywords to the generative AI model, requesting it to collect related information. The generative AI model analyzes past posts and materials and lists related information, such as "introductory articles on data science" or "basics of data analysis using Python." This list of information is then sent via the server to the device and displayed to the user.

[1753] Furthermore, to stimulate discussion, the server periodically generates new topics and questions. For example, a topic such as "What will be the technology trends next month?" is generated. This topic is sent to the device and notified to the user. Users can then post comments in response, for example, "Advances in AI and machine learning are attracting attention." These comments are then sent to the server and notified to other users, further stimulating discussion.

[1754] To understand how this system works, consider the following example prompt:

[1755] "Please explain in detail the difference between for loops and while loops in Python."

[1756] "Can you recommend some useful articles on the basics of data science?"

[1757] "I want to discuss the latest technology trends, so please generate new topics."

[1758] By inputting prompts like the ones above into the generative AI model, we can understand specifically how the system will provide answers and information. This system is designed to improve the efficiency of online community management and enhance user convenience.

[1759] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1760] Answers to questions

[1761] Step 1:

[1762] A user logs in to an online community platform and posts a question. For example, they type, "What is the difference between a for loop and a while loop in Python?" This input is registered on the device as question data.

[1763] Step 2:

[1764] The terminal sends the question data to the server. The entered question data is sent to the server via an HTTP request. The format of the sent data is the question content in text format.

[1765] Step 3:

[1766] The server receives the question data and sends a request to the generative AI model. The input question data is analyzed, and the data format is converted into a format that the generative AI model can accept before being sent to the model. As the generative AI model, for example, a widely used general generative artificial intelligence model can be used.

[1767] Step 4:

[1768] The generative AI model analyzes the question and generates an appropriate answer. It analyzes the input question and generates answer data in text format based on past data and the scene. For example, it generates an answer such as, "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true."

[1769] Step 5:

[1770] The server receives the generated answer and sends it to the device. The text-format answer data returned from the generative AI model is converted into an appropriate output format (e.g., JSON format) before being sent to the device.

[1771] Step 6:

[1772] The device displays the answer to the user. It parses the received JSON data and displays it on the screen in a user-friendly format. Specifically, the display area on the browser displays the message, "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true."

[1773] Providing useful information

[1774] Step 1:

[1775] A user searches for information on a specific topic, for example, by typing "useful articles about data science." This input is registered as search data on the device.

[1776] Step 2:

[1777] The terminal sends the search keywords to the server. The entered search data is sent to the server via an HTTP request. The data sent is in the form of the search keywords in text format.

[1778] Step 3:

[1779] The server receives the search keywords and sends a request to the generative AI model. The server analyzes the input search data, converts the data format into a format that the generative AI model can accept, and then sends it to the model.

[1780] Step 4:

[1781] The generative AI model analyzes keywords and lists related information. Based on the keywords entered, it references past posts and materials to generate related information (a list of information in text format). For example, it finds information such as "Introductory articles on data science" and "The basics of data analysis using Python."

[1782] Step 5:

[1783] The server sends the organized information list to the device. The text-format information list returned by the generative AI model is converted into an appropriate output format (e.g., JSON format) and then sent to the device.

[1784] Step 6:

[1785] The device displays a list of information to the user. It parses the received JSON data and displays it on the screen in a user-friendly format. Specifically, it displays links such as "Introductory articles on data science" and "Basics of data analysis using Python."

[1786] Facilitating discussion

[1787] Step 1:

[1788] The server periodically generates new topics and questions, for example, "What are the technology trends next month?" using a generative AI model.

[1789] Step 2:

[1790] The server sends the generated topics to the terminal. The topic data generated by the generative AI model is converted into an appropriate output format (e.g., JSON format) and then sent to the terminal.

[1791] Step 3:

[1792] The device displays the new topic to the user. It parses the received JSON data and displays it as a new topic to the user. Specifically, the browser displays "New Topic: What are the technology trends for next month?"

[1793] Step 4:

[1794] A user posts a comment on a new topic. For example, they write, "The progress of AI and machine learning is attracting attention." This comment is registered on the device as comment data.

[1795] Step 5:

[1796] The device sends the comment to the server. The entered comment data is sent to the server via an HTTP request.

[1797] Step 6:

[1798] The server receives the comment and notifies the other user's device. The server converts the received comment data into an appropriate output format (for example, JSON format) and sends it to the other user's device.

[1799] Step 7:

[1800] Other users can participate in the discussion. Check the comment notifications you receive and post new comments to stimulate the discussion. For example, you could reply, "I agree. The field of deep learning is particularly advanced."

[1801] (Application example 1)

[1802] 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."

[1803] Currently, in many factories, it often takes a long time for workers to find solutions to technical questions or problems. Furthermore, workers must check multiple materials and documents to find the information they need, which is inefficient. Furthermore, a lack of real-time discussion and knowledge sharing on-site hinders information sharing and technological improvement. To solve these problems, a system is needed in which factory robots themselves can answer workers' questions, provide necessary information, and facilitate discussion.

[1804] 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.

[1805] In this invention, the server includes a question receiving means for using a generative artificial intelligence model to provide appropriate answers to questions from users on the online community platform, a generating means for sending the content of the question to the generative artificial intelligence model and generating an answer, an answer output means for displaying the generated answer to the user, a worker question receiving means for receiving questions from workers in a system incorporated in a factory robot, a robot display means for displaying the answer on a robot operation panel, a search receiving means for analyzing past posts and related materials in the online community and providing useful information to users, and a search engine for sending search keywords to the generative artificial intelligence model and collecting related information. The system includes an analysis means, an information display means for organizing the collected information and displaying it to the user, a worker information search means for allowing factory workers to search for useful information related to a specific technology, a robot information display means for displaying information on a robot operation panel, a new topic generation means for promoting discussions within an online community using a generative artificial intelligence model, a topic notification means for notifying users of the generated topics, a comment notification means for receiving user comments and notifying other users, a discussion topic generation means for promoting discussions among factory workers, and a robot comment display means for displaying comments on the robot operation panel. This enables workers to obtain answers to technical questions in real time and quickly search for and share necessary information, while also stimulating discussions on site, enabling efficient problem solving and knowledge sharing.

[1806] A "generative artificial intelligence model" is an artificial intelligence technology for generating natural language text based on input data.

[1807] An "online community platform" is a digital service that allows users to interact and share information over the Internet.

[1808] The "question receiving means" is an interface for receiving questions from users.

[1809] "Generation means" is a process for analyzing the content of a question and generating an appropriate answer using a generative artificial intelligence model.

[1810] The "answer output means" is an interface for displaying the generated answer to the user.

[1811] A "factory robot" is an industrial machine that is programmed to perform automated tasks.

[1812] The "means for receiving questions from workers" is an interface that allows the robot to receive technical questions from factory workers.

[1813] The "robot display means" is an interface for displaying data on the robot's operation panel.

[1814] The "search receiving means" is an interface that allows users to input search keywords and topics.

[1815] "Analysis means" refers to the process of analyzing input data using a generative artificial intelligence model and collecting relevant information.

[1816] The "information display means" is an interface for organizing collected information and displaying it to the user.

[1817] The "worker information search means" is an interface that allows factory workers to search for specific techniques or information.

[1818] A "discussion topic generator" is a process that generates new topics to facilitate discussion.

[1819] The "topic notification means" is an interface for notifying users of generated discussion topics.

[1820] The "comment notification means" is an interface for notifying other users of comments posted by a user.

[1821] The "robot comment display means" is an interface for displaying comments on the robot's operation panel.

[1822] This invention is a system that utilizes a generative artificial intelligence model to support factory workers. This system realizes functions such as providing answers to questions, organizing and providing useful information, and facilitating discussions.

[1823] Specifically, the following processing is performed.

[1824] The server uses the generative artificial intelligence model to provide appropriate answers to questions from factory workers. The worker inputs a question through the robot operation panel, and the data is sent to the server through a question receiving means. On the server, the generative artificial intelligence model analyzes the question and generates an appropriate answer. The generated answer is displayed on the robot operation panel through an answer output means. As a specific example, when a worker asks, "How do I troubleshoot signal analysis?", the generative artificial intelligence model responds, "To identify the root cause of the problem, first observe the signal waveform using an oscilloscope. If an abnormal pattern is found, analyze that part in more detail. Adjust the filter if necessary and check the signal regularity."

[1825] The server also provides useful materials when factory workers search for specific technologies or information. When a worker enters search keywords, the data is sent to the server through a search receiving means. On the server, a generative AI model analyzes past posts and related materials, collecting and organizing related information. The collected information is displayed on the robot operation panel through an information display means. For example, if a worker searches for "the latest methods for optimizing automation processes," the generative AI model will list "overviews of the latest research" and "concrete application examples" and provide them to the worker.

[1826] Furthermore, the server generates new topics and notifies comments to promote discussions among factory workers. New discussion topics are periodically generated by a new topic generation means and notified to workers via a topic notification means. Workers enter comments on the notified topics, and these comments are notified to other workers via the comment notification means. This process stimulates the exchange of opinions on-site and promotes problem solving and technological improvement. For example, if a topic such as "What are the technological trends for next month?" is generated and a worker comments, "Advances in AI and machine learning are attracting attention," other workers are notified and a discussion begins.

[1827] The specific implementation of this system utilizes OpenAI's GPT-3 API to display answers, information, and comments on the operation panel of a factory robot. Workers can enter questions and comments on topics through the robot's operation panel, enabling real-time answers, information search, and discussion.

[1828] Examples of prompt sentences include:

[1829] Example 1:

[1830] "Question from a factory worker: How do I troubleshoot signal analysis?"

[1831] "Specific answer provided: To identify the root cause of the problem, first observe the signal waveform using an oscilloscope. If an abnormal pattern is found, analyze that area further. Adjust the filter as needed to check for signal regularity."

[1832] Example 2:

[1833] "Topic request from a factory worker: What are the latest techniques for optimizing automated processes?"

[1834] "Specific information provided: Provide workers with an overview of the latest research and a list of specific applications."

[1835] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1836] Step 1:

[1837] A user uses the operation panel of a factory robot to input technical questions, information searches, and discussion topics. For example, the user inputs a question such as "How do I troubleshoot signal analysis?" The user's input data is sent to the server through the worker question receiving means.

[1838] Step 2:

[1839] The server uses a question receiving means to pass the question data sent by the user to the generative AI model and request that it generate an answer.The server then analyzes the input question and sends it as a prompt to the API of the generative AI model.

[1840] Step 3:

[1841] The generative AI model generates an appropriate answer based on the prompt. For example, it might generate an answer such as, "Use an oscilloscope to observe the signal waveform." The model generates answer data as natural language text by referencing past knowledge bases and case studies.

[1842] Step 4:

[1843] The server receives the answer from the generative artificial intelligence model using the generating means. The received answer data is passed directly to the answer output means, where it is processed to be displayed on the robot operation panel.

[1844] Step 5:

[1845] The terminal displays the generated answer on the user's operation panel through the answer output means, and the user can check the generated answer on the robot's operation panel and follow the specific instructions.

[1846] Step 6:

[1847] When a user searches for a specific technology or information, the user inputs search keywords using the operation panel. The search keywords are sent to the server through the search receiving means. For example, a user searches for "latest methods for optimizing automated processes."

[1848] Step 7:

[1849] The server uses the search receiving means to send search keywords to the generative artificial intelligence model and request the collection of related information. The generative artificial intelligence model analyzes related materials based on the input keywords and lists useful information.

[1850] Step 8:

[1851] The generative artificial intelligence model generates related information and transmits it to the server, which uses the information display means to organize the received related information and convert it into a display format.

[1852] Step 9:

[1853] The terminal displays the collected useful information on the operation panel through the information display means, allowing the user to check the necessary information and use it in their work.

[1854] Step 10:

[1855] The server periodically generates new discussion topics using the new topic generation means, and the generated topics are notified to users via the topic notification means.

[1856] Step 11:

[1857] A user inputs a comment on a new topic and sends it to the server via the operation panel. The input comment is notified to other users via the comment notification means.

[1858] Step 12:

[1859] The server notifies all users of comments, promoting discussion. Users can check other users' comments through the operation panel, exchange opinions, and share information.

[1860] 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.

[1861] This invention is a system that supports the operation of an online community platform by combining a generative AI model and an emotion engine. This system provides answers to questions, organizes and provides useful information, and promotes discussions, realizing interactions that respond to the user's emotional state.

[1862] Answering questions with emotion recognition

[1863] Processing Flow

[1864] 1. A user logs in to an online community platform, enters "What is the difference between a for loop and a while loop in Python?" in the question posting interface, and presses the "Submit" button.

[1865] 2. The device sends the entered question to the server.

[1866] 3. The server analyzes the user's emotional state using the emotion engine along with the content of the user's question.

[1867] 4. The server passes the question and the user's emotional state to the generative AI model and sends a request to generate an answer.

[1868] 5. A generative AI model analyzes the question and generates an appropriate answer with a tone and content that reflects the user's emotional state (e.g., "For loops are used to repeat a set number of times, while while loops are used to repeat while a condition is true.").

[1869] 6. The server sends the generated response to the device.

[1870] 7. The device displays the answer to the user.

[1871] Providing useful information with emotion recognition

[1872] Processing Flow

[1873] 1. A user types "useful articles about data science" into the search interface of an online community platform and presses the "Search" button.

[1874] 2. The device sends the entered search keywords to the server.

[1875] 3. The server analyzes the user's emotional state using an emotion engine along with the received search keywords.

[1876] 4. The server passes the search keywords and the user's emotional state to the generative AI model and sends a request to collect related information.

[1877] 5. A generative AI model analyzes search keywords and lists relevant information with priority and display content based on the user's emotional state (e.g., "Introductory articles on data science" or "Basics of data analysis using Python").

[1878] 6. The server sends the organized information list to the terminal.

[1879] 7. The terminal displays the information list to the user.

[1880] Facilitating discussions with emotion awareness

[1881] Processing Flow

[1882] 1. The server periodically calls the API of the generative artificial intelligence model to request the generation of new topics and questions.

[1883] 2. Generative AI models analyze past community posts and trends to generate interesting new topics and questions (e.g., "What are the technology trends next month?").

[1884] 3. For topics generated by the generative AI model, an emotion engine is used to tailor feedback and responses according to the user's emotional state.

[1885] 4. The server sends the generated topic to the terminal and notifies the user.

[1886] 5. The device displays a new topic notification to the user.

[1887] 6. A user posts a comment on a new topic saying, "Advances in AI and machine learning are attracting attention."

[1888] 7. The device sends the user's comments to the server, and the emotion engine analyzes the user's emotional state.

[1889] 8. The server notifies other users of the received comments and emotional state.

[1890] 9. Other users can join the discussion based on the notifications they receive, further stimulating the discussion.

[1891] In this way, inventions that combine emotion engines will make online community management even more user-friendly, enabling more appropriate and personalized interactions. By providing answers, organizing information, and promoting discussions in accordance with the user's emotional state, the community will become more attractive and people willing to participate will increase.

[1892] The processing flow will be explained below.

[1893] Answering questions with emotion recognition

[1894] Processing Flow

[1895] Step 1:

[1896] A user logs in to an online community platform, enters "What is the difference between a for loop and a while loop in Python?" in the question posting interface, and presses the "Submit" button.

[1897] Step 2:

[1898] The terminal sends the entered question to the server.

[1899] Step 3:

[1900] The server receives the question and uses an emotion engine to analyze the user's emotional state, thereby determining the emotion (e.g., excitement, annoyance, confusion, etc.) at the time the user submits the question.

[1901] Step 4:

[1902] The server passes the question and the user's emotional state to a generative AI model and sends a request to generate an answer.

[1903] Step 5:

[1904] The generative AI model analyzes the question and the user's emotional state to generate an answer with the appropriate tone and content. For example, if the user is confused, the generated answer will be more polite and detailed.

[1905] Step 6:

[1906] The server receives the generated response and transmits it to the terminal.

[1907] Step 7:

[1908] The terminal displays the answer to the user.

[1909] Providing useful information with emotion recognition

[1910] Processing Flow

[1911] Step 1:

[1912] A user types "helpful articles about data science" into the search interface of an online community platform and presses the "Search" button.

[1913] Step 2:

[1914] The terminal transmits the entered search keyword to the server.

[1915] Step 3:

[1916] The server receives the search keywords and uses an emotion engine to analyze the user's emotional state, thereby determining the type of information the user is currently interested in and their emotions (e.g., excitement, curiosity, professional interest, etc.).

[1917] Step 4:

[1918] The server passes the search keywords and emotional state to a generative artificial intelligence model and sends a request to collect related information.

[1919] Step 5:

[1920] A generative artificial intelligence model analyzes search keywords and emotional state to generate a list of information with adjusted priorities and content (e.g., "Introductory articles on data science" or "Basics of data analysis using Python").

[1921] Step 6:

[1922] The server receives the generated information list and transmits it to the terminal.

[1923] Step 7:

[1924] The terminal displays the information list to the user.

[1925] Facilitating discussions with emotion awareness

[1926] Processing Flow

[1927] Step 1:

[1928] The server periodically calls the API of the generative artificial intelligence model, requesting the generation of new topics and questions.

[1929] Step 2:

[1930] A generative artificial intelligence model analyzes past community posts and trends to generate interesting new topics and questions (e.g., "What are the technology trends next month?").

[1931] Step 3:

[1932] A server receives the generated topics, analyzes the user's emotional state using an emotion engine, and generates emotional feedback related to the topics.

[1933] Step 4:

[1934] The server sends the generated topic and emotional feedback to the terminal and notifies the user.

[1935] Step 5:

[1936] The device displays new topic notifications to the user.

[1937] Step 6:

[1938] A user posts a comment on a new topic saying, "Advances in AI and machine learning are attracting attention."

[1939] Step 7:

[1940] The device sends the user's comments to the server, and the emotion engine analyzes the user's emotional state.

[1941] Step 8:

[1942] The server notifies the received comments and emotional states to the terminals of other users.

[1943] Step 9:

[1944] Other users can join the discussion based on the notifications they receive, further stimulating the discussion.

[1945] By using the above processing flow, the system of the present invention combined with the emotion engine can provide appropriate and personalized interactions according to the user's emotional state.

[1946] Example 2

[1947] 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."

[1948] In online community platforms, it is important to provide quick and appropriate answers to users' diverse questions, effectively present useful information when users search, and stimulate discussions. However, conventional systems lack interactions that take into account the user's emotional state, which has led to issues such as reduced user satisfaction and community activity.

[1949] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a question receiving means for receiving a question from a user, an answer generating means for analyzing the question content and the user's emotional state and transmitting the content to a generative AI model to generate an answer, and an answer output means for displaying the generated answer to the user. This makes it possible to provide an answer according to the user's emotional state.

[1950] The server includes a search receiving means for receiving search keywords from a user and analyzing the user's emotional state, an information collecting means for transmitting the search keywords and the user's emotional state to a generative artificial intelligence model and collecting related information, and an information display means for organizing the collected information and displaying it to the user, thereby making it possible to provide useful information according to the user's emotional state.

[1951] The server includes a new topic generation means for generating new discussion topics using a generative artificial intelligence model, a topic notification means for notifying users of the generated topics, and a comment notification means for receiving comments posted by users and notifying other users of the comments, thereby enabling the promotion of discussions.

[1952] The "question receiving means" is a function or device for receiving questions from users.

[1953] "Answer generation means" refers to a function or device that analyzes the question content and the user's emotional state, and sends the results to a generative artificial intelligence model to generate an answer.

[1954] The "answer output means" refers to a function or device for displaying the generated answer to the user.

[1955] The "search receiving means" is a function or device for receiving search keywords from a user and analyzing the user's emotional state.

[1956] "Information collection means" refers to a function or device for sending search keywords and the user's emotional state to a generative artificial intelligence model and collecting related information.

[1957] "Information display means" refers to a function or device for organizing collected information and displaying it to the user.

[1958] "New topic generation means" refers to a function or device for generating new discussion topics using a generative artificial intelligence model.

[1959] The "topic notification means" is a function or device for notifying users of the generated topic.

[1960] The "comment notification means" is a function or device for receiving comments posted by a user and notifying other users of the comments.

[1961] This invention is a management support system for an online community platform that combines a generative AI model and an emotion engine. This system answers questions with emotion recognition, provides useful information, and promotes discussion.

[1962] Functions and technologies used

[1963] Providing answers to questions

[1964] When a user logs in to an online community platform and submits a question, the terminal sends the question data to a server. The server then analyzes the user's emotional state using an emotion engine along with the received question content. In this case, the emotion engine uses what is commonly known as an emotion analysis API (e.g., an emotion analysis tool or emotion analysis technology).

[1965] The server then passes the question and the user's emotional state to a generative AI model (commonly known as an AI model) and sends a request to generate an answer. For example, a generative AI model. This generative AI model analyzes the question and generates an appropriate answer with a tone and content that matches the user's emotional state. This generated answer is then sent back from the server to the device, where it is displayed to the user.

[1966] Examples:

[1967] User Question: "What is the difference between a for loop and a while loop in Python?"

[1968] Example prompt: "The user asks, 'What is the difference between a for loop and a while loop in Python?' and their emotional state is curious. Please generate a kind and concise answer."

[1969] Providing useful information

[1970] When a user enters and submits a search keyword, the device sends the search keyword to the server. The server then uses an emotion engine to analyze the user's emotional state along with the received search keyword. The analysis uses a generically named emotion analysis API.

[1971] The server then passes the search keywords and the user's emotional state to a generative AI model and sends a request to collect related information. The generative AI model analyzes the search keywords and lists related information with priority and display content according to the user's emotional state. The organized information list is then sent back from the server to the device, where it is displayed to the user.

[1972] Examples:

[1973] User search keywords: "helpful articles about data science"

[1974] Example prompt: "A user has searched for 'helpful articles about data science' and is in an excited emotional state. Please provide a list of articles that are easy to understand and aimed at beginners."

[1975] Facilitating discussion

[1976] The server periodically calls the API of the generative AI model to request the generation of new topics and questions. The generative AI model analyzes past community posts and trends to generate interesting new topics and questions. It then uses an emotion engine to adjust the feedback and response content for the generated topics, which the server then sends to the device and notifies the user.

[1977] When a user posts a comment on a new topic, the device sends the comment to the server, where the emotion engine analyzes the user's emotional state. The server then notifies other users of the received comment and emotional state, stimulating discussions.

[1978] Examples:

[1979] New discussion topic: "What are the technology trends for next month?"

[1980] Example prompt: "Generate new discussion topics based on trends across the community. Topics that many users find entertaining and exciting."

[1981] In this way, systems that utilize emotion understanding can realize user-friendly designs for managing online communities. From selecting topics to providing content and answers, it is possible to provide optimal interactions according to the user's emotional state.

[1982] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1983] Answering questions with emotion recognition

[1984] Step 1:

[1985] A user logs into an online community platform, enters a question, and presses the "Submit" button.

[1986] How it works: A user accesses the question form using a browser or a dedicated app, enters "What is the difference between a for loop and a while loop in Python?", and clicks the submit button.

[1987] Input: Text data of the question

[1988] Output: Instructions to submit a question

[1989] Step 2:

[1990] The terminal transmits the input question data to the server.

[1991] How it works: The device sends the question entered by the user to the server as an HTTP request, which includes the user ID and the question.

[1992] Input: HTTP request data (user ID, question)

[1993] Output: The request sent to the server

[1994] Step 3:

[1995] The server uses an emotion engine to analyze the question content and the user's emotional state.

[1996] How it works: The server sends the question content as an API request to the emotion engine, and analyzes the returned emotion data. The emotion engine uses the generic name emotion analysis API.

[1997] Input: Text data of the question

[1998] Output: Emotional information (e.g. curious, confused)

[1999] Step 4:

[2000] The server sends the question and the user's emotional state to the generative AI model and sends a request to generate an answer.

[2001] Operation: The server generates a prompt containing the question and emotion data for the API of the generative AI model, and sends an API request.

[2002] Input: Question content, emotion data

[2003] Output: Answer generation request

[2004] Step 5:

[2005] A generative AI model analyzes the question and generates an answer with a tone and content that reflects the user's emotional state.

[2006] How it works: The model parses the prompt and generates an appropriate answer, which is returned to the server as an API response.

[2007] Input: Prompt sentence (question content, emotion data)

[2008] Output: The generated answer

[2009] Step 6:

[2010] The server sends the generated response to the terminal.

[2011] How it works: The server sends a response containing the generated answer to the device as an HTTP request.

[2012] Input: Generated answer

[2013] Output: Sending response data

[2014] Step 7:

[2015] The terminal displays the answer to the user.

[2016] Operation: The device displays the received response data on the screen, providing visual feedback to the user.

[2017] Input: Response data

[2018] Output: Update the screen display

[2019] Providing useful information with emotion recognition

[2020] Step 1:

[2021] A user enters keywords into the search interface of an online community platform and presses the "Search" button.

[2022] What happens: A user enters "helpful articles about data science" into the search form and clicks the search button.

[2023] Input: Search keyword text data

[2024] Output: Search submission instructions

[2025] Step 2:

[2026] The terminal transmits the entered search keyword to the server.

[2027] How it works: The device sends the search keyword to the server as an HTTP request. The request includes the user ID and the search keyword.

[2028] Input: HTTP request data (user ID, search keywords)

[2029] Output: The request sent to the server

[2030] Step 3:

[2031] The server analyzes the received search keywords and the user's emotional state using an emotion engine.

[2032] How it works: The server sends search keywords as API requests to the emotion engine and analyzes the returned emotion data.

[2033] Input: Search keyword text data

[2034] Output: Emotional information (e.g., excited, relaxed)

[2035] Step 4:

[2036] The server sends the search keywords and the user's emotional state to a generative artificial intelligence model and sends a request to collect related information.

[2037] How it works: The server generates a prompt containing search keywords and emotion data for the API of the generative AI model and sends an API request.

[2038] Input: Search keywords, emotion data

[2039] Output: Information collection request

[2040] Step 5:

[2041] A generative artificial intelligence model analyzes search keywords and lists relevant information based on priority and content.

[2042] How it works: The model parses the prompt, gathers the appropriate information, and generates a list, which is returned to the server as an API response.

[2043] Input: Prompt sentence (search keywords, emotion data)

[2044] Output: Generated information list

[2045] Step 6:

[2046] The server transmits the generated information list to the terminal.

[2047] Operation: The server sends a response containing the generated information list to the terminal as an HTTP request.

[2048] Input: Generated information list

[2049] Output: Sending a list of information

[2050] Step 7:

[2051] The terminal displays the information list to the user.

[2052] Operation: The device displays the received information list on the screen, providing visual feedback to the user.

[2053] Input: Information List

[2054] Output: Update the screen display

[2055] Facilitating discussions with emotion awareness

[2056] Step 1:

[2057] The server periodically calls the API of the generative artificial intelligence model, requesting the generation of new topics and questions.

[2058] How it works: The server sets up a periodic job and calls the API of the generative AI model at specific time intervals.

[2059] Input: Trigger signal for periodic job

[2060] Output: New topic creation request

[2061] Step 2:

[2062] A generative artificial intelligence model analyzes past community posts and trends to generate interesting new topics and questions.

[2063] How it works: The model analyzes historical data and generates new topics, which are then returned to the server as API responses.

[2064] Input: Prompt text (past posting data, trend information)

[2065] Output: Generated topics

[2066] Step 3:

[2067] The generative artificial intelligence model uses an emotion engine to analyze the user's emotional state and adjust the feedback depending on the topic.

[2068] How it works: For each topic, sentiment analysis is performed to tailor feedback based on the user's past sentiment data.

[2069] Input: Generated topics

[2070] Output: Sentiment analysis feedback

[2071] Step 4:

[2072] The server sends the generated topic to the terminal and notifies the user.

[2073] Operation: The server sends the generated topic to the terminal as a notification message.

[2074] Input: Generated topics

[2075] Output: Topic notification data

[2076] Step 5:

[2077] The device displays new topic notifications to the user.

[2078] Behavior: The device displays a notification message in a pop-up window or in the notification bar.

[2079] Input: Topic notification data

[2080] Output: On-screen notification

[2081] Step 6:

[2082] A user enters a comment on a new topic and clicks the post button.

[2083] What happens: A user enters their opinion into the comment form and clicks the post button.

[2084] Input: Text data of comment content

[2085] Output: Instructions to send comments

[2086] Step 7:

[2087] The terminal transmits the user's comments to the server.

[2088] How it works: The device sends the user's comments as an HTTP request to the server, and the server analyzes the user's emotional state using an emotion engine.

[2089] Input: HTTP request data (user ID, comment content)

[2090] Output: Send comment data

[2091] Step 8:

[2092] The server notifies the received comments and emotional states to the terminals of other users.

[2093] How it works: The server sends notification messages to other relevant users based on the comments and emotion data.

[2094] Input: Comment content, emotion data

[2095] Output: Comment notification data

[2096] Step 9:

[2097] Other users join the discussion, making it more lively.

[2098] What happens: Other users see the notification, join the discussion, and post comments.

[2099] Enter: Comment Notification

[2100] Output: Stimulating discussion

[2101] This will create an online community management support system that utilizes emotion recognition and generative AI models. The system will provide appropriate answers according to the user's emotional state, present useful information, and promote discussion.

[2102] (Application example 2)

[2103] 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."

[2104] In online and real-world environments, it is important to provide appropriate interactions without being hindered by the emotional state of users and customers. However, existing systems do not take the emotional state of users and customers into account, which can lead to reduced satisfaction and effectiveness. In addition, providing information and promoting discussions is done uniformly without adapting to the emotional state, which creates the challenge of not being able to provide services tailored to individual needs.

[2105] The specific processing by the specific 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 a question receiving means, a generating means, an answer output means, a sentiment analysis means, and an answer adjustment means. This makes it possible to adjust answers based on the emotional state of the user or customer and provide more personalized interactions. In addition, by using an information priority adjustment means, the priority of information provided to the user can be adjusted according to the emotional state, and by using a discussion activation means, lively discussions based on sentiment analysis can be promoted.

[2106] The "question receiving means" is a system or device for receiving questions from users.

[2107] The "generation means" is a system or device that generates an answer using a generative artificial intelligence model based on the content of the received question.

[2108] The "answer output means" is a system or device for displaying or providing the generated answer to the user.

[2109] An "emotion analysis means" is a system or device for analyzing emotions using facial expressions and other data of a customer.

[2110] The "answer adjustment means" is a system or device for adjusting the tone and content of the generated answer based on the emotion data obtained by the emotion analysis means.

[2111] The "search receiving means" is a system or device for receiving search keywords from a user.

[2112] "Analysis means" refers to a system or device for sending search keywords to a generative artificial intelligence model and collecting related information.

[2113] "Information display means" refers to a system or device for organizing collected information and displaying it to the user.

[2114] The "information priority adjustment means" is a system or device for adjusting the priority of collected information in consideration of the emotional state of the user obtained by emotion analysis.

[2115] A "new topic generation means" is a system or device for generating new topics using a generative artificial intelligence model.

[2116] The "topic notification means" is a system or device for notifying users of generated topics.

[2117] The "comment notification means" is a system or device for receiving a user's comment and notifying other users of the comment.

[2118] The "discussion activation means" is a system or device for activating discussions using sentiment analysis.

[2119] This invention is a system that combines a generative artificial intelligence model and an emotion analysis engine to improve customer experience in brick-and-mortar stores. A specific example of this system is described below.

[2120] System configuration

[2121] The system comprises a question receiving means, a generating means, an answer output means, a sentiment analysis means, and an answer adjustment means.

[2122] 1. How to receive questions:

[2123] Questions from users are received through a smartphone application, which has an interface that allows users to freely input questions.

[2124] 2. Generation means:

[2125] A question is sent via an online API to a generative AI model (e.g., GPT-4), which analyzes the question and generates an appropriate answer.

[2126] 3. Answer output means:

[2127] This is a means for displaying the generated answers to the user. The answers are displayed on the smartphone application.

[2128] 4. Emotion analysis means:

[2129] Customers' facial expressions are captured using a smartphone camera and analyzed using an emotion analysis engine (for example, Microsoft Azure's Emotion API), which allows us to identify the customer's current emotional state.

[2130] 5. Response adjustment method:

[2131] The responses generated by the generative AI model are adjusted based on emotional data obtained through sentiment analysis. For example, if a customer is feeling stressed, the system will provide responses in a more relaxing tone.

[2132] System Operation

[2133] This system uses the following hardware and software:

[2134] Hardware

[2135] Smartphone (iOS or Android)

[2136] Server (Linux server)

[2137] Camera (built-in camera on smartphone)

[2138] software

[2139] Emotion engine (Microsoft Azure Emotion API)

[2140] Generative AI model (using GPT-4)

[2141] App development framework (React Native)

[2142] Database (MySQL or PostgreSQL)

[2143] Data processing and calculation

[2144] The data is processed and calculated as follows:

[2145] Customer facial expression data is captured by a camera and their emotional state is analyzed using an emotion analysis engine.

[2146] Based on your emotional state, the responses generated by the generative AI model are adjusted to optimize tone and content.

[2147] Specific examples

[2148] A customer types "Tell me about the latest trending products" into a smartphone app and submits it. At this time, the smartphone camera captures the customer's face and performs emotional analysis. As a result, the generative AI model generates a tone-adjusted response based on the customer's emotional state, such as "Here are the latest trending products. They have a particularly relaxing effect, making them perfect for when you're tired," and displays it on the smartphone.

[2149] Prompt Sentence Examples

[2150] User prompt: "What are the latest trending products?"

[2151] This will enable a more personalized customer experience in physical stores and improve customer satisfaction.

[2152] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2153] Step 1:

[2154] A user inputs a question into a smartphone app. For example, "What are the latest trending products?" and presses the send button. The input includes the user's question text. The device receives this question data and sends it to the server.

[2155] Step 2:

[2156] The server receives question data sent by the user. The received data includes the user's question text. The server sends this question text to a generative AI model and requests it to generate an answer.

[2157] Step 3:

[2158] A generative AI model generates an answer based on the question received from the server. The input includes the user's question text. The model analyzes the question, generates an appropriate answer text, and sends it back to the server.

[2159] Step 4:

[2160] The server receives the answer text received from the generative AI model. The received data includes the generated answer text. The server temporarily stores this answer and waits until it receives emotion data from the device.

[2161] Step 5:

[2162] The device captures the user's facial expressions using the smartphone's built-in camera and sends them to the emotion analysis engine. The input data includes facial expression images. The device receives the emotion data as the analysis result and sends it to the server.

[2163] Step 6:

[2164] The server receives the emotion data sent from the emotion analysis engine. The received data includes the user's emotional state. Based on the emotion data, the server sends a request to the generative AI model to adjust the pre-generated answer text.

[2165] Step 7:

[2166] A generative AI model adjusts the response text based on the emotion data received from the server. The input includes the stored response text and emotion data. The model adjusts the tone of the response to match the user's emotional state and sends the adjusted response text back to the server.

[2167] Step 8:

[2168] The server transmits the adjusted answer text to the terminal. The received data includes the answer text adjusted to match the emotional state.

[2169] Step 9:

[2170] The device displays the adjusted answer text to the user, who then accepts the answer displayed on the smartphone app to complete the interaction.

[2171] 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.

[2172] 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.

[2173] 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.

[2174] 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.

[2175] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2176] 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.

[2177] 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).

[2178] Human emotions are based on v...

Claims

1. Using generative artificial intelligence models to provide appropriate answers to user questions in an online community platform A question receiving means; Send the question to a generative AI model to generate an answer. generating means; To display the generated answer to the user An answer output means; A system including:

2. Analyzing past posts and related materials in online communities to provide users with useful information search receiving means; Sending search keywords to a generative AI model to gather related information Analysis means; To organize the collected information and display it to the user information display means; The system of claim 1 , comprising:

3. Using generative artificial intelligence models to facilitate discussions within online communities A new topic generation means; To notify users of generated topics a topic notification means; To receive user comments and notify other users A comment notification means; The system of claim 1 , comprising:

Images