System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a support request from a user; means for obtaining a user's historical support history and device information based on the support request; means for generating a problem solution using a generative model using the obtained information; means for providing the generated solution to the user; and means for receiving feedback from the user on the provided solution.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] With traditional in-store support systems, support is only available during business hours, making it difficult for users to quickly resolve urgent issues. While online support systems exist, they are often limited to basic FAQs and may not be able to provide appropriate solutions to individual user problems. This results in lower user satisfaction, which has a negative impact on sales and brand image. [Means for solving the problem]

[0005] To solve the above problems, the present invention proposes a support system including a means for receiving a support request from a user, a means for acquiring the user's past support history and device information based on the support request, a means for generating a solution to a problem using a generative model with the acquired information, a means for providing the generated solution to the user, and a means for receiving user feedback on the provided solution. This system enables users to receive individual support 24 hours a day, from anywhere, thereby improving the efficiency of problem solving. Furthermore, by retraining the generative model based on user feedback, it is possible to always provide support using the latest information and methods.

[0006] "Support Request" means the inquiry information that a User submits to the System for help.

[0007] "Your Support History" means a database or record containing information about all support you have received in the past and the outcomes of those support efforts.

[0008] "Device information" refers to detailed information about the model, settings, status, etc. of the device (smartphone, PC, tablet, etc.) used by the user.

[0009] A "generative model" refers to an algorithm or software that uses machine learning or artificial intelligence techniques to generate solutions or predictions based on input data.

[0010] A "problem-solving solution" refers to a specific solution or procedure for a specific problem or question.

[0011] "Feedback" refers to opinions and information provided by users, including reactions to and suggestions for improvement regarding the solutions to problems provided.

[0012] "Support System" means a set of hardware and software components designed to provide user support. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention is a system designed to enable users to receive support 24 hours a day. Specifically, it comprises a means for receiving a support request from a user, a means for acquiring the user's past support history and device information, a means for generating a solution to a problem using a generative model, a means for providing the generated solution to the user, and a means for receiving user feedback.

[0035] Explanation of program processing

[0036] 1. The server starts first and loads the necessary data and AI models.

[0037] The server establishes a database connection and loads user information, support history, and FAQs into a cache.

[0038] The server loads the generative AI model and updates it if necessary from an external source.

[0039] 2. The user requests support using their device (smartphone or PC).

[0040] The user opens a dedicated application on the device and fills out an inquiry form.

[0041] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[0042] 3. The device sends the request to the server.

[0043] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[0044] 4. The server receives the request and retrieves the user's support history and device information.

[0045] The server searches the database for the corresponding user ID and retrieves the necessary information.

[0046] 5. The server inputs the problem summary and historical data into the AI ​​model and generates a solution.

[0047] The server uses the AI ​​model to generate a solution based on the user's current problem and past patterns.

[0048] 6. The server converts the generated solution into a format that is easy for the user to understand and sends it to the terminal.

[0049] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[0050] 7. The device displays the received information to the user.

[0051] The device displays instructions on the screen and the user attempts to solve the problem.

[0052] 8. The user follows the steps to resolve the issue and provides feedback on success or failure.

[0053] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[0054] 9. The server receives the feedback and records it in a database.

[0055] The server stores the feedback information in a database and updates the AI ​​model as needed.

[0056] Specific examples

[0057] For example, say a user is having trouble setting up Wi-Fi on their smartphone.

[0058] 1. The user enters the problem "I can't connect to Wi-Fi" on their device, attaches a screenshot, and submits a request.

[0059] 2. The server receives the request and retrieves the support history and the user's device information.

[0060] 3. The server uses the acquired information to use AI models to generate solutions to common Wi-Fi configuration issues and user-specific troubleshooting steps.

[0061] 4. The server sends the generated instructions to the user's device using text and images.

[0062] 5. The device displays the received instructions on the screen, and the user attempts to set up Wi-Fi by following the instructions.

[0063] 6. The user sends feedback from the device to the server, indicating whether the setup was successful or not.

[0064] 7. The server receives the feedback, records it in the system database, and retrains the generative model if necessary.

[0065] This system allows users to receive fast, accurate support 24 hours a day.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The server starts up and loads the necessary data and AI models.

[0069] The server establishes a database connection and loads user information, support history, and FAQs into memory.

[0070] The server loads the generative AI model and updates it if necessary from an external source.

[0071] Step 2:

[0072] The user requests support using a device (smartphone or PC).

[0073] The user opens a dedicated application on the device and fills out an inquiry form.

[0074] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[0075] Step 3:

[0076] The device sends a request to the server.

[0077] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[0078] Step 4:

[0079] The server receives the request and retrieves the user's support history and device information.

[0080] The server searches the database for the corresponding user ID and retrieves the necessary information.

[0081] Step 5:

[0082] The server inputs a problem summary and historical data into the AI ​​model and generates a solution.

[0083] The server uses the AI ​​model to generate a solution based on the user's current problem and past patterns.

[0084] Step 6:

[0085] The server converts the generated solution into a format that is easy for the user to understand and sends it to the terminal.

[0086] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[0087] Step 7:

[0088] The device displays the received information to the user.

[0089] The device displays instructions on the screen and the user attempts to solve the problem.

[0090] Step 8:

[0091] The user follows the steps to resolve the issue and provides feedback on success or failure.

[0092] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[0093] Step 9:

[0094] The server receives the feedback and records it in a database.

[0095] The server stores the feedback information in a database and updates the AI ​​model as needed.

[0096] Example 1

[0097] 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."

[0098] In recent years, with the advancement of electronic devices and information and communication technology, users are increasingly encountering problems with complex devices and software. To quickly address these issues, 24-hour support is necessary, but current support systems are insufficient and fail to satisfy users. Furthermore, manual support by support staff can be time-consuming and costly, resulting in prolonged resolution times. Given this background, there is a demand for automated support systems that can quickly and efficiently resolve user problems.

[0099] 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.

[0100] In this invention, the server includes means for receiving a support request from a user, means for retrieving the user's past support history and device information from a database based on the received support request, means for utilizing a generative AI model using the retrieved information to send prompt text and generate a solution to the problem, means for converting the generated solution into a format that is easy for the user to understand (text, image, etc.) and sending it to the user terminal, and means for receiving and recording user feedback on the provided solution, thereby enabling users to receive fast and highly accurate support 24 hours a day.

[0101] A "server" is a central computer system that receives requests from users and processes data.

[0102] "Support Request" means a request submitted by a User to resolve a Device or Software issue.

[0103] A "database" is an information system for systematically storing and managing user information, support history, device information, etc.

[0104] A "generative AI model" is an artificial intelligence model that automatically generates solutions to problems based on input information.

[0105] A "prompt sentence" is text data input into a generative AI model that contains instructions and conditions for solving a problem.

[0106] A "solution" is a procedure or method for solving a user's problem obtained using a generative AI model.

[0107] A "user terminal" is a computer device (such as a smartphone or PC) used by a user, which receives and displays information from a server.

[0108] "Feedback" refers to evaluation information that a user sends back to the server regarding the effectiveness and results of the solution provided.

[0109] Based on these definitions, the technical scope of the invention is clearly defined.

[0110] This invention is a system that allows users to receive support 24 hours a day. Specifically, it is implemented using the following hardware and software.

[0111] Hardware and Software Configuration

[0112] 1. Server: A high-performance computing system that receives requests, connects to a database, and executes generative AI models. Examples include Linux (registered trademark)-based servers and cloud services (AWS (registered trademark), Google (registered trademark) Cloud, etc.).

[0113] 2. Database: Stores user information, support history, FAQs, etc. Uses relational databases such as MySQL (registered trademark) and PostgreSQL.

[0114] 3. Generative AI models: Generate solutions to problems using deep learning models such as GPT-3 (registered trademark) and BERT.

[0115] 4. User device: A computing device that users use on a daily basis, such as a smartphone or PC.

[0116] Specific functions of the system

[0117] 1. The server receives a support request from the user, often in the form of an HTTP POST request.

[0118] 2. The server connects to the database and retrieves the user's past support history and device information.

[0119] 3. The server sends a prompt to the generative AI model to generate a solution to the problem. An example of a prompt is, "A user is reporting an issue where they cannot connect to Wi-Fi. Based on their past support history and device information, what is the best course of action to resolve this user's issue?"

[0120] 4. The server converts the generated solution into text or image format and sends it to the user's device.

[0121] 5. The device receives the solution from the server and displays it on the screen.

[0122] 6. The user follows the provided steps to resolve the issue.

[0123] 7. The user provides feedback on whether the solution worked or not.

[0124] 8. The server receives the feedback and records it in a database. It may also retrain the generative AI model based on the feedback information.

[0125] Usage example

[0126] For example, a user may have problems connecting to Wi-Fi on their smartphone. The user opens a dedicated application and submits a screenshot of the problem, stating "Wi-Fi cannot be connected." The server receives the request and retrieves past support history and device information from the database. It then sends prompt text to the generative AI model to generate a solution for Wi-Fi settings. The server converts the generated solution into text and image format and sends it to the user's device. The user then checks the solution on their device, follows the steps to solve the problem, and submits feedback.

[0127] This system allows users to receive fast, highly accurate support 24 hours a day.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] The server receives a support request from the user.

[0131] Specifically, the server receives information (e.g., a summary of the problem, an error message, and a screenshot) as an HTTP POST request. The input is the query sent by the user from the device. The server parses the received data and converts it into an internal format.

[0132] Step 2:

[0133] The server connects to the database and retrieves the user's past support history and device information.

[0134] The server uses the user ID to send an SQL query to the database to retrieve the corresponding user information. The input is the user ID and the requested information fields. The output is the past support history and device information.

[0135] Step 3:

[0136] The server sends prompts to the generative AI model to generate solutions to the problem.

[0137] The server creates a prompt based on the acquired information and sends it to the generative AI model. The inputs include the user's problem information, past support data, and device information. The generative AI model then runs a deep learning algorithm based on this information to generate a solution to the problem. The output is a text version of the solution.

[0138] Step 4:

[0139] The server converts the generated solution into a format that is easy for the user to understand and sends it to the user's terminal.

[0140] The server formats the generated solution into text or image format and sends it as an HTTP response. The input is the solution received from the generative AI model. The output is the solution data received by the user device.

[0141] Step 5:

[0142] The device receives the solution from the server and displays it on the screen.

[0143] The terminal parses the HTTP response and displays the solution to the user. As input, it has the solution data sent by the server. As output, it has a representation of the solution that the user can view.

[0144] Step 6:

[0145] The user follows the steps provided to resolve the issue.

[0146] The input is the displayed solution steps. The output is the problem being solved. The specific action is for the user to follow the instructions on the device.

[0147] Step 7:

[0148] The user provides feedback on whether the solution worked.

[0149] The user uses a feedback form in the application to enter and submit a success or failure rating. The input is the feedback content. The output is the rating data sent to the server.

[0150] Step 8:

[0151] The server receives the feedback and records it in a database.

[0152] The server analyzes the received feedback and records it in a database. The input is the feedback data from the user. The output is the feedback information stored in the database. If necessary, it retrains the generative AI model.

[0153] Through these processing steps, users can receive fast and accurate support 24 hours a day.

[0154] (Application example 1)

[0155] 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."

[0156] The goal is to provide a system that allows users of autonomous vehicles to receive prompt and highly accurate support 24 hours a day. In particular, there is a need to establish a means of providing users with appropriate solutions in real time for problems and issues specific to autonomous vehicles.

[0157] 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.

[0158] In this invention, the server includes means for receiving a support request from a user, means for acquiring the user's past support history and device information based on the support request, means for generating a solution to the problem using a generative AI model with the acquired information, means for providing the generated solution to the user, means for receiving user feedback on the provided solution, and display means including images and audio guides for displaying the generated solution, thereby enabling users of autonomous vehicles to receive prompt and appropriate support at any time of day.

[0159] "Means for receiving support requests from users" refers to an interface that allows users to input their problems or questions and send them to the system.

[0160] "Means for acquiring a user's past support history and device information" is a function for acquiring from a database the history of support the user has received in the past and information on the device the user is currently using.

[0161] "Means for generating solutions using generative AI models" refers to the process of using artificial intelligence models based on acquired information to derive appropriate solutions to users' problems.

[0162] "Means to provide to the user" refers to an interface that provides the generated solution in a format that is easy for the user to understand.

[0163] "Means for receiving user feedback" refers to a function that allows users to send back to the system their evaluations and results of the solutions provided.

[0164] "Display means including visual and audio guides" refers to devices or interfaces for visually and audibly presenting the generated solution to the user.

[0165] "Means for retraining the generative AI model" refers to the process of retraining the generative AI model based on user feedback to improve the accuracy of its solutions.

[0166] The present invention provides a system that enables users of autonomous vehicles to receive prompt and highly accurate support 24 hours a day. A specific embodiment of this system is described below.

[0167] System Configuration

[0168] 1. Server:

[0169] The server is connected to a database that stores data such as user information, support history, and FAQs.

[0170] The server is implemented in a programming language such as Python.

[0171] The server has the ability to generate solutions from support requests using generative AI models (e.g., GPT-4 (registered trademark)).

[0172] 2. On the user's device:

[0173] User devices include smartphones, tablets, and PCs.

[0174] A dedicated support application is installed on the device.

[0175] 3. Get device information:

[0176] The server retrieves past support history and device information from a database based on the user's support request.

[0177] Data processing and calculation

[0178] Information Collection:

[0179] When a user submits a support request, the device sends the input information (such as a summary of the problem, error messages, screenshots, etc.) to the server as an HTTP request.

[0180] The server retrieves user information, past support history, and device information from the database.

[0181] Generate solutions:

[0182] The server provides the generative AI model with information about the current problem and past data as input.

[0183] The generative AI model uses this information to generate the most appropriate solution to the problem.

[0184] Solution provided:

[0185] The server converts the generated solution into a user-friendly format (text, images, audio guide, etc.) and sends it to the terminal as an HTTP response.

[0186] The terminal displays the received information to the user.

[0187] Receive feedback and retrain:

[0188] The user provides feedback on whether they succeeded or failed in resolving the issue.

[0189] The server records this feedback in a database and retrains the generative AI model as needed.

[0190] Specific examples

[0191] For example, consider a case where a user reports an issue with the self-parking feature of their self-driving vehicle not working.

[0192] 1. The user enters the problem "Automatic parking function is not working" into the smartphone app and submits a request along with screenshots and error messages.

[0193] 2. The server receives this request and retrieves the user's past support history and vehicle information from the database.

[0194] 3. The server inputs the acquired information into a generative AI model to generate specific troubleshooting steps.

[0195] 4. The server compiles the generated instructions into text and audio guides and sends them to the user's device.

[0196] 5. The user follows the instructions received to check the vehicle's settings and attempt to resolve the issue.

[0197] 6. The user selects success or failure within the app and submits feedback.

[0198] 7. The server receives the feedback, records it in a database, and retrains the generative AI model if necessary.

[0199] Prompt Sentence Examples

[0200] For example, the prompt text might look like this:

[0201] Please enter a description of the problem: Autopark feature not working

[0202] Did this solve your problem? (yes / no): no

[0203] This will ensure that users of autonomous vehicles can receive prompt and appropriate support at any time.

[0204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0205] Step 1:

[0206] A user submits a support request from their device. Input information includes a summary of the problem, an error message, a screenshot, etc. This data is sent from the device to the server as an HTTP request. The device converts this request into a packet format and sends it to the server.

[0207] Step 2:

[0208] The server receives a support request. It searches the database based on the user ID in the request to retrieve the user's past support history and device information. At this stage, the server establishes a database connection and loads the necessary information into a cache.

[0209] Step 3:

[0210] The server uses the information it acquires to provide input data to the generative AI model. Specifically, the user's current problem, past support history, device information, etc. are provided as input to the generative AI model (e.g., GPT-4). This is where data processing and normalization are performed.

[0211] Step 4:

[0212] The generative AI model generates a solution to the problem. The server generates the solution in text format as the output of the AI ​​model, as well as images and audio guidance if necessary. Data calculations are performed here to obtain a solution to the user's specific problem.

[0213] Step 5:

[0214] The server provides the generated solution to the user's device, and then sends the generated solution to the device as an HTTP response, which includes data converted into formats such as text, images, and audio.

[0215] Step 6:

[0216] The device displays the received information to the user. The device displays the transmitted text, images, and audio instructions on the screen, allowing the user to implement solutions. This allows the user to follow specific steps to solve the problem.

[0217] Step 7:

[0218] The user attempts to solve the problem and sends the results as feedback from the device to the server. The user selects whether the solution was successful or not and enters feedback information. The device then sends this as an HTTP request to the server.

[0219] Step 8:

[0220] The server receives the feedback and records it in a database. The server analyzes the received feedback and retrains the generative AI model as needed. This feedback process allows the system to constantly improve and provide more accurate solutions.

[0221] 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.

[0222] This invention combines a system that allows users to receive support 24 hours a day with an emotion engine that recognizes user emotions. Specifically, the system is configured to include a means for receiving support requests from users, a means for acquiring the user's past support history and device information, a means for generating solutions to problems using a generative model, a means for providing the generated solutions to users, a means for receiving user feedback, and an emotion engine.

[0223] Explanation of program processing

[0224] 1. The server starts first and loads the necessary data, AI models, and emotion engines.

[0225] The server establishes a database connection and loads user information, support history, and FAQs into memory.

[0226] The server loads the generative AI model and emotion engine, updating it if necessary from external sources.

[0227] 2. The user requests support using their device (smartphone or PC).

[0228] The user opens a dedicated application on the device and fills out an inquiry form.

[0229] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[0230] 3. The device sends the request to the server.

[0231] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[0232] 4. The server receives the request and retrieves the user's support history and device information.

[0233] The server searches the database for the corresponding user ID and retrieves the necessary information.

[0234] 5. The server inputs the problem summary and historical data into the AI ​​model and generates a solution.

[0235] The server uses the AI ​​model to generate a solution based on the user's current problem and past patterns.

[0236] 6. The server optimizes the generated solution using the emotion engine.

[0237] The server analyzes the user's current emotional state and optimizes the solution to suit that emotion.

[0238] 7. The server converts the optimized solution into a user-friendly format and sends it to the device.

[0239] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[0240] 8. The device displays the information it has received to the user.

[0241] The device displays instructions on the screen and the user attempts to solve the problem.

[0242] 9. The user follows the steps to resolve the issue and provides feedback on success or failure.

[0243] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[0244] 10. The server receives the feedback and records it in a database.

[0245] The server stores the feedback information in a database, updates the AI ​​model as needed, and uses an emotion engine to analyze emotions based on the feedback content.

[0246] Specific examples

[0247] For example, say a user is having trouble setting up Wi-Fi on their smartphone.

[0248] 1. The user enters the problem "I can't connect to Wi-Fi" on their device, attaches a screenshot, and submits a request.

[0249] 2. The server receives the request and retrieves the support history and the user's device information.

[0250] 3. The server uses the acquired information to use AI models to generate solutions to common Wi-Fi configuration issues and user-specific troubleshooting steps.

[0251] 4. The server uses an emotion engine to optimize the generated instructions to match the user's emotions. For example, if the user is "confused," the server will explain the instructions in a gentle tone.

[0252] 5. The server sends the optimized instructions to the user's device.

[0253] 6. The device displays the received instructions on the screen, and the user attempts to set up Wi-Fi by following the instructions.

[0254] 7. The user sends feedback from the device to the server, indicating whether the setup was successful or not.

[0255] 8. The server receives the feedback, records it in the system database, retrains the generative model if necessary, and analyzes the feedback using the emotion engine to provide future support.

[0256] The system allows users to receive fast, accurate and emotionally sensitive support 24 hours a day.

[0257] The processing flow will be explained below.

[0258] Step 1:

[0259] The server starts up and loads the necessary data, AI models, and emotion engines.

[0260] The server establishes a database connection and loads user information, support history, and FAQs into memory.

[0261] The server loads the generative AI model and emotion engine, updating it if necessary from external sources.

[0262] Step 2:

[0263] Users can request support using their own devices (smartphones or PCs).

[0264] The user opens a dedicated application on the device and fills out an inquiry form.

[0265] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[0266] Step 3:

[0267] The device sends a request to the server.

[0268] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[0269] Step 4:

[0270] The server receives the request and retrieves the user's support history and device information.

[0271] The server searches the database for the corresponding user ID and retrieves the necessary information.

[0272] Step 5:

[0273] The server uses an emotion engine to analyze the user's emotional state.

[0274] The server uses an emotion engine to assess the user's current emotional state (e.g., confusion, anger, relief, etc.) based on the request data and past interactions.

[0275] Step 6:

[0276] The server inputs a problem summary, past data, and analyzed emotional information into the AI ​​model, and generates a solution.

[0277] The server uses an AI model to generate a solution based on the user's current problem, past patterns, and emotional state.

[0278] Step 7:

[0279] The server optimizes the generated solution using an emotion engine.

[0280] Based on the analysis results of the emotion engine, the server optimizes the solution with a tone and expression that corresponds to the user's emotional state.

[0281] Step 8:

[0282] The server converts the optimized solution into a user-friendly format and sends it to the device.

[0283] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[0284] Step 9:

[0285] The device displays the received information to the user.

[0286] The device displays instructions on the screen and the user attempts to solve the problem.

[0287] Step 10:

[0288] The user follows the steps to resolve the issue and provides feedback on success or failure.

[0289] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[0290] Step 11:

[0291] The server receives the feedback and records it in a database.

[0292] The server stores the feedback information in a database and updates the AI ​​model as needed. It also analyzes the feedback using an emotion engine and uses it to provide future support.

[0293] Example 2

[0294] 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."

[0295] In traditional support systems, when users request support, appropriate solutions are often not provided quickly, resulting in a poor user experience. Furthermore, solutions provided without considering the user's feelings can reduce user satisfaction. Furthermore, feedback is not utilized in the system, which makes it difficult to improve support quality.

[0296] 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 means for receiving a support request from a user, a means for acquiring the user's past support history and electronic device information, a means for generating a solution to a problem using a generation algorithm based on the acquired information, a means for optimizing the generated solution using a sentiment analysis engine, a means for providing the optimized solution to the user, and a means for receiving user feedback on the provided solution. This allows users to receive fast, highly accurate support 24 hours a day, and provides solutions that take the user's emotions into consideration. Furthermore, utilizing feedback in the system enables continuous improvement of support quality.

[0297] "Support Request" means a request submitted by a User to the System for support.

[0298] "Past support history" refers to records and information regarding the support a user has previously received.

[0299] "Electronic device information" refers to detailed technical information about the devices a user uses.

[0300] A "generative algorithm" is a computational method or model that generates solutions to problems based on collected data.

[0301] An "emotion analysis engine" is a software component that analyzes a user's emotional state and optimizes solutions based on the results.

[0302] "Delivery means" refers to the method or technique used to present the generated solution to the user.

[0303] "Feedback" refers to the ratings and comments users make on the solutions provided.

[0304] "Retraining" is the process of updating the generative algorithm with new data and feedback collected to generate more accurate solutions.

[0305] This invention combines a system that allows users to receive support 24 hours a day with an emotion analysis engine that recognizes the emotions of users. A specific embodiment of this system will be described below.

[0306] The server starts up and loads the necessary data, generative AI model, and sentiment analysis engine. The server connects to a database (e.g., MySQL or PostgreSQL) and loads user information, support history, and FAQ data into RAM. This database connection allows the server to retrieve necessary data such as the user's past support history and electronic device information. The server also loads the generative AI model (e.g., GPT-4) and sentiment analysis engine (e.g., Empathizer) from disk and updates them from an external source (e.g., a cloud server) as needed.

[0307] A user requests support using a device such as a smartphone or PC. The user opens a dedicated application (e.g., a customer support app), enters a summary of the problem in the inquiry form, and uploads any error messages and screenshots. Once the input is complete, the user clicks the "Submit" button. The device converts the entered information into a packet format (e.g., JSON format), generates an HTTP request, and sends it to the server's API endpoint.

[0308] The server receives the request and retrieves the user's support history and device information. It then executes a database query to search for the user ID and uses the retrieved information to generate a prompt for the generative AI model. For example, the prompt can include a problem summary such as "I can't connect to Wi-Fi" and past support history.

[0309] The generative AI model generates a solution based on the prompt. The generated solution is then optimized by a sentiment analysis engine. The sentiment analysis engine analyzes the user's emotional state based on their past conversation patterns and real-time data. For example, if the user is confused, the engine reframes the solution in a gentler, more polite tone. Specifically, it adds a message such as "Don't worry, let's solve this together" to the generated solution.

[0310] The server converts the optimized solution into a user-friendly format and sends it to the device. The server formats the solution as a text document or image guidelines and sends it to the device as an HTTP response. The device analyzes the received information and displays it to the user. The user then follows the displayed steps to try to solve the problem.

[0311] Regardless of whether the user has solved the problem, feedback is provided within the application. The user selects whether the solution was successful or not, enters any additional comments, and clicks the "Submit" button. The feedback is sent from the device to the server, which receives it, records it in a database, and retrains the generative AI model as needed. The sentiment analysis engine also performs sentiment analysis based on the feedback content, which is used to improve future support.

[0312] This system allows users to receive fast, accurate support 24 hours a day, providing solutions that are considerate of their emotions, and by incorporating feedback into the system, it is possible to continuously improve the quality of support.

[0313] Example prompt:

[0314] "I can't connect to Wi-Fi. The error message is 'Unable to connect to network'. I've had a similar issue twice in my history, and a reboot fixed it once."

[0315] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0316] Step 1:

[0317] The server starts up and loads the necessary data, generative AI models, and sentiment analysis engines.

[0318] After the operating system starts, the server establishes a network connection. Next, it connects to a database (e.g., MySQL or PostgreSQL) and loads user information, support history, and FAQ data into RAM. It then loads a generative AI model (e.g., GPT-4) and a sentiment analysis engine (e.g., Empathizer) from disk. This prepares the server with the necessary data, such as the user's support history and electronic device information.

[0319] Input: Database access information, storage paths for generative AI models and sentiment analysis engines

[0320] Output: User information, support history, FAQ data, generative AI models and sentiment analysis engines loaded into server memory

[0321] Step 2:

[0322] Users can request support using their own devices (smartphones or PCs).

[0323] The user opens the dedicated application, enters detailed information (problem summary, error message, screenshot) into the inquiry form, and clicks the "Submit" button.

[0324] Input: User-entered problem summary, error message, and screenshot

[0325] Output: The input information that is sent

[0326] Step 3:

[0327] The device sends a request to the server.

[0328] The terminal converts the input information into a packet format, generates an HTTP request, and sends it to the server's API endpoint.

[0329] Input: Support request information entered by the user

[0330] Output: HTTP request sent to the server

[0331] Step 4:

[0332] The server receives the request and obtains the user's past support history and electronic device information.

[0333] The server analyzes the received HTTP request, extracts the user ID and problem summary, and then executes a database query to search for information based on the corresponding user ID, retrieving past support history and device information.

[0334] Input: HTTP request, user information

[0335] Output: Retrieved past support history and electronic device information

[0336] Step 5:

[0337] The server inputs a problem summary and past data into the generated AI model and generates a solution.

[0338] The server inputs a summary of the problem and past data as a prompt to the generative AI model, which then generates a solution based on this.

[0339] Input: Problem summary, past data

[0340] Output: A solution from the generative AI model

[0341] Step 6:

[0342] The server optimizes the generated solution using a sentiment analysis engine.

[0343] The server uses an emotion analysis engine to analyze the user's emotional state and optimizes the generated solution according to the user's emotions, for example, reframing a confused user in a gentler tone.

[0344] Input: Solution from a generative AI model, user emotional state

[0345] Output: A solution optimized by the sentiment analysis engine

[0346] Step 7:

[0347] The server converts the optimized solution into a user-friendly format and sends it to the terminal.

[0348] The server formats the solution as a text document or image guidelines and sends it to the device as an HTTP response.

[0349] Input: Optimized solution

[0350] Output: The solution sent as an HTTP response

[0351] Step 8:

[0352] The terminal displays the received information to the user.

[0353] The terminal analyzes the received HTTP response, extracts the solution text and images, and displays them to the user.

[0354] Input: HTTP response

[0355] Output: The solution that is displayed to the user

[0356] Step 9:

[0357] The user follows the steps to resolve the issue and provides feedback on success or failure.

[0358] The user attempts to solve the problem within the application, provides feedback on success or failure, and clicks the "Submit" button.

[0359] Input: User feedback information

[0360] Output: Feedback information to be sent

[0361] Step 10:

[0362] The server receives the feedback and records it in a database.

[0363] The server stores the received feedback information in a database and, if necessary, retrains the generative AI model. It also performs sentiment analysis and uses the information to improve future support.

[0364] Input: Feedback information

[0365] Output: Feedback information recorded in a database, updated generative AI model

[0366] (Application example 2)

[0367] 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."

[0368] In conventional support systems, a uniform response is given without considering the user's emotional state, which can lead to a decrease in user satisfaction. In addition, in today's world where 24-hour support is required, providing support that is quick and considerate of the user's emotions is a challenge.

[0369] 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 means for receiving a support request from a user, means for acquiring the user's past support history and device information, means for generating a solution to the problem using a generative model with the acquired information, means for recognizing the user's emotional state and optimizing the solution based on the emotion, means for providing the generated solution to the user, and means for receiving the user's feedback on the provided solution. This enables user-friendly support that is available 24 hours a day and takes emotions into consideration.

[0370] "User" refers to a person who uses the System and provides assistance requests or feedback.

[0371] "Assistance Request" means a request made by a User seeking service or support.

[0372] "Support history" refers to a record of support a user has received in the past, and is information stored in a database.

[0373] "Device information" refers to detailed information about the device used by the user, including, for example, the model name, settings, and status.

[0374] A "generative model" refers to an algorithmic model that uses AI technology to generate solutions to problems.

[0375] "Problem Solution" refers to the specific solution or procedure for a user's request for assistance.

[0376] "Emotional state" refers to the psychological state of the user when they make a support request, and is information obtained through analysis.

[0377] "Optimization" refers to the process of adjusting and refining the generated problem solution based on the user's emotional state.

[0378] "Feedback" refers to users' reactions and evaluations of the services and solutions provided.

[0379] This invention is a system that allows users to receive support 24 hours a day for problems or questions about food delivery. This system is combined with an emotion engine that recognizes the user's emotions to realize responses that take the user's emotions into consideration. An embodiment of this system is described in detail below.

[0380] System Overview

[0381] The system consists of the following main components:

[0382] 1. A means of receiving assistance requests from users

[0383] 2. Means of obtaining support history and device information

[0384] 3. A method for generating solutions using generative models

[0385] 4. Using an emotion engine to optimize emotion-based solutions

[0386] 5. A means of providing optimized solutions to users

[0387] 6. How to receive user feedback

[0388] Programs and hardware used

[0389] The server implements the system using the following hardware and software.

[0390] Hardware: A server with a powerful processor, sufficient memory, and a fast network interface.

[0391] software:

[0392] Database: A database that stores user information, assistance history, and device information.

[0393] Emotion Engine: Software that uses Natural Language Processing (NLP) technology to analyze user emotions.

[0394] Generative model: An AI model that uses machine learning algorithms to generate solutions to problems (e.g., GPT-3 and BERT models).

[0395] Application Server: Software that manages user requests and interacts with the generative model and emotion engine.

[0396] Data processing and calculation

[0397] 1. Receiving your request for assistance:

[0398] A user sends a request for assistance to the server using a smartphone or web app, including a detailed description of the problem and screenshots, if necessary.

[0399] 2. Obtaining User Information:

[0400] The server connects to the database and retrieves the user's past support history and device information based on the received user ID.

[0401] 3. Emotion analysis:

[0402] The emotion engine analyzes the text data of the request for assistance to detect the user's emotional state, identifying emotions such as "confusion," "anger," and "sadness."

[0403] 4. Generate solutions to problems:

[0404] Based on the acquired user information and the content of the assistance request, the generative model generates an optimal solution to the problem, using the prompt sentence as input.

[0405] 5. Emotion-based optimization:

[0406] The emotion engine optimizes the tone and style of the generated solutions based on the user's emotional state. For example, if the user is confused, the explanation will be delivered in a gentle tone.

[0407] 6. Offerings to Users:

[0408] The optimized solution is sent to the user's device, where the user can review the steps and attempt to resolve the issue.

[0409] 7. Receiving and Processing Feedback:

[0410] Users can provide feedback on the solutions provided, which is received by the server and stored in a database. The feedback is used to retrain the generative model to improve its accuracy in solving future problems.

[0411] Specific examples

[0412] For example, if a user sends a request for assistance stating "my order hasn't arrived," the system operates as follows:

[0413] 1. Receiving your request for assistance:

[0414] A user submits a request for assistance, detailing that their order has not arrived and attaching screenshots.

[0415] 2. Obtaining User Information:

[0416] The server retrieves the user's past order history and device information from the database.

[0417] 3. Emotion analysis:

[0418] The emotion engine analyzes the user's "confused" emotions from requests for assistance.

[0419] 4. Generate solutions to problems:

[0420] Based on the information obtained, the generative model generates a solution such as "Restart the app to check the order status, then check your order history."

[0421] 5. Emotion-based optimization:

[0422] The emotion engine optimizes the solution to a gentle tone: "Please wait a moment. Please restart the app and check your order history again."

[0423] 6. Offerings to Users:

[0424] The optimized solution is sent to the user's device, where the user can review and try the steps.

[0425] 7. Receiving and Processing Feedback:

[0426] When a user sends feedback that the problem has been resolved, the server stores this in a database and uses it for future support.

[0427] Example prompt sentence:

[0428] text

[0429] For users who are confused about not receiving their order, generate a support message in a human tone, like this:

[0430] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0431] Step 1:

[0432] The device receives a request for assistance from the user. The user provides a detailed description of the problem and any necessary screenshots using a smartphone app or web app. The device converts this input information into a packet format and sends it to the server as an HTTP request. Specifically, the device attaches the problem "My order hasn't arrived" and screenshots.

[0433] Step 2:

[0434] The server receives the assistance request and retrieves the user's past assistance history and device information from the database. Specifically, it accesses the database, searches for related data based on the user ID, and retrieves the past order history and device information. This allows the assistance history and device information to be imported into the server as input data.

[0435] Step 3:

[0436] The server uses an emotion engine to analyze the user's emotional state from the request for assistance. The input data is the text of the request for assistance, and NLP technology is used to recognize emotional states such as "confusion." The analyzed emotional state is output as "confusion."

[0437] Step 4:

[0438] The server uses a generative model to generate a solution to the problem based on the information it obtains. The input data is the content of the assistance request, past assistance history, and device information, and the AI ​​model generates a solution such as "Restart the app to check the order status, then check your order history."

[0439] Step 5:

[0440] The server uses an emotion engine to optimize the generated solution according to the user's emotional state. The input data is "Please restart the app to check the order status, then check your order history" and the emotional state is "confused," and the emotion engine outputs a gentle solution saying, "Please wait a moment. Please restart the app and check your order history again."

[0441] Step 6:

[0442] The server sends the optimized solution to the user's device. The input data is the optimized solution, which is sent to the device as an HTTP response. The device displays this solution to the user, who can then check the solution and attempt to solve the problem.

[0443] Step 7:

[0444] The user acts on the provided solution and sends the result as feedback from the device to the server. The input data is the feedback, and the device sends feedback information such as "the problem has been solved" to the server as an HTTP request.

[0445] Step 8:

[0446] The server receives the feedback and records it in a database. The input data is the feedback information, which is then stored in the database. Furthermore, the generative model is retrained based on the feedback, improving its accuracy for subsequent assistance requests.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] [Second embodiment]

[0451] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0452] 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.

[0453] 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).

[0454] 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.

[0455] 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.

[0456] 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).

[0457] 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.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] 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."

[0463] This invention is a system designed to enable users to receive support 24 hours a day. Specifically, it comprises a means for receiving a support request from a user, a means for acquiring the user's past support history and device information, a means for generating a solution to a problem using a generative model, a means for providing the generated solution to the user, and a means for receiving user feedback.

[0464] Explanation of program processing

[0465] 1. The server starts first and loads the necessary data and AI models.

[0466] The server establishes a database connection and loads user information, support history, and FAQs into a cache.

[0467] The server loads the generative AI model and updates it if necessary from an external source.

[0468] 2. The user requests support using their device (smartphone or PC).

[0469] The user opens a dedicated application on the device and fills out an inquiry form.

[0470] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[0471] 3. The device sends the request to the server.

[0472] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[0473] 4. The server receives the request and retrieves the user's support history and device information.

[0474] The server searches the database for the corresponding user ID and retrieves the necessary information.

[0475] 5. The server inputs the problem summary and historical data into the AI ​​model and generates a solution.

[0476] The server uses the AI ​​model to generate a solution based on the user's current problem and past patterns.

[0477] 6. The server converts the generated solution into a format that is easy for the user to understand and sends it to the terminal.

[0478] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[0479] 7. The device displays the received information to the user.

[0480] The device displays instructions on the screen and the user attempts to solve the problem.

[0481] 8. The user follows the steps to resolve the issue and provides feedback on success or failure.

[0482] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[0483] 9. The server receives the feedback and records it in a database.

[0484] The server stores the feedback information in a database and updates the AI ​​model as needed.

[0485] Specific examples

[0486] For example, say a user is having trouble setting up Wi-Fi on their smartphone.

[0487] 1. The user enters the problem "I can't connect to Wi-Fi" on their device, attaches a screenshot, and submits a request.

[0488] 2. The server receives the request and retrieves the support history and the user's device information.

[0489] 3. The server uses the acquired information to use AI models to generate solutions to common Wi-Fi configuration issues and user-specific troubleshooting steps.

[0490] 4. The server sends the generated instructions to the user's device using text and images.

[0491] 5. The device displays the received instructions on the screen, and the user attempts to set up Wi-Fi by following the instructions.

[0492] 6. The user sends feedback from the device to the server, indicating whether the setup was successful or not.

[0493] 7. The server receives the feedback, records it in the system database, and retrains the generative model if necessary.

[0494] This system allows users to receive fast, accurate support 24 hours a day.

[0495] The processing flow will be explained below.

[0496] Step 1:

[0497] The server starts up and loads the necessary data and AI models.

[0498] The server establishes a database connection and loads user information, support history, and FAQs into memory.

[0499] The server loads the generative AI model and updates it if necessary from an external source.

[0500] Step 2:

[0501] The user requests support using a device (smartphone or PC).

[0502] The user opens a dedicated application on the device and fills out an inquiry form.

[0503] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[0504] Step 3:

[0505] The device sends a request to the server.

[0506] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[0507] Step 4:

[0508] The server receives the request and retrieves the user's support history and device information.

[0509] The server searches the database for the corresponding user ID and retrieves the necessary information.

[0510] Step 5:

[0511] The server inputs a problem summary and historical data into the AI ​​model and generates a solution.

[0512] The server uses the AI ​​model to generate a solution based on the user's current problem and past patterns.

[0513] Step 6:

[0514] The server converts the generated solution into a format that is easy for the user to understand and sends it to the terminal.

[0515] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[0516] Step 7:

[0517] The device displays the received information to the user.

[0518] The device displays instructions on the screen and the user attempts to solve the problem.

[0519] Step 8:

[0520] The user follows the steps to resolve the issue and provides feedback on success or failure.

[0521] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[0522] Step 9:

[0523] The server receives the feedback and records it in a database.

[0524] The server stores the feedback information in a database and updates the AI ​​model as needed.

[0525] Example 1

[0526] 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."

[0527] In recent years, with the advancement of electronic devices and information and communication technology, users are increasingly encountering problems with complex devices and software. To quickly address these issues, 24-hour support is necessary, but current support systems are insufficient and fail to satisfy users. Furthermore, manual support by support staff can be time-consuming and costly, resulting in prolonged resolution times. Given this background, there is a demand for automated support systems that can quickly and efficiently resolve user problems.

[0528] 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.

[0529] In this invention, the server includes means for receiving a support request from a user, means for retrieving the user's past support history and device information from a database based on the received support request, means for utilizing a generative AI model using the retrieved information to send prompt text and generate a solution to the problem, means for converting the generated solution into a format that is easy for the user to understand (text, image, etc.) and sending it to the user terminal, and means for receiving and recording user feedback on the provided solution, thereby enabling users to receive fast and highly accurate support 24 hours a day.

[0530] A "server" is a central computer system that receives requests from users and processes data.

[0531] "Support Request" means a request submitted by a User to resolve a Device or Software issue.

[0532] A "database" is an information system for systematically storing and managing user information, support history, device information, etc.

[0533] A "generative AI model" is an artificial intelligence model that automatically generates solutions to problems based on input information.

[0534] A "prompt sentence" is text data input into a generative AI model that contains instructions and conditions for solving a problem.

[0535] A "solution" is a procedure or method for solving a user's problem obtained using a generative AI model.

[0536] A "user terminal" is a computer device (such as a smartphone or PC) used by a user, which receives and displays information from a server.

[0537] "Feedback" refers to evaluation information that a user sends back to the server regarding the effectiveness and results of the solution provided.

[0538] Based on these definitions, the technical scope of the invention is clearly defined.

[0539] This invention is a system that allows users to receive support 24 hours a day. Specifically, it is implemented using the following hardware and software.

[0540] Hardware and Software Configuration

[0541] 1. Server: A high-performance computing system that receives requests, connects to a database, and runs generative AI models. Examples include Linux-based servers and cloud services (AWS, Google Cloud, etc.).

[0542] 2. Database: Stores user information, support history, FAQs, etc. Uses a relational database such as MySQL or PostgreSQL.

[0543] 3. Generative AI models: Generate solutions to problems using deep learning models such as GPT-3 and BERT.

[0544] 4. User device: A computing device that users use on a daily basis, such as a smartphone or PC.

[0545] Specific functions of the system

[0546] 1. The server receives a support request from the user, often in the form of an HTTP POST request.

[0547] 2. The server connects to the database and retrieves the user's past support history and device information.

[0548] 3. The server sends a prompt to the generative AI model to generate a solution to the problem. An example of a prompt is, "A user is reporting an issue where they cannot connect to Wi-Fi. Based on their past support history and device information, what is the best course of action to resolve this user's issue?"

[0549] 4. The server converts the generated solution into text or image format and sends it to the user's device.

[0550] 5. The device receives the solution from the server and displays it on the screen.

[0551] 6. The user follows the provided steps to resolve the issue.

[0552] 7. The user provides feedback on whether the solution worked or not.

[0553] 8. The server receives the feedback and records it in a database. It may also retrain the generative AI model based on the feedback information.

[0554] Usage example

[0555] For example, a user may have problems connecting to Wi-Fi on their smartphone. The user opens a dedicated application and submits a screenshot of the problem, stating "Wi-Fi cannot be connected." The server receives the request and retrieves past support history and device information from the database. It then sends prompt text to the generative AI model to generate a solution for Wi-Fi settings. The server converts the generated solution into text and image format and sends it to the user's device. The user then checks the solution on their device, follows the steps to solve the problem, and submits feedback.

[0556] This system allows users to receive fast, highly accurate support 24 hours a day.

[0557] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0558] Step 1:

[0559] The server receives a support request from the user.

[0560] Specifically, the server receives information (e.g., a summary of the problem, an error message, and a screenshot) as an HTTP POST request. The input is the query sent by the user from the device. The server parses the received data and converts it into an internal format.

[0561] Step 2:

[0562] The server connects to the database and retrieves the user's past support history and device information.

[0563] The server uses the user ID to send an SQL query to the database to retrieve the corresponding user information. The input is the user ID and the requested information fields. The output is the past support history and device information.

[0564] Step 3:

[0565] The server sends prompts to the generative AI model to generate solutions to the problem.

[0566] The server creates a prompt based on the acquired information and sends it to the generative AI model. The inputs include the user's problem information, past support data, and device information. The generative AI model then runs a deep learning algorithm based on this information to generate a solution to the problem. The output is a text version of the solution.

[0567] Step 4:

[0568] The server converts the generated solution into a format that is easy for the user to understand and sends it to the user's terminal.

[0569] The server formats the generated solution into text or image format and sends it as an HTTP response. The input is the solution received from the generative AI model. The output is the solution data received by the user device.

[0570] Step 5:

[0571] The device receives the solution from the server and displays it on the screen.

[0572] The terminal parses the HTTP response and displays the solution to the user. As input, it has the solution data sent by the server. As output, it has a representation of the solution that the user can view.

[0573] Step 6:

[0574] The user follows the steps provided to resolve the issue.

[0575] The input is the displayed solution steps. The output is the problem being solved. The specific action is for the user to follow the instructions on the device.

[0576] Step 7:

[0577] The user provides feedback on whether the solution worked.

[0578] The user uses a feedback form in the application to enter and submit a success or failure rating. The input is the feedback content. The output is the rating data sent to the server.

[0579] Step 8:

[0580] The server receives the feedback and records it in a database.

[0581] The server analyzes the received feedback and records it in a database. The input is the feedback data from the user. The output is the feedback information stored in the database. If necessary, it retrains the generative AI model.

[0582] Through these processing steps, users can receive fast and accurate support 24 hours a day.

[0583] (Application example 1)

[0584] 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."

[0585] The goal is to provide a system that allows users of autonomous vehicles to receive prompt and highly accurate support 24 hours a day. In particular, there is a need to establish a means of providing users with appropriate solutions in real time for problems and issues specific to autonomous vehicles.

[0586] 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.

[0587] In this invention, the server includes means for receiving a support request from a user, means for acquiring the user's past support history and device information based on the support request, means for generating a solution to the problem using a generative AI model with the acquired information, means for providing the generated solution to the user, means for receiving user feedback on the provided solution, and display means including images and audio guides for displaying the generated solution, thereby enabling users of autonomous vehicles to receive prompt and appropriate support at any time of day.

[0588] "Means for receiving support requests from users" refers to an interface that allows users to input their problems or questions and send them to the system.

[0589] "Means for acquiring a user's past support history and device information" is a function for acquiring from a database the history of support the user has received in the past and information on the device the user is currently using.

[0590] "Means for generating solutions using generative AI models" refers to the process of using artificial intelligence models based on acquired information to derive appropriate solutions to users' problems.

[0591] "Means to provide to the user" refers to an interface that provides the generated solution in a format that is easy for the user to understand.

[0592] "Means for receiving user feedback" refers to a function that allows users to send back to the system their evaluations and results of the solutions provided.

[0593] "Display means including visual and audio guides" refers to devices or interfaces for visually and audibly presenting the generated solution to the user.

[0594] "Means for retraining the generative AI model" refers to the process of retraining the generative AI model based on user feedback to improve the accuracy of its solutions.

[0595] The present invention provides a system that enables users of autonomous vehicles to receive prompt and highly accurate support 24 hours a day. A specific embodiment of this system is described below.

[0596] System Configuration

[0597] 1. Server:

[0598] The server is connected to a database that stores data such as user information, support history, and FAQs.

[0599] The server is implemented in a programming language such as Python.

[0600] The server has the ability to generate solutions from support requests using generative AI models (e.g., GPT-4).

[0601] 2. On the user's device:

[0602] User devices include smartphones, tablets, and PCs.

[0603] A dedicated support application is installed on the device.

[0604] 3. Get device information:

[0605] The server retrieves past support history and device information from a database based on the user's support request.

[0606] Data processing and calculation

[0607] Information Collection:

[0608] When a user submits a support request, the device sends the input information (such as a summary of the problem, error messages, screenshots, etc.) to the server as an HTTP request.

[0609] The server retrieves user information, past support history, and device information from the database.

[0610] Generate solutions:

[0611] The server provides the generative AI model with information about the current problem and past data as input.

[0612] The generative AI model uses this information to generate the most appropriate solution to the problem.

[0613] Solution provided:

[0614] The server converts the generated solution into a user-friendly format (text, images, audio guide, etc.) and sends it to the terminal as an HTTP response.

[0615] The terminal displays the received information to the user.

[0616] Receive feedback and retrain:

[0617] The user provides feedback on whether they succeeded or failed in resolving the issue.

[0618] The server records this feedback in a database and retrains the generative AI model as needed.

[0619] Specific examples

[0620] For example, consider a case where a user reports an issue with the self-parking feature of their self-driving vehicle not working.

[0621] 1. The user enters the problem "Automatic parking function is not working" into the smartphone app and submits a request along with screenshots and error messages.

[0622] 2. The server receives this request and retrieves the user's past support history and vehicle information from the database.

[0623] 3. The server inputs the acquired information into a generative AI model to generate specific troubleshooting steps.

[0624] 4. The server compiles the generated instructions into text and audio guides and sends them to the user's device.

[0625] 5. The user follows the instructions received to check the vehicle's settings and attempt to resolve the issue.

[0626] 6. The user selects success or failure within the app and submits feedback.

[0627] 7. The server receives the feedback, records it in a database, and retrains the generative AI model if necessary.

[0628] Prompt Sentence Examples

[0629] For example, the prompt text might look like this:

[0630] Please enter a description of the problem: Autopark feature not working

[0631] Did this solve your problem? (yes / no): no

[0632] This will ensure that users of autonomous vehicles can receive prompt and appropriate support at any time.

[0633] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0634] Step 1:

[0635] A user submits a support request from their device. Input information includes a summary of the problem, an error message, a screenshot, etc. This data is sent from the device to the server as an HTTP request. The device converts this request into a packet format and sends it to the server.

[0636] Step 2:

[0637] The server receives a support request. It searches the database based on the user ID in the request to retrieve the user's past support history and device information. At this stage, the server establishes a database connection and loads the necessary information into a cache.

[0638] Step 3:

[0639] The server uses the information it acquires to provide input data to the generative AI model. Specifically, the user's current problem, past support history, device information, etc. are provided as input to the generative AI model (e.g., GPT-4). This is where data processing and normalization are performed.

[0640] Step 4:

[0641] The generative AI model generates a solution to the problem. The server generates the solution in text format as the output of the AI ​​model, as well as images and audio guidance if necessary. Data calculations are performed here to obtain a solution to the user's specific problem.

[0642] Step 5:

[0643] The server provides the generated solution to the user's device, and then sends the generated solution to the device as an HTTP response, which includes data converted into formats such as text, images, and audio.

[0644] Step 6:

[0645] The device displays the received information to the user. The device displays the transmitted text, images, and audio instructions on the screen, allowing the user to implement solutions. This allows the user to follow specific steps to solve the problem.

[0646] Step 7:

[0647] The user attempts to solve the problem and sends the results as feedback from the device to the server. The user selects whether the solution was successful or not and enters feedback information. The device then sends this as an HTTP request to the server.

[0648] Step 8:

[0649] The server receives the feedback and records it in a database. The server analyzes the received feedback and retrains the generative AI model as needed. This feedback process allows the system to constantly improve and provide more accurate solutions.

[0650] 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.

[0651] This invention combines a system that allows users to receive support 24 hours a day with an emotion engine that recognizes user emotions. Specifically, the system is configured to include a means for receiving support requests from users, a means for acquiring the user's past support history and device information, a means for generating solutions to problems using a generative model, a means for providing the generated solutions to users, a means for receiving user feedback, and an emotion engine.

[0652] Explanation of program processing

[0653] 1. The server starts first and loads the necessary data, AI models, and emotion engines.

[0654] The server establishes a database connection and loads user information, support history, and FAQs into memory.

[0655] The server loads the generative AI model and emotion engine, updating it if necessary from external sources.

[0656] 2. The user requests support using their device (smartphone or PC).

[0657] The user opens a dedicated application on the device and fills out an inquiry form.

[0658] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[0659] 3. The device sends the request to the server.

[0660] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[0661] 4. The server receives the request and retrieves the user's support history and device information.

[0662] The server searches the database for the corresponding user ID and retrieves the necessary information.

[0663] 5. The server inputs the problem summary and historical data into the AI ​​model and generates a solution.

[0664] The server uses the AI ​​model to generate a solution based on the user's current problem and past patterns.

[0665] 6. The server optimizes the generated solution using the emotion engine.

[0666] The server analyzes the user's current emotional state and optimizes the solution to suit that emotion.

[0667] 7. The server converts the optimized solution into a user-friendly format and sends it to the device.

[0668] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[0669] 8. The device displays the information it has received to the user.

[0670] The device displays instructions on the screen and the user attempts to solve the problem.

[0671] 9. The user follows the steps to resolve the issue and provides feedback on success or failure.

[0672] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[0673] 10. The server receives the feedback and records it in a database.

[0674] The server stores the feedback information in a database, updates the AI ​​model as needed, and uses an emotion engine to analyze emotions based on the feedback content.

[0675] Specific examples

[0676] For example, say a user is having trouble setting up Wi-Fi on their smartphone.

[0677] 1. The user enters the problem "I can't connect to Wi-Fi" on their device, attaches a screenshot, and submits a request.

[0678] 2. The server receives the request and retrieves the support history and the user's device information.

[0679] 3. The server uses the acquired information to use AI models to generate solutions to common Wi-Fi configuration issues and user-specific troubleshooting steps.

[0680] 4. The server uses an emotion engine to optimize the generated instructions to match the user's emotions. For example, if the user is "confused," the server will explain the instructions in a gentle tone.

[0681] 5. The server sends the optimized instructions to the user's device.

[0682] 6. The device displays the received instructions on the screen, and the user attempts to set up Wi-Fi by following the instructions.

[0683] 7. The user sends feedback from the device to the server, indicating whether the setup was successful or not.

[0684] 8. The server receives the feedback, records it in the system database, retrains the generative model if necessary, and analyzes the feedback using the emotion engine to provide future support.

[0685] The system allows users to receive fast, accurate and emotionally sensitive support 24 hours a day.

[0686] The processing flow will be explained below.

[0687] Step 1:

[0688] The server starts up and loads the necessary data, AI models, and emotion engines.

[0689] The server establishes a database connection and loads user information, support history, and FAQs into memory.

[0690] The server loads the generative AI model and emotion engine, updating it if necessary from external sources.

[0691] Step 2:

[0692] Users can request support using their own devices (smartphones or PCs).

[0693] The user opens a dedicated application on the device and fills out an inquiry form.

[0694] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[0695] Step 3:

[0696] The device sends a request to the server.

[0697] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[0698] Step 4:

[0699] The server receives the request and retrieves the user's support history and device information.

[0700] The server searches the database for the corresponding user ID and retrieves the necessary information.

[0701] Step 5:

[0702] The server uses an emotion engine to analyze the user's emotional state.

[0703] The server uses an emotion engine to assess the user's current emotional state (e.g., confusion, anger, relief, etc.) based on the request data and past interactions.

[0704] Step 6:

[0705] The server inputs a problem summary, past data, and analyzed emotional information into the AI ​​model, and generates a solution.

[0706] The server uses an AI model to generate a solution based on the user's current problem, past patterns, and emotional state.

[0707] Step 7:

[0708] The server optimizes the generated solution using an emotion engine.

[0709] Based on the analysis results of the emotion engine, the server optimizes the solution with a tone and expression that corresponds to the user's emotional state.

[0710] Step 8:

[0711] The server converts the optimized solution into a user-friendly format and sends it to the device.

[0712] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[0713] Step 9:

[0714] The device displays the received information to the user.

[0715] The device displays instructions on the screen and the user attempts to solve the problem.

[0716] Step 10:

[0717] The user follows the steps to resolve the issue and provides feedback on success or failure.

[0718] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[0719] Step 11:

[0720] The server receives the feedback and records it in a database.

[0721] The server stores the feedback information in a database and updates the AI ​​model as needed. It also analyzes the feedback using an emotion engine and uses it to provide future support.

[0722] Example 2

[0723] 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."

[0724] In traditional support systems, when users request support, appropriate solutions are often not provided quickly, resulting in a poor user experience. Furthermore, solutions provided without considering the user's feelings can reduce user satisfaction. Furthermore, feedback is not utilized in the system, which makes it difficult to improve support quality.

[0725] 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 means for receiving a support request from a user, a means for acquiring the user's past support history and electronic device information, a means for generating a solution to a problem using a generation algorithm based on the acquired information, a means for optimizing the generated solution using a sentiment analysis engine, a means for providing the optimized solution to the user, and a means for receiving user feedback on the provided solution. This allows users to receive fast, highly accurate support 24 hours a day, and provides solutions that take the user's emotions into consideration. Furthermore, utilizing feedback in the system enables continuous improvement of support quality.

[0726] "Support Request" means a request submitted by a User to the System for support.

[0727] "Past support history" refers to records and information regarding the support a user has previously received.

[0728] "Electronic device information" refers to detailed technical information about the devices a user uses.

[0729] A "generative algorithm" is a computational method or model that generates solutions to problems based on collected data.

[0730] An "emotion analysis engine" is a software component that analyzes a user's emotional state and optimizes solutions based on the results.

[0731] "Delivery means" refers to the method or technique used to present the generated solution to the user.

[0732] "Feedback" refers to the ratings and comments users make on the solutions provided.

[0733] "Retraining" is the process of updating the generative algorithm with new data and feedback collected to generate more accurate solutions.

[0734] This invention combines a system that allows users to receive support 24 hours a day with an emotion analysis engine that recognizes the emotions of users. A specific embodiment of this system will be described below.

[0735] The server starts up and loads the necessary data, generative AI model, and sentiment analysis engine. The server connects to a database (e.g., MySQL or PostgreSQL) and loads user information, support history, and FAQ data into RAM. This database connection allows the server to retrieve necessary data such as the user's past support history and electronic device information. The server also loads the generative AI model (e.g., GPT-4) and sentiment analysis engine (e.g., Empathizer) from disk and updates them from an external source (e.g., a cloud server) as needed.

[0736] A user requests support using a device such as a smartphone or PC. The user opens a dedicated application (e.g., a customer support app), enters a summary of the problem in the inquiry form, and uploads any error messages and screenshots. Once the input is complete, the user clicks the "Submit" button. The device converts the entered information into a packet format (e.g., JSON format), generates an HTTP request, and sends it to the server's API endpoint.

[0737] The server receives the request and retrieves the user's support history and device information. It then executes a database query to search for the user ID and uses the retrieved information to generate a prompt for the generative AI model. For example, the prompt can include a problem summary such as "I can't connect to Wi-Fi" and past support history.

[0738] The generative AI model generates a solution based on the prompt. The generated solution is then optimized by a sentiment analysis engine. The sentiment analysis engine analyzes the user's emotional state based on their past conversation patterns and real-time data. For example, if the user is confused, the engine reframes the solution in a gentler, more polite tone. Specifically, it adds a message such as "Don't worry, let's solve this together" to the generated solution.

[0739] The server converts the optimized solution into a user-friendly format and sends it to the device. The server formats the solution as a text document or image guidelines and sends it to the device as an HTTP response. The device analyzes the received information and displays it to the user. The user then follows the displayed steps to try to solve the problem.

[0740] Regardless of whether the user has solved the problem, feedback is provided within the application. The user selects whether the solution was successful or not, enters any additional comments, and clicks the "Submit" button. The feedback is sent from the device to the server, which receives it, records it in a database, and retrains the generative AI model as needed. The sentiment analysis engine also performs sentiment analysis based on the feedback content, which is used to improve future support.

[0741] This system allows users to receive fast, accurate support 24 hours a day, providing solutions that are considerate of their emotions, and by incorporating feedback into the system, it is possible to continuously improve the quality of support.

[0742] Example prompt:

[0743] "I can't connect to Wi-Fi. The error message is 'Unable to connect to network'. I've had a similar issue twice in my history, and a reboot fixed it once."

[0744] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0745] Step 1:

[0746] The server starts up and loads the necessary data, generative AI models, and sentiment analysis engines.

[0747] After the operating system starts, the server establishes a network connection. Next, it connects to a database (e.g., MySQL or PostgreSQL) and loads user information, support history, and FAQ data into RAM. It then loads a generative AI model (e.g., GPT-4) and a sentiment analysis engine (e.g., Empathizer) from disk. This prepares the server with the necessary data, such as the user's support history and electronic device information.

[0748] Input: Database access information, storage paths for generative AI models and sentiment analysis engines

[0749] Output: User information, support history, FAQ data, generative AI models and sentiment analysis engines loaded into server memory

[0750] Step 2:

[0751] Users can request support using their own devices (smartphones or PCs).

[0752] The user opens the dedicated application, enters detailed information (problem summary, error message, screenshot) into the inquiry form, and clicks the "Submit" button.

[0753] Input: User-entered problem summary, error message, and screenshot

[0754] Output: The input information that is sent

[0755] Step 3:

[0756] The device sends a request to the server.

[0757] The terminal converts the input information into a packet format, generates an HTTP request, and sends it to the server's API endpoint.

[0758] Input: Support request information entered by the user

[0759] Output: HTTP request sent to the server

[0760] Step 4:

[0761] The server receives the request and obtains the user's past support history and electronic device information.

[0762] The server analyzes the received HTTP request, extracts the user ID and problem summary, and then executes a database query to search for information based on the corresponding user ID, retrieving past support history and device information.

[0763] Input: HTTP request, user information

[0764] Output: Retrieved past support history and electronic device information

[0765] Step 5:

[0766] The server inputs a problem summary and past data into the generated AI model and generates a solution.

[0767] The server inputs a summary of the problem and past data as a prompt to the generative AI model, which then generates a solution based on this.

[0768] Input: Problem summary, past data

[0769] Output: A solution from the generative AI model

[0770] Step 6:

[0771] The server optimizes the generated solution using a sentiment analysis engine.

[0772] The server uses an emotion analysis engine to analyze the user's emotional state and optimizes the generated solution according to the user's emotions, for example, reframing a confused user in a gentler tone.

[0773] Input: Solution from a generative AI model, user emotional state

[0774] Output: A solution optimized by the sentiment analysis engine

[0775] Step 7:

[0776] The server converts the optimized solution into a user-friendly format and sends it to the terminal.

[0777] The server formats the solution as a text document or image guidelines and sends it to the device as an HTTP response.

[0778] Input: Optimized solution

[0779] Output: The solution sent as an HTTP response

[0780] Step 8:

[0781] The terminal displays the received information to the user.

[0782] The terminal analyzes the received HTTP response, extracts the solution text and images, and displays them to the user.

[0783] Input: HTTP response

[0784] Output: The solution that is displayed to the user

[0785] Step 9:

[0786] The user follows the steps to resolve the issue and provides feedback on success or failure.

[0787] The user attempts to solve the problem within the application, provides feedback on success or failure, and clicks the "Submit" button.

[0788] Input: User feedback information

[0789] Output: Feedback information to be sent

[0790] Step 10:

[0791] The server receives the feedback and records it in a database.

[0792] The server stores the received feedback information in a database and, if necessary, retrains the generative AI model. It also performs sentiment analysis and uses the information to improve future support.

[0793] Input: Feedback information

[0794] Output: Feedback information recorded in a database, updated generative AI model

[0795] (Application example 2)

[0796] 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."

[0797] In conventional support systems, a uniform response is given without considering the user's emotional state, which can lead to a decrease in user satisfaction. In addition, in today's world where 24-hour support is required, providing support that is quick and considerate of the user's emotions is a challenge.

[0798] 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 means for receiving a support request from a user, means for acquiring the user's past support history and device information, means for generating a solution to the problem using a generative model with the acquired information, means for recognizing the user's emotional state and optimizing the solution based on the emotion, means for providing the generated solution to the user, and means for receiving the user's feedback on the provided solution. This enables user-friendly support that is available 24 hours a day and takes emotions into consideration.

[0799] "User" refers to a person who uses the System and provides assistance requests or feedback.

[0800] "Assistance Request" means a request made by a User seeking service or support.

[0801] "Support history" refers to a record of support a user has received in the past, and is information stored in a database.

[0802] "Device information" refers to detailed information about the device used by the user, including, for example, the model name, settings, and status.

[0803] A "generative model" refers to an algorithmic model that uses AI technology to generate solutions to problems.

[0804] "Problem Solution" refers to the specific solution or procedure for a user's request for assistance.

[0805] "Emotional state" refers to the psychological state of the user when they make a support request, and is information obtained through analysis.

[0806] "Optimization" refers to the process of adjusting and refining the generated problem solution based on the user's emotional state.

[0807] "Feedback" refers to users' reactions and evaluations of the services and solutions provided.

[0808] This invention is a system that allows users to receive support 24 hours a day for problems or questions about food delivery. This system is combined with an emotion engine that recognizes the user's emotions to realize responses that take the user's emotions into consideration. An embodiment of this system is described in detail below.

[0809] System Overview

[0810] The system consists of the following main components:

[0811] 1. A means of receiving assistance requests from users

[0812] 2. Means of obtaining support history and device information

[0813] 3. A method for generating solutions using generative models

[0814] 4. Using an emotion engine to optimize emotion-based solutions

[0815] 5. A means of providing optimized solutions to users

[0816] 6. How to receive user feedback

[0817] Programs and hardware used

[0818] The server implements the system using the following hardware and software.

[0819] Hardware: A server with a powerful processor, sufficient memory, and a fast network interface.

[0820] software:

[0821] Database: A database that stores user information, assistance history, and device information.

[0822] Emotion Engine: Software that uses Natural Language Processing (NLP) technology to analyze user emotions.

[0823] Generative model: An AI model that uses machine learning algorithms to generate solutions to problems (e.g., GPT-3 and BERT models).

[0824] Application Server: Software that manages user requests and interacts with the generative model and emotion engine.

[0825] Data processing and calculation

[0826] 1. Receiving your request for assistance:

[0827] A user sends a request for assistance to the server using a smartphone or web app, including a detailed description of the problem and screenshots, if necessary.

[0828] 2. Obtaining User Information:

[0829] The server connects to the database and retrieves the user's past support history and device information based on the received user ID.

[0830] 3. Emotion analysis:

[0831] The emotion engine analyzes the text data of the request for assistance to detect the user's emotional state, identifying emotions such as "confusion," "anger," and "sadness."

[0832] 4. Generate solutions to problems:

[0833] Based on the acquired user information and the content of the assistance request, the generative model generates an optimal solution to the problem, using the prompt sentence as input.

[0834] 5. Emotion-based optimization:

[0835] The emotion engine optimizes the tone and style of the generated solutions based on the user's emotional state. For example, if the user is confused, the explanation will be delivered in a gentle tone.

[0836] 6. Offerings to Users:

[0837] The optimized solution is sent to the user's device, where the user can review the steps and attempt to resolve the issue.

[0838] 7. Receiving and Processing Feedback:

[0839] Users can provide feedback on the solutions provided, which is received by the server and stored in a database. The feedback is used to retrain the generative model to improve its accuracy in solving future problems.

[0840] Specific examples

[0841] For example, if a user sends a request for assistance stating "my order hasn't arrived," the system operates as follows:

[0842] 1. Receiving your request for assistance:

[0843] A user submits a request for assistance, detailing that their order has not arrived and attaching screenshots.

[0844] 2. Obtaining User Information:

[0845] The server retrieves the user's past order history and device information from the database.

[0846] 3. Emotion analysis:

[0847] The emotion engine analyzes the user's "confused" emotions from requests for assistance.

[0848] 4. Generate solutions to problems:

[0849] Based on the information obtained, the generative model generates a solution such as "Restart the app to check the order status, then check your order history."

[0850] 5. Emotion-based optimization:

[0851] The emotion engine optimizes the solution to a gentle tone: "Please wait a moment. Please restart the app and check your order history again."

[0852] 6. Offerings to Users:

[0853] The optimized solution is sent to the user's device, where the user can review and try the steps.

[0854] 7. Receiving and Processing Feedback:

[0855] When a user sends feedback that the problem has been resolved, the server stores this in a database and uses it for future support.

[0856] Example prompt sentence:

[0857] text

[0858] For users who are confused about not receiving their order, generate a support message in a human tone, like this:

[0859] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0860] Step 1:

[0861] The device receives a request for assistance from the user. The user provides a detailed description of the problem and any necessary screenshots using a smartphone app or web app. The device converts this input information into a packet format and sends it to the server as an HTTP request. Specifically, the device attaches the problem "My order hasn't arrived" and screenshots.

[0862] Step 2:

[0863] The server receives the assistance request and retrieves the user's past assistance history and device information from the database. Specifically, it accesses the database, searches for related data based on the user ID, and retrieves the past order history and device information. This allows the assistance history and device information to be imported into the server as input data.

[0864] Step 3:

[0865] The server uses an emotion engine to analyze the user's emotional state from the request for assistance. The input data is the text of the request for assistance, and NLP technology is used to recognize emotional states such as "confusion." The analyzed emotional state is output as "confusion."

[0866] Step 4:

[0867] The server uses a generative model to generate a solution to the problem based on the information it obtains. The input data is the content of the assistance request, past assistance history, and device information, and the AI ​​model generates a solution such as "Restart the app to check the order status, then check your order history."

[0868] Step 5:

[0869] The server uses an emotion engine to optimize the generated solution according to the user's emotional state. The input data is "Please restart the app to check the order status, then check your order history" and the emotional state is "confused," and the emotion engine outputs a gentle solution saying, "Please wait a moment. Please restart the app and check your order history again."

[0870] Step 6:

[0871] The server sends the optimized solution to the user's device. The input data is the optimized solution, which is sent to the device as an HTTP response. The device displays this solution to the user, who can then check the solution and attempt to solve the problem.

[0872] Step 7:

[0873] The user acts on the provided solution and sends the result as feedback from the device to the server. The input data is the feedback, and the device sends feedback information such as "the problem has been solved" to the server as an HTTP request.

[0874] Step 8:

[0875] The server receives the feedback and records it in a database. The input data is the feedback information, which is then stored in the database. Furthermore, the generative model is retrained based on the feedback, improving its accuracy for subsequent assistance requests.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] [Third embodiment]

[0880] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0881] 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.

[0882] 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).

[0883] 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.

[0884] 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.

[0885] 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).

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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."

[0892] This invention is a system designed to enable users to receive support 24 hours a day. Specifically, it comprises a means for receiving a support request from a user, a means for acquiring the user's past support history and device information, a means for generating a solution to a problem using a generative model, a means for providing the generated solution to the user, and a means for receiving user feedback.

[0893] Explanation of program processing

[0894] 1. The server starts first and loads the necessary data and AI models.

[0895] The server establishes a database connection and loads user information, support history, and FAQs into a cache.

[0896] The server loads the generative AI model and updates it if necessary from an external source.

[0897] 2. The user requests support using their device (smartphone or PC).

[0898] The user opens a dedicated application on the device and fills out an inquiry form.

[0899] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[0900] 3. The device sends the request to the server.

[0901] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[0902] 4. The server receives the request and retrieves the user's support history and device information.

[0903] The server searches the database for the corresponding user ID and retrieves the necessary information.

[0904] 5. The server inputs the problem summary and historical data into the AI ​​model and generates a solution.

[0905] The server uses the AI ​​model to generate a solution based on the user's current problem and past patterns.

[0906] 6. The server converts the generated solution into a format that is easy for the user to understand and sends it to the terminal.

[0907] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[0908] 7. The device displays the received information to the user.

[0909] The device displays instructions on the screen and the user attempts to solve the problem.

[0910] 8. The user follows the steps to resolve the issue and provides feedback on success or failure.

[0911] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[0912] 9. The server receives the feedback and records it in a database.

[0913] The server stores the feedback information in a database and updates the AI ​​model as needed.

[0914] Specific examples

[0915] For example, say a user is having trouble setting up Wi-Fi on their smartphone.

[0916] 1. The user enters the problem "I can't connect to Wi-Fi" on their device, attaches a screenshot, and submits a request.

[0917] 2. The server receives the request and retrieves the support history and the user's device information.

[0918] 3. The server uses the acquired information to use AI models to generate solutions to common Wi-Fi configuration issues and user-specific troubleshooting steps.

[0919] 4. The server sends the generated instructions to the user's device using text and images.

[0920] 5. The device displays the received instructions on the screen, and the user attempts to set up Wi-Fi by following the instructions.

[0921] 6. The user sends feedback from the device to the server, indicating whether the setup was successful or not.

[0922] 7. The server receives the feedback, records it in the system database, and retrains the generative model if necessary.

[0923] This system allows users to receive fast, accurate support 24 hours a day.

[0924] The processing flow will be explained below.

[0925] Step 1:

[0926] The server starts up and loads the necessary data and AI models.

[0927] The server establishes a database connection and loads user information, support history, and FAQs into memory.

[0928] The server loads the generative AI model and updates it if necessary from an external source.

[0929] Step 2:

[0930] The user requests support using a device (smartphone or PC).

[0931] The user opens a dedicated application on the device and fills out an inquiry form.

[0932] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[0933] Step 3:

[0934] The device sends a request to the server.

[0935] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[0936] Step 4:

[0937] The server receives the request and retrieves the user's support history and device information.

[0938] The server searches the database for the corresponding user ID and retrieves the necessary information.

[0939] Step 5:

[0940] The server inputs a problem summary and historical data into the AI ​​model and generates a solution.

[0941] The server uses the AI ​​model to generate a solution based on the user's current problem and past patterns.

[0942] Step 6:

[0943] The server converts the generated solution into a format that is easy for the user to understand and sends it to the terminal.

[0944] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[0945] Step 7:

[0946] The device displays the received information to the user.

[0947] The device displays instructions on the screen and the user attempts to solve the problem.

[0948] Step 8:

[0949] The user follows the steps to resolve the issue and provides feedback on success or failure.

[0950] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[0951] Step 9:

[0952] The server receives the feedback and records it in a database.

[0953] The server stores the feedback information in a database and updates the AI ​​model as needed.

[0954] Example 1

[0955] 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."

[0956] In recent years, with the advancement of electronic devices and information and communication technology, users are increasingly encountering problems with complex devices and software. To quickly address these issues, 24-hour support is necessary, but current support systems are insufficient and fail to satisfy users. Furthermore, manual support by support staff can be time-consuming and costly, resulting in prolonged resolution times. Given this background, there is a demand for automated support systems that can quickly and efficiently resolve user problems.

[0957] 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.

[0958] In this invention, the server includes means for receiving a support request from a user, means for retrieving the user's past support history and device information from a database based on the received support request, means for utilizing a generative AI model using the retrieved information to send prompt text and generate a solution to the problem, means for converting the generated solution into a format that is easy for the user to understand (text, image, etc.) and sending it to the user terminal, and means for receiving and recording user feedback on the provided solution, thereby enabling users to receive fast and highly accurate support 24 hours a day.

[0959] A "server" is a central computer system that receives requests from users and processes data.

[0960] "Support Request" means a request submitted by a User to resolve a Device or Software issue.

[0961] A "database" is an information system for systematically storing and managing user information, support history, device information, etc.

[0962] A "generative AI model" is an artificial intelligence model that automatically generates solutions to problems based on input information.

[0963] A "prompt sentence" is text data input into a generative AI model that contains instructions and conditions for solving a problem.

[0964] A "solution" is a procedure or method for solving a user's problem obtained using a generative AI model.

[0965] A "user terminal" is a computer device (such as a smartphone or PC) used by a user, which receives and displays information from a server.

[0966] "Feedback" refers to evaluation information that a user sends back to the server regarding the effectiveness and results of the solution provided.

[0967] Based on these definitions, the technical scope of the invention is clearly defined.

[0968] This invention is a system that allows users to receive support 24 hours a day. Specifically, it is implemented using the following hardware and software.

[0969] Hardware and Software Configuration

[0970] 1. Server: A high-performance computing system that receives requests, connects to a database, and runs generative AI models. Examples include Linux-based servers and cloud services (AWS, Google Cloud, etc.).

[0971] 2. Database: Stores user information, support history, FAQs, etc. Uses a relational database such as MySQL or PostgreSQL.

[0972] 3. Generative AI models: Generate solutions to problems using deep learning models such as GPT-3 and BERT.

[0973] 4. User device: A computing device that users use on a daily basis, such as a smartphone or PC.

[0974] Specific functions of the system

[0975] 1. The server receives a support request from the user, often in the form of an HTTP POST request.

[0976] 2. The server connects to the database and retrieves the user's past support history and device information.

[0977] 3. The server sends a prompt to the generative AI model to generate a solution to the problem. An example of a prompt is, "A user is reporting an issue where they cannot connect to Wi-Fi. Based on their past support history and device information, what is the best course of action to resolve this user's issue?"

[0978] 4. The server converts the generated solution into text or image format and sends it to the user's device.

[0979] 5. The device receives the solution from the server and displays it on the screen.

[0980] 6. The user follows the provided steps to resolve the issue.

[0981] 7. The user provides feedback on whether the solution worked or not.

[0982] 8. The server receives the feedback and records it in a database. It may also retrain the generative AI model based on the feedback information.

[0983] Usage example

[0984] For example, a user may have problems connecting to Wi-Fi on their smartphone. The user opens a dedicated application and submits a screenshot of the problem, stating "Wi-Fi cannot be connected." The server receives the request and retrieves past support history and device information from the database. It then sends prompt text to the generative AI model to generate a solution for Wi-Fi settings. The server converts the generated solution into text and image format and sends it to the user's device. The user then checks the solution on their device, follows the steps to solve the problem, and submits feedback.

[0985] This system allows users to receive fast, highly accurate support 24 hours a day.

[0986] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0987] Step 1:

[0988] The server receives a support request from the user.

[0989] Specifically, the server receives information (e.g., a summary of the problem, an error message, and a screenshot) as an HTTP POST request. The input is the query sent by the user from the device. The server parses the received data and converts it into an internal format.

[0990] Step 2:

[0991] The server connects to the database and retrieves the user's past support history and device information.

[0992] The server uses the user ID to send an SQL query to the database to retrieve the corresponding user information. The input is the user ID and the requested information fields. The output is the past support history and device information.

[0993] Step 3:

[0994] The server sends prompts to the generative AI model to generate solutions to the problem.

[0995] The server creates a prompt based on the acquired information and sends it to the generative AI model. The inputs include the user's problem information, past support data, and device information. The generative AI model then runs a deep learning algorithm based on this information to generate a solution to the problem. The output is a text version of the solution.

[0996] Step 4:

[0997] The server converts the generated solution into a format that is easy for the user to understand and sends it to the user's terminal.

[0998] The server formats the generated solution into text or image format and sends it as an HTTP response. The input is the solution received from the generative AI model. The output is the solution data received by the user device.

[0999] Step 5:

[1000] The device receives the solution from the server and displays it on the screen.

[1001] The terminal parses the HTTP response and displays the solution to the user. As input, it has the solution data sent by the server. As output, it has a representation of the solution that the user can view.

[1002] Step 6:

[1003] The user follows the steps provided to resolve the issue.

[1004] The input is the displayed solution steps. The output is the problem being solved. The specific action is for the user to follow the instructions on the device.

[1005] Step 7:

[1006] The user provides feedback on whether the solution worked.

[1007] The user uses a feedback form in the application to enter and submit a success or failure rating. The input is the feedback content. The output is the rating data sent to the server.

[1008] Step 8:

[1009] The server receives the feedback and records it in a database.

[1010] The server analyzes the received feedback and records it in a database. The input is the feedback data from the user. The output is the feedback information stored in the database. If necessary, it retrains the generative AI model.

[1011] Through these processing steps, users can receive fast and accurate support 24 hours a day.

[1012] (Application example 1)

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

[1014] The goal is to provide a system that allows users of autonomous vehicles to receive prompt and highly accurate support 24 hours a day. In particular, there is a need to establish a means of providing users with appropriate solutions in real time for problems and issues specific to autonomous vehicles.

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

[1016] In this invention, the server includes means for receiving a support request from a user, means for acquiring the user's past support history and device information based on the support request, means for generating a solution to the problem using a generative AI model with the acquired information, means for providing the generated solution to the user, means for receiving user feedback on the provided solution, and display means including images and audio guides for displaying the generated solution, thereby enabling users of autonomous vehicles to receive prompt and appropriate support at any time of day.

[1017] "Means for receiving support requests from users" refers to an interface that allows users to input their problems or questions and send them to the system.

[1018] "Means for acquiring a user's past support history and device information" is a function for acquiring from a database the history of support the user has received in the past and information on the device the user is currently using.

[1019] "Means for generating solutions using generative AI models" refers to the process of using artificial intelligence models based on acquired information to derive appropriate solutions to users' problems.

[1020] "Means to provide to the user" refers to an interface that provides the generated solution in a format that is easy for the user to understand.

[1021] "Means for receiving user feedback" refers to a function that allows users to send back to the system their evaluations and results of the solutions provided.

[1022] "Display means including visual and audio guides" refers to devices or interfaces for visually and audibly presenting the generated solution to the user.

[1023] "Means for retraining the generative AI model" refers to the process of retraining the generative AI model based on user feedback to improve the accuracy of its solutions.

[1024] The present invention provides a system that enables users of autonomous vehicles to receive prompt and highly accurate support 24 hours a day. A specific embodiment of this system is described below.

[1025] System Configuration

[1026] 1. Server:

[1027] The server is connected to a database that stores data such as user information, support history, and FAQs.

[1028] The server is implemented in a programming language such as Python.

[1029] The server has the ability to generate solutions from support requests using generative AI models (e.g., GPT-4).

[1030] 2. On the user's device:

[1031] User devices include smartphones, tablets, and PCs.

[1032] A dedicated support application is installed on the device.

[1033] 3. Get device information:

[1034] The server retrieves past support history and device information from a database based on the user's support request.

[1035] Data processing and calculation

[1036] Information Collection:

[1037] When a user submits a support request, the device sends the input information (such as a summary of the problem, error messages, screenshots, etc.) to the server as an HTTP request.

[1038] The server retrieves user information, past support history, and device information from the database.

[1039] Generate solutions:

[1040] The server provides the generative AI model with information about the current problem and past data as input.

[1041] The generative AI model uses this information to generate the most appropriate solution to the problem.

[1042] Solution provided:

[1043] The server converts the generated solution into a user-friendly format (text, images, audio guide, etc.) and sends it to the terminal as an HTTP response.

[1044] The terminal displays the received information to the user.

[1045] Receive feedback and retrain:

[1046] The user provides feedback on whether they succeeded or failed in resolving the issue.

[1047] The server records this feedback in a database and retrains the generative AI model as needed.

[1048] Specific examples

[1049] For example, consider a case where a user reports an issue with the self-parking feature of their self-driving vehicle not working.

[1050] 1. The user enters the problem "Automatic parking function is not working" into the smartphone app and submits a request along with screenshots and error messages.

[1051] 2. The server receives this request and retrieves the user's past support history and vehicle information from the database.

[1052] 3. The server inputs the acquired information into a generative AI model to generate specific troubleshooting steps.

[1053] 4. The server compiles the generated instructions into text and audio guides and sends them to the user's device.

[1054] 5. The user follows the instructions received to check the vehicle's settings and attempt to resolve the issue.

[1055] 6. The user selects success or failure within the app and submits feedback.

[1056] 7. The server receives the feedback, records it in a database, and retrains the generative AI model if necessary.

[1057] Prompt Sentence Examples

[1058] For example, the prompt text might look like this:

[1059] Please enter a description of the problem: Autopark feature not working

[1060] Did this solve your problem? (yes / no): no

[1061] This will ensure that users of autonomous vehicles can receive prompt and appropriate support at any time.

[1062] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1063] Step 1:

[1064] A user submits a support request from their device. Input information includes a summary of the problem, an error message, a screenshot, etc. This data is sent from the device to the server as an HTTP request. The device converts this request into a packet format and sends it to the server.

[1065] Step 2:

[1066] The server receives a support request. It searches the database based on the user ID in the request to retrieve the user's past support history and device information. At this stage, the server establishes a database connection and loads the necessary information into a cache.

[1067] Step 3:

[1068] The server uses the information it acquires to provide input data to the generative AI model. Specifically, the user's current problem, past support history, device information, etc. are provided as input to the generative AI model (e.g., GPT-4). This is where data processing and normalization are performed.

[1069] Step 4:

[1070] The generative AI model generates a solution to the problem. The server generates the solution in text format as the output of the AI ​​model, as well as images and audio guidance if necessary. Data calculations are performed here to obtain a solution to the user's specific problem.

[1071] Step 5:

[1072] The server provides the generated solution to the user's device, and then sends the generated solution to the device as an HTTP response, which includes data converted into formats such as text, images, and audio.

[1073] Step 6:

[1074] The device displays the received information to the user. The device displays the transmitted text, images, and audio instructions on the screen, allowing the user to implement solutions. This allows the user to follow specific steps to solve the problem.

[1075] Step 7:

[1076] The user attempts to solve the problem and sends the results as feedback from the device to the server. The user selects whether the solution was successful or not and enters feedback information. The device then sends this as an HTTP request to the server.

[1077] Step 8:

[1078] The server receives the feedback and records it in a database. The server analyzes the received feedback and retrains the generative AI model as needed. This feedback process allows the system to constantly improve and provide more accurate solutions.

[1079] 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.

[1080] This invention combines a system that allows users to receive support 24 hours a day with an emotion engine that recognizes user emotions. Specifically, the system is configured to include a means for receiving support requests from users, a means for acquiring the user's past support history and device information, a means for generating solutions to problems using a generative model, a means for providing the generated solutions to users, a means for receiving user feedback, and an emotion engine.

[1081] Explanation of program processing

[1082] 1. The server starts first and loads the necessary data, AI models, and emotion engines.

[1083] The server establishes a database connection and loads user information, support history, and FAQs into memory.

[1084] The server loads the generative AI model and emotion engine, updating it if necessary from external sources.

[1085] 2. The user requests support using their device (smartphone or PC).

[1086] The user opens a dedicated application on the device and fills out an inquiry form.

[1087] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[1088] 3. The device sends the request to the server.

[1089] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[1090] 4. The server receives the request and retrieves the user's support history and device information.

[1091] The server searches the database for the corresponding user ID and retrieves the necessary information.

[1092] 5. The server inputs the problem summary and historical data into the AI ​​model and generates a solution.

[1093] The server uses the AI ​​model to generate a solution based on the user's current problem and past patterns.

[1094] 6. The server optimizes the generated solution using the emotion engine.

[1095] The server analyzes the user's current emotional state and optimizes the solution to suit that emotion.

[1096] 7. The server converts the optimized solution into a user-friendly format and sends it to the device.

[1097] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[1098] 8. The device displays the information it has received to the user.

[1099] The device displays instructions on the screen and the user attempts to solve the problem.

[1100] 9. The user follows the steps to resolve the issue and provides feedback on success or failure.

[1101] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[1102] 10. The server receives the feedback and records it in a database.

[1103] The server stores the feedback information in a database, updates the AI ​​model as needed, and uses an emotion engine to analyze emotions based on the feedback content.

[1104] Specific examples

[1105] For example, say a user is having trouble setting up Wi-Fi on their smartphone.

[1106] 1. The user enters the problem "I can't connect to Wi-Fi" on their device, attaches a screenshot, and submits a request.

[1107] 2. The server receives the request and retrieves the support history and the user's device information.

[1108] 3. The server uses the acquired information to use AI models to generate solutions to common Wi-Fi configuration issues and user-specific troubleshooting steps.

[1109] 4. The server uses an emotion engine to optimize the generated instructions to match the user's emotions. For example, if the user is "confused," the server will explain the instructions in a gentle tone.

[1110] 5. The server sends the optimized instructions to the user's device.

[1111] 6. The device displays the received instructions on the screen, and the user attempts to set up Wi-Fi by following the instructions.

[1112] 7. The user sends feedback from the device to the server, indicating whether the setup was successful or not.

[1113] 8. The server receives the feedback, records it in the system database, retrains the generative model if necessary, and analyzes the feedback using the emotion engine to provide future support.

[1114] The system allows users to receive fast, accurate and emotionally sensitive support 24 hours a day.

[1115] The processing flow will be explained below.

[1116] Step 1:

[1117] The server starts up and loads the necessary data, AI models, and emotion engines.

[1118] The server establishes a database connection and loads user information, support history, and FAQs into memory.

[1119] The server loads the generative AI model and emotion engine, updating it if necessary from external sources.

[1120] Step 2:

[1121] Users can request support using their own devices (smartphones or PCs).

[1122] The user opens a dedicated application on the device and fills out an inquiry form.

[1123] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[1124] Step 3:

[1125] The device sends a request to the server.

[1126] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[1127] Step 4:

[1128] The server receives the request and retrieves the user's support history and device information.

[1129] The server searches the database for the corresponding user ID and retrieves the necessary information.

[1130] Step 5:

[1131] The server uses an emotion engine to analyze the user's emotional state.

[1132] The server uses an emotion engine to assess the user's current emotional state (e.g., confusion, anger, relief, etc.) based on the request data and past interactions.

[1133] Step 6:

[1134] The server inputs a problem summary, past data, and analyzed emotional information into the AI ​​model, and generates a solution.

[1135] The server uses an AI model to generate a solution based on the user's current problem, past patterns, and emotional state.

[1136] Step 7:

[1137] The server optimizes the generated solution using an emotion engine.

[1138] Based on the analysis results of the emotion engine, the server optimizes the solution with a tone and expression that corresponds to the user's emotional state.

[1139] Step 8:

[1140] The server converts the optimized solution into a user-friendly format and sends it to the device.

[1141] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[1142] Step 9:

[1143] The device displays the received information to the user.

[1144] The device displays instructions on the screen and the user attempts to solve the problem.

[1145] Step 10:

[1146] The user follows the steps to resolve the issue and provides feedback on success or failure.

[1147] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[1148] Step 11:

[1149] The server receives the feedback and records it in a database.

[1150] The server stores the feedback information in a database and updates the AI ​​model as needed. It also analyzes the feedback using an emotion engine and uses it to provide future support.

[1151] Example 2

[1152] 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."

[1153] In traditional support systems, when users request support, appropriate solutions are often not provided quickly, resulting in a poor user experience. Furthermore, solutions provided without considering the user's feelings can reduce user satisfaction. Furthermore, feedback is not utilized in the system, which makes it difficult to improve support quality.

[1154] 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 means for receiving a support request from a user, a means for acquiring the user's past support history and electronic device information, a means for generating a solution to a problem using a generation algorithm based on the acquired information, a means for optimizing the generated solution using a sentiment analysis engine, a means for providing the optimized solution to the user, and a means for receiving user feedback on the provided solution. This allows users to receive fast, highly accurate support 24 hours a day, and provides solutions that take the user's emotions into consideration. Furthermore, utilizing feedback in the system enables continuous improvement of support quality.

[1155] "Support Request" means a request submitted by a User to the System for support.

[1156] "Past support history" refers to records and information regarding the support a user has previously received.

[1157] "Electronic device information" refers to detailed technical information about the devices a user uses.

[1158] A "generative algorithm" is a computational method or model that generates solutions to problems based on collected data.

[1159] An "emotion analysis engine" is a software component that analyzes a user's emotional state and optimizes solutions based on the results.

[1160] "Delivery means" refers to the method or technique used to present the generated solution to the user.

[1161] "Feedback" refers to the ratings and comments users make on the solutions provided.

[1162] "Retraining" is the process of updating the generative algorithm with new data and feedback collected to generate more accurate solutions.

[1163] This invention combines a system that allows users to receive support 24 hours a day with an emotion analysis engine that recognizes the emotions of users. A specific embodiment of this system will be described below.

[1164] The server starts up and loads the necessary data, generative AI model, and sentiment analysis engine. The server connects to a database (e.g., MySQL or PostgreSQL) and loads user information, support history, and FAQ data into RAM. This database connection allows the server to retrieve necessary data such as the user's past support history and electronic device information. The server also loads the generative AI model (e.g., GPT-4) and sentiment analysis engine (e.g., Empathizer) from disk and updates them from an external source (e.g., a cloud server) as needed.

[1165] A user requests support using a device such as a smartphone or PC. The user opens a dedicated application (e.g., a customer support app), enters a summary of the problem in the inquiry form, and uploads any error messages and screenshots. Once the input is complete, the user clicks the "Submit" button. The device converts the entered information into a packet format (e.g., JSON format), generates an HTTP request, and sends it to the server's API endpoint.

[1166] The server receives the request and retrieves the user's support history and device information. It then executes a database query to search for the user ID and uses the retrieved information to generate a prompt for the generative AI model. For example, the prompt can include a problem summary such as "I can't connect to Wi-Fi" and past support history.

[1167] The generative AI model generates a solution based on the prompt. The generated solution is then optimized by a sentiment analysis engine. The sentiment analysis engine analyzes the user's emotional state based on their past conversation patterns and real-time data. For example, if the user is confused, the engine reframes the solution in a gentler, more polite tone. Specifically, it adds a message such as "Don't worry, let's solve this together" to the generated solution.

[1168] The server converts the optimized solution into a user-friendly format and sends it to the device. The server formats the solution as a text document or image guidelines and sends it to the device as an HTTP response. The device analyzes the received information and displays it to the user. The user then follows the displayed steps to try to solve the problem.

[1169] Regardless of whether the user has solved the problem, feedback is provided within the application. The user selects whether the solution was successful or not, enters any additional comments, and clicks the "Submit" button. The feedback is sent from the device to the server, which receives it, records it in a database, and retrains the generative AI model as needed. The sentiment analysis engine also performs sentiment analysis based on the feedback content, which is used to improve future support.

[1170] This system allows users to receive fast, accurate support 24 hours a day, providing solutions that are considerate of their emotions, and by incorporating feedback into the system, it is possible to continuously improve the quality of support.

[1171] Example prompt:

[1172] "I can't connect to Wi-Fi. The error message is 'Unable to connect to network'. I've had a similar issue twice in my history, and a reboot fixed it once."

[1173] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1174] Step 1:

[1175] The server starts up and loads the necessary data, generative AI models, and sentiment analysis engines.

[1176] After the operating system starts, the server establishes a network connection. Next, it connects to a database (e.g., MySQL or PostgreSQL) and loads user information, support history, and FAQ data into RAM. It then loads a generative AI model (e.g., GPT-4) and a sentiment analysis engine (e.g., Empathizer) from disk. This prepares the server with the necessary data, such as the user's support history and electronic device information.

[1177] Input: Database access information, storage paths for generative AI models and sentiment analysis engines

[1178] Output: User information, support history, FAQ data, generative AI models and sentiment analysis engines loaded into server memory

[1179] Step 2:

[1180] Users can request support using their own devices (smartphones or PCs).

[1181] The user opens the dedicated application, enters detailed information (problem summary, error message, screenshot) into the inquiry form, and clicks the "Submit" button.

[1182] Input: User-entered problem summary, error message, and screenshot

[1183] Output: The input information that is sent

[1184] Step 3:

[1185] The device sends a request to the server.

[1186] The terminal converts the input information into a packet format, generates an HTTP request, and sends it to the server's API endpoint.

[1187] Input: Support request information entered by the user

[1188] Output: HTTP request sent to the server

[1189] Step 4:

[1190] The server receives the request and obtains the user's past support history and electronic device information.

[1191] The server analyzes the received HTTP request, extracts the user ID and problem summary, and then executes a database query to search for information based on the corresponding user ID, retrieving past support history and device information.

[1192] Input: HTTP request, user information

[1193] Output: Retrieved past support history and electronic device information

[1194] Step 5:

[1195] The server inputs a problem summary and past data into the generated AI model and generates a solution.

[1196] The server inputs a summary of the problem and past data as a prompt to the generative AI model, which then generates a solution based on this.

[1197] Input: Problem summary, past data

[1198] Output: A solution from the generative AI model

[1199] Step 6:

[1200] The server optimizes the generated solution using a sentiment analysis engine.

[1201] The server uses an emotion analysis engine to analyze the user's emotional state and optimizes the generated solution according to the user's emotions, for example, reframing a confused user in a gentler tone.

[1202] Input: Solution from a generative AI model, user emotional state

[1203] Output: A solution optimized by the sentiment analysis engine

[1204] Step 7:

[1205] The server converts the optimized solution into a user-friendly format and sends it to the terminal.

[1206] The server formats the solution as a text document or image guidelines and sends it to the device as an HTTP response.

[1207] Input: Optimized solution

[1208] Output: The solution sent as an HTTP response

[1209] Step 8:

[1210] The terminal displays the received information to the user.

[1211] The terminal analyzes the received HTTP response, extracts the solution text and images, and displays them to the user.

[1212] Input: HTTP response

[1213] Output: The solution that is displayed to the user

[1214] Step 9:

[1215] The user follows the steps to resolve the issue and provides feedback on success or failure.

[1216] The user attempts to solve the problem within the application, provides feedback on success or failure, and clicks the "Submit" button.

[1217] Input: User feedback information

[1218] Output: Feedback information to be sent

[1219] Step 10:

[1220] The server receives the feedback and records it in a database.

[1221] The server stores the received feedback information in a database and, if necessary, retrains the generative AI model. It also performs sentiment analysis and uses the information to improve future support.

[1222] Input: Feedback information

[1223] Output: Feedback information recorded in a database, updated generative AI model

[1224] (Application example 2)

[1225] 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."

[1226] In conventional support systems, a uniform response is given without considering the user's emotional state, which can lead to a decrease in user satisfaction. In addition, in today's world where 24-hour support is required, providing support that is quick and considerate of the user's emotions is a challenge.

[1227] 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 means for receiving a support request from a user, means for acquiring the user's past support history and device information, means for generating a solution to the problem using a generative model with the acquired information, means for recognizing the user's emotional state and optimizing the solution based on the emotion, means for providing the generated solution to the user, and means for receiving the user's feedback on the provided solution. This enables user-friendly support that is available 24 hours a day and takes emotions into consideration.

[1228] "User" refers to a person who uses the System and provides assistance requests or feedback.

[1229] "Assistance Request" means a request made by a User seeking service or support.

[1230] "Support history" refers to a record of support a user has received in the past, and is information stored in a database.

[1231] "Device information" refers to detailed information about the device used by the user, including, for example, the model name, settings, and status.

[1232] A "generative model" refers to an algorithmic model that uses AI technology to generate solutions to problems.

[1233] "Problem Solution" refers to the specific solution or procedure for a user's request for assistance.

[1234] "Emotional state" refers to the psychological state of the user when they make a support request, and is information obtained through analysis.

[1235] "Optimization" refers to the process of adjusting and refining the generated problem solution based on the user's emotional state.

[1236] "Feedback" refers to users' reactions and evaluations of the services and solutions provided.

[1237] This invention is a system that allows users to receive support 24 hours a day for problems or questions about food delivery. This system is combined with an emotion engine that recognizes the user's emotions to realize responses that take the user's emotions into consideration. An embodiment of this system is described in detail below.

[1238] System Overview

[1239] The system consists of the following main components:

[1240] 1. A means of receiving assistance requests from users

[1241] 2. Means of obtaining support history and device information

[1242] 3. A method for generating solutions using generative models

[1243] 4. Using an emotion engine to optimize emotion-based solutions

[1244] 5. A means of providing optimized solutions to users

[1245] 6. How to receive user feedback

[1246] Programs and hardware used

[1247] The server implements the system using the following hardware and software.

[1248] Hardware: A server with a powerful processor, sufficient memory, and a fast network interface.

[1249] software:

[1250] Database: A database that stores user information, assistance history, and device information.

[1251] Emotion Engine: Software that uses Natural Language Processing (NLP) technology to analyze user emotions.

[1252] Generative model: An AI model that uses machine learning algorithms to generate solutions to problems (e.g., GPT-3 and BERT models).

[1253] Application Server: Software that manages user requests and interacts with the generative model and emotion engine.

[1254] Data processing and calculation

[1255] 1. Receiving your request for assistance:

[1256] A user sends a request for assistance to the server using a smartphone or web app, including a detailed description of the problem and screenshots, if necessary.

[1257] 2. Obtaining User Information:

[1258] The server connects to the database and retrieves the user's past support history and device information based on the received user ID.

[1259] 3. Emotion analysis:

[1260] The emotion engine analyzes the text data of the request for assistance to detect the user's emotional state, identifying emotions such as "confusion," "anger," and "sadness."

[1261] 4. Generate solutions to problems:

[1262] Based on the acquired user information and the content of the assistance request, the generative model generates an optimal solution to the problem, using the prompt sentence as input.

[1263] 5. Emotion-based optimization:

[1264] The emotion engine optimizes the tone and style of the generated solutions based on the user's emotional state. For example, if the user is confused, the explanation will be delivered in a gentle tone.

[1265] 6. Offerings to Users:

[1266] The optimized solution is sent to the user's device, where the user can review the steps and attempt to resolve the issue.

[1267] 7. Receiving and Processing Feedback:

[1268] Users can provide feedback on the solutions provided, which is received by the server and stored in a database. The feedback is used to retrain the generative model to improve its accuracy in solving future problems.

[1269] Specific examples

[1270] For example, if a user sends a request for assistance stating "my order hasn't arrived," the system operates as follows:

[1271] 1. Receiving your request for assistance:

[1272] A user submits a request for assistance, detailing that their order has not arrived and attaching screenshots.

[1273] 2. Obtaining User Information:

[1274] The server retrieves the user's past order history and device information from the database.

[1275] 3. Emotion analysis:

[1276] The emotion engine analyzes the user's "confused" emotions from requests for assistance.

[1277] 4. Generate solutions to problems:

[1278] Based on the information obtained, the generative model generates a solution such as "Restart the app to check the order status, then check your order history."

[1279] 5. Emotion-based optimization:

[1280] The emotion engine optimizes the solution to a gentle tone: "Please wait a moment. Please restart the app and check your order history again."

[1281] 6. Offerings to Users:

[1282] The optimized solution is sent to the user's device, where the user can review and try the steps.

[1283] 7. Receiving and Processing Feedback:

[1284] When a user sends feedback that the problem has been resolved, the server stores this in a database and uses it for future support.

[1285] Example prompt sentence:

[1286] text

[1287] For users who are confused about not receiving their order, generate a support message in a human tone, like this:

[1288] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1289] Step 1:

[1290] The device receives a request for assistance from the user. The user provides a detailed description of the problem and any necessary screenshots using a smartphone app or web app. The device converts this input information into a packet format and sends it to the server as an HTTP request. Specifically, the device attaches the problem "My order hasn't arrived" and screenshots.

[1291] Step 2:

[1292] The server receives the assistance request and retrieves the user's past assistance history and device information from the database. Specifically, it accesses the database, searches for related data based on the user ID, and retrieves the past order history and device information. This allows the assistance history and device information to be imported into the server as input data.

[1293] Step 3:

[1294] The server uses an emotion engine to analyze the user's emotional state from the request for assistance. The input data is the text of the request for assistance, and NLP technology is used to recognize emotional states such as "confusion." The analyzed emotional state is output as "confusion."

[1295] Step 4:

[1296] The server uses a generative model to generate a solution to the problem based on the information it obtains. The input data is the content of the assistance request, past assistance history, and device information, and the AI ​​model generates a solution such as "Restart the app to check the order status, then check your order history."

[1297] Step 5:

[1298] The server uses an emotion engine to optimize the generated solution according to the user's emotional state. The input data is "Please restart the app to check the order status, then check your order history" and the emotional state is "confused," and the emotion engine outputs a gentle solution saying, "Please wait a moment. Please restart the app and check your order history again."

[1299] Step 6:

[1300] The server sends the optimized solution to the user's device. The input data is the optimized solution, which is sent to the device as an HTTP response. The device displays this solution to the user, who can then check the solution and attempt to solve the problem.

[1301] Step 7:

[1302] The user acts on the provided solution and sends the result as feedback from the device to the server. The input data is the feedback, and the device sends feedback information such as "the problem has been solved" to the server as an HTTP request.

[1303] Step 8:

[1304] The server receives the feedback and records it in a database. The input data is the feedback information, which is then stored in the database. Furthermore, the generative model is retrained based on the feedback, improving its accuracy for subsequent assistance requests.

[1305] 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.

[1306] 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.

[1307] 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.

[1308] [Fourth embodiment]

[1309] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1310] 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.

[1311] 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).

[1312] 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.

[1313] 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.

[1314] 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).

[1315] 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.

[1316] 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.

[1317] 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.

[1318] 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.

[1319] 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.

[1320] 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.

[1321] 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."

[1322] This invention is a system designed to enable users to receive support 24 hours a day. Specifically, it comprises a means for receiving a support request from a user, a means for acquiring the user's past support history and device information, a means for generating a solution to a problem using a generative model, a means for providing the generated solution to the user, and a means for receiving user feedback.

[1323] Explanation of program processing

[1324] 1. The server starts first and loads the necessary data and AI models.

[1325] The server establishes a database connection and loads user information, support history, and FAQs into a cache.

[1326] The server loads the generative AI model and updates it if necessary from an external source.

[1327] 2. The user requests support using their device (smartphone or PC).

[1328] The user opens a dedicated application on the device and fills out an inquiry form.

[1329] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[1330] 3. The device sends the request to the server.

[1331] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[1332] 4. The server receives the request and retrieves the user's support history and device information.

[1333] The server searches the database for the corresponding user ID and retrieves the necessary information.

[1334] 5. The server inputs the problem summary and historical data into the AI ​​model and generates a solution.

[1335] The server uses the AI ​​model to generate a solution based on the user's current problem and past patterns.

[1336] 6. The server converts the generated solution into a format that is easy for the user to understand and sends it to the terminal.

[1337] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[1338] 7. The device displays the received information to the user.

[1339] The device displays instructions on the screen and the user attempts to solve the problem.

[1340] 8. The user follows the steps to resolve the issue and provides feedback on success or failure.

[1341] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[1342] 9. The server receives the feedback and records it in a database.

[1343] The server stores the feedback information in a database and updates the AI ​​model as needed.

[1344] Specific examples

[1345] For example, say a user is having trouble setting up Wi-Fi on their smartphone.

[1346] 1. The user enters the problem "I can't connect to Wi-Fi" on their device, attaches a screenshot, and submits a request.

[1347] 2. The server receives the request and retrieves the support history and the user's device information.

[1348] 3. The server uses the acquired information to use AI models to generate solutions to common Wi-Fi configuration issues and user-specific troubleshooting steps.

[1349] 4. The server sends the generated instructions to the user's device using text and images.

[1350] 5. The device displays the received instructions on the screen, and the user attempts to set up Wi-Fi by following the instructions.

[1351] 6. The user sends feedback from the device to the server, indicating whether the setup was successful or not.

[1352] 7. The server receives the feedback, records it in the system database, and retrains the generative model if necessary.

[1353] This system allows users to receive fast, accurate support 24 hours a day.

[1354] The processing flow will be explained below.

[1355] Step 1:

[1356] The server starts up and loads the necessary data and AI models.

[1357] The server establishes a database connection and loads user information, support history, and FAQs into memory.

[1358] The server loads the generative AI model and updates it if necessary from an external source.

[1359] Step 2:

[1360] The user requests support using a device (smartphone or PC).

[1361] The user opens a dedicated application on the device and fills out an inquiry form.

[1362] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[1363] Step 3:

[1364] The device sends a request to the server.

[1365] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[1366] Step 4:

[1367] The server receives the request and retrieves the user's support history and device information.

[1368] The server searches the database for the corresponding user ID and retrieves the necessary information.

[1369] Step 5:

[1370] The server inputs a problem summary and historical data into the AI ​​model and generates a solution.

[1371] The server uses the AI ​​model to generate a solution based on the user's current problem and past patterns.

[1372] Step 6:

[1373] The server converts the generated solution into a format that is easy for the user to understand and sends it to the terminal.

[1374] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[1375] Step 7:

[1376] The device displays the received information to the user.

[1377] The device displays instructions on the screen and the user attempts to solve the problem.

[1378] Step 8:

[1379] The user follows the steps to resolve the issue and provides feedback on success or failure.

[1380] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[1381] Step 9:

[1382] The server receives the feedback and records it in a database.

[1383] The server stores the feedback information in a database and updates the AI ​​model as needed.

[1384] Example 1

[1385] 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."

[1386] In recent years, with the advancement of electronic devices and information and communication technology, users are increasingly encountering problems with complex devices and software. To quickly address these issues, 24-hour support is necessary, but current support systems are insufficient and fail to satisfy users. Furthermore, manual support by support staff can be time-consuming and costly, resulting in prolonged resolution times. Given this background, there is a demand for automated support systems that can quickly and efficiently resolve user problems.

[1387] 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.

[1388] In this invention, the server includes means for receiving a support request from a user, means for retrieving the user's past support history and device information from a database based on the received support request, means for utilizing a generative AI model using the retrieved information to send prompt text and generate a solution to the problem, means for converting the generated solution into a format that is easy for the user to understand (text, image, etc.) and sending it to the user terminal, and means for receiving and recording user feedback on the provided solution, thereby enabling users to receive fast and highly accurate support 24 hours a day.

[1389] A "server" is a central computer system that receives requests from users and processes data.

[1390] "Support Request" means a request submitted by a User to resolve a Device or Software issue.

[1391] A "database" is an information system for systematically storing and managing user information, support history, device information, etc.

[1392] A "generative AI model" is an artificial intelligence model that automatically generates solutions to problems based on input information.

[1393] A "prompt sentence" is text data input into a generative AI model that contains instructions and conditions for solving a problem.

[1394] A "solution" is a procedure or method for solving a user's problem obtained using a generative AI model.

[1395] A "user terminal" is a computer device (such as a smartphone or PC) used by a user, which receives and displays information from a server.

[1396] "Feedback" refers to evaluation information that a user sends back to the server regarding the effectiveness and results of the solution provided.

[1397] Based on these definitions, the technical scope of the invention is clearly defined.

[1398] This invention is a system that allows users to receive support 24 hours a day. Specifically, it is implemented using the following hardware and software.

[1399] Hardware and Software Configuration

[1400] 1. Server: A high-performance computing system that receives requests, connects to a database, and runs generative AI models. Examples include Linux-based servers and cloud services (AWS, Google Cloud, etc.).

[1401] 2. Database: Stores user information, support history, FAQs, etc. Uses a relational database such as MySQL or PostgreSQL.

[1402] 3. Generative AI models: Generate solutions to problems using deep learning models such as GPT-3 and BERT.

[1403] 4. User device: A computing device that users use on a daily basis, such as a smartphone or PC.

[1404] Specific functions of the system

[1405] 1. The server receives a support request from the user, often in the form of an HTTP POST request.

[1406] 2. The server connects to the database and retrieves the user's past support history and device information.

[1407] 3. The server sends a prompt to the generative AI model to generate a solution to the problem. An example of a prompt is, "A user is reporting an issue where they cannot connect to Wi-Fi. Based on their past support history and device information, what is the best course of action to resolve this user's issue?"

[1408] 4. The server converts the generated solution into text or image format and sends it to the user's device.

[1409] 5. The device receives the solution from the server and displays it on the screen.

[1410] 6. The user follows the provided steps to resolve the issue.

[1411] 7. The user provides feedback on whether the solution worked or not.

[1412] 8. The server receives the feedback and records it in a database. It may also retrain the generative AI model based on the feedback information.

[1413] Usage example

[1414] For example, a user may have problems connecting to Wi-Fi on their smartphone. The user opens a dedicated application and submits a screenshot of the problem, stating "Wi-Fi cannot be connected." The server receives the request and retrieves past support history and device information from the database. It then sends prompt text to the generative AI model to generate a solution for Wi-Fi settings. The server converts the generated solution into text and image format and sends it to the user's device. The user then checks the solution on their device, follows the steps to solve the problem, and submits feedback.

[1415] This system allows users to receive fast, highly accurate support 24 hours a day.

[1416] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1417] Step 1:

[1418] The server receives a support request from the user.

[1419] Specifically, the server receives information (e.g., a summary of the problem, an error message, and a screenshot) as an HTTP POST request. The input is the query sent by the user from the device. The server parses the received data and converts it into an internal format.

[1420] Step 2:

[1421] The server connects to the database and retrieves the user's past support history and device information.

[1422] The server uses the user ID to send an SQL query to the database to retrieve the corresponding user information. The input is the user ID and the requested information fields. The output is the past support history and device information.

[1423] Step 3:

[1424] The server sends prompts to the generative AI model to generate solutions to the problem.

[1425] The server creates a prompt based on the acquired information and sends it to the generative AI model. The inputs include the user's problem information, past support data, and device information. The generative AI model then runs a deep learning algorithm based on this information to generate a solution to the problem. The output is a text version of the solution.

[1426] Step 4:

[1427] The server converts the generated solution into a format that is easy for the user to understand and sends it to the user's terminal.

[1428] The server formats the generated solution into text or image format and sends it as an HTTP response. The input is the solution received from the generative AI model. The output is the solution data received by the user device.

[1429] Step 5:

[1430] The device receives the solution from the server and displays it on the screen.

[1431] The terminal parses the HTTP response and displays the solution to the user. As input, it has the solution data sent by the server. As output, it has a representation of the solution that the user can view.

[1432] Step 6:

[1433] The user follows the steps provided to resolve the issue.

[1434] The input is the displayed solution steps. The output is the problem being solved. The specific action is for the user to follow the instructions on the device.

[1435] Step 7:

[1436] The user provides feedback on whether the solution worked.

[1437] The user uses a feedback form in the application to enter and submit a success or failure rating. The input is the feedback content. The output is the rating data sent to the server.

[1438] Step 8:

[1439] The server receives the feedback and records it in a database.

[1440] The server analyzes the received feedback and records it in a database. The input is the feedback data from the user. The output is the feedback information stored in the database. If necessary, it retrains the generative AI model.

[1441] Through these processing steps, users can receive fast and accurate support 24 hours a day.

[1442] (Application example 1)

[1443] 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."

[1444] The goal is to provide a system that allows users of autonomous vehicles to receive prompt and highly accurate support 24 hours a day. In particular, there is a need to establish a means of providing users with appropriate solutions in real time for problems and issues specific to autonomous vehicles.

[1445] 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.

[1446] In this invention, the server includes means for receiving a support request from a user, means for acquiring the user's past support history and device information based on the support request, means for generating a solution to the problem using a generative AI model with the acquired information, means for providing the generated solution to the user, means for receiving user feedback on the provided solution, and display means including images and audio guides for displaying the generated solution, thereby enabling users of autonomous vehicles to receive prompt and appropriate support at any time of day.

[1447] "Means for receiving support requests from users" refers to an interface that allows users to input their problems or questions and send them to the system.

[1448] "Means for acquiring a user's past support history and device information" is a function for acquiring from a database the history of support the user has received in the past and information on the device the user is currently using.

[1449] "Means for generating solutions using generative AI models" refers to the process of using artificial intelligence models based on acquired information to derive appropriate solutions to users' problems.

[1450] "Means to provide to the user" refers to an interface that provides the generated solution in a format that is easy for the user to understand.

[1451] "Means for receiving user feedback" refers to a function that allows users to send back to the system their evaluations and results of the solutions provided.

[1452] "Display means including visual and audio guides" refers to devices or interfaces for visually and audibly presenting the generated solution to the user.

[1453] "Means for retraining the generative AI model" refers to the process of retraining the generative AI model based on user feedback to improve the accuracy of its solutions.

[1454] The present invention provides a system that enables users of autonomous vehicles to receive prompt and highly accurate support 24 hours a day. A specific embodiment of this system is described below.

[1455] System Configuration

[1456] 1. Server:

[1457] The server is connected to a database that stores data such as user information, support history, and FAQs.

[1458] The server is implemented in a programming language such as Python.

[1459] The server has the ability to generate solutions from support requests using generative AI models (e.g., GPT-4).

[1460] 2. On the user's device:

[1461] User devices include smartphones, tablets, and PCs.

[1462] A dedicated support application is installed on the device.

[1463] 3. Get device information:

[1464] The server retrieves past support history and device information from a database based on the user's support request.

[1465] Data processing and calculation

[1466] Information Collection:

[1467] When a user submits a support request, the device sends the input information (such as a summary of the problem, error messages, screenshots, etc.) to the server as an HTTP request.

[1468] The server retrieves user information, past support history, and device information from the database.

[1469] Generate solutions:

[1470] The server provides the generative AI model with information about the current problem and past data as input.

[1471] The generative AI model uses this information to generate the most appropriate solution to the problem.

[1472] Solution provided:

[1473] The server converts the generated solution into a user-friendly format (text, images, audio guide, etc.) and sends it to the terminal as an HTTP response.

[1474] The terminal displays the received information to the user.

[1475] Receive feedback and retrain:

[1476] The user provides feedback on whether they succeeded or failed in resolving the issue.

[1477] The server records this feedback in a database and retrains the generative AI model as needed.

[1478] Specific examples

[1479] For example, consider a case where a user reports an issue with the self-parking feature of their self-driving vehicle not working.

[1480] 1. The user enters the problem "Automatic parking function is not working" into the smartphone app and submits a request along with screenshots and error messages.

[1481] 2. The server receives this request and retrieves the user's past support history and vehicle information from the database.

[1482] 3. The server inputs the acquired information into a generative AI model to generate specific troubleshooting steps.

[1483] 4. The server compiles the generated instructions into text and audio guides and sends them to the user's device.

[1484] 5. The user follows the instructions received to check the vehicle's settings and attempt to resolve the issue.

[1485] 6. The user selects success or failure within the app and submits feedback.

[1486] 7. The server receives the feedback, records it in a database, and retrains the generative AI model if necessary.

[1487] Prompt Sentence Examples

[1488] For example, the prompt text might look like this:

[1489] Please enter a description of the problem: Autopark feature not working

[1490] Did this solve your problem? (yes / no): no

[1491] This will ensure that users of autonomous vehicles can receive prompt and appropriate support at any time.

[1492] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1493] Step 1:

[1494] A user submits a support request from their device. Input information includes a summary of the problem, an error message, a screenshot, etc. This data is sent from the device to the server as an HTTP request. The device converts this request into a packet format and sends it to the server.

[1495] Step 2:

[1496] The server receives a support request. It searches the database based on the user ID in the request to retrieve the user's past support history and device information. At this stage, the server establishes a database connection and loads the necessary information into a cache.

[1497] Step 3:

[1498] The server uses the information it acquires to provide input data to the generative AI model. Specifically, the user's current problem, past support history, device information, etc. are provided as input to the generative AI model (e.g., GPT-4). This is where data processing and normalization are performed.

[1499] Step 4:

[1500] The generative AI model generates a solution to the problem. The server generates the solution in text format as the output of the AI ​​model, as well as images and audio guidance if necessary. Data calculations are performed here to obtain a solution to the user's specific problem.

[1501] Step 5:

[1502] The server provides the generated solution to the user's device, and then sends the generated solution to the device as an HTTP response, which includes data converted into formats such as text, images, and audio.

[1503] Step 6:

[1504] The device displays the received information to the user. The device displays the transmitted text, images, and audio instructions on the screen, allowing the user to implement solutions. This allows the user to follow specific steps to solve the problem.

[1505] Step 7:

[1506] The user attempts to solve the problem and sends the results as feedback from the device to the server. The user selects whether the solution was successful or not and enters feedback information. The device then sends this as an HTTP request to the server.

[1507] Step 8:

[1508] The server receives the feedback and records it in a database. The server analyzes the received feedback and retrains the generative AI model as needed. This feedback process allows the system to constantly improve and provide more accurate solutions.

[1509] 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.

[1510] This invention combines a system that allows users to receive support 24 hours a day with an emotion engine that recognizes user emotions. Specifically, the system is configured to include a means for receiving support requests from users, a means for acquiring the user's past support history and device information, a means for generating solutions to problems using a generative model, a means for providing the generated solutions to users, a means for receiving user feedback, and an emotion engine.

[1511] Explanation of program processing

[1512] 1. The server starts first and loads the necessary data, AI models, and emotion engines.

[1513] The server establishes a database connection and loads user information, support history, and FAQs into memory.

[1514] The server loads the generative AI model and emotion engine, updating it if necessary from external sources.

[1515] 2. The user requests support using their device (smartphone or PC).

[1516] The user opens a dedicated application on the device and fills out an inquiry form.

[1517] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[1518] 3. The device sends the request to the server.

[1519] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[1520] 4. The server receives the request and retrieves the user's support history and device information.

[1521] The server searches the database for the corresponding user ID and retrieves the necessary information.

[1522] 5. The server inputs the problem summary and historical data into the AI ​​model and generates a solution.

[1523] The server uses the AI ​​model to generate a solution based on the user's current problem and past patterns.

[1524] 6. The server optimizes the generated solution using the emotion engine.

[1525] The server analyzes the user's current emotional state and optimizes the solution to suit that emotion.

[1526] 7. The server converts the optimized solution into a user-friendly format and sends it to the device.

[1527] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[1528] 8. The device displays the information it has received to the user.

[1529] The device displays instructions on the screen and the user attempts to solve the problem.

[1530] 9. The user follows the steps to resolve the issue and provides feedback on success or failure.

[1531] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[1532] 10. The server receives the feedback and records it in a database.

[1533] The server stores the feedback information in a database, updates the AI ​​model as needed, and uses an emotion engine to analyze emotions based on the feedback content.

[1534] Specific examples

[1535] For example, say a user is having trouble setting up Wi-Fi on their smartphone.

[1536] 1. The user enters the problem "I can't connect to Wi-Fi" on their device, attaches a screenshot, and submits a request.

[1537] 2. The server receives the request and retrieves the support history and the user's device information.

[1538] 3. The server uses the acquired information to use AI models to generate solutions to common Wi-Fi configuration issues and user-specific troubleshooting steps.

[1539] 4. The server uses an emotion engine to optimize the generated instructions to match the user's emotions. For example, if the user is "confused," the server will explain the instructions in a gentle tone.

[1540] 5. The server sends the optimized instructions to the user's device.

[1541] 6. The device displays the received instructions on the screen, and the user attempts to set up Wi-Fi by following the instructions.

[1542] 7. The user sends feedback from the device to the server, indicating whether the setup was successful or not.

[1543] 8. The server receives the feedback, records it in the system database, retrains the generative model if necessary, and analyzes the feedback using the emotion engine to provide future support.

[1544] The system allows users to receive fast, accurate and emotionally sensitive support 24 hours a day.

[1545] The processing flow will be explained below.

[1546] Step 1:

[1547] The server starts up and loads the necessary data, AI models, and emotion engines.

[1548] The server establishes a database connection and loads user information, support history, and FAQs into memory.

[1549] The server loads the generative AI model and emotion engine, updating it if necessary from external sources.

[1550] Step 2:

[1551] Users can request support using their own devices (smartphones or PCs).

[1552] The user opens a dedicated application on the device and fills out an inquiry form.

[1553] The user submits a summary of the problem, error messages, screenshots, etc. via the application.

[1554] Step 3:

[1555] The device sends a request to the server.

[1556] The terminal converts the input information into a packet format and sends an HTTP request to the server.

[1557] Step 4:

[1558] The server receives the request and retrieves the user's support history and device information.

[1559] The server searches the database for the corresponding user ID and retrieves the necessary information.

[1560] Step 5:

[1561] The server uses an emotion engine to analyze the user's emotional state.

[1562] The server uses an emotion engine to assess the user's current emotional state (e.g., confusion, anger, relief, etc.) based on the request data and past interactions.

[1563] Step 6:

[1564] The server inputs a problem summary, past data, and analyzed emotional information into the AI ​​model, and generates a solution.

[1565] The server uses an AI model to generate a solution based on the user's current problem, past patterns, and emotional state.

[1566] Step 7:

[1567] The server optimizes the generated solution using an emotion engine.

[1568] Based on the analysis results of the emotion engine, the server optimizes the solution with a tone and expression that corresponds to the user's emotional state.

[1569] Step 8:

[1570] The server converts the optimized solution into a user-friendly format and sends it to the device.

[1571] The server summarizes the solution procedure in text or image format and sends it to the terminal as an HTTP response.

[1572] Step 9:

[1573] The device displays the received information to the user.

[1574] The device displays instructions on the screen and the user attempts to solve the problem.

[1575] Step 10:

[1576] The user follows the steps to resolve the issue and provides feedback on success or failure.

[1577] The user selects success or failure of the solution within the application and sends feedback to the server via the terminal.

[1578] Step 11:

[1579] The server receives the feedback and records it in a database.

[1580] The server stores the feedback information in a database and updates the AI ​​model as needed. It also analyzes the feedback using an emotion engine and uses it to provide future support.

[1581] Example 2

[1582] 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."

[1583] In traditional support systems, when users request support, appropriate solutions are often not provided quickly, resulting in a poor user experience. Furthermore, solutions provided without considering the user's feelings can reduce user satisfaction. Furthermore, feedback is not utilized in the system, which makes it difficult to improve support quality.

[1584] 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 means for receiving a support request from a user, a means for acquiring the user's past support history and electronic device information, a means for generating a solution to a problem using a generation algorithm based on the acquired information, a means for optimizing the generated solution using a sentiment analysis engine, a means for providing the optimized solution to the user, and a means for receiving user feedback on the provided solution. This allows users to receive fast, highly accurate support 24 hours a day, and provides solutions that take the user's emotions into consideration. Furthermore, utilizing feedback in the system enables continuous improvement of support quality.

[1585] "Support Request" means a request submitted by a User to the System for support.

[1586] "Past support history" refers to records and information regarding the support a user has previously received.

[1587] "Electronic device information" refers to detailed technical information about the devices a user uses.

[1588] A "generative algorithm" is a computational method or model that generates solutions to problems based on collected data.

[1589] An "emotion analysis engine" is a software component that analyzes a user's emotional state and optimizes solutions based on the results.

[1590] "Delivery means" refers to the method or technique used to present the generated solution to the user.

[1591] "Feedback" refers to the ratings and comments users make on the solutions provided.

[1592] "Retraining" is the process of updating the generative algorithm with new data and feedback collected to generate more accurate solutions.

[1593] This invention combines a system that allows users to receive support 24 hours a day with an emotion analysis engine that recognizes the emotions of users. A specific embodiment of this system will be described below.

[1594] The server starts up and loads the necessary data, generative AI model, and sentiment analysis engine. The server connects to a database (e.g., MySQL or PostgreSQL) and loads user information, support history, and FAQ data into RAM. This database connection allows the server to retrieve necessary data such as the user's past support history and electronic device information. The server also loads the generative AI model (e.g., GPT-4) and sentiment analysis engine (e.g., Empathizer) from disk and updates them from an external source (e.g., a cloud server) as needed.

[1595] A user requests support using a device such as a smartphone or PC. The user opens a dedicated application (e.g., a customer support app), enters a summary of the problem in the inquiry form, and uploads any error messages and screenshots. Once the input is complete, the user clicks the "Submit" button. The device converts the entered information into a packet format (e.g., JSON format), generates an HTTP request, and sends it to the server's API endpoint.

[1596] The server receives the request and retrieves the user's support history and device information. It then executes a database query to search for the user ID and uses the retrieved information to generate a prompt for the generative AI model. For example, the prompt can include a problem summary such as "I can't connect to Wi-Fi" and past support history.

[1597] The generative AI model generates a solution based on the prompt. The generated solution is then optimized by a sentiment analysis engine. The sentiment analysis engine analyzes the user's emotional state based on their past conversation patterns and real-time data. For example, if the user is confused, the engine reframes the solution in a gentler, more polite tone. Specifically, it adds a message such as "Don't worry, let's solve this together" to the generated solution.

[1598] The server converts the optimized solution into a user-friendly format and sends it to the device. The server formats the solution as a text document or image guidelines and sends it to the device as an HTTP response. The device analyzes the received information and displays it to the user. The user then follows the displayed steps to try to solve the problem.

[1599] Regardless of whether the user has solved the problem, feedback is provided within the application. The user selects whether the solution was successful or not, enters any additional comments, and clicks the "Submit" button. The feedback is sent from the device to the server, which receives it, records it in a database, and retrains the generative AI model as needed. The sentiment analysis engine also performs sentiment analysis based on the feedback content, which is used to improve future support.

[1600] This system allows users to receive fast, accurate support 24 hours a day, providing solutions that are considerate of their emotions, and by incorporating feedback into the system, it is possible to continuously improve the quality of support.

[1601] Example prompt:

[1602] "I can't connect to Wi-Fi. The error message is 'Unable to connect to network'. I've had a similar issue twice in my history, and a reboot fixed it once."

[1603] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1604] Step 1:

[1605] The server starts up and loads the necessary data, generative AI models, and sentiment analysis engines.

[1606] After the operating system starts, the server establishes a network connection. Next, it connects to a database (e.g., MySQL or PostgreSQL) and loads user information, support history, and FAQ data into RAM. It then loads a generative AI model (e.g., GPT-4) and a sentiment analysis engine (e.g., Empathizer) from disk. This prepares the server with the necessary data, such as the user's support history and electronic device information.

[1607] Input: Database access information, storage paths for generative AI models and sentiment analysis engines

[1608] Output: User information, support history, FAQ data, generative AI models and sentiment analysis engines loaded into server memory

[1609] Step 2:

[1610] Users can request support using their own devices (smartphones or PCs).

[1611] The user opens the dedicated application, enters detailed information (problem summary, error message, screenshot) into the inquiry form, and clicks the "Submit" button.

[1612] Input: User-entered problem summary, error message, and screenshot

[1613] Output: The input information that is sent

[1614] Step 3:

[1615] The device sends a request to the server.

[1616] The terminal converts the input information into a packet format, generates an HTTP request, and sends it to the server's API endpoint.

[1617] Input: Support request information entered by the user

[1618] Output: HTTP request sent to the server

[1619] Step 4:

[1620] The server receives the request and obtains the user's past support history and electronic device information.

[1621] The server analyzes the received HTTP request, extracts the user ID and problem summary, and then executes a database query to search for information based on the corresponding user ID, retrieving past support history and device information.

[1622] Input: HTTP request, user information

[1623] Output: Retrieved past support history and electronic device information

[1624] Step 5:

[1625] The server inputs a problem summary and past data into the generated AI model and generates a solution.

[1626] The server inputs a summary of the problem and past data as a prompt to the generative AI model, which then generates a solution based on this.

[1627] Input: Problem summary, past data

[1628] Output: A solution from the generative AI model

[1629] Step 6:

[1630] The server optimizes the generated solution using a sentiment analysis engine.

[1631] The server uses an emotion analysis engine to analyze the user's emotional state and optimizes the generated solution according to the user's emotions, for example, reframing a confused user in a gentler tone.

[1632] Input: Solution from a generative AI model, user emotional state

[1633] Output: A solution optimized by the sentiment analysis engine

[1634] Step 7:

[1635] The server converts the optimized solution into a user-friendly format and sends it to the terminal.

[1636] The server formats the solution as a text document or image guidelines and sends it to the device as an HTTP response.

[1637] Input: Optimized solution

[1638] Output: The solution sent as an HTTP response

[1639] Step 8:

[1640] The terminal displays the received information to the user.

[1641] The terminal analyzes the received HTTP response, extracts the solution text and images, and displays them to the user.

[1642] Input: HTTP response

[1643] Output: The solution that is displayed to the user

[1644] Step 9:

[1645] The user follows the steps to resolve the issue and provides feedback on success or failure.

[1646] The user attempts to solve the problem within the application, provides feedback on success or failure, and clicks the "Submit" button.

[1647] Input: User feedback information

[1648] Output: Feedback information to be sent

[1649] Step 10:

[1650] The server receives the feedback and records it in a database.

[1651] The server stores the received feedback information in a database and, if necessary, retrains the generative AI model. It also performs sentiment analysis and uses the information to improve future support.

[1652] Input: Feedback information

[1653] Output: Feedback information recorded in a database, updated generative AI model

[1654] (Application example 2)

[1655] 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."

[1656] In conventional support systems, a uniform response is given without considering the user's emotional state, which can lead to a decrease in user satisfaction. In addition, in today's world where 24-hour support is required, providing support that is quick and considerate of the user's emotions is a challenge.

[1657] 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 means for receiving a support request from a user, means for acquiring the user's past support history and device information, means for generating a solution to the problem using a generative model with the acquired information, means for recognizing the user's emotional state and optimizing the solution based on the emotion, means for providing the generated solution to the user, and means for receiving the user's feedback on the provided solution. This enables user-friendly support that is available 24 hours a day and takes emotions into consideration.

[1658] "User" refers to a person who uses the System and provides assistance requests or feedback.

[1659] "Assistance Request" means a request made by a User seeking service or support.

[1660] "Support history" refers to a record of support a user has received in the past, and is information stored in a database.

[1661] "Device information" refers to detailed information about the device used by the user, including, for example, the model name, settings, and status.

[1662] A "generative model" refers to an algorithmic model that uses AI technology to generate solutions to problems.

[1663] "Problem Solution" refers to the specific solution or procedure for a user's request for assistance.

[1664] "Emotional state" refers to the psychological state of the user when they make a support request, and is information obtained through analysis.

[1665] "Optimization" refers to the process of adjusting and refining the generated problem solution based on the user's emotional state.

[1666] "Feedback" refers to users' reactions and evaluations of the services and solutions provided.

[1667] This invention is a system that allows users to receive support 24 hours a day for problems or questions about food delivery. This system is combined with an emotion engine that recognizes the user's emotions to realize responses that take the user's emotions into consideration. An embodiment of this system is described in detail below.

[1668] System Overview

[1669] The system consists of the following main components:

[1670] 1. A means of receiving assistance requests from users

[1671] 2. Means of obtaining support history and device information

[1672] 3. A method for generating solutions using generative models

[1673] 4. Using an emotion engine to optimize emotion-based solutions

[1674] 5. A means of providing optimized solutions to users

[1675] 6. How to receive user feedback

[1676] Programs and hardware used

[1677] The server implements the system using the following hardware and software.

[1678] Hardware: A server with a powerful processor, sufficient memory, and a fast network interface.

[1679] software:

[1680] Database: A database that stores user information, assistance history, and device information.

[1681] Emotion Engine: Software that uses Natural Language Processing (NLP) technology to analyze user emotions.

[1682] Generative model: An AI model that uses machine learning algorithms to generate solutions to problems (e.g., GPT-3 and BERT models).

[1683] Application Server: Software that manages user requests and interacts with the generative model and emotion engine.

[1684] Data processing and calculation

[1685] 1. Receiving your request for assistance:

[1686] A user sends a request for assistance to the server using a smartphone or web app, including a detailed description of the problem and screenshots, if necessary.

[1687] 2. Obtaining User Information:

[1688] The server connects to the database and retrieves the user's past support history and device information based on the received user ID.

[1689] 3. Emotion analysis:

[1690] The emotion engine analyzes the text data of the request for assistance to detect the user's emotional state, identifying emotions such as "confusion," "anger," and "sadness."

[1691] 4. Generate solutions to problems:

[1692] Based on the acquired user information and the content of the assistance request, the generative model generates an optimal solution to the problem, using the prompt sentence as input.

[1693] 5. Emotion-based optimization:

[1694] The emotion engine optimizes the tone and style of the generated solutions based on the user's emotional state. For example, if the user is confused, the explanation will be delivered in a gentle tone.

[1695] 6. Offerings to Users:

[1696] The optimized solution is sent to the user's device, where the user can review the steps and attempt to resolve the issue.

[1697] 7. Receiving and Processing Feedback:

[1698] Users can provide feedback on the solutions provided, which is received by the server and stored in a database. The feedback is used to retrain the generative model to improve its accuracy in solving future problems.

[1699] Specific examples

[1700] For example, if a user sends a request for assistance stating "my order hasn't arrived," the system operates as follows:

[1701] 1. Receiving your request for assistance:

[1702] A user submits a request for assistance, detailing that their order has not arrived and attaching screenshots.

[1703] 2. Obtaining User Information:

[1704] The server retrieves the user's past order history and device information from the database.

[1705] 3. Emotion analysis:

[1706] The emotion engine analyzes the user's "confused" emotions from requests for assistance.

[1707] 4. Generate solutions to problems:

[1708] Based on the information obtained, the generative model generates a solution such as "Restart the app to check the order status, then check your order history."

[1709] 5. Emotion-based optimization:

[1710] The emotion engine optimizes the solution to a gentle tone: "Please wait a moment. Please restart the app and check your order history again."

[1711] 6. Offerings to Users:

[1712] The optimized solution is sent to the user's device, where the user can review and try the steps.

[1713] 7. Receiving and Processing Feedback:

[1714] When a user sends feedback that the problem has been resolved, the server stores this in a database and uses it for future support.

[1715] Example prompt sentence:

[1716] text

[1717] For users who are confused about not receiving their order, generate a support message in a human tone, like this:

[1718] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1719] Step 1:

[1720] The device receives a request for assistance from the user. The user provides a detailed description of the problem and any necessary screenshots using a smartphone app or web app. The device converts this input information into a packet format and sends it to the server as an HTTP request. Specifically, the device attaches the problem "My order hasn't arrived" and screenshots.

[1721] Step 2:

[1722] The server receives the assistance request and retrieves the user's past assistance history and device information from the database. Specifically, it accesses the database, searches for related data based on the user ID, and retrieves the past order history and device information. This allows the assistance history and device information to be imported into the server as input data.

[1723] Step 3:

[1724] The server uses an emotion engine to analyze the user's emotional state from the request for assistance. The input data is the text of the request for assistance, and NLP technology is used to recognize emotional states such as "confusion." The analyzed emotional state is output as "confusion."

[1725] Step 4:

[1726] The server uses a generative model to generate a solution to the problem based on the information it obtains. The input data is the content of the assistance request, past assistance history, and device information, and the AI ​​model generates a solution such as "Restart the app to check the order status, then check your order history."

[1727] Step 5:

[1728] The server uses an emotion engine to optimize the generated solution according to the user's emotional state. The input data is "Please restart the app to check the order status, then check your order history" and the emotional state is "confused," and the emotion engine outputs a gentle solution saying, "Please wait a moment. Please restart the app and check your order history again."

[1729] Step 6:

[1730] The server sends the optimized solution to the user's device. The input data is the optimized solution, which is sent to the device as an HTTP response. The device displays this solution to the user, who can then check the solution and attempt to solve the problem.

[1731] Step 7:

[1732] The user acts on the provided solution and sends the result as feedback from the device to the server. The input data is the feedback, and the device sends feedback information such as "the problem has been solved" to the server as an HTTP request.

[1733] Step 8:

[1734] The server receives the feedback and records it in a database. The input data is the feedback information, which is then stored in the database. Furthermore, the generative model is retrained based on the feedback, improving its accuracy for subsequent assistance requests.

[1735] 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.

[1736] 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.

[1737] 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.

[1738] 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.

[1739] 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.

[1740] 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.

[1741] 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).

[1742] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1743] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1744] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1745] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1746] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1747] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1748] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1749] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1750] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1751] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1752] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1753] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1754] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1755] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1756] The following is further disclosed regarding the above embodiment.

[1757] (Claim 1)

[1758] a means of receiving support requests from users;

[1759] means for acquiring the user's past support history and device information based on the support request;

[1760] means for generating a solution to the problem using a generative model based on the acquired information;

[1761] means for providing the generated solution to a user;

[1762] means for receiving user feedback on the provided solution;

[1763] A system including:

[1764] (Claim 2)

[1765] The system of claim 1 , further comprising: means for displaying the generated solution to a user.

[1766] (Claim 3)

[1767] The system of claim 1 , further comprising: means for retraining a generative model based on the user feedback.

[1768] "Example 1"

[1769] (Claim 1)

[1770] a means by which the server receives support requests from users;

[1771] means for retrieving the user's past support history and device information from a database based on the received support request;

[1772] a means for using the acquired information to utilize a generative AI model to send prompt sentences to generate solutions to the problem;

[1773] A means for converting the generated solution into a format that is easy for the user to understand (such as text or images) and transmitting it to a user terminal;

[1774] means for receiving and recording user feedback on the provided solution;

[1775] A system including:

[1776] (Claim 2)

[1777] 10. The system of claim 1, further comprising: means for displaying the generated solution on a user terminal.

[1778] (Claim 3)

[1779] 10. The system of claim 1, further comprising: means for retraining the generative AI model based on the user feedback.

[1780] "Application Example 1"

[1781] (Claim 1)

[1782] a means of receiving support requests from users;

[1783] means for acquiring the user's past support history and device information based on the support request;

[1784] A means for generating a solution to the problem using a generative AI model based on the acquired information;

[1785] means for providing the generated solution to a user;

[1786] means for receiving user feedback on the provided solution;

[1787] display means including visual and audio prompts for displaying the generated solution;

[1788] A system including:

[1789] (Claim 2)

[1790] 10. The system of claim 1, further comprising visual and audio prompting means for displaying the generated solution to the user.

[1791] (Claim 3)

[1792] 10. The system of claim 1, further comprising: means for retraining the generative AI model based on user feedback.

[1793] "Example 2: Combining Emotion Engines"

[1794] (Claim 1)

[1795] a means of receiving support requests from users;

[1796] means for acquiring the user's past support history and electronic device information based on the support request;

[1797] means for generating a solution to the problem using a generation algorithm using the acquired information;

[1798] means for optimizing the generated solutions using a sentiment analysis engine;

[1799] means for providing the optimized solution to a user;

[1800] means for receiving user feedback on the provided solution;

[1801] A system including:

[1802] (Claim 2)

[1803] The system of claim 1 , further comprising: means for displaying the generated solution to a user.

[1804] (Claim 3)

[1805] The system of claim 1 , further comprising: means for retraining a generation algorithm based on the user feedback.

[1806] "Application example 2 when combining emotion engines"

[1807] (Claim 1)

[1808] a means for receiving a request for assistance from a user;

[1809] means for acquiring the user's past support history and device information based on the support request;

[1810] means for generating a solution to the problem using a generative model based on the acquired information;

[1811] A means of recognizing the user's emotional state and optimizing solutions based on that emotion;

[1812] means for providing the generated solution to a user;

[1813] means for receiving user feedback on the provided solution;

[1814] A system including:

[1815] (Claim 2)

[1816] The system of claim 1 , further comprising: means for displaying the generated solution to a user.

[1817] (Claim 3)

[1818] The system of claim 1 , further comprising: means for retraining a generative model based on the user feedback. [Explanation of symbols]

[1819] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of receiving support requests from users; means for acquiring the user's past support history and device information based on the support request; means for generating a solution to the problem using a generative model based on the acquired information; means for providing the generated solution to a user; means for receiving user feedback on the provided solution; A system including:

2. The system of claim 1 , further comprising: means for displaying the generated solution to a user.

3. The system of claim 1 , further comprising: means for retraining a generative model based on the user feedback.

Images