system

Abstract

Provide a system. A method for collecting feedback from users; A means of analyzing the collected feedback and extracting problems and requests, means for generating suggestions based on the extracted information; means for automatically generating responses to user queries; A system including:

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] Conventional customer support and feedback systems have had problems with their ability to respond quickly and accurately, resulting in low user satisfaction. They also lack the ability to effectively collect and analyze user feedback and inquiries, and to quickly provide appropriate proposals based on that information. Therefore, there was a need for a system that could accurately grasp user needs and respond quickly. [Means for solving the problem]

[0005] The present invention provides a system for collecting and analyzing user feedback and generating appropriate proposals. This system includes a means for collecting user feedback, a means for analyzing the collected feedback and extracting problems and requests, a means for generating proposals based on the extracted information, and a means for automatically generating responses to user inquiries.

[0006] Specifically, the system stores collected feedback in a database and saves the analyzed results as structured data. It then reviews the generated suggestions, selects the most appropriate one, and notifies the user. It also analyzes the inquiry, generates a response based on past data and FAQs, and sends it to the user. This allows the entire process, from collecting feedback to analyzing it, generating suggestions, and providing customer support, to be carried out quickly and accurately, improving user satisfaction.

[0007] "User" refers to any individual or legal entity that uses the System.

[0008] "Feedback" refers to information such as opinions, requests, problems, etc. that users provide to the system.

[0009] "Means of collection" refers to the function of obtaining feedback from users and incorporating it into the system.

[0010] "Means for analysis" refers to the function of analyzing collected feedback and extracting useful information.

[0011] "Means for generating proposals" refers to the function of creating improvement measures or new proposals based on the analyzed information.

[0012] "Means for generating a response" refers to a function that automatically creates an appropriate response to a user's inquiry.

[0013] "Database" refers to a structured data repository for storing information such as feedback, analysis results, and generated recommendations within the system.

[0014] "Structured data" refers to data that has been collected, organized, and stored in a certain format.

[0015] "Means of review" refers to the function of evaluating the generated proposals and selecting the most suitable ones.

[0016] "Means for notifying" refers to a function that notifies the user of the selected suggestion or response.

[0017] "Inquiry" refers to a question or problem report that a user makes to the system.

[0018] "FAQ" refers to a collection of data that compiles frequently asked questions and their answers. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention relates to a system that effectively collects and analyzes user feedback, generates proposals based on the collected feedback, and provides prompt customer support. This system has the following processing flow:

[0041] System configuration and operation

[0042] 1. Gathering Feedback:

[0043] Users enter their issues and feedback through the chatbot.

[0044] Example: User types "My app crashes frequently."

[0045] The device receives user feedback in real time and transmits the data to the server.

[0046] Example: The device sends feedback to the server saying "frequent crashes."

[0047] 2. Save your feedback:

[0048] The server stores the received feedback in a dedicated feedback database.

[0049] Example: Add an entry to the feedback database saying "frequent crashes."

[0050] 3. Feedback analysis:

[0051] The server periodically retrieves new feedback data from the database.

[0052] Example: Schedule a job to retrieve new feedback data every hour.

[0053] The generative AI model uses text analysis algorithms to extract issues and requests from within the feedback.

[0054] Example: A generative AI model extracts keywords such as "frequent crashes" and "after update."

[0055] The server stores the analysis results as structured data in an error log or a user suggestion list.

[0056] Example: Record the extracted keyword "frequent crashes" in the error log.

[0057] 4. Proposal generation:

[0058] The server uses the saved analysis results to input data based on the user's needs into the generative AI model.

[0059] Example: The analysis results "frequent crashes" and "after update" are input into the generative AI model.

[0060] The generative AI model generates suggestions using analysis results, past data, or inference algorithms.

[0061] For example, generating suggestions such as "Optimize for performance" and "Steps to check logs."

[0062] The server reviews the generated proposals and selects the most appropriate one.

[0063] Example: Select "Log collection procedures to identify the cause of a crash" from the suggestions.

[0064] The server stores the selected suggestions in a database and notifies the user if necessary.

[0065] Example: Add the suggestion to the "Suggestion List" and notify relevant users.

[0066] 5. Response to inquiries:

[0067] A user submits a query using a chatbot or support form.

[0068] Example: User types "I want to reset my password."

[0069] The terminal transmits the inquiry to the server.

[0070] Example: Send the query "Password reset" to the server.

[0071] The server receives the query and sends it to the generative AI model.

[0072] Example: Input the inquiry "Password reset" into the generative AI model.

[0073] The generative AI model generates appropriate responses based on past inquiry data and FAQs.

[0074] Example: A generative AI model generates a response containing "password reset instructions."

[0075] The server sends the generated response to the terminal and sends it back to the user.

[0076] Example: The generated "password reset procedure" is sent to the terminal and displayed on the user's screen.

[0077] This allows for quick and accurate responses to user feedback and inquiries. In particular, the system aims to improve user experience by automating all processes, from feedback collection and analysis to proposal generation and customer support. As a specific example, if a user provides feedback that "the app crashes frequently," the system can collect and analyze that feedback and suggest log collection procedures to identify the cause of the crashes. This allows for quick resolution of user problems and increased satisfaction.

[0078] The processing flow will be explained below.

[0079] Step 1:

[0080] Users enter their issues and feedback through the chatbot.

[0081] Example: User types "The app crashes frequently."

[0082] Step 2:

[0083] The device receives user feedback in real time and transmits the data to the server.

[0084] Example: The device packets the feedback content as "frequent crashes" and sends it to the server.

[0085] Step 3:

[0086] The server stores the received feedback in a dedicated feedback database.

[0087] Example: Add an entry to your feedback database saying "frequent crashes."

[0088] Step 4:

[0089] The server periodically retrieves new feedback data from the database.

[0090] Example: Schedule a job to retrieve new feedback data every hour.

[0091] Step 5:

[0092] The generative AI model uses text analysis algorithms to extract issues and requests from within the feedback.

[0093] Example: A generative AI model extracts keywords such as "frequent crashes" and "after update."

[0094] Step 6:

[0095] The server stores the analysis results as structured data in an error log or a user suggestion list.

[0096] Example: Record the extracted keyword "frequent crashes" in the error log.

[0097] Step 7:

[0098] The server uses the saved analysis results to input data based on the user's needs into the generative AI model.

[0099] Example: The analysis results "frequent crashes" and "after update" are input into the generation AI model.

[0100] Step 8:

[0101] The generative AI model generates suggestions using analysis results, past data, or inference algorithms.

[0102] Example: A generative AI model generates suggestions such as "optimizations for improving performance" and "procedures for checking logs."

[0103] Step 9:

[0104] The server reviews the generated proposals and selects the most appropriate one.

[0105] Example: Select "Log collection procedures to identify the cause of a crash" from the suggestions.

[0106] Step 10:

[0107] The server stores the selected suggestions in a database and notifies the user if necessary.

[0108] Example: Add the suggestion to the "Suggestion List" and notify relevant users.

[0109] Step 11:

[0110] A user submits a query using a chatbot or support form.

[0111] Example: User types "I want to reset my password."

[0112] Step 12:

[0113] The terminal transmits the inquiry to the server.

[0114] Example: Send the inquiry "Password reset" to the server.

[0115] Step 13:

[0116] The server receives the query and sends it to the generative AI model.

[0117] Example: Input the inquiry "Password reset" into the generation AI model.

[0118] Step 14:

[0119] The generative AI model generates appropriate responses based on past inquiry data and FAQs.

[0120] Example: A generative AI model generates a response that includes "password reset instructions."

[0121] Step 15:

[0122] The server sends the generated response to the terminal and sends it back to the user.

[0123] Example: The generated "password reset procedure" is sent to the terminal and displayed on the user's screen.

[0124] Example 1

[0125] 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."

[0126] Conventional feedback collection systems have faced challenges in providing quick and accurate responses to user feedback and inquiries. Specifically, because feedback processing is done manually, it takes time to respond, resulting in a poor user experience. In addition, the analysis of feedback and the generation of suggestions are not automated, making it difficult to provide consistent responses.

[0127] 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.

[0128] In this invention, the server includes means for collecting feedback from users, means for transmitting the collected feedback to the server in real time, means for storing the collected feedback in a database, means for periodically retrieving the stored feedback, means for inputting the feedback retrieved from the database into a generative AI model for analysis, means for storing the results of the analyzed feedback as structured data, means for generating proposals based on the analysis results, means for selecting the generated proposals and notifying the user as necessary, and means for generating appropriate responses to user inquiries. This enables quick and accurate responses to user feedback and inquiries. Specifically, automating all processes from collecting feedback to analyzing it, generating proposals, and responding to inquiries can improve the user experience.

[0129] "User" means an individual or organization that uses the system to provide feedback or inquiries.

[0130] "Feedback" refers to information such as opinions, problems, and requests that users provide regarding systems and services.

[0131] A "terminal" is a hardware device that a user uses to enter feedback and queries and to communicate with a server.

[0132] "Server" is a central processing system that receives feedback and queries, analyzes, stores, generates suggestions, and generates responses.

[0133] A "chatbot" is an automated response system that interacts with users and collects feedback and inquiries.

[0134] A "database" is an information management system that systematically stores collected data such as feedback, analysis results, and proposals.

[0135] A "generative AI model" is a model that includes artificial intelligence algorithms to analyze user feedback and inquiries and generate appropriate suggestions and responses.

[0136] "Analysis" is the process of using a generative AI model to extract problems and requests from feedback and inquiries and organize them as structured data.

[0137] "Proposals" are solutions or improvement ideas generated by the generative AI model based on the analysis results.

[0138] An "inquiry" is a question or request that a user makes to a system or service.

[0139] A "response" is an answer or solution that a generative AI model or server provides to a user's query.

[0140] A "prompt sentence" is an input sentence given to a generative AI model that contains instructions for performing a specific analysis or generation process.

[0141] "Structured data" is data that has been systematically organized from analysis results and converted into a format that can be stored in a database.

[0142] This invention provides a system that effectively collects and analyzes user feedback, generates proposals based on the results, and provides prompt customer support. This system is mainly composed of users, terminals, a server, and a generative AI model.

[0143] System Components

[0144] User

[0145] A user is an individual or organization that utilizes the system to submit feedback or inquiries. Users use the chatbot interface to input feedback such as problems or requests. For example, a user may report a problem to the system by inputting "my app crashes frequently."

[0146] Terminal

[0147] The terminal is a device through which the user can input feedback and inquiries and communicate with the server. When the user inputs feedback into the chatbot interface, the terminal sends the feedback to the server in real time. For example, the terminal sends feedback such as "frequent crashes" to the server.

[0148] server

[0149] The server is responsible for the core processing of this system. The server has the following specific functions:

[0150] 1. Saving feedback: The feedback submitted by the user is saved in a database, such as Amazon RDS or Google Cloud SQL.

[0151] 2. Feedback Analysis: Feedback data is input into a generative AI model for analysis. Text analysis algorithms such as OpenAI® GPT-4® and BERT are used for the analysis. For example, keywords such as "frequent crashes" and "after update" are extracted from the feedback.

[0152] 3. Saving the analysis results: Saving the analysis results as structured data in an error log or a user suggestion list, using database INSERT and UPDATE queries.

[0153] 4. Proposal Generation: Based on the analysis results, appropriate suggestions are generated using a generative AI model. The most appropriate suggestion is selected from the generated suggestions and notified to the user as needed. For example, suggestions such as "optimization for performance improvement" or "log verification procedures" are generated.

[0154] Generative AI Models

[0155] A generative AI model is a model that includes artificial intelligence algorithms to analyze user feedback and inquiries and generate appropriate suggestions and responses. Generative AI models require powerful text generation capabilities for natural language processing. Specifically, the following prompt sentences are used:

[0156] User feedback: "The app crashes frequently"

[0157] Prompt the generative AI model: "Based on user feedback, explain how you identified the cause of frequent crashes."

[0158] Generated suggestion: "To help us determine why the app is crashing, please collect logs by following these steps..."

[0159] This system allows for quick and accurate responses to user feedback and inquiries, and by automating all processes, it improves the user experience.

[0160] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0161] Step 1:

[0162] User provides feedback through the chatbot

[0163] Input: The user enters text about their problem or request (e.g., "My app keeps crashing") into the chatbot.

[0164] Specific behavior: A user accesses the chatbot, enters feedback in the input field, and then presses the submit button.

[0165] Output: The entered feedback text.

[0166] Step 2:

[0167] The device sends feedback to the server in real time.

[0168] Input: The feedback text entered by the user.

[0169] Specific behavior: Calls the chatbot API and generates an HTTP POST request to send the feedback text to the server.

[0170] Output: Feedback data sent to the server.

[0171] Step 3:

[0172] The server stores the feedback in a database

[0173] Input: Feedback data sent to the server.

[0174] Specific behavior: Executes a database INSERT query to store the feedback data in a database (e.g., Amazon RDS or Google Cloud SQL).

[0175] Output: Feedback entries stored in a database.

[0176] Step 4:

[0177] The server periodically retrieves new feedback data.

[0178] Input: Feedback data stored in the database.

[0179] What it does: Schedule a cron job to periodically (e.g., hourly) run a SELECT query to retrieve new feedback data.

[0180] Output: The new feedback data retrieved by the server.

[0181] Step 5:

[0182] Generative AI models analyze feedback

[0183] Input: New feedback data retrieved by the server.

[0184] Specific operation: The feedback data is input into a generative AI model (e.g., OpenAI GPT-4), and text analysis is performed to extract problems and requests.

[0185] Prompt: "Based on user feedback, explain how you identify the cause of frequent crashes."

[0186] Output: Analyzed keywords and issues (e.g. "frequent crashes", "after update").

[0187] Step 6:

[0188] The server stores the analysis results as structured data.

[0189] Input: Parsed keywords and issues.

[0190] What it does: Executes an INSERT or UPDATE query in the database and saves the parsed results as structured data in an error log and a user suggestions list.

[0191] Output: Analysis result entries stored in a database.

[0192] Step 7:

[0193] The server generates suggestions based on the generative AI model

[0194] Input: Structured analysis result data.

[0195] What it does: Formats the analysis results and feeds them into a generative AI model to generate appropriate recommendations.

[0196] Prompt: "Based on your analysis, please explain the steps you would take to identify the cause of the frequent crashes."

[0197] Output: Generated suggestions (e.g. "Optimize for performance", "Steps to check logs").

[0198] Step 8:

[0199] The server selects the generated proposal and notifies the user if necessary.

[0200] Input: The generated proposals.

[0201] What it does: Uses an automated rating algorithm to select the most appropriate suggestion, adds it to the suggestions list, and notifies the user if necessary using the notification API.

[0202] Output: Selected proposal and notification to user.

[0203] Step 9:

[0204] A user contacts us using a chatbot or support form

[0205] Input: User query text (e.g. "I would like to reset my password").

[0206] Specific action: A user enters and submits an inquiry through a chatbot or support form.

[0207] Output: The input query text.

[0208] Step 10:

[0209] The device sends the inquiry to the server

[0210] Input: The query text entered by the user.

[0211] Specific behavior: Uses the chatbot API to generate an HTTP POST request that sends the inquiry to the server.

[0212] Output: The query data sent to the server.

[0213] Step 11:

[0214] The server sends the query to the generative AI model

[0215] Input: The query data sent to the server.

[0216] Specific operation: Call the API of the generative AI model and input the inquiry data.

[0217] Output: The inquiry data fed into the generative AI model.

[0218] Step 12:

[0219] Generative AI models generate appropriate responses

[0220] Input: The inquiry data fed into the generative AI model.

[0221] Specific behavior: Uses the model's inference engine to generate appropriate responses based on past inquiry data and FAQs.

[0222] Prompt: "Please explain the password reset procedure."

[0223] Output: The generated response (e.g., "Password reset instructions").

[0224] Step 13:

[0225] The server generates a response and sends it back to the user.

[0226] Input: The generated response.

[0227] What it does: Uses the chatbot's API to generate an HTTP POST request that sends the generated response to the user's device.

[0228] Output: The response data sent to the user device.

[0229] This allows for quick and accurate responses to user feedback and inquiries, and in particular, automating the entire process from collecting feedback to analyzing it, generating suggestions, and responding to inquiries can improve the user experience.

[0230] (Application example 1)

[0231] 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."

[0232] Current feedback collection and customer support systems have difficulty effectively analyzing user feedback and quickly providing suggestions based on it. Furthermore, they do not provide appropriate customer support based on the feedback in a timely manner. This problem results in a poor user experience and reduces customer satisfaction.

[0233] 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.

[0234] In this invention, the server includes means for collecting feedback from users, means for analyzing the collected feedback and extracting problems and requests, means for generating proposals based on the extracted information, means for notifying the user of the proposals based on the analyzed feedback, and means for automatically generating responses to inquiries from users. This makes it possible to consistently and effectively perform processes from collecting feedback to analyzing it, generating proposals, and providing appropriate customer support.

[0235] "User" refers to a person or entity that uses the system.

[0236] "Feedback" refers to information such as opinions, problems, and requests provided by users.

[0237] "Means for collecting" refers to the methods and devices for receiving and storing feedback from users.

[0238] "Means for analyzing" refers to a method or device for analyzing collected feedback information and identifying problems or needs.

[0239] "Extraction means" refers to a method or device for extracting from the data the problems and needs obtained through analysis.

[0240] "Means for generating proposals" refers to a method or apparatus that generates solutions or proposals based on the extracted information.

[0241] The term "means for automatically generating a response to an inquiry" refers to a method or device for automatically generating a response appropriate to the content of a user's inquiry.

[0242] "Means for notifying" refers to a method or device for notifying the user of the generated suggestions.

[0243] "Database" refers to a system for systematically storing and managing data such as feedback information and analysis results.

[0244] "Structured data" refers to data that has been organized and stored in a specific format as a result of analyzed feedback.

[0245] The present invention relates to a system for effectively collecting user feedback and providing customer support on an online shopping site. This system includes means for collecting user feedback in real time, analyzing it to identify problems and requests, generating appropriate suggestions, and notifying the users. It also includes means for automatically generating responses to user inquiries.

[0246] The system operates as follows.

[0247] 1. Gathering feedback

[0248] The user provides feedback through a smartphone app. When the user types in "I'm not satisfied with the product I recently purchased. I'd like to return it," the device receives the feedback and sends it to the server in real time.

[0249] 2. Saving your feedback

[0250] The server stores the received feedback in a database. For example, feedback such as "I'm not happy with the product I recently purchased and would like to return it" is recorded in the database.

[0251] 3. Feedback Analysis

[0252] The server periodically retrieves new feedback data from the database and performs text analysis using a generative AI model to extract problems and requests such as "dissatisfaction" and "returns" from the feedback.

[0253] Hardware / Software used

[0254] Server: A server that stores and analyzes data

[0255] Generative AI models: used to perform text analysis

[0256] 4. Proposal Generation

[0257] The server generates a suggestion based on the parsed information, for example, "We're sorry for your inconvenience. Please see below for return procedures." and notifies the user.

[0258] 5. Response to inquiries

[0259] If a user makes a separate inquiry, the server uses the generative AI model to generate an appropriate response based on past data and FAQs. For example, in response to the inquiry, "How do I process a return?", the server generates a response saying, "Please follow the steps below to process a return," and notifies the user.

[0260] Hardware / Software used

[0261] Server: A system for processing query data.

[0262] Generative AI models: used to generate appropriate responses

[0263] Specific examples

[0264] User feedback: "My recently purchased smartphone runs out of battery quickly."

[0265] Analysis result: Battery-related issues

[0266] Suggestion: "To save battery, we recommend lowering your screen brightness and closing apps you're not using."

[0267] Inquiry prompt: "How do I process a return?"

[0268] This system will improve the user experience on online shopping sites and increase customer satisfaction.

[0269] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0270] Step 1:

[0271] The user enters feedback through a smartphone app. For example, the user provides feedback such as, "I'm not satisfied with the product I recently purchased. I'd like to return it." This becomes input data.

[0272] Step 2:

[0273] The terminal obtains the input feedback and transmits it to the server in real time, where the input data is the raw feedback information and the output data is the feedback information transmitted to the server.

[0274] Step 3:

[0275] The server stores the received feedback information in a database, where the input data is the feedback information sent from the terminal and the output data is the feedback entry stored in the database.

[0276] Step 4:

[0277] The server periodically retrieves new feedback data from the database, where the input data is the feedback information in the database and the output data is the feedback data for analysis.

[0278] Step 5:

[0279] The server uses a generative AI model to analyze the feedback data and extract problems and requests. The input data is the feedback data, and the output data is the extracted problems and requests. Specifically, it uses a text analysis algorithm to identify keywords in the feedback.

[0280] Step 6:

[0281] The server uses a generative AI model to generate a proposal based on the extracted information. The input data are the extracted problems and requests, and the output data is the generated proposal. For example, a proposal might be generated that says, "We apologize for the inconvenience. Please see below for the return procedure."

[0282] Step 7:

[0283] The server notifies the user of the generated proposal. The input data is the generated proposal, and the output data is the notification sent to the user. The user receives the proposal notification through their terminal.

[0284] Step 8:

[0285] When a user makes an inquiry, for example, they input, "Please tell me how to process a return." This is the input data.

[0286] Step 9:

[0287] The terminal sends the query to the server. The input data is the user's query, and the output data is the query information sent to the server.

[0288] Step 10:

[0289] The server uses the generative AI model to generate an automated response to the inquiry. The input data is the inquiry information, and the output data is the generated response. For example, it generates a response such as, "Please follow the steps below to process your return."

[0290] Step 11:

[0291] The server sends the generated response to the user. The input data is the generated response, and the output data is the reply sent to the user. The user receives the reply through their terminal.

[0292] 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.

[0293] This invention relates to a system that effectively collects and analyzes feedback and inquiries from users, recognizes their emotions, and then generates appropriate suggestions and responses. This system is characterized by a combination of the processing flow and emotion engine described below.

[0294] System configuration and operation

[0295] 1. Feedback collection and emotion recognition:

[0296] Users enter their issues and feedback through the chatbot.

[0297] Example: User types, "My app crashes so often. It's really frustrating."

[0298] The device receives user feedback in real time and recognizes the user's emotions using an emotion engine.

[0299] The emotion engine identifies the emotion "anger" from the user's input text.

[0300] The device transmits the feedback content and the recognized emotion information to the server as data.

[0301] Example: Send feedback to the server as "frequent crashes" or "angry."

[0302] 2. Feedback storage and analysis:

[0303] The server stores the received feedback in a dedicated feedback database.

[0304] Example: Adding entries to the feedback database for "frequent crashes" and "angry."

[0305] The server periodically retrieves new feedback data from the database and analyzes it using the generative AI model.

[0306] Example: Schedule a job to retrieve new feedback data every hour, and the generative AI model will analyze and extract "frequent crashes" and "anger."

[0307] 3. Save the analysis results and generate suggestions:

[0308] The server stores the results of the parsed feedback as structured data.

[0309] Example: Save the extracted keywords "frequent crashes" and "anger" in the error log.

[0310] The server uses an emotion engine to request a generative AI model to make suggestions based on the user's emotions.

[0311] The emotion engine provides the emotion information of "anger" to the generative AI model, which then generates suggestions based on that information.

[0312] 4. Proposal Review and Notification:

[0313] The server reviews the generated proposals and selects the most appropriate one.

[0314] Example: Select "Quick log collection procedure to identify the cause of a crash" from the suggestions.

[0315] The server stores the selected suggestions in a database and notifies the user if necessary.

[0316] Example: Add the selected suggestion to the "suggestion list" and notify relevant users.

[0317] 5. Receiving and responding to inquiries:

[0318] A user submits a query using a chatbot or support form.

[0319] Example: User types, "I want to reset my password. I'm having so much trouble."

[0320] The terminal transmits the inquiry to the server.

[0321] Example: Send the inquiry "Password reset" and "Confused" to the server.

[0322] The server receives the query content through the emotion engine and sends it to the generative AI model.

[0323] Example: The inquiry content "Password reset" and "Confused" are input into the generative AI model.

[0324] A generative AI model generates responses based on past inquiry data and FAQs, while an emotion engine adjusts the appropriate tone.

[0325] Example: The emotion engine generates a "kind and polite" response to the "confused" emotion.

[0326] The server sends the generated response to the terminal and sends it back to the user.

[0327] Example: The generated "password reset procedure" is sent to the terminal and the message "Don't worry, you can reset your password by following the steps" is displayed on the user screen.

[0328] In this way, it is possible to respond to user feedback and inquiries quickly and appropriately according to their emotions. In particular, by combining an emotion engine, it is possible to recognize the user's emotions and adjust suggestions and responses based on those emotions, further improving the user experience. As a specific example, if a user gives feedback such as "The app crashes frequently. It's really frustrating," the system can collect and analyze that feedback, recognize the emotion of "anger," and propose a quick solution to identify the cause of the crash. This allows the user's problems to be resolved quickly and increases their emotional satisfaction.

[0329] The processing flow will be explained below.

[0330] Step 1:

[0331] Users enter their issues and feedback through the chatbot.

[0332] Example: User types, "My app crashes so often. It's really frustrating."

[0333] Step 2:

[0334] The device receives user feedback in real time and recognizes the user's emotions using an emotion engine.

[0335] The emotion engine identifies the emotion "anger" from the user's input text.

[0336] Step 3:

[0337] The device transmits the feedback content and the recognized emotion information to the server as data.

[0338] Example: Send feedback to the server as "frequent crashes" or "angry."

[0339] Step 4:

[0340] The server stores the received feedback in a dedicated feedback database.

[0341] Example: Adding entries to the feedback database for "frequent crashes" and "angry."

[0342] Step 5:

[0343] The server periodically retrieves new feedback data from the database.

[0344] Example: Schedule a job to retrieve new feedback data every hour.

[0345] Step 6:

[0346] The generative AI model uses text analysis algorithms to extract issues and requests from within the feedback.

[0347] Example: A generative AI model extracts keywords such as "frequent crashes," "after update," and "anger."

[0348] Step 7:

[0349] The server stores the analysis results and emotional information as structured data in an error log or user suggestion list.

[0350] Example: Save the extracted keywords "frequent crashes" and "anger" in the error log.

[0351] Step 8:

[0352] The server uses the saved analysis results to input data based on the user's needs into the generative AI model.

[0353] Example: The analysis results "frequent crashes," "after update," and "anger" are input into the generative AI model.

[0354] Step 9:

[0355] The generative AI model generates suggestions using analysis results, past data, or inference algorithms, where an emotion engine takes into account the user's emotional information.

[0356] Example: A generative AI model generates "log collection procedures to identify the cause of a crash," and an emotion engine adds polite language to correspond to "anger."

[0357] Step 10:

[0358] The server reviews the generated proposals and selects the most appropriate one.

[0359] Example: Select "Quick log collection procedure to identify the cause of a crash" from the suggestions.

[0360] Step 11:

[0361] The server stores the selected suggestions in a database and notifies the user if necessary.

[0362] Example: Add the suggestion to the "Suggestion List" and notify relevant users.

[0363] Step 12:

[0364] A user submits a query using a chatbot or support form.

[0365] Example: User types, "I want to reset my password. I'm having so much trouble."

[0366] Step 13:

[0367] The terminal transmits the inquiry to the server.

[0368] Example: Send the inquiry "Password reset" and "Confused" to the server.

[0369] Step 14:

[0370] The server receives the query and sends it to the generative AI model.

[0371] Example: The inquiry content "Password reset" and "Confused" are input into the generative AI model.

[0372] Step 15:

[0373] A generative AI model generates appropriate responses based on past inquiry data and FAQs, while an emotion engine adjusts the appropriate tone.

[0374] Example: A generative AI model generates "password reset instructions," and an emotion engine adds a "kind and polite" response to "confusion."

[0375] Step 16:

[0376] The server sends the generated response to the terminal and sends it back to the user.

[0377] Example: The generated "password reset procedure" is sent to the terminal and the message "Don't worry, you can reset your password by following the steps" is displayed on the user screen.

[0378] Example 2

[0379] 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."

[0380] Conventional feedback collection systems have been limited to simple text analysis and quantitative data collection without considering user emotions, making it difficult to respond appropriately to the user's psychological state. As a result, they have not been able to sufficiently improve the user experience or quickly resolve problems. A new system that can solve this problem and quickly provide suggestions and responses that correspond to the user's emotions is needed.

[0381] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0382] In this invention, the server includes means for receiving feedback from a user in real time and recognizing emotions, means for transmitting the recognized emotion information and the feedback content as data, means for saving the received feedback in a database, means for periodically updating the saved data and analyzing it using a generative AI model, means for saving the analysis results as structured data, means for generating suggestions based on the analysis results, and means for generating automatic responses in response to user inquiries, thereby enabling prompt and appropriate suggestions and responses that take the user's emotions into consideration.

[0383] "Feedback" refers to information such as opinions, problem reports, and requests provided by users.

[0384] "Emotion recognition" is the process of analyzing a user's input text and identifying the emotions contained within it.

[0385] "Emotion information" is information about emotions (e.g., anger, confusion, joy, etc.) identified from the analyzed feedback.

[0386] A "database" is a system for storing collected feedback and analysis results in a structured format.

[0387] A "generative AI model" is an artificial intelligence technology that generates appropriate suggestions and responses based on user feedback and inquiries.

[0388] "Structured data" is data that has a specific format or structure and can be efficiently stored and managed in a database.

[0389] "Suggestions" are specific instructions for action or solutions provided to the user based on the analysis results and emotional information.

[0390] An "automated response" is an automatically generated answer to a user's inquiry, created by a generative AI model.

[0391] "Analysis" is the process of examining the collected feedback in detail and extracting and evaluating problems and requests.

[0392] "Real-time" refers to the timeline in which user feedback and inquiries are processed and responded to immediately after they are entered.

[0393] This invention relates to a system that effectively collects and analyzes feedback and inquiries from users, recognizes their emotions, and then generates appropriate suggestions and responses. This system is characterized by a combination of the processing flow and emotion engine described below.

[0394] This system is primarily composed of a server and a user device. Specific hardware features include a high-performance cloud server as the server and a PC or smartphone as the user device. The software uses an emotion engine (e.g., Azure® Cognitive Services or IBM Watson®) and a generative AI model (e.g., OpenAI's GPT-3®).

[0395] Feedback collection and emotion recognition

[0396] Users use their devices to input their problems and feedback through the chatbot. For example, a user might type, "My app keeps crashing. It's really frustrating."

[0397] The device receives this user feedback in real time and uses an emotion engine to recognize the user's emotions. The device then calls a text analysis API to identify the emotion "anger" from the input text.

[0398] The device sends the feedback content and the recognized emotion information to the server as data. Specifically, the feedback content "frequent crashes" and the emotion "anger" are sent to the server in JSON format.

[0399] Feedback storage and analysis

[0400] The server stores the received feedback in a dedicated feedback database (e.g., MySQL or MongoDB). The server adds a new entry to the feedback database and saves the data.

[0401] The server uses a job scheduler (e.g., a Cron job) to periodically retrieve new feedback data from the database and analyze it using the generative AI model. This allows the server to retrieve and analyze new feedback data every hour.

[0402] Saving analysis results and generating proposals

[0403] The server stores the analyzed feedback results as structured data. The analysis results received from the generative AI model are stored in an error log database in JSON format.

[0404] The server uses the emotion engine to request a generative AI model to make a suggestion based on the user's emotion. The server provides the emotion information "anger" to the generative AI model, which then generates a suggestion: "Procedures for rapid log collection to identify the cause of the crash."

[0405] Proposal review and notification

[0406] The server reviews the generated proposals, selects the most appropriate proposal, adds the proposals to a list, and selects the best proposal either manually or through an automated process.

[0407] The server saves the selected suggestion in a database and notifies the user if necessary. The server saves the selected suggestion in a "suggestion list" and calls the notification API to send a message to the user.

[0408] Receiving and responding to inquiries

[0409] A user submits a query using a support form or chatbot. For example, they type, "I want to reset my password. I'm having a really hard time."

[0410] The device sends this inquiry to the server. The device sends the inquiry "Password reset" and the emotion "Confused" in JSON format to the server.

[0411] The server receives the inquiry via the emotion engine and sends it to the generative AI model, which then references the FAQ database and generates "password reset instructions" in a "friendly and polite" tone.

[0412] The server sends the generated response to the terminal and returns it to the user. It also sends the generated "password reset procedure" to the terminal and displays on the user's screen, "Don't worry, you can reset your password by following the steps."

[0413] Prompt Sentence Examples

[0414] "Please explain how the system responds when users give feedback that the app crashes too frequently."

[0415] "Could you please elaborate on how the system responds when a user is having trouble resetting their password?"

[0416] In this way, it is possible to respond to user feedback and inquiries quickly and appropriately according to their emotions, and this system is expected to significantly improve the user experience.

[0417] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0418] Step 1:

[0419] A user enters feedback using a chatbot.

[0420] Specific operation: The user opens the chatbot screen on a PC or smartphone and enters their problem or feedback. For example, they enter text such as, "The app keeps crashing. It's really frustrating."

[0421] Input: Text data entered by the user.

[0422] Output: Raw feedback data received on the user's device.

[0423] Step 2:

[0424] The device receives feedback in real time and recognizes emotions using an emotion engine.

[0425] Specific operation: The terminal sends the input text data to a text analysis API (e.g., an emotion engine) to analyze the emotion. The emotion engine identifies emotion information (e.g., "anger") from the text.

[0426] Input: Feedback text from the user.

[0427] Output: Identified emotion information (e.g., "anger").

[0428] Step 3:

[0429] The device transmits the feedback content and emotional information to the server as data.

[0430] Specific operation: The device converts the feedback content "frequent crashes" and emotional information "anger" into JSON format and sends it to the server.

[0431] Input: Feedback text and accompanying sentiment information.

[0432] Output: The JSON data sent to the server.

[0433] Step 4:

[0434] The server stores the received feedback in a feedback database.

[0435] Specific behavior: The server extracts the received JSON data, creates a new entry in the database, and saves it.

[0436] Input: JSON data sent from the terminal.

[0437] Output: A new feedback entry in the database.

[0438] Step 5:

[0439] The server periodically collects feedback data and analyzes it using a generative AI model.

[0440] How it works: The server uses a job scheduler (e.g., a Cron job) to retrieve new feedback from the database every hour, and sends it to the generative AI model for analysis. The generative AI model then analyzes the feedback in detail to identify problems and requests.

[0441] Input: New feedback data in the database.

[0442] Output: Analysis results from the generative AI model.

[0443] Step 6:

[0444] The server stores the analysis results as structured data.

[0445] Specific operation: The server stores the analysis results received from the generative AI model in JSON format in the error log database.

[0446] Input: Analysis results from a generative AI model.

[0447] Output: Analysis results stored as structured data.

[0448] Step 7:

[0449] The server utilizes an emotion engine to generate suggestions according to the user's emotions.

[0450] Specific operation: The server provides the emotional information "anger" to the generative AI model, and based on that, generates a suggestion for "quick log collection procedures to identify the cause of the crash."

[0451] Input: User emotion information and analysis results.

[0452] Output: Sentiment-based suggestions.

[0453] Step 8:

[0454] The server reviews the generated proposals and selects the most appropriate one.

[0455] What happens: The server adds the generated suggestions to a list and then selects the best suggestion either manually or through an automated process.

[0456] Input: Multiple proposals from a generative AI model.

[0457] Output: The selected best proposal.

[0458] Step 9:

[0459] The server stores the selected suggestions in a database and notifies the user if necessary.

[0460] Specific behavior: The server saves the selected suggestion in a "suggestion list" and calls the notification API to send a message to the user.

[0461] Input: Selected suggestion.

[0462] Output: Suggestions stored in database and notification to user.

[0463] Step 10:

[0464] A user submits a query using a support form or chatbot.

[0465] Specific action: For example, type "I want to reset my password. I'm having a really hard time."

[0466] Input: User query text.

[0467] Output: The raw query data received at the terminal.

[0468] Step 11:

[0469] The terminal transmits the inquiry to the server.

[0470] Specific operation: The device sends the inquiry "Password reset" and emotional information "Confused" in JSON format to the server.

[0471] Input: User inquiry and emotional information.

[0472] Output: The JSON data sent to the server.

[0473] Step 12:

[0474] The server receives the query via the emotion engine and sends it to the generative AI model.

[0475] Specific operation: The server analyzes the content through the emotion engine, sends the query content to the generative AI model, and generates a response.

[0476] Input: JSON data sent from the terminal.

[0477] Output: Response generated by the generative AI model.

[0478] Step 13:

[0479] A generative AI model generates responses based on past inquiry data and FAQs, while an emotion engine adjusts the appropriate tone.

[0480] Specific operation: The generative AI model refers to a database of FAQs and creates "password reset instructions" in a "friendly and polite" tone.

[0481] Input: Past inquiry data and current inquiry details.

[0482] Output: A response generated in a "friendly and polite" tone.

[0483] Step 14:

[0484] The server sends the generated response to the terminal and sends it back to the user.

[0485] Specific operation: The generated response content is sent to the terminal in JSON format, and the terminal displays "Don't worry, you can reset your password by following the steps" on the chat screen.

[0486] Input: The response from the generative AI model.

[0487] Output: The response message that is displayed on the user's terminal.

[0488] (Application example 2)

[0489] 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."

[0490] Conventional feedback collection and analysis systems do not adequately consider the emotional information in the feedback provided by users, resulting in the problem of not being able to provide appropriate suggestions or responses based on the user's actual emotional state. Furthermore, while there is a demand for fast, emotionally sensitive responses to user inquiries, there is currently no system that can adequately meet this demand.

[0491] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting feedback from users, means for analyzing the collected feedback to extract problems and requests and recognize the user's emotions, means for generating suggestions based on the extracted information and the recognized emotions, and means for automatically generating responses to inquiries from users. This makes it possible to analyze and suggest feedback based on the user's emotions, and to respond to user inquiries quickly and with consideration for the user's emotions.

[0492] "Means for collecting user feedback" refers to a device or process for collecting information such as opinions, impressions, and problems that users provide to the system.

[0493] "Means for analyzing collected feedback, extracting problems and requests, and recognizing user emotions" refers to a device or process for processing collected feedback data, analyzing user emotions, and identifying problems and requests contained in the feedback.

[0494] "Means for generating suggestions based on extracted information and recognized emotions" refers to a device or process that uses the information obtained through the analysis and the user's emotional information to generate appropriate suggestions or solutions for the user.

[0495] The "means for automatically generating a response to a user's inquiry" refers to a device or process for automatically creating and providing a response to the content of a user's inquiry.

[0496] "Means for storing collected feedback in a database" refers to a device or process for storing collected feedback data in a database for easy later access.

[0497] "Means for storing structured data including emotional information of the analyzed feedback data" refers to a device or process for structuring the feedback data including the emotional information obtained by the analysis and storing it in a database.

[0498] "Means for a generative AI model to analyze based on emotions and generate appropriate suggestions or responses based on prompts" refers to a device or process that allows a generative AI model to analyze based on a user's emotional information and generate appropriate suggestions or responses based on specific instructions (prompts).

[0499] In this invention, the configuration and operation for realizing a system that effectively collects and analyzes user feedback and makes appropriate suggestions and responses based on the user's emotional information will be described below.

[0500] 1. Collecting User Feedback

[0501] Users submit feedback using a smartphone application, which is provided as text input and includes, for example, "I didn't enjoy the movie that was recently released. I'm a little annoyed. Is there a more exciting movie out there?"

[0502] 2. Emotion recognition

[0503] The device analyzes the collected feedback in real time using a natural language processing library (e.g., spaCy) and an emotion recognition engine (e.g., an emotion analysis tool using an NLP model), thereby identifying emotions such as "irritation" from the user's feedback.

[0504] 3. Data storage

[0505] The device sends the feedback data along with the emotion information recognized by the device to the server, which then stores it in a database (e.g., MongoDB), where the feedback and associated emotion information are stored as structured data.

[0506] 4. Analysis and proposal generation

[0507] The server periodically retrieves feedback data from the database and analyzes it using a generative AI model (e.g., GPT-4). Based on the information and emotional information extracted through the analysis, the generative AI model creates and executes prompts to generate appropriate suggestions and solutions.

[0508] 5. Notice to Users

[0509] The generated suggestions and responses are sent to the user's terminal by the server, and the user receives them through the application. For example, in response to feedback such as "The recent movie was not interesting," a suggestion such as "Suggestion: Please check out the following for more exciting movies" may be made.

[0510] Specifically, this includes the following steps:

[0511] The user enters feedback such as, "The movie that was recently released wasn't interesting. I'm a little annoyed. Are there any more exciting movies?"

[0512] The device recognizes the emotion as "irritation" and sends feedback to the server.

[0513] The server stores the feedback and emotional information in a database, and the generative AI model generates appropriate suggestions.

[0514] The suggestion is notified to the user as "Suggestion: Check out the following for more exciting movies."

[0515] Hardware and software used:

[0516] Smartphone (ANDROID (registered trademark), iOS)

[0517] Natural language processing library (spaCy)

[0518] Emotion recognition engine (NLP model)

[0519] Database (MongoDB)

[0520] Generative AI model (GPT-4)

[0521] This allows for analysis and suggestion of feedback based on the user's emotions, enabling fast and emotionally sensitive responses to queries.

[0522] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0523] Step 1:

[0524] The user inputs feedback into the smartphone application. For example, the input might be, "The movie that was recently released wasn't interesting. I'm a little annoyed. Is there a more exciting movie?" The input text data is sent to the device.

[0525] Step 2:

[0526] The device analyzes the collected feedback text using a natural language processing library (e.g., spaCy) and an emotion recognition engine (e.g., an emotion analysis tool using an NLP model). It receives the feedback text as input and identifies the emotion as "irritation" from the content of the text.

[0527] Step 3:

[0528] The device sends the analyzed emotion information and feedback data to the server, which stores the received feedback data and emotion information in a database (e.g., MongoDB). The data is stored in a structured format.

[0529] Step 4:

[0530] The server reads new feedback data from the database according to a regular schedule and analyzes it using a generative AI model (e.g., GPT-4). The generative AI model uses the feedback text and emotional information as input, and generates necessary information and suggestions based on that. For example, analysis is performed based on a prompt sentence corresponding to the emotion "irritation."

[0531] Step 5:

[0532] The generative AI model outputs suggestions and solutions, which are then reviewed by the server, which selects the most appropriate suggestion and makes adjustments as needed. The selected suggestion or solution is then stored as structured data.

[0533] Step 6:

[0534] The server notifies the generated suggestion to the user's device. The device receives the suggestion and displays it to the user. For example, "Suggestion: Check out the following for more exciting movies."

[0535] Step 7:

[0536] When a user submits a new inquiry, the inquiry is sent to the server in a similar manner and analyzed by the emotion recognition and generative AI model. An appropriate response is then generated and notified to the user. For example, if the issue is not resolved, a response such as "Don't worry, we'll contact our support team" is displayed.

[0537] As a result, a system is constructed that can provide appropriate suggestions and responses based on emotions in response to user feedback and inquiries.

[0538] 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.

[0539] 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.

[0540] 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.

[0541] [Second embodiment]

[0542] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0543] 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.

[0544] 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).

[0545] 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.

[0546] 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.

[0547] 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).

[0548] 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.

[0549] 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.

[0550] 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.

[0551] 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.

[0552] 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.

[0553] 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."

[0554] The present invention relates to a system that effectively collects and analyzes user feedback, generates proposals based on the collected feedback, and provides prompt customer support. This system has the following processing flow:

[0555] System configuration and operation

[0556] 1. Gathering Feedback:

[0557] Users enter their issues and feedback through the chatbot.

[0558] Example: User types "My app crashes frequently."

[0559] The device receives user feedback in real time and transmits the data to the server.

[0560] Example: The device sends feedback to the server saying "frequent crashes."

[0561] 2. Save your feedback:

[0562] The server stores the received feedback in a dedicated feedback database.

[0563] Example: Add an entry to the feedback database saying "frequent crashes."

[0564] 3. Feedback analysis:

[0565] The server periodically retrieves new feedback data from the database.

[0566] Example: Schedule a job to retrieve new feedback data every hour.

[0567] The generative AI model uses text analysis algorithms to extract issues and requests from within the feedback.

[0568] Example: A generative AI model extracts keywords such as "frequent crashes" and "after update."

[0569] The server stores the analysis results as structured data in an error log or a user suggestion list.

[0570] Example: Record the extracted keyword "frequent crashes" in the error log.

[0571] 4. Proposal generation:

[0572] The server uses the saved analysis results to input data based on the user's needs into the generative AI model.

[0573] Example: The analysis results "frequent crashes" and "after update" are input into the generative AI model.

[0574] The generative AI model generates suggestions using analysis results, past data, or inference algorithms.

[0575] For example, generating suggestions such as "Optimize for performance" and "Steps to check logs."

[0576] The server reviews the generated proposals and selects the most appropriate one.

[0577] Example: Select "Log collection procedures to identify the cause of a crash" from the suggestions.

[0578] The server stores the selected suggestions in a database and notifies the user if necessary.

[0579] Example: Add the suggestion to the "Suggestion List" and notify relevant users.

[0580] 5. Response to inquiries:

[0581] A user submits a query using a chatbot or support form.

[0582] Example: User types "I want to reset my password."

[0583] The terminal transmits the inquiry to the server.

[0584] Example: Send the query "Password reset" to the server.

[0585] The server receives the query and sends it to the generative AI model.

[0586] Example: Input the inquiry "Password reset" into the generative AI model.

[0587] The generative AI model generates appropriate responses based on past inquiry data and FAQs.

[0588] Example: A generative AI model generates a response containing "password reset instructions."

[0589] The server sends the generated response to the terminal and sends it back to the user.

[0590] Example: The generated "password reset procedure" is sent to the terminal and displayed on the user's screen.

[0591] This allows for quick and accurate responses to user feedback and inquiries. In particular, the system aims to improve user experience by automating all processes, from feedback collection and analysis to proposal generation and customer support. As a specific example, if a user provides feedback that "the app crashes frequently," the system can collect and analyze that feedback and suggest log collection procedures to identify the cause of the crashes. This allows for quick resolution of user problems and increased satisfaction.

[0592] The processing flow will be explained below.

[0593] Step 1:

[0594] Users enter their issues and feedback through the chatbot.

[0595] Example: User types "The app crashes frequently."

[0596] Step 2:

[0597] The device receives user feedback in real time and transmits the data to the server.

[0598] Example: The device packets the feedback content as "frequent crashes" and sends it to the server.

[0599] Step 3:

[0600] The server stores the received feedback in a dedicated feedback database.

[0601] Example: Add an entry to your feedback database saying "frequent crashes."

[0602] Step 4:

[0603] The server periodically retrieves new feedback data from the database.

[0604] Example: Schedule a job to retrieve new feedback data every hour.

[0605] Step 5:

[0606] The generative AI model uses text analysis algorithms to extract issues and requests from within the feedback.

[0607] Example: A generative AI model extracts keywords such as "frequent crashes" and "after update."

[0608] Step 6:

[0609] The server stores the analysis results as structured data in an error log or a user suggestion list.

[0610] Example: Record the extracted keyword "frequent crashes" in the error log.

[0611] Step 7:

[0612] The server uses the saved analysis results to input data based on the user's needs into the generative AI model.

[0613] Example: The analysis results "frequent crashes" and "after update" are input into the generation AI model.

[0614] Step 8:

[0615] The generative AI model generates suggestions using analysis results, past data, or inference algorithms.

[0616] Example: A generative AI model generates suggestions such as "optimizations for improving performance" and "procedures for checking logs."

[0617] Step 9:

[0618] The server reviews the generated proposals and selects the most appropriate one.

[0619] Example: Select "Log collection procedures to identify the cause of a crash" from the suggestions.

[0620] Step 10:

[0621] The server stores the selected suggestions in a database and notifies the user if necessary.

[0622] Example: Add the suggestion to the "Suggestion List" and notify relevant users.

[0623] Step 11:

[0624] A user submits a query using a chatbot or support form.

[0625] Example: User types "I want to reset my password."

[0626] Step 12:

[0627] The terminal transmits the inquiry to the server.

[0628] Example: Send the inquiry "Password reset" to the server.

[0629] Step 13:

[0630] The server receives the query and sends it to the generative AI model.

[0631] Example: Input the inquiry "Password reset" into the generation AI model.

[0632] Step 14:

[0633] The generative AI model generates appropriate responses based on past inquiry data and FAQs.

[0634] Example: A generative AI model generates a response that includes "password reset instructions."

[0635] Step 15:

[0636] The server sends the generated response to the terminal and sends it back to the user.

[0637] Example: The generated "password reset procedure" is sent to the terminal and displayed on the user's screen.

[0638] Example 1

[0639] 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."

[0640] Conventional feedback collection systems have faced challenges in providing quick and accurate responses to user feedback and inquiries. Specifically, because feedback processing is done manually, it takes time to respond, resulting in a poor user experience. In addition, the analysis of feedback and the generation of suggestions are not automated, making it difficult to provide consistent responses.

[0641] 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.

[0642] In this invention, the server includes means for collecting feedback from users, means for transmitting the collected feedback to the server in real time, means for storing the collected feedback in a database, means for periodically retrieving the stored feedback, means for inputting the feedback retrieved from the database into a generative AI model for analysis, means for storing the results of the analyzed feedback as structured data, means for generating proposals based on the analysis results, means for selecting the generated proposals and notifying the user as necessary, and means for generating appropriate responses to user inquiries. This enables quick and accurate responses to user feedback and inquiries. Specifically, automating all processes from collecting feedback to analyzing it, generating proposals, and responding to inquiries can improve the user experience.

[0643] "User" means an individual or organization that uses the system to provide feedback or inquiries.

[0644] "Feedback" refers to information such as opinions, problems, and requests that users provide regarding systems and services.

[0645] A "terminal" is a hardware device that a user uses to enter feedback and queries and to communicate with a server.

[0646] "Server" is a central processing system that receives feedback and queries, analyzes, stores, generates suggestions, and generates responses.

[0647] A "chatbot" is an automated response system that interacts with users and collects feedback and inquiries.

[0648] A "database" is an information management system that systematically stores collected data such as feedback, analysis results, and proposals.

[0649] A "generative AI model" is a model that includes artificial intelligence algorithms to analyze user feedback and inquiries and generate appropriate suggestions and responses.

[0650] "Analysis" is the process of using a generative AI model to extract problems and requests from feedback and inquiries and organize them as structured data.

[0651] "Proposals" are solutions or improvement ideas generated by the generative AI model based on the analysis results.

[0652] An "inquiry" is a question or request that a user makes to a system or service.

[0653] A "response" is an answer or solution that a generative AI model or server provides to a user's query.

[0654] A "prompt sentence" is an input sentence given to a generative AI model that contains instructions for performing a specific analysis or generation process.

[0655] "Structured data" is data that has been systematically organized from analysis results and converted into a format that can be stored in a database.

[0656] This invention provides a system that effectively collects and analyzes user feedback, generates proposals based on the results, and provides prompt customer support. This system is mainly composed of users, terminals, a server, and a generative AI model.

[0657] System Components

[0658] User

[0659] A user is an individual or organization that utilizes the system to submit feedback or inquiries. Users use the chatbot interface to input feedback such as problems or requests. For example, a user may report a problem to the system by inputting "my app crashes frequently."

[0660] Terminal

[0661] The terminal is a device through which the user can input feedback and inquiries and communicate with the server. When the user inputs feedback into the chatbot interface, the terminal sends the feedback to the server in real time. For example, the terminal sends feedback such as "frequent crashes" to the server.

[0662] server

[0663] The server is responsible for the core processing of this system. The server has the following specific functions:

[0664] 1. Feedback storage: The feedback submitted by the user is stored in a database, such as Amazon RDS or Google Cloud SQL.

[0665] 2. Feedback Analysis: Feedback data is input into a generative AI model for analysis. Text analysis algorithms such as OpenAI GPT-4 and BERT are used for the analysis. For example, keywords such as "frequent crashes" and "after an update" are extracted from the feedback.

[0666] 3. Saving the analysis results: Saving the analysis results as structured data in an error log or a user suggestion list, using database INSERT and UPDATE queries.

[0667] 4. Proposal Generation: Based on the analysis results, appropriate suggestions are generated using a generative AI model. The most appropriate suggestion is selected from the generated suggestions and notified to the user as needed. For example, suggestions such as "optimization for performance improvement" or "log verification procedures" are generated.

[0668] Generative AI Models

[0669] A generative AI model is a model that includes artificial intelligence algorithms to analyze user feedback and inquiries and generate appropriate suggestions and responses. Generative AI models require powerful text generation capabilities for natural language processing. Specifically, the following prompt sentences are used:

[0670] User feedback: "The app crashes frequently"

[0671] Prompt the generative AI model: "Based on user feedback, explain how you identified the cause of frequent crashes."

[0672] Generated suggestion: "To help us determine why the app is crashing, please collect logs by following these steps..."

[0673] This system allows for quick and accurate responses to user feedback and inquiries, and by automating all processes, it improves the user experience.

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

[0675] Step 1:

[0676] User provides feedback through the chatbot

[0677] Input: The user enters text about their problem or request (e.g., "My app keeps crashing") into the chatbot.

[0678] Specific behavior: A user accesses the chatbot, enters feedback in the input field, and then presses the submit button.

[0679] Output: The entered feedback text.

[0680] Step 2:

[0681] The device sends feedback to the server in real time.

[0682] Input: The feedback text entered by the user.

[0683] Specific behavior: Calls the chatbot API and generates an HTTP POST request to send the feedback text to the server.

[0684] Output: Feedback data sent to the server.

[0685] Step 3:

[0686] The server stores the feedback in a database

[0687] Input: Feedback data sent to the server.

[0688] Specific behavior: Executes a database INSERT query to store the feedback data in a database (e.g., Amazon RDS or Google Cloud SQL).

[0689] Output: Feedback entries stored in a database.

[0690] Step 4:

[0691] The server periodically retrieves new feedback data.

[0692] Input: Feedback data stored in the database.

[0693] What it does: Schedule a cron job to periodically (e.g., hourly) run a SELECT query to retrieve new feedback data.

[0694] Output: The new feedback data retrieved by the server.

[0695] Step 5:

[0696] Generative AI models analyze feedback

[0697] Input: New feedback data retrieved by the server.

[0698] Specific operation: The feedback data is input into a generative AI model (e.g., OpenAI GPT-4), and text analysis is performed to extract problems and requests.

[0699] Prompt: "Based on user feedback, explain how you identify the cause of frequent crashes."

[0700] Output: Analyzed keywords and issues (e.g. "frequent crashes", "after update").

[0701] Step 6:

[0702] The server stores the analysis results as structured data.

[0703] Input: Parsed keywords and issues.

[0704] What it does: Executes an INSERT or UPDATE query in the database and saves the parsed results as structured data in an error log and a user suggestions list.

[0705] Output: Analysis result entries stored in a database.

[0706] Step 7:

[0707] The server generates suggestions based on the generative AI model

[0708] Input: Structured analysis result data.

[0709] What it does: Formats the analysis results and feeds them into a generative AI model to generate appropriate recommendations.

[0710] Prompt: "Based on your analysis, please explain the steps you would take to identify the cause of the frequent crashes."

[0711] Output: Generated suggestions (e.g. "Optimize for performance", "Steps to check logs").

[0712] Step 8:

[0713] The server selects the generated proposal and notifies the user if necessary.

[0714] Input: The generated proposals.

[0715] What it does: Uses an automated rating algorithm to select the most appropriate suggestion, adds it to the suggestions list, and notifies the user if necessary using the notification API.

[0716] Output: Selected proposal and notification to user.

[0717] Step 9:

[0718] A user contacts us using a chatbot or support form

[0719] Input: User query text (e.g. "I would like to reset my password").

[0720] Specific action: A user enters and submits an inquiry through a chatbot or support form.

[0721] Output: The input query text.

[0722] Step 10:

[0723] The device sends the inquiry to the server

[0724] Input: The query text entered by the user.

[0725] Specific behavior: Uses the chatbot API to generate an HTTP POST request that sends the inquiry to the server.

[0726] Output: The query data sent to the server.

[0727] Step 11:

[0728] The server sends the query to the generative AI model

[0729] Input: The query data sent to the server.

[0730] Specific operation: Call the API of the generative AI model and input the inquiry data.

[0731] Output: The inquiry data fed into the generative AI model.

[0732] Step 12:

[0733] Generative AI models generate appropriate responses

[0734] Input: The inquiry data fed into the generative AI model.

[0735] Specific behavior: Uses the model's inference engine to generate appropriate responses based on past inquiry data and FAQs.

[0736] Prompt: "Please explain the password reset procedure."

[0737] Output: The generated response (e.g., "Password reset instructions").

[0738] Step 13:

[0739] The server generates a response and sends it back to the user.

[0740] Input: The generated response.

[0741] What it does: Uses the chatbot's API to generate an HTTP POST request that sends the generated response to the user's device.

[0742] Output: The response data sent to the user device.

[0743] This allows for quick and accurate responses to user feedback and inquiries, and in particular, automating the entire process from collecting feedback to analyzing it, generating suggestions, and responding to inquiries can improve the user experience.

[0744] (Application example 1)

[0745] 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."

[0746] Current feedback collection and customer support systems have difficulty effectively analyzing user feedback and quickly providing suggestions based on it. Furthermore, they do not provide appropriate customer support based on the feedback in a timely manner. This problem results in a poor user experience and reduces customer satisfaction.

[0747] 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.

[0748] In this invention, the server includes means for collecting feedback from users, means for analyzing the collected feedback and extracting problems and requests, means for generating proposals based on the extracted information, means for notifying the user of the proposals based on the analyzed feedback, and means for automatically generating responses to inquiries from users. This makes it possible to consistently and effectively perform processes from collecting feedback to analyzing it, generating proposals, and providing appropriate customer support.

[0749] "User" refers to a person or entity that uses the system.

[0750] "Feedback" refers to information such as opinions, problems, and requests provided by users.

[0751] "Means for collecting" refers to the methods and devices for receiving and storing feedback from users.

[0752] "Means for analyzing" refers to a method or device for analyzing collected feedback information and identifying problems or needs.

[0753] "Extraction means" refers to a method or device for extracting from the data the problems and needs obtained through analysis.

[0754] "Means for generating proposals" refers to a method or apparatus that generates solutions or proposals based on the extracted information.

[0755] The term "means for automatically generating a response to an inquiry" refers to a method or device for automatically generating a response appropriate to the content of a user's inquiry.

[0756] "Means for notifying" refers to a method or device for notifying the user of the generated suggestions.

[0757] "Database" refers to a system for systematically storing and managing data such as feedback information and analysis results.

[0758] "Structured data" refers to data that has been organized and stored in a specific format as a result of analyzed feedback.

[0759] The present invention relates to a system for effectively collecting user feedback and providing customer support on an online shopping site. This system includes means for collecting user feedback in real time, analyzing it to identify problems and requests, generating appropriate suggestions, and notifying the users. It also includes means for automatically generating responses to user inquiries.

[0760] The system operates as follows.

[0761] 1. Gathering feedback

[0762] The user provides feedback through a smartphone app. When the user types in "I'm not satisfied with the product I recently purchased. I'd like to return it," the device receives the feedback and sends it to the server in real time.

[0763] 2. Saving your feedback

[0764] The server stores the received feedback in a database. For example, feedback such as "I'm not happy with the product I recently purchased and would like to return it" is recorded in the database.

[0765] 3. Feedback Analysis

[0766] The server periodically retrieves new feedback data from the database and performs text analysis using a generative AI model to extract problems and requests such as "dissatisfaction" and "returns" from the feedback.

[0767] Hardware / Software used

[0768] Server: A server that stores and analyzes data

[0769] Generative AI models: used to perform text analysis

[0770] 4. Proposal Generation

[0771] The server generates a suggestion based on the parsed information, for example, "We're sorry for your inconvenience. Please see below for return procedures." and notifies the user.

[0772] 5. Response to inquiries

[0773] If a user makes a separate inquiry, the server uses the generative AI model to generate an appropriate response based on past data and FAQs. For example, in response to the inquiry, "How do I process a return?", the server generates a response saying, "Please follow the steps below to process a return," and notifies the user.

[0774] Hardware / Software used

[0775] Server: A system for processing query data.

[0776] Generative AI models: used to generate appropriate responses

[0777] Specific examples

[0778] User feedback: "My recently purchased smartphone runs out of battery quickly."

[0779] Analysis result: Battery-related issues

[0780] Suggestion: "To save battery, we recommend lowering your screen brightness and closing apps you're not using."

[0781] Inquiry prompt: "How do I process a return?"

[0782] This system will improve the user experience on online shopping sites and increase customer satisfaction.

[0783] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0784] Step 1:

[0785] The user enters feedback through a smartphone app. For example, the user provides feedback such as, "I'm not satisfied with the product I recently purchased. I'd like to return it." This becomes input data.

[0786] Step 2:

[0787] The terminal obtains the input feedback and transmits it to the server in real time, where the input data is the raw feedback information and the output data is the feedback information transmitted to the server.

[0788] Step 3:

[0789] The server stores the received feedback information in a database, where the input data is the feedback information sent from the terminal and the output data is the feedback entry stored in the database.

[0790] Step 4:

[0791] The server periodically retrieves new feedback data from the database, where the input data is the feedback information in the database and the output data is the feedback data for analysis.

[0792] Step 5:

[0793] The server uses a generative AI model to analyze the feedback data and extract problems and requests. The input data is the feedback data, and the output data is the extracted problems and requests. Specifically, it uses a text analysis algorithm to identify keywords in the feedback.

[0794] Step 6:

[0795] The server uses a generative AI model to generate a proposal based on the extracted information. The input data are the extracted problems and requests, and the output data is the generated proposal. For example, a proposal might be generated that says, "We apologize for the inconvenience. Please see below for the return procedure."

[0796] Step 7:

[0797] The server notifies the user of the generated proposal. The input data is the generated proposal, and the output data is the notification sent to the user. The user receives the proposal notification through their terminal.

[0798] Step 8:

[0799] When a user makes an inquiry, for example, they input, "Please tell me how to process a return." This is the input data.

[0800] Step 9:

[0801] The terminal sends the query to the server. The input data is the user's query, and the output data is the query information sent to the server.

[0802] Step 10:

[0803] The server uses the generative AI model to generate an automated response to the inquiry. The input data is the inquiry information, and the output data is the generated response. For example, it generates a response such as, "Please follow the steps below to process your return."

[0804] Step 11:

[0805] The server sends the generated response to the user. The input data is the generated response, and the output data is the reply sent to the user. The user receives the reply through their terminal.

[0806] 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.

[0807] This invention relates to a system that effectively collects and analyzes feedback and inquiries from users, recognizes their emotions, and then generates appropriate suggestions and responses. This system is characterized by a combination of the processing flow and emotion engine described below.

[0808] System configuration and operation

[0809] 1. Feedback collection and emotion recognition:

[0810] Users enter their issues and feedback through the chatbot.

[0811] Example: User types, "My app crashes so often. It's really frustrating."

[0812] The device receives user feedback in real time and recognizes the user's emotions using an emotion engine.

[0813] The emotion engine identifies the emotion "anger" from the user's input text.

[0814] The device transmits the feedback content and the recognized emotion information to the server as data.

[0815] Example: Send feedback to the server as "frequent crashes" or "angry."

[0816] 2. Feedback storage and analysis:

[0817] The server stores the received feedback in a dedicated feedback database.

[0818] Example: Adding entries to the feedback database for "frequent crashes" and "angry."

[0819] The server periodically retrieves new feedback data from the database and analyzes it using the generative AI model.

[0820] Example: Schedule a job to retrieve new feedback data every hour, and the generative AI model will analyze and extract "frequent crashes" and "anger."

[0821] 3. Save the analysis results and generate suggestions:

[0822] The server stores the results of the parsed feedback as structured data.

[0823] Example: Save the extracted keywords "frequent crashes" and "anger" in the error log.

[0824] The server uses an emotion engine to request a generative AI model to make suggestions based on the user's emotions.

[0825] The emotion engine provides the emotion information of "anger" to the generative AI model, which then generates suggestions based on that information.

[0826] 4. Proposal Review and Notification:

[0827] The server reviews the generated proposals and selects the most appropriate one.

[0828] Example: Select "Quick log collection procedure to identify the cause of a crash" from the suggestions.

[0829] The server stores the selected suggestions in a database and notifies the user if necessary.

[0830] Example: Add the selected suggestion to the "suggestion list" and notify relevant users.

[0831] 5. Receiving and responding to inquiries:

[0832] A user submits a query using a chatbot or support form.

[0833] Example: User types, "I want to reset my password. I'm having so much trouble."

[0834] The terminal transmits the inquiry to the server.

[0835] Example: Send the inquiry "Password reset" and "Confused" to the server.

[0836] The server receives the query content through the emotion engine and sends it to the generative AI model.

[0837] Example: The inquiry content "Password reset" and "Confused" are input into the generative AI model.

[0838] A generative AI model generates responses based on past inquiry data and FAQs, while an emotion engine adjusts the appropriate tone.

[0839] Example: The emotion engine generates a "kind and polite" response to the "confused" emotion.

[0840] The server sends the generated response to the terminal and sends it back to the user.

[0841] Example: The generated "password reset procedure" is sent to the terminal and the message "Don't worry, you can reset your password by following the steps" is displayed on the user screen.

[0842] In this way, it is possible to respond to user feedback and inquiries quickly and appropriately according to their emotions. In particular, by combining an emotion engine, it is possible to recognize the user's emotions and adjust suggestions and responses based on those emotions, further improving the user experience. As a specific example, if a user gives feedback such as "The app crashes frequently. It's really frustrating," the system can collect and analyze that feedback, recognize the emotion of "anger," and propose a quick solution to identify the cause of the crash. This allows the user's problems to be resolved quickly and increases their emotional satisfaction.

[0843] The processing flow will be explained below.

[0844] Step 1:

[0845] Users enter their issues and feedback through the chatbot.

[0846] Example: User types, "My app crashes so often. It's really frustrating."

[0847] Step 2:

[0848] The device receives user feedback in real time and recognizes the user's emotions using an emotion engine.

[0849] The emotion engine identifies the emotion "anger" from the user's input text.

[0850] Step 3:

[0851] The device transmits the feedback content and the recognized emotion information to the server as data.

[0852] Example: Send feedback to the server as "frequent crashes" or "angry."

[0853] Step 4:

[0854] The server stores the received feedback in a dedicated feedback database.

[0855] Example: Adding entries to the feedback database for "frequent crashes" and "angry."

[0856] Step 5:

[0857] The server periodically retrieves new feedback data from the database.

[0858] Example: Schedule a job to retrieve new feedback data every hour.

[0859] Step 6:

[0860] The generative AI model uses text analysis algorithms to extract issues and requests from within the feedback.

[0861] Example: A generative AI model extracts keywords such as "frequent crashes," "after update," and "anger."

[0862] Step 7:

[0863] The server stores the analysis results and emotional information as structured data in an error log or user suggestion list.

[0864] Example: Save the extracted keywords "frequent crashes" and "anger" in the error log.

[0865] Step 8:

[0866] The server uses the saved analysis results to input data based on the user's needs into the generative AI model.

[0867] Example: The analysis results "frequent crashes," "after update," and "anger" are input into the generative AI model.

[0868] Step 9:

[0869] The generative AI model generates suggestions using analysis results, past data, or inference algorithms, where an emotion engine takes into account the user's emotional information.

[0870] Example: A generative AI model generates "log collection procedures to identify the cause of a crash," and an emotion engine adds polite language to correspond to "anger."

[0871] Step 10:

[0872] The server reviews the generated proposals and selects the most appropriate one.

[0873] Example: Select "Quick log collection procedure to identify the cause of a crash" from the suggestions.

[0874] Step 11:

[0875] The server stores the selected suggestions in a database and notifies the user if necessary.

[0876] Example: Add the suggestion to the "Suggestion List" and notify relevant users.

[0877] Step 12:

[0878] A user submits a query using a chatbot or support form.

[0879] Example: User types, "I want to reset my password. I'm having so much trouble."

[0880] Step 13:

[0881] The terminal transmits the inquiry to the server.

[0882] Example: Send the inquiry "Password reset" and "Confused" to the server.

[0883] Step 14:

[0884] The server receives the query and sends it to the generative AI model.

[0885] Example: The inquiry content "Password reset" and "Confused" are input into the generative AI model.

[0886] Step 15:

[0887] A generative AI model generates appropriate responses based on past inquiry data and FAQs, while an emotion engine adjusts the appropriate tone.

[0888] Example: A generative AI model generates "password reset instructions," and an emotion engine adds a "kind and polite" response to "confusion."

[0889] Step 16:

[0890] The server sends the generated response to the terminal and sends it back to the user.

[0891] Example: The generated "password reset procedure" is sent to the terminal and the message "Don't worry, you can reset your password by following the steps" is displayed on the user screen.

[0892] Example 2

[0893] 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."

[0894] Conventional feedback collection systems have been limited to simple text analysis and quantitative data collection without considering user emotions, making it difficult to respond appropriately to the user's psychological state. As a result, they have not been able to sufficiently improve the user experience or quickly resolve problems. A new system that can solve this problem and quickly provide suggestions and responses that correspond to the user's emotions is needed.

[0895] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0896] In this invention, the server includes means for receiving feedback from a user in real time and recognizing emotions, means for transmitting the recognized emotion information and the feedback content as data, means for saving the received feedback in a database, means for periodically updating the saved data and analyzing it using a generative AI model, means for saving the analysis results as structured data, means for generating suggestions based on the analysis results, and means for generating automatic responses in response to user inquiries, thereby enabling prompt and appropriate suggestions and responses that take the user's emotions into consideration.

[0897] "Feedback" refers to information such as opinions, problem reports, and requests provided by users.

[0898] "Emotion recognition" is the process of analyzing a user's input text and identifying the emotions contained within it.

[0899] "Emotion information" is information about emotions (e.g., anger, confusion, joy, etc.) identified from the analyzed feedback.

[0900] A "database" is a system for storing collected feedback and analysis results in a structured format.

[0901] A "generative AI model" is an artificial intelligence technology that generates appropriate suggestions and responses based on user feedback and inquiries.

[0902] "Structured data" is data that has a specific format or structure and can be efficiently stored and managed in a database.

[0903] "Suggestions" are specific instructions for action or solutions provided to the user based on the analysis results and emotional information.

[0904] An "automated response" is an automatically generated answer to a user's inquiry, created by a generative AI model.

[0905] "Analysis" is the process of examining the collected feedback in detail and extracting and evaluating problems and requests.

[0906] "Real-time" refers to the timeline in which user feedback and inquiries are processed and responded to immediately after they are entered.

[0907] This invention relates to a system that effectively collects and analyzes feedback and inquiries from users, recognizes their emotions, and then generates appropriate suggestions and responses. This system is characterized by a combination of the processing flow and emotion engine described below.

[0908] This system is primarily composed of a server and a user device. Specific hardware features include a high-performance cloud server for the server and a PC or smartphone for the user device. The software uses an emotion engine (e.g., Azure Cognitive Services or IBM Watson) and a generative AI model (e.g., OpenAI's GPT-3).

[0909] Feedback collection and emotion recognition

[0910] Users use their devices to input their problems and feedback through the chatbot. For example, a user might type, "My app keeps crashing. It's really frustrating."

[0911] The device receives this user feedback in real time and uses an emotion engine to recognize the user's emotions. The device then calls a text analysis API to identify the emotion "anger" from the input text.

[0912] The device sends the feedback content and the recognized emotion information to the server as data. Specifically, the feedback content "frequent crashes" and the emotion "anger" are sent to the server in JSON format.

[0913] Feedback storage and analysis

[0914] The server stores the received feedback in a dedicated feedback database (e.g. MySQL or MongoDB). The server adds a new entry to the feedback database and saves the data.

[0915] The server uses a job scheduler (e.g., a Cron job) to periodically retrieve new feedback data from the database and analyze it using the generative AI model. This allows the server to retrieve and analyze new feedback data every hour.

[0916] Saving analysis results and generating proposals

[0917] The server stores the analyzed feedback results as structured data. The analysis results received from the generative AI model are stored in an error log database in JSON format.

[0918] The server uses the emotion engine to request a generative AI model to make a suggestion based on the user's emotion. The server provides the emotion information "anger" to the generative AI model, which then generates a suggestion: "Procedures for rapid log collection to identify the cause of the crash."

[0919] Proposal review and notification

[0920] The server reviews the generated proposals, selects the most appropriate proposal, adds the proposals to a list, and selects the best proposal either manually or through an automated process.

[0921] The server saves the selected suggestion in a database and notifies the user if necessary. The server saves the selected suggestion in a "suggestion list" and calls the notification API to send a message to the user.

[0922] Receiving and responding to inquiries

[0923] A user submits a query using a support form or chatbot. For example, they type, "I want to reset my password. I'm having a really hard time."

[0924] The device sends this inquiry to the server. The device sends the inquiry "Password reset" and the emotion "Confused" in JSON format to the server.

[0925] The server receives the inquiry via the emotion engine and sends it to the generative AI model, which then references the FAQ database and generates "password reset instructions" in a "friendly and polite" tone.

[0926] The server sends the generated response to the terminal and returns it to the user. It also sends the generated "password reset procedure" to the terminal and displays on the user's screen, "Don't worry, you can reset your password by following the steps."

[0927] Prompt Sentence Examples

[0928] "Please explain how the system responds when users give feedback that the app crashes too frequently."

[0929] "Could you please elaborate on how the system responds when a user is having trouble resetting their password?"

[0930] In this way, it is possible to respond to user feedback and inquiries quickly and appropriately according to their emotions, and this system is expected to significantly improve the user experience.

[0931] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0932] Step 1:

[0933] A user enters feedback using a chatbot.

[0934] Specific operation: The user opens the chatbot screen on a PC or smartphone and enters their problem or feedback. For example, they enter text such as, "The app keeps crashing. It's really frustrating."

[0935] Input: Text data entered by the user.

[0936] Output: Raw feedback data received on the user's device.

[0937] Step 2:

[0938] The device receives feedback in real time and recognizes emotions using an emotion engine.

[0939] Specific operation: The terminal sends the input text data to a text analysis API (e.g., an emotion engine) to analyze the emotion. The emotion engine identifies emotion information (e.g., "anger") from the text.

[0940] Input: Feedback text from the user.

[0941] Output: Identified emotion information (e.g., "anger").

[0942] Step 3:

[0943] The device transmits the feedback content and emotional information to the server as data.

[0944] Specific operation: The device converts the feedback content "frequent crashes" and emotional information "anger" into JSON format and sends it to the server.

[0945] Input: Feedback text and accompanying sentiment information.

[0946] Output: The JSON data sent to the server.

[0947] Step 4:

[0948] The server stores the received feedback in a feedback database.

[0949] Specific behavior: The server extracts the received JSON data, creates a new entry in the database, and saves it.

[0950] Input: JSON data sent from the terminal.

[0951] Output: A new feedback entry in the database.

[0952] Step 5:

[0953] The server periodically collects feedback data and analyzes it using a generative AI model.

[0954] How it works: The server uses a job scheduler (e.g., a Cron job) to retrieve new feedback from the database every hour, and sends it to the generative AI model for analysis. The generative AI model then analyzes the feedback in detail to identify problems and requests.

[0955] Input: New feedback data in the database.

[0956] Output: Analysis results from the generative AI model.

[0957] Step 6:

[0958] The server stores the analysis results as structured data.

[0959] Specific operation: The server stores the analysis results received from the generative AI model in JSON format in the error log database.

[0960] Input: Analysis results from a generative AI model.

[0961] Output: Analysis results stored as structured data.

[0962] Step 7:

[0963] The server utilizes an emotion engine to generate suggestions according to the user's emotions.

[0964] Specific operation: The server provides the emotional information "anger" to the generative AI model, and based on that, generates a suggestion for "quick log collection procedures to identify the cause of the crash."

[0965] Input: User emotion information and analysis results.

[0966] Output: Sentiment-based suggestions.

[0967] Step 8:

[0968] The server reviews the generated proposals and selects the most appropriate one.

[0969] What happens: The server adds the generated suggestions to a list and then selects the best suggestion either manually or through an automated process.

[0970] Input: Multiple proposals from a generative AI model.

[0971] Output: The selected best proposal.

[0972] Step 9:

[0973] The server stores the selected suggestions in a database and notifies the user if necessary.

[0974] Specific behavior: The server saves the selected suggestion in a "suggestion list" and calls the notification API to send a message to the user.

[0975] Input: Selected suggestion.

[0976] Output: Suggestions stored in database and notification to user.

[0977] Step 10:

[0978] A user submits a query using a support form or chatbot.

[0979] Specific action: For example, type "I want to reset my password. I'm having a really hard time."

[0980] Input: User query text.

[0981] Output: The raw query data received at the terminal.

[0982] Step 11:

[0983] The terminal transmits the inquiry to the server.

[0984] Specific operation: The device sends the inquiry "Password reset" and emotional information "Confused" in JSON format to the server.

[0985] Input: User inquiry and emotional information.

[0986] Output: The JSON data sent to the server.

[0987] Step 12:

[0988] The server receives the query via the emotion engine and sends it to the generative AI model.

[0989] Specific operation: The server analyzes the content through the emotion engine, sends the query content to the generative AI model, and generates a response.

[0990] Input: JSON data sent from the terminal.

[0991] Output: Response generated by the generative AI model.

[0992] Step 13:

[0993] A generative AI model generates responses based on past inquiry data and FAQs, while an emotion engine adjusts the appropriate tone.

[0994] Specific operation: The generative AI model refers to a database of FAQs and creates "password reset instructions" in a "friendly and polite" tone.

[0995] Input: Past inquiry data and current inquiry details.

[0996] Output: A response generated in a "friendly and polite" tone.

[0997] Step 14:

[0998] The server sends the generated response to the terminal and sends it back to the user.

[0999] Specific operation: The generated response content is sent to the terminal in JSON format, and the terminal displays "Don't worry, you can reset your password by following the steps" on the chat screen.

[1000] Input: The response from the generative AI model.

[1001] Output: The response message that is displayed on the user's terminal.

[1002] (Application example 2)

[1003] 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."

[1004] Conventional feedback collection and analysis systems do not adequately consider the emotional information in the feedback provided by users, resulting in the problem of not being able to provide appropriate suggestions or responses based on the user's actual emotional state. Furthermore, while there is a demand for fast, emotionally sensitive responses to user inquiries, there is currently no system that can adequately meet this demand.

[1005] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting feedback from users, means for analyzing the collected feedback to extract problems and requests and recognize the user's emotions, means for generating suggestions based on the extracted information and the recognized emotions, and means for automatically generating responses to inquiries from users. This makes it possible to analyze and suggest feedback based on the user's emotions, and to respond to user inquiries quickly and with consideration for the user's emotions.

[1006] "Means for collecting user feedback" refers to a device or process for collecting information such as opinions, impressions, and problems that users provide to the system.

[1007] "Means for analyzing collected feedback, extracting problems and requests, and recognizing user emotions" refers to a device or process for processing collected feedback data, analyzing user emotions, and identifying problems and requests contained in the feedback.

[1008] "Means for generating suggestions based on extracted information and recognized emotions" refers to a device or process that uses the information obtained through the analysis and the user's emotional information to generate appropriate suggestions or solutions for the user.

[1009] The "means for automatically generating a response to a user's inquiry" refers to a device or process for automatically creating and providing a response to the content of a user's inquiry.

[1010] "Means for storing collected feedback in a database" refers to a device or process for storing collected feedback data in a database for easy later access.

[1011] "Means for storing structured data including emotional information of the analyzed feedback data" refers to a device or process for structuring the feedback data including the emotional information obtained by the analysis and storing it in a database.

[1012] "Means for a generative AI model to analyze based on emotions and generate appropriate suggestions or responses based on prompts" refers to a device or process that allows a generative AI model to analyze based on a user's emotional information and generate appropriate suggestions or responses based on specific instructions (prompts).

[1013] In this invention, the configuration and operation for realizing a system that effectively collects and analyzes user feedback and makes appropriate suggestions and responses based on the user's emotional information will be described below.

[1014] 1. Collecting User Feedback

[1015] Users submit feedback using a smartphone application, which is provided as text input and includes, for example, "I didn't enjoy the movie that was recently released. I'm a little annoyed. Is there a more exciting movie out there?"

[1016] 2. Emotion recognition

[1017] The device analyzes the collected feedback in real time using a natural language processing library (e.g., spaCy) and an emotion recognition engine (e.g., an emotion analysis tool using an NLP model), thereby identifying emotions such as "irritation" from the user's feedback.

[1018] 3. Data storage

[1019] The device sends the feedback data along with the emotion information recognized by the device to the server, which then stores it in a database (e.g., MongoDB), where the feedback and associated emotion information are stored as structured data.

[1020] 4. Analysis and proposal generation

[1021] The server periodically retrieves feedback data from the database and analyzes it using a generative AI model (e.g., GPT-4). Based on the information and emotional information extracted through the analysis, the generative AI model creates and executes prompts to generate appropriate suggestions and solutions.

[1022] 5. Notice to Users

[1023] The generated suggestions and responses are sent to the user's terminal by the server, and the user receives them through the application. For example, in response to feedback such as "The recent movie was not interesting," a suggestion such as "Suggestion: Please check out the following for more exciting movies" may be made.

[1024] Specifically, this includes the following steps:

[1025] The user enters feedback such as, "The movie that was recently released wasn't interesting. I'm a little annoyed. Are there any more exciting movies?"

[1026] The device recognizes the emotion as "irritation" and sends feedback to the server.

[1027] The server stores the feedback and emotional information in a database, and the generative AI model generates appropriate suggestions.

[1028] The suggestion is notified to the user as "Suggestion: Check out the following for more exciting movies."

[1029] Hardware and software used:

[1030] Smartphone (Android, iOS)

[1031] Natural language processing library (spaCy)

[1032] Emotion recognition engine (NLP model)

[1033] Database (MongoDB)

[1034] Generative AI model (GPT-4)

[1035] This allows for analysis and suggestion of feedback based on the user's emotions, enabling fast and emotionally sensitive responses to queries.

[1036] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1037] Step 1:

[1038] The user inputs feedback into the smartphone application. For example, the input might be, "The movie that was recently released wasn't interesting. I'm a little annoyed. Is there a more exciting movie?" The input text data is sent to the device.

[1039] Step 2:

[1040] The device analyzes the collected feedback text using a natural language processing library (e.g., spaCy) and an emotion recognition engine (e.g., an emotion analysis tool using an NLP model). It receives the feedback text as input and identifies the emotion as "irritation" from the content of the text.

[1041] Step 3:

[1042] The device sends the analyzed emotion information and feedback data to the server, which stores the received feedback data and emotion information in a database (e.g., MongoDB). The data is stored in a structured format.

[1043] Step 4:

[1044] The server reads new feedback data from the database according to a regular schedule and analyzes it using a generative AI model (e.g., GPT-4). The generative AI model uses the feedback text and emotional information as input, and generates necessary information and suggestions based on that. For example, analysis is performed based on a prompt sentence corresponding to the emotion "irritation."

[1045] Step 5:

[1046] The generative AI model outputs suggestions and solutions, which are then reviewed by the server, which selects the most appropriate suggestion and makes adjustments as needed. The selected suggestion or solution is then stored as structured data.

[1047] Step 6:

[1048] The server notifies the generated suggestion to the user's device. The device receives the suggestion and displays it to the user. For example, "Suggestion: Check out the following for more exciting movies."

[1049] Step 7:

[1050] When a user submits a new inquiry, the inquiry is sent to the server in a similar manner and analyzed by the emotion recognition and generative AI model. An appropriate response is then generated and notified to the user. For example, if the issue is not resolved, a response such as "Don't worry, we'll contact our support team" is displayed.

[1051] As a result, a system is constructed that can provide appropriate suggestions and responses based on emotions in response to user feedback and inquiries.

[1052] 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.

[1053] 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.

[1054] 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.

[1055] [Third embodiment]

[1056] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1057] 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.

[1058] 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).

[1059] 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.

[1060] 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.

[1061] 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).

[1062] 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.

[1063] 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.

[1064] 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.

[1065] 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.

[1066] 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.

[1067] 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."

[1068] The present invention relates to a system that effectively collects and analyzes user feedback, generates proposals based on the collected feedback, and provides prompt customer support. This system has the following processing flow:

[1069] System configuration and operation

[1070] 1. Gathering Feedback:

[1071] Users enter their issues and feedback through the chatbot.

[1072] Example: User types "My app crashes frequently."

[1073] The device receives user feedback in real time and transmits the data to the server.

[1074] Example: The device sends feedback to the server saying "frequent crashes."

[1075] 2. Save your feedback:

[1076] The server stores the received feedback in a dedicated feedback database.

[1077] Example: Add an entry to the feedback database saying "frequent crashes."

[1078] 3. Feedback analysis:

[1079] The server periodically retrieves new feedback data from the database.

[1080] Example: Schedule a job to retrieve new feedback data every hour.

[1081] The generative AI model uses text analysis algorithms to extract issues and requests from within the feedback.

[1082] Example: A generative AI model extracts keywords such as "frequent crashes" and "after update."

[1083] The server stores the analysis results as structured data in an error log or a user suggestion list.

[1084] Example: Record the extracted keyword "frequent crashes" in the error log.

[1085] 4. Proposal generation:

[1086] The server uses the saved analysis results to input data based on the user's needs into the generative AI model.

[1087] Example: The analysis results "frequent crashes" and "after update" are input into the generative AI model.

[1088] The generative AI model generates suggestions using analysis results, past data, or inference algorithms.

[1089] For example, generating suggestions such as "Optimize for performance" and "Steps to check logs."

[1090] The server reviews the generated proposals and selects the most appropriate one.

[1091] Example: Select "Log collection procedures to identify the cause of a crash" from the suggestions.

[1092] The server stores the selected suggestions in a database and notifies the user if necessary.

[1093] Example: Add the suggestion to the "Suggestion List" and notify relevant users.

[1094] 5. Response to inquiries:

[1095] A user submits a query using a chatbot or support form.

[1096] Example: User types "I want to reset my password."

[1097] The terminal transmits the inquiry to the server.

[1098] Example: Send the query "Password reset" to the server.

[1099] The server receives the query and sends it to the generative AI model.

[1100] Example: Input the inquiry "Password reset" into the generative AI model.

[1101] The generative AI model generates appropriate responses based on past inquiry data and FAQs.

[1102] Example: A generative AI model generates a response containing "password reset instructions."

[1103] The server sends the generated response to the terminal and sends it back to the user.

[1104] Example: The generated "password reset procedure" is sent to the terminal and displayed on the user's screen.

[1105] This allows for quick and accurate responses to user feedback and inquiries. In particular, the system aims to improve user experience by automating all processes, from feedback collection and analysis to proposal generation and customer support. As a specific example, if a user provides feedback that "the app crashes frequently," the system can collect and analyze that feedback and suggest log collection procedures to identify the cause of the crashes. This allows for quick resolution of user problems and increased satisfaction.

[1106] The processing flow will be explained below.

[1107] Step 1:

[1108] Users enter their issues and feedback through the chatbot.

[1109] Example: User types "The app crashes frequently."

[1110] Step 2:

[1111] The device receives user feedback in real time and transmits the data to the server.

[1112] Example: The device packets the feedback content as "frequent crashes" and sends it to the server.

[1113] Step 3:

[1114] The server stores the received feedback in a dedicated feedback database.

[1115] Example: Add an entry to your feedback database saying "frequent crashes."

[1116] Step 4:

[1117] The server periodically retrieves new feedback data from the database.

[1118] Example: Schedule a job to retrieve new feedback data every hour.

[1119] Step 5:

[1120] The generative AI model uses text analysis algorithms to extract issues and requests from within the feedback.

[1121] Example: A generative AI model extracts keywords such as "frequent crashes" and "after update."

[1122] Step 6:

[1123] The server stores the analysis results as structured data in an error log or a user suggestion list.

[1124] Example: Record the extracted keyword "frequent crashes" in the error log.

[1125] Step 7:

[1126] The server uses the saved analysis results to input data based on the user's needs into the generative AI model.

[1127] Example: The analysis results "frequent crashes" and "after update" are input into the generation AI model.

[1128] Step 8:

[1129] The generative AI model generates suggestions using analysis results, past data, or inference algorithms.

[1130] Example: A generative AI model generates suggestions such as "optimizations for improving performance" and "procedures for checking logs."

[1131] Step 9:

[1132] The server reviews the generated proposals and selects the most appropriate one.

[1133] Example: Select "Log collection procedures to identify the cause of a crash" from the suggestions.

[1134] Step 10:

[1135] The server stores the selected suggestions in a database and notifies the user if necessary.

[1136] Example: Add the suggestion to the "Suggestion List" and notify relevant users.

[1137] Step 11:

[1138] A user submits a query using a chatbot or support form.

[1139] Example: User types "I want to reset my password."

[1140] Step 12:

[1141] The terminal transmits the inquiry to the server.

[1142] Example: Send the inquiry "Password reset" to the server.

[1143] Step 13:

[1144] The server receives the query and sends it to the generative AI model.

[1145] Example: Input the inquiry "Password reset" into the generation AI model.

[1146] Step 14:

[1147] The generative AI model generates appropriate responses based on past inquiry data and FAQs.

[1148] Example: A generative AI model generates a response that includes "password reset instructions."

[1149] Step 15:

[1150] The server sends the generated response to the terminal and sends it back to the user.

[1151] Example: The generated "password reset procedure" is sent to the terminal and displayed on the user's screen.

[1152] Example 1

[1153] 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."

[1154] Conventional feedback collection systems have faced challenges in providing quick and accurate responses to user feedback and inquiries. Specifically, because feedback processing is done manually, it takes time to respond, resulting in a poor user experience. In addition, the analysis of feedback and the generation of suggestions are not automated, making it difficult to provide consistent responses.

[1155] 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.

[1156] In this invention, the server includes means for collecting feedback from users, means for transmitting the collected feedback to the server in real time, means for storing the collected feedback in a database, means for periodically retrieving the stored feedback, means for inputting the feedback retrieved from the database into a generative AI model for analysis, means for storing the results of the analyzed feedback as structured data, means for generating proposals based on the analysis results, means for selecting the generated proposals and notifying the user as necessary, and means for generating appropriate responses to user inquiries. This enables quick and accurate responses to user feedback and inquiries. Specifically, automating all processes from collecting feedback to analyzing it, generating proposals, and responding to inquiries can improve the user experience.

[1157] "User" means an individual or organization that uses the system to provide feedback or inquiries.

[1158] "Feedback" refers to information such as opinions, problems, and requests that users provide regarding systems and services.

[1159] A "terminal" is a hardware device that a user uses to enter feedback and queries and to communicate with a server.

[1160] "Server" is a central processing system that receives feedback and queries, analyzes, stores, generates suggestions, and generates responses.

[1161] A "chatbot" is an automated response system that interacts with users and collects feedback and inquiries.

[1162] A "database" is an information management system that systematically stores collected data such as feedback, analysis results, and proposals.

[1163] A "generative AI model" is a model that includes artificial intelligence algorithms to analyze user feedback and inquiries and generate appropriate suggestions and responses.

[1164] "Analysis" is the process of using a generative AI model to extract problems and requests from feedback and inquiries and organize them as structured data.

[1165] "Proposals" are solutions or improvement ideas generated by the generative AI model based on the analysis results.

[1166] An "inquiry" is a question or request that a user makes to a system or service.

[1167] A "response" is an answer or solution that a generative AI model or server provides to a user's query.

[1168] A "prompt sentence" is an input sentence given to a generative AI model that contains instructions for performing a specific analysis or generation process.

[1169] "Structured data" is data that has been systematically organized from analysis results and converted into a format that can be stored in a database.

[1170] This invention provides a system that effectively collects and analyzes user feedback, generates proposals based on the results, and provides prompt customer support. This system is mainly composed of users, terminals, a server, and a generative AI model.

[1171] System Components

[1172] User

[1173] A user is an individual or organization that utilizes the system to submit feedback or inquiries. Users use the chatbot interface to input feedback such as problems or requests. For example, a user may report a problem to the system by inputting "my app crashes frequently."

[1174] Terminal

[1175] The terminal is a device through which the user can input feedback and inquiries and communicate with the server. When the user inputs feedback into the chatbot interface, the terminal sends the feedback to the server in real time. For example, the terminal sends feedback such as "frequent crashes" to the server.

[1176] server

[1177] The server is responsible for the core processing of this system. The server has the following specific functions:

[1178] 1. Feedback storage: The feedback submitted by the user is stored in a database, such as Amazon RDS or Google Cloud SQL.

[1179] 2. Feedback Analysis: Feedback data is input into a generative AI model for analysis. Text analysis algorithms such as OpenAI GPT-4 and BERT are used for the analysis. For example, keywords such as "frequent crashes" and "after an update" are extracted from the feedback.

[1180] 3. Saving the analysis results: Saving the analysis results as structured data in an error log or a user suggestion list, using database INSERT and UPDATE queries.

[1181] 4. Proposal Generation: Based on the analysis results, appropriate suggestions are generated using a generative AI model. The most appropriate suggestion is selected from the generated suggestions and notified to the user as needed. For example, suggestions such as "optimization for performance improvement" or "log verification procedures" are generated.

[1182] Generative AI Models

[1183] A generative AI model is a model that includes artificial intelligence algorithms to analyze user feedback and inquiries and generate appropriate suggestions and responses. Generative AI models require powerful text generation capabilities for natural language processing. Specifically, the following prompt sentences are used:

[1184] User feedback: "The app crashes frequently"

[1185] Prompt the generative AI model: "Based on user feedback, explain how you identified the cause of frequent crashes."

[1186] Generated suggestion: "To help us determine why the app is crashing, please collect logs by following these steps..."

[1187] This system allows for quick and accurate responses to user feedback and inquiries, and by automating all processes, it improves the user experience.

[1188] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1189] Step 1:

[1190] User provides feedback through the chatbot

[1191] Input: The user enters text about their problem or request (e.g., "My app keeps crashing") into the chatbot.

[1192] Specific behavior: A user accesses the chatbot, enters feedback in the input field, and then presses the submit button.

[1193] Output: The entered feedback text.

[1194] Step 2:

[1195] The device sends feedback to the server in real time.

[1196] Input: The feedback text entered by the user.

[1197] Specific behavior: Calls the chatbot API and generates an HTTP POST request to send the feedback text to the server.

[1198] Output: Feedback data sent to the server.

[1199] Step 3:

[1200] The server stores the feedback in a database

[1201] Input: Feedback data sent to the server.

[1202] Specific behavior: Executes a database INSERT query to store the feedback data in a database (e.g., Amazon RDS or Google Cloud SQL).

[1203] Output: Feedback entries stored in a database.

[1204] Step 4:

[1205] The server periodically retrieves new feedback data.

[1206] Input: Feedback data stored in the database.

[1207] What it does: Schedule a cron job to periodically (e.g., hourly) run a SELECT query to retrieve new feedback data.

[1208] Output: The new feedback data retrieved by the server.

[1209] Step 5:

[1210] Generative AI models analyze feedback

[1211] Input: New feedback data retrieved by the server.

[1212] Specific operation: The feedback data is input into a generative AI model (e.g., OpenAI GPT-4), and text analysis is performed to extract problems and requests.

[1213] Prompt: "Based on user feedback, explain how you identify the cause of frequent crashes."

[1214] Output: Analyzed keywords and issues (e.g. "frequent crashes", "after update").

[1215] Step 6:

[1216] The server stores the analysis results as structured data.

[1217] Input: Parsed keywords and issues.

[1218] What it does: Executes an INSERT or UPDATE query in the database and saves the parsed results as structured data in an error log and a user suggestions list.

[1219] Output: Analysis result entries stored in a database.

[1220] Step 7:

[1221] The server generates suggestions based on the generative AI model

[1222] Input: Structured analysis result data.

[1223] What it does: Formats the analysis results and feeds them into a generative AI model to generate appropriate recommendations.

[1224] Prompt: "Based on your analysis, please explain the steps you would take to identify the cause of the frequent crashes."

[1225] Output: Generated suggestions (e.g. "Optimize for performance", "Steps to check logs").

[1226] Step 8:

[1227] The server selects the generated proposal and notifies the user if necessary.

[1228] Input: The generated proposals.

[1229] What it does: Uses an automated rating algorithm to select the most appropriate suggestion, adds it to the suggestions list, and notifies the user if necessary using the notification API.

[1230] Output: Selected proposal and notification to user.

[1231] Step 9:

[1232] A user contacts us using a chatbot or support form

[1233] Input: User query text (e.g. "I would like to reset my password").

[1234] Specific action: A user enters and submits an inquiry through a chatbot or support form.

[1235] Output: The input query text.

[1236] Step 10:

[1237] The device sends the inquiry to the server

[1238] Input: The query text entered by the user.

[1239] Specific behavior: Uses the chatbot API to generate an HTTP POST request that sends the inquiry to the server.

[1240] Output: The query data sent to the server.

[1241] Step 11:

[1242] The server sends the query to the generative AI model

[1243] Input: The query data sent to the server.

[1244] Specific operation: Call the API of the generative AI model and input the inquiry data.

[1245] Output: The inquiry data fed into the generative AI model.

[1246] Step 12:

[1247] Generative AI models generate appropriate responses

[1248] Input: The inquiry data fed into the generative AI model.

[1249] Specific behavior: Uses the model's inference engine to generate appropriate responses based on past inquiry data and FAQs.

[1250] Prompt: "Please explain the password reset procedure."

[1251] Output: The generated response (e.g., "Password reset instructions").

[1252] Step 13:

[1253] The server generates a response and sends it back to the user.

[1254] Input: The generated response.

[1255] What it does: Uses the chatbot's API to generate an HTTP POST request that sends the generated response to the user's device.

[1256] Output: The response data sent to the user device.

[1257] This allows for quick and accurate responses to user feedback and inquiries, and in particular, automating the entire process from collecting feedback to analyzing it, generating suggestions, and responding to inquiries can improve the user experience.

[1258] (Application example 1)

[1259] 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."

[1260] Current feedback collection and customer support systems have difficulty effectively analyzing user feedback and quickly providing suggestions based on it. Furthermore, they do not provide appropriate customer support based on the feedback in a timely manner. This problem results in a poor user experience and reduces customer satisfaction.

[1261] 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.

[1262] In this invention, the server includes means for collecting feedback from users, means for analyzing the collected feedback and extracting problems and requests, means for generating proposals based on the extracted information, means for notifying the user of the proposals based on the analyzed feedback, and means for automatically generating responses to inquiries from users. This makes it possible to consistently and effectively perform processes from collecting feedback to analyzing it, generating proposals, and providing appropriate customer support.

[1263] "User" refers to a person or entity that uses the system.

[1264] "Feedback" refers to information such as opinions, problems, and requests provided by users.

[1265] "Means for collecting" refers to the methods and devices for receiving and storing feedback from users.

[1266] "Means for analyzing" refers to a method or device for analyzing collected feedback information and identifying problems or needs.

[1267] "Extraction means" refers to a method or device for extracting from the data the problems and needs obtained through analysis.

[1268] "Means for generating proposals" refers to a method or apparatus that generates solutions or proposals based on the extracted information.

[1269] The term "means for automatically generating a response to an inquiry" refers to a method or device for automatically generating a response appropriate to the content of a user's inquiry.

[1270] "Means for notifying" refers to a method or device for notifying the user of the generated suggestions.

[1271] "Database" refers to a system for systematically storing and managing data such as feedback information and analysis results.

[1272] "Structured data" refers to data that has been organized and stored in a specific format as a result of analyzed feedback.

[1273] The present invention relates to a system for effectively collecting user feedback and providing customer support on an online shopping site. This system includes means for collecting user feedback in real time, analyzing it to identify problems and requests, generating appropriate suggestions, and notifying the users. It also includes means for automatically generating responses to user inquiries.

[1274] The system operates as follows.

[1275] 1. Gathering feedback

[1276] The user provides feedback through a smartphone app. When the user types in "I'm not satisfied with the product I recently purchased. I'd like to return it," the device receives the feedback and sends it to the server in real time.

[1277] 2. Saving your feedback

[1278] The server stores the received feedback in a database. For example, feedback such as "I'm not happy with the product I recently purchased and would like to return it" is recorded in the database.

[1279] 3. Feedback Analysis

[1280] The server periodically retrieves new feedback data from the database and performs text analysis using a generative AI model to extract problems and requests such as "dissatisfaction" and "returns" from the feedback.

[1281] Hardware / Software used

[1282] Server: A server that stores and analyzes data

[1283] Generative AI models: used to perform text analysis

[1284] 4. Proposal Generation

[1285] The server generates a suggestion based on the parsed information, for example, "We're sorry for your inconvenience. Please see below for return procedures." and notifies the user.

[1286] 5. Response to inquiries

[1287] If a user makes a separate inquiry, the server uses the generative AI model to generate an appropriate response based on past data and FAQs. For example, in response to the inquiry, "How do I process a return?", the server generates a response saying, "Please follow the steps below to process a return," and notifies the user.

[1288] Hardware / Software used

[1289] Server: A system for processing query data.

[1290] Generative AI models: used to generate appropriate responses

[1291] Specific examples

[1292] User feedback: "My recently purchased smartphone runs out of battery quickly."

[1293] Analysis result: Battery-related issues

[1294] Suggestion: "To save battery, we recommend lowering your screen brightness and closing apps you're not using."

[1295] Inquiry prompt: "How do I process a return?"

[1296] This system will improve the user experience on online shopping sites and increase customer satisfaction.

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

[1298] Step 1:

[1299] The user enters feedback through a smartphone app. For example, the user provides feedback such as, "I'm not satisfied with the product I recently purchased. I'd like to return it." This becomes input data.

[1300] Step 2:

[1301] The terminal obtains the input feedback and transmits it to the server in real time, where the input data is the raw feedback information and the output data is the feedback information transmitted to the server.

[1302] Step 3:

[1303] The server stores the received feedback information in a database, where the input data is the feedback information sent from the terminal and the output data is the feedback entry stored in the database.

[1304] Step 4:

[1305] The server periodically retrieves new feedback data from the database, where the input data is the feedback information in the database and the output data is the feedback data for analysis.

[1306] Step 5:

[1307] The server uses a generative AI model to analyze the feedback data and extract problems and requests. The input data is the feedback data, and the output data is the extracted problems and requests. Specifically, it uses a text analysis algorithm to identify keywords in the feedback.

[1308] Step 6:

[1309] The server uses a generative AI model to generate a proposal based on the extracted information. The input data are the extracted problems and requests, and the output data is the generated proposal. For example, a proposal might be generated that says, "We apologize for the inconvenience. Please see below for the return procedure."

[1310] Step 7:

[1311] The server notifies the user of the generated proposal. The input data is the generated proposal, and the output data is the notification sent to the user. The user receives the proposal notification through their terminal.

[1312] Step 8:

[1313] When a user makes an inquiry, for example, they input, "Please tell me how to process a return." This is the input data.

[1314] Step 9:

[1315] The terminal sends the query to the server. The input data is the user's query, and the output data is the query information sent to the server.

[1316] Step 10:

[1317] The server uses the generative AI model to generate an automated response to the inquiry. The input data is the inquiry information, and the output data is the generated response. For example, it generates a response such as, "Please follow the steps below to process your return."

[1318] Step 11:

[1319] The server sends the generated response to the user. The input data is the generated response, and the output data is the reply sent to the user. The user receives the reply through their terminal.

[1320] 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.

[1321] This invention relates to a system that effectively collects and analyzes feedback and inquiries from users, recognizes their emotions, and then generates appropriate suggestions and responses. This system is characterized by a combination of the processing flow and emotion engine described below.

[1322] System configuration and operation

[1323] 1. Feedback collection and emotion recognition:

[1324] Users enter their issues and feedback through the chatbot.

[1325] Example: User types, "My app crashes so often. It's really frustrating."

[1326] The device receives user feedback in real time and recognizes the user's emotions using an emotion engine.

[1327] The emotion engine identifies the emotion "anger" from the user's input text.

[1328] The device transmits the feedback content and the recognized emotion information to the server as data.

[1329] Example: Send feedback to the server as "frequent crashes" or "angry."

[1330] 2. Feedback storage and analysis:

[1331] The server stores the received feedback in a dedicated feedback database.

[1332] Example: Adding entries to the feedback database for "frequent crashes" and "angry."

[1333] The server periodically retrieves new feedback data from the database and analyzes it using the generative AI model.

[1334] Example: Schedule a job to retrieve new feedback data every hour, and the generative AI model will analyze and extract "frequent crashes" and "anger."

[1335] 3. Save the analysis results and generate suggestions:

[1336] The server stores the results of the parsed feedback as structured data.

[1337] Example: Save the extracted keywords "frequent crashes" and "anger" in the error log.

[1338] The server uses an emotion engine to request a generative AI model to make suggestions based on the user's emotions.

[1339] The emotion engine provides the emotion information of "anger" to the generative AI model, which then generates suggestions based on that information.

[1340] 4. Proposal Review and Notification:

[1341] The server reviews the generated proposals and selects the most appropriate one.

[1342] Example: Select "Quick log collection procedure to identify the cause of a crash" from the suggestions.

[1343] The server stores the selected suggestions in a database and notifies the user if necessary.

[1344] Example: Add the selected suggestion to the "suggestion list" and notify relevant users.

[1345] 5. Receiving and responding to inquiries:

[1346] A user submits a query using a chatbot or support form.

[1347] Example: User types, "I want to reset my password. I'm having so much trouble."

[1348] The terminal transmits the inquiry to the server.

[1349] Example: Send the inquiry "Password reset" and "Confused" to the server.

[1350] The server receives the query content through the emotion engine and sends it to the generative AI model.

[1351] Example: The inquiry content "Password reset" and "Confused" are input into the generative AI model.

[1352] A generative AI model generates responses based on past inquiry data and FAQs, while an emotion engine adjusts the appropriate tone.

[1353] Example: The emotion engine generates a "kind and polite" response to the "confused" emotion.

[1354] The server sends the generated response to the terminal and sends it back to the user.

[1355] Example: The generated "password reset procedure" is sent to the terminal and the message "Don't worry, you can reset your password by following the steps" is displayed on the user screen.

[1356] In this way, it is possible to respond to user feedback and inquiries quickly and appropriately according to their emotions. In particular, by combining an emotion engine, it is possible to recognize the user's emotions and adjust suggestions and responses based on those emotions, further improving the user experience. As a specific example, if a user gives feedback such as "The app crashes frequently. It's really frustrating," the system can collect and analyze that feedback, recognize the emotion of "anger," and propose a quick solution to identify the cause of the crash. This allows the user's problems to be resolved quickly and increases their emotional satisfaction.

[1357] The processing flow will be explained below.

[1358] Step 1:

[1359] Users enter their issues and feedback through the chatbot.

[1360] Example: User types, "My app crashes so often. It's really frustrating."

[1361] Step 2:

[1362] The device receives user feedback in real time and recognizes the user's emotions using an emotion engine.

[1363] The emotion engine identifies the emotion "anger" from the user's input text.

[1364] Step 3:

[1365] The device transmits the feedback content and the recognized emotion information to the server as data.

[1366] Example: Send feedback to the server as "frequent crashes" or "angry."

[1367] Step 4:

[1368] The server stores the received feedback in a dedicated feedback database.

[1369] Example: Adding entries to the feedback database for "frequent crashes" and "angry."

[1370] Step 5:

[1371] The server periodically retrieves new feedback data from the database.

[1372] Example: Schedule a job to retrieve new feedback data every hour.

[1373] Step 6:

[1374] The generative AI model uses text analysis algorithms to extract issues and requests from within the feedback.

[1375] Example: A generative AI model extracts keywords such as "frequent crashes," "after update," and "anger."

[1376] Step 7:

[1377] The server stores the analysis results and emotional information as structured data in an error log or user suggestion list.

[1378] Example: Save the extracted keywords "frequent crashes" and "anger" in the error log.

[1379] Step 8:

[1380] The server uses the saved analysis results to input data based on the user's needs into the generative AI model.

[1381] Example: The analysis results "frequent crashes," "after update," and "anger" are input into the generative AI model.

[1382] Step 9:

[1383] The generative AI model generates suggestions using analysis results, past data, or inference algorithms, where an emotion engine takes into account the user's emotional information.

[1384] Example: A generative AI model generates "log collection procedures to identify the cause of a crash," and an emotion engine adds polite language to correspond to "anger."

[1385] Step 10:

[1386] The server reviews the generated proposals and selects the most appropriate one.

[1387] Example: Select "Quick log collection procedure to identify the cause of a crash" from the suggestions.

[1388] Step 11:

[1389] The server stores the selected suggestions in a database and notifies the user if necessary.

[1390] Example: Add the suggestion to the "Suggestion List" and notify relevant users.

[1391] Step 12:

[1392] A user submits a query using a chatbot or support form.

[1393] Example: User types, "I want to reset my password. I'm having so much trouble."

[1394] Step 13:

[1395] The terminal transmits the inquiry to the server.

[1396] Example: Send the inquiry "Password reset" and "Confused" to the server.

[1397] Step 14:

[1398] The server receives the query and sends it to the generative AI model.

[1399] Example: The inquiry content "Password reset" and "Confused" are input into the generative AI model.

[1400] Step 15:

[1401] A generative AI model generates appropriate responses based on past inquiry data and FAQs, while an emotion engine adjusts the appropriate tone.

[1402] Example: A generative AI model generates "password reset instructions," and an emotion engine adds a "kind and polite" response to "confusion."

[1403] Step 16:

[1404] The server sends the generated response to the terminal and sends it back to the user.

[1405] Example: The generated "password reset procedure" is sent to the terminal and the message "Don't worry, you can reset your password by following the steps" is displayed on the user screen.

[1406] Example 2

[1407] 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."

[1408] Conventional feedback collection systems have been limited to simple text analysis and quantitative data collection without considering user emotions, making it difficult to respond appropriately to the user's psychological state. As a result, they have not been able to sufficiently improve the user experience or quickly resolve problems. A new system that can solve this problem and quickly provide suggestions and responses that correspond to the user's emotions is needed.

[1409] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1410] In this invention, the server includes means for receiving feedback from a user in real time and recognizing emotions, means for transmitting the recognized emotion information and the feedback content as data, means for saving the received feedback in a database, means for periodically updating the saved data and analyzing it using a generative AI model, means for saving the analysis results as structured data, means for generating suggestions based on the analysis results, and means for generating automatic responses in response to user inquiries, thereby enabling prompt and appropriate suggestions and responses that take the user's emotions into consideration.

[1411] "Feedback" refers to information such as opinions, problem reports, and requests provided by users.

[1412] "Emotion recognition" is the process of analyzing a user's input text and identifying the emotions contained within it.

[1413] "Emotion information" is information about emotions (e.g., anger, confusion, joy, etc.) identified from the analyzed feedback.

[1414] A "database" is a system for storing collected feedback and analysis results in a structured format.

[1415] A "generative AI model" is an artificial intelligence technology that generates appropriate suggestions and responses based on user feedback and inquiries.

[1416] "Structured data" is data that has a specific format or structure and can be efficiently stored and managed in a database.

[1417] "Suggestions" are specific instructions for action or solutions provided to the user based on the analysis results and emotional information.

[1418] An "automated response" is an automatically generated answer to a user's inquiry, created by a generative AI model.

[1419] "Analysis" is the process of examining the collected feedback in detail and extracting and evaluating problems and requests.

[1420] "Real-time" refers to the timeline in which user feedback and inquiries are processed and responded to immediately after they are entered.

[1421] This invention relates to a system that effectively collects and analyzes feedback and inquiries from users, recognizes their emotions, and then generates appropriate suggestions and responses. This system is characterized by a combination of the processing flow and emotion engine described below.

[1422] This system is primarily composed of a server and a user device. Specific hardware features include a high-performance cloud server for the server and a PC or smartphone for the user device. The software uses an emotion engine (e.g., Azure Cognitive Services or IBM Watson) and a generative AI model (e.g., OpenAI's GPT-3).

[1423] Feedback collection and emotion recognition

[1424] Users use their devices to input their problems and feedback through the chatbot. For example, a user might type, "My app keeps crashing. It's really frustrating."

[1425] The device receives this user feedback in real time and uses an emotion engine to recognize the user's emotions. The device then calls a text analysis API to identify the emotion "anger" from the input text.

[1426] The device sends the feedback content and the recognized emotion information to the server as data. Specifically, the feedback content "frequent crashes" and the emotion "anger" are sent to the server in JSON format.

[1427] Feedback storage and analysis

[1428] The server stores the received feedback in a dedicated feedback database (e.g. MySQL or MongoDB). The server adds a new entry to the feedback database and saves the data.

[1429] The server uses a job scheduler (e.g., a Cron job) to periodically retrieve new feedback data from the database and analyze it using the generative AI model. This allows the server to retrieve and analyze new feedback data every hour.

[1430] Saving analysis results and generating proposals

[1431] The server stores the analyzed feedback results as structured data. The analysis results received from the generative AI model are stored in an error log database in JSON format.

[1432] The server uses the emotion engine to request a generative AI model to make a suggestion based on the user's emotion. The server provides the emotion information "anger" to the generative AI model, which then generates a suggestion: "Procedures for rapid log collection to identify the cause of the crash."

[1433] Proposal review and notification

[1434] The server reviews the generated proposals, selects the most appropriate proposal, adds the proposals to a list, and selects the best proposal either manually or through an automated process.

[1435] The server saves the selected suggestion in a database and notifies the user if necessary. The server saves the selected suggestion in a "suggestion list" and calls the notification API to send a message to the user.

[1436] Receiving and responding to inquiries

[1437] A user submits a query using a support form or chatbot. For example, they type, "I want to reset my password. I'm having a really hard time."

[1438] The device sends this inquiry to the server. The device sends the inquiry "Password reset" and the emotion "Confused" in JSON format to the server.

[1439] The server receives the inquiry via the emotion engine and sends it to the generative AI model, which then references the FAQ database and generates "password reset instructions" in a "friendly and polite" tone.

[1440] The server sends the generated response to the terminal and returns it to the user. It also sends the generated "password reset procedure" to the terminal and displays on the user's screen, "Don't worry, you can reset your password by following the steps."

[1441] Prompt Sentence Examples

[1442] "Please explain how the system responds when users give feedback that the app crashes too frequently."

[1443] "Could you please elaborate on how the system responds when a user is having trouble resetting their password?"

[1444] In this way, it is possible to respond to user feedback and inquiries quickly and appropriately according to their emotions, and this system is expected to significantly improve the user experience.

[1445] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1446] Step 1:

[1447] A user enters feedback using a chatbot.

[1448] Specific operation: The user opens the chatbot screen on a PC or smartphone and enters their problem or feedback. For example, they enter text such as, "The app keeps crashing. It's really frustrating."

[1449] Input: Text data entered by the user.

[1450] Output: Raw feedback data received on the user's device.

[1451] Step 2:

[1452] The device receives feedback in real time and recognizes emotions using an emotion engine.

[1453] Specific operation: The terminal sends the input text data to a text analysis API (e.g., an emotion engine) to analyze the emotion. The emotion engine identifies emotion information (e.g., "anger") from the text.

[1454] Input: Feedback text from the user.

[1455] Output: Identified emotion information (e.g., "anger").

[1456] Step 3:

[1457] The device transmits the feedback content and emotional information to the server as data.

[1458] Specific operation: The device converts the feedback content "frequent crashes" and emotional information "anger" into JSON format and sends it to the server.

[1459] Input: Feedback text and accompanying sentiment information.

[1460] Output: The JSON data sent to the server.

[1461] Step 4:

[1462] The server stores the received feedback in a feedback database.

[1463] Specific behavior: The server extracts the received JSON data, creates a new entry in the database, and saves it.

[1464] Input: JSON data sent from the terminal.

[1465] Output: A new feedback entry in the database.

[1466] Step 5:

[1467] The server periodically collects feedback data and analyzes it using a generative AI model.

[1468] How it works: The server uses a job scheduler (e.g., a Cron job) to retrieve new feedback from the database every hour, and sends it to the generative AI model for analysis. The generative AI model then analyzes the feedback in detail to identify problems and requests.

[1469] Input: New feedback data in the database.

[1470] Output: Analysis results from the generative AI model.

[1471] Step 6:

[1472] The server stores the analysis results as structured data.

[1473] Specific operation: The server stores the analysis results received from the generative AI model in JSON format in the error log database.

[1474] Input: Analysis results from a generative AI model.

[1475] Output: Analysis results stored as structured data.

[1476] Step 7:

[1477] The server utilizes an emotion engine to generate suggestions according to the user's emotions.

[1478] Specific operation: The server provides the emotional information "anger" to the generative AI model, and based on that, generates a suggestion for "quick log collection procedures to identify the cause of the crash."

[1479] Input: User emotion information and analysis results.

[1480] Output: Sentiment-based suggestions.

[1481] Step 8:

[1482] The server reviews the generated proposals and selects the most appropriate one.

[1483] What happens: The server adds the generated suggestions to a list and then selects the best suggestion either manually or through an automated process.

[1484] Input: Multiple proposals from a generative AI model.

[1485] Output: The selected best proposal.

[1486] Step 9:

[1487] The server stores the selected suggestions in a database and notifies the user if necessary.

[1488] Specific behavior: The server saves the selected suggestion in a "suggestion list" and calls the notification API to send a message to the user.

[1489] Input: Selected suggestion.

[1490] Output: Suggestions stored in database and notification to user.

[1491] Step 10:

[1492] A user submits a query using a support form or chatbot.

[1493] Specific action: For example, type "I want to reset my password. I'm having a really hard time."

[1494] Input: User query text.

[1495] Output: The raw query data received at the terminal.

[1496] Step 11:

[1497] The terminal transmits the inquiry to the server.

[1498] Specific operation: The device sends the inquiry "Password reset" and emotional information "Confused" in JSON format to the server.

[1499] Input: User inquiry and emotional information.

[1500] Output: The JSON data sent to the server.

[1501] Step 12:

[1502] The server receives the query via the emotion engine and sends it to the generative AI model.

[1503] Specific operation: The server analyzes the content through the emotion engine, sends the query content to the generative AI model, and generates a response.

[1504] Input: JSON data sent from the terminal.

[1505] Output: Response generated by the generative AI model.

[1506] Step 13:

[1507] A generative AI model generates responses based on past inquiry data and FAQs, while an emotion engine adjusts the appropriate tone.

[1508] Specific operation: The generative AI model refers to a database of FAQs and creates "password reset instructions" in a "friendly and polite" tone.

[1509] Input: Past inquiry data and current inquiry details.

[1510] Output: A response generated in a "friendly and polite" tone.

[1511] Step 14:

[1512] The server sends the generated response to the terminal and sends it back to the user.

[1513] Specific operation: The generated response content is sent to the terminal in JSON format, and the terminal displays "Don't worry, you can reset your password by following the steps" on the chat screen.

[1514] Input: The response from the generative AI model.

[1515] Output: The response message that is displayed on the user's terminal.

[1516] (Application example 2)

[1517] 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."

[1518] Conventional feedback collection and analysis systems do not adequately consider the emotional information in the feedback provided by users, resulting in the problem of not being able to provide appropriate suggestions or responses based on the user's actual emotional state. Furthermore, while there is a demand for fast, emotionally sensitive responses to user inquiries, there is currently no system that can adequately meet this demand.

[1519] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting feedback from users, means for analyzing the collected feedback to extract problems and requests and recognize the user's emotions, means for generating suggestions based on the extracted information and the recognized emotions, and means for automatically generating responses to inquiries from users. This makes it possible to analyze and suggest feedback based on the user's emotions, and to respond to user inquiries quickly and with consideration for the user's emotions.

[1520] "Means for collecting user feedback" refers to a device or process for collecting information such as opinions, impressions, and problems that users provide to the system.

[1521] "Means for analyzing collected feedback, extracting problems and requests, and recognizing user emotions" refers to a device or process for processing collected feedback data, analyzing user emotions, and identifying problems and requests contained in the feedback.

[1522] "Means for generating suggestions based on extracted information and recognized emotions" refers to a device or process that uses the information obtained through the analysis and the user's emotional information to generate appropriate suggestions or solutions for the user.

[1523] The "means for automatically generating a response to a user's inquiry" refers to a device or process for automatically creating and providing a response to the content of a user's inquiry.

[1524] "Means for storing collected feedback in a database" refers to a device or process for storing collected feedback data in a database for easy later access.

[1525] "Means for storing structured data including emotional information of the analyzed feedback data" refers to a device or process for structuring the feedback data including the emotional information obtained by the analysis and storing it in a database.

[1526] "Means for a generative AI model to analyze based on emotions and generate appropriate suggestions or responses based on prompts" refers to a device or process that allows a generative AI model to analyze based on a user's emotional information and generate appropriate suggestions or responses based on specific instructions (prompts).

[1527] In this invention, the configuration and operation for realizing a system that effectively collects and analyzes user feedback and makes appropriate suggestions and responses based on the user's emotional information will be described below.

[1528] 1. Collecting User Feedback

[1529] Users submit feedback using a smartphone application, which is provided as text input and includes, for example, "I didn't enjoy the movie that was recently released. I'm a little annoyed. Is there a more exciting movie out there?"

[1530] 2. Emotion recognition

[1531] The device analyzes the collected feedback in real time using a natural language processing library (e.g., spaCy) and an emotion recognition engine (e.g., an emotion analysis tool using an NLP model), thereby identifying emotions such as "irritation" from the user's feedback.

[1532] 3. Data storage

[1533] The device sends the feedback data along with the emotion information recognized by the device to the server, which then stores it in a database (e.g., MongoDB), where the feedback and associated emotion information are stored as structured data.

[1534] 4. Analysis and proposal generation

[1535] The server periodically retrieves feedback data from the database and analyzes it using a generative AI model (e.g., GPT-4). Based on the information and emotional information extracted through the analysis, the generative AI model creates and executes prompts to generate appropriate suggestions and solutions.

[1536] 5. Notice to Users

[1537] The generated suggestions and responses are sent to the user's terminal by the server, and the user receives them through the application. For example, in response to feedback such as "The recent movie was not interesting," a suggestion such as "Suggestion: Please check out the following for more exciting movies" may be made.

[1538] Specifically, this includes the following steps:

[1539] The user enters feedback such as, "The movie that was recently released wasn't interesting. I'm a little annoyed. Are there any more exciting movies?"

[1540] The device recognizes the emotion as "irritation" and sends feedback to the server.

[1541] The server stores the feedback and emotional information in a database, and the generative AI model generates appropriate suggestions.

[1542] The suggestion is notified to the user as "Suggestion: Check out the following for more exciting movies."

[1543] Hardware and software used:

[1544] Smartphone (Android, iOS)

[1545] Natural language processing library (spaCy)

[1546] Emotion recognition engine (NLP model)

[1547] Database (MongoDB)

[1548] Generative AI model (GPT-4)

[1549] This allows for analysis and suggestion of feedback based on the user's emotions, enabling fast and emotionally sensitive responses to queries.

[1550] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1551] Step 1:

[1552] The user inputs feedback into the smartphone application. For example, the input might be, "The movie that was recently released wasn't interesting. I'm a little annoyed. Is there a more exciting movie?" The input text data is sent to the device.

[1553] Step 2:

[1554] The device analyzes the collected feedback text using a natural language processing library (e.g., spaCy) and an emotion recognition engine (e.g., an emotion analysis tool using an NLP model). It receives the feedback text as input and identifies the emotion as "irritation" from the content of the text.

[1555] Step 3:

[1556] The device sends the analyzed emotion information and feedback data to the server, which stores the received feedback data and emotion information in a database (e.g., MongoDB). The data is stored in a structured format.

[1557] Step 4:

[1558] The server reads new feedback data from the database according to a regular schedule and analyzes it using a generative AI model (e.g., GPT-4). The generative AI model uses the feedback text and emotional information as input, and generates necessary information and suggestions based on that. For example, analysis is performed based on a prompt sentence corresponding to the emotion "irritation."

[1559] Step 5:

[1560] The generative AI model outputs suggestions and solutions, which are then reviewed by the server, which selects the most appropriate suggestion and makes adjustments as needed. The selected suggestion or solution is then stored as structured data.

[1561] Step 6:

[1562] The server notifies the generated suggestion to the user's device. The device receives the suggestion and displays it to the user. For example, "Suggestion: Check out the following for more exciting movies."

[1563] Step 7:

[1564] When a user submits a new inquiry, the inquiry is sent to the server in a similar manner and analyzed by the emotion recognition and generative AI model. An appropriate response is then generated and notified to the user. For example, if the issue is not resolved, a response such as "Don't worry, we'll contact our support team" is displayed.

[1565] As a result, a system is constructed that can provide appropriate suggestions and responses based on emotions in response to user feedback and inquiries.

[1566] 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.

[1567] 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.

[1568] 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.

[1569] [Fourth embodiment]

[1570] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1571] 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.

[1572] 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).

[1573] 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.

[1574] 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.

[1575] 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).

[1576] 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.

[1577] 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.

[1578] 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.

[1579] 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.

[1580] 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.

[1581] 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.

[1582] 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."

[1583] The present invention relates to a system that effectively collects and analyzes user feedback, generates proposals based on the collected feedback, and provides prompt customer support. This system has the following processing flow:

[1584] System configuration and operation

[1585] 1. Gathering Feedback:

[1586] Users enter their issues and feedback through the chatbot.

[1587] Example: User types "My app crashes frequently."

[1588] The device receives user feedback in real time and transmits the data to the server.

[1589] Example: The device sends feedback to the server saying "frequent crashes."

[1590] 2. Save your feedback:

[1591] The server stores the received feedback in a dedicated feedback database.

[1592] Example: Add an entry to the feedback database saying "frequent crashes."

[1593] 3. Feedback analysis:

[1594] The server periodically retrieves new feedback data from the database.

[1595] Example: Schedule a job to retrieve new feedback data every hour.

[1596] The generative AI model uses text analysis algorithms to extract issues and requests from within the feedback.

[1597] Example: A generative AI model extracts keywords such as "frequent crashes" and "after update."

[1598] The server stores the analysis results as structured data in an error log or a user suggestion list.

[1599] Example: Record the extracted keyword "frequent crashes" in the error log.

[1600] 4. Proposal generation:

[1601] The server uses the saved analysis results to input data based on the user's needs into the generative AI model.

[1602] Example: The analysis results "frequent crashes" and "after update" are input into the generative AI model.

[1603] The generative AI model generates suggestions using analysis results, past data, or inference algorithms.

[1604] For example, generating suggestions such as "Optimize for performance" and "Steps to check logs."

[1605] The server reviews the generated proposals and selects the most appropriate one.

[1606] Example: Select "Log collection procedures to identify the cause of a crash" from the suggestions.

[1607] The server stores the selected suggestions in a database and notifies the user if necessary.

[1608] Example: Add the suggestion to the "Suggestion List" and notify relevant users.

[1609] 5. Response to inquiries:

[1610] A user submits a query using a chatbot or support form.

[1611] Example: User types "I want to reset my password."

[1612] The terminal transmits the inquiry to the server.

[1613] Example: Send the query "Password reset" to the server.

[1614] The server receives the query and sends it to the generative AI model.

[1615] Example: Input the inquiry "Password reset" into the generative AI model.

[1616] The generative AI model generates appropriate responses based on past inquiry data and FAQs.

[1617] Example: A generative AI model generates a response containing "password reset instructions."

[1618] The server sends the generated response to the terminal and sends it back to the user.

[1619] Example: The generated "password reset procedure" is sent to the terminal and displayed on the user's screen.

[1620] This allows for quick and accurate responses to user feedback and inquiries. In particular, the system aims to improve user experience by automating all processes, from feedback collection and analysis to proposal generation and customer support. As a specific example, if a user provides feedback that "the app crashes frequently," the system can collect and analyze that feedback and suggest log collection procedures to identify the cause of the crashes. This allows for quick resolution of user problems and increased satisfaction.

[1621] The processing flow will be explained below.

[1622] Step 1:

[1623] Users enter their issues and feedback through the chatbot.

[1624] Example: User types "The app crashes frequently."

[1625] Step 2:

[1626] The device receives user feedback in real time and transmits the data to the server.

[1627] Example: The device packets the feedback content as "frequent crashes" and sends it to the server.

[1628] Step 3:

[1629] The server stores the received feedback in a dedicated feedback database.

[1630] Example: Add an entry to your feedback database saying "frequent crashes."

[1631] Step 4:

[1632] The server periodically retrieves new feedback data from the database.

[1633] Example: Schedule a job to retrieve new feedback data every hour.

[1634] Step 5:

[1635] The generative AI model uses text analysis algorithms to extract issues and requests from within the feedback.

[1636] Example: A generative AI model extracts keywords such as "frequent crashes" and "after update."

[1637] Step 6:

[1638] The server stores the analysis results as structured data in an error log or a user suggestion list.

[1639] Example: Record the extracted keyword "frequent crashes" in the error log.

[1640] Step 7:

[1641] The server uses the saved analysis results to input data based on the user's needs into the generative AI model.

[1642] Example: The analysis results "frequent crashes" and "after update" are input into the generation AI model.

[1643] Step 8:

[1644] The generative AI model generates suggestions using analysis results, past data, or inference algorithms.

[1645] Example: A generative AI model generates suggestions such as "optimizations for improving performance" and "procedures for checking logs."

[1646] Step 9:

[1647] The server reviews the generated proposals and selects the most appropriate one.

[1648] Example: Select "Log collection procedures to identify the cause of a crash" from the suggestions.

[1649] Step 10:

[1650] The server stores the selected suggestions in a database and notifies the user if necessary.

[1651] Example: Add the suggestion to the "Suggestion List" and notify relevant users.

[1652] Step 11:

[1653] A user submits a query using a chatbot or support form.

[1654] Example: User types "I want to reset my password."

[1655] Step 12:

[1656] The terminal transmits the inquiry to the server.

[1657] Example: Send the inquiry "Password reset" to the server.

[1658] Step 13:

[1659] The server receives the query and sends it to the generative AI model.

[1660] Example: Input the inquiry "Password reset" into the generation AI model.

[1661] Step 14:

[1662] The generative AI model generates appropriate responses based on past inquiry data and FAQs.

[1663] Example: A generative AI model generates a response that includes "password reset instructions."

[1664] Step 15:

[1665] The server sends the generated response to the terminal and sends it back to the user.

[1666] Example: The generated "password reset procedure" is sent to the terminal and displayed on the user's screen.

[1667] Example 1

[1668] 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."

[1669] Conventional feedback collection systems have faced challenges in providing quick and accurate responses to user feedback and inquiries. Specifically, because feedback processing is done manually, it takes time to respond, resulting in a poor user experience. In addition, the analysis of feedback and the generation of suggestions are not automated, making it difficult to provide consistent responses.

[1670] 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.

[1671] In this invention, the server includes means for collecting feedback from users, means for transmitting the collected feedback to the server in real time, means for storing the collected feedback in a database, means for periodically retrieving the stored feedback, means for inputting the feedback retrieved from the database into a generative AI model for analysis, means for storing the results of the analyzed feedback as structured data, means for generating proposals based on the analysis results, means for selecting the generated proposals and notifying the user as necessary, and means for generating appropriate responses to user inquiries. This enables quick and accurate responses to user feedback and inquiries. Specifically, automating all processes from collecting feedback to analyzing it, generating proposals, and responding to inquiries can improve the user experience.

[1672] "User" means an individual or organization that uses the system to provide feedback or inquiries.

[1673] "Feedback" refers to information such as opinions, problems, and requests that users provide regarding systems and services.

[1674] A "terminal" is a hardware device that a user uses to enter feedback and queries and to communicate with a server.

[1675] "Server" is a central processing system that receives feedback and queries, analyzes, stores, generates suggestions, and generates responses.

[1676] A "chatbot" is an automated response system that interacts with users and collects feedback and inquiries.

[1677] A "database" is an information management system that systematically stores collected data such as feedback, analysis results, and proposals.

[1678] A "generative AI model" is a model that includes artificial intelligence algorithms to analyze user feedback and inquiries and generate appropriate suggestions and responses.

[1679] "Analysis" is the process of using a generative AI model to extract problems and requests from feedback and inquiries and organize them as structured data.

[1680] "Proposals" are solutions or improvement ideas generated by the generative AI model based on the analysis results.

[1681] An "inquiry" is a question or request that a user makes to a system or service.

[1682] A "response" is an answer or solution that a generative AI model or server provides to a user's query.

[1683] A "prompt sentence" is an input sentence given to a generative AI model that contains instructions for performing a specific analysis or generation process.

[1684] "Structured data" is data that has been systematically organized from analysis results and converted into a format that can be stored in a database.

[1685] This invention provides a system that effectively collects and analyzes user feedback, generates proposals based on the results, and provides prompt customer support. This system is mainly composed of users, terminals, a server, and a generative AI model.

[1686] System Components

[1687] User

[1688] A user is an individual or organization that utilizes the system to submit feedback or inquiries. Users use the chatbot interface to input feedback such as problems or requests. For example, a user may report a problem to the system by inputting "my app crashes frequently."

[1689] Terminal

[1690] The terminal is a device through which the user can input feedback and inquiries and communicate with the server. When the user inputs feedback into the chatbot interface, the terminal sends the feedback to the server in real time. For example, the terminal sends feedback such as "frequent crashes" to the server.

[1691] server

[1692] The server is responsible for the core processing of this system. The server has the following specific functions:

[1693] 1. Feedback storage: The feedback submitted by the user is stored in a database, such as Amazon RDS or Google Cloud SQL.

[1694] 2. Feedback Analysis: Feedback data is input into a generative AI model for analysis. Text analysis algorithms such as OpenAI GPT-4 and BERT are used for the analysis. For example, keywords such as "frequent crashes" and "after an update" are extracted from the feedback.

[1695] 3. Saving the analysis results: Saving the analysis results as structured data in an error log or a user suggestion list, using database INSERT and UPDATE queries.

[1696] 4. Proposal Generation: Based on the analysis results, appropriate suggestions are generated using a generative AI model. The most appropriate suggestion is selected from the generated suggestions and notified to the user as needed. For example, suggestions such as "optimization for performance improvement" or "log verification procedures" are generated.

[1697] Generative AI Models

[1698] A generative AI model is a model that includes artificial intelligence algorithms to analyze user feedback and inquiries and generate appropriate suggestions and responses. Generative AI models require powerful text generation capabilities for natural language processing. Specifically, the following prompt sentences are used:

[1699] User feedback: "The app crashes frequently"

[1700] Prompt the generative AI model: "Based on user feedback, explain how you identified the cause of frequent crashes."

[1701] Generated suggestion: "To help us determine why the app is crashing, please collect logs by following these steps..."

[1702] This system allows for quick and accurate responses to user feedback and inquiries, and by automating all processes, it improves the user experience.

[1703] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1704] Step 1:

[1705] User provides feedback through the chatbot

[1706] Input: The user enters text about their problem or request (e.g., "My app keeps crashing") into the chatbot.

[1707] Specific behavior: A user accesses the chatbot, enters feedback in the input field, and then presses the submit button.

[1708] Output: The entered feedback text.

[1709] Step 2:

[1710] The device sends feedback to the server in real time.

[1711] Input: The feedback text entered by the user.

[1712] Specific behavior: Calls the chatbot API and generates an HTTP POST request to send the feedback text to the server.

[1713] Output: Feedback data sent to the server.

[1714] Step 3:

[1715] The server stores the feedback in a database

[1716] Input: Feedback data sent to the server.

[1717] Specific behavior: Executes a database INSERT query to store the feedback data in a database (e.g., Amazon RDS or Google Cloud SQL).

[1718] Output: Feedback entries stored in a database.

[1719] Step 4:

[1720] The server periodically retrieves new feedback data.

[1721] Input: Feedback data stored in the database.

[1722] What it does: Schedule a cron job to periodically (e.g., hourly) run a SELECT query to retrieve new feedback data.

[1723] Output: The new feedback data retrieved by the server.

[1724] Step 5:

[1725] Generative AI models analyze feedback

[1726] Input: New feedback data retrieved by the server.

[1727] Specific operation: The feedback data is input into a generative AI model (e.g., OpenAI GPT-4), and text analysis is performed to extract problems and requests.

[1728] Prompt: "Based on user feedback, explain how you identify the cause of frequent crashes."

[1729] Output: Analyzed keywords and issues (e.g. "frequent crashes", "after update").

[1730] Step 6:

[1731] The server stores the analysis results as structured data.

[1732] Input: Parsed keywords and issues.

[1733] What it does: Executes an INSERT or UPDATE query in the database and saves the parsed results as structured data in an error log and a user suggestions list.

[1734] Output: Analysis result entries stored in a database.

[1735] Step 7:

[1736] The server generates suggestions based on the generative AI model

[1737] Input: Structured analysis result data.

[1738] What it does: Formats the analysis results and feeds them into a generative AI model to generate appropriate recommendations.

[1739] Prompt: "Based on your analysis, please explain the steps you would take to identify the cause of the frequent crashes."

[1740] Output: Generated suggestions (e.g. "Optimize for performance", "Steps to check logs").

[1741] Step 8:

[1742] The server selects the generated proposal and notifies the user if necessary.

[1743] Input: The generated proposals.

[1744] What it does: Uses an automated rating algorithm to select the most appropriate suggestion, adds it to the suggestions list, and notifies the user if necessary using the notification API.

[1745] Output: Selected proposal and notification to user.

[1746] Step 9:

[1747] A user contacts us using a chatbot or support form

[1748] Input: User query text (e.g. "I would like to reset my password").

[1749] Specific action: A user enters and submits an inquiry through a chatbot or support form.

[1750] Output: The input query text.

[1751] Step 10:

[1752] The device sends the inquiry to the server

[1753] Input: The query text entered by the user.

[1754] Specific behavior: Uses the chatbot API to generate an HTTP POST request that sends the inquiry to the server.

[1755] Output: The query data sent to the server.

[1756] Step 11:

[1757] The server sends the query to the generative AI model

[1758] Input: The query data sent to the server.

[1759] Specific operation: Call the API of the generative AI model and input the inquiry data.

[1760] Output: The inquiry data fed into the generative AI model.

[1761] Step 12:

[1762] Generative AI models generate appropriate responses

[1763] Input: The inquiry data fed into the generative AI model.

[1764] Specific behavior: Uses the model's inference engine to generate appropriate responses based on past inquiry data and FAQs.

[1765] Prompt: "Please explain the password reset procedure."

[1766] Output: The generated response (e.g., "Password reset instructions").

[1767] Step 13:

[1768] The server generates a response and sends it back to the user.

[1769] Input: The generated response.

[1770] What it does: Uses the chatbot's API to generate an HTTP POST request that sends the generated response to the user's device.

[1771] Output: The response data sent to the user device.

[1772] This allows for quick and accurate responses to user feedback and inquiries, and in particular, automating the entire process from collecting feedback to analyzing it, generating suggestions, and responding to inquiries can improve the user experience.

[1773] (Application example 1)

[1774] 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."

[1775] Current feedback collection and customer support systems have difficulty effectively analyzing user feedback and quickly providing suggestions based on it. Furthermore, they do not provide appropriate customer support based on the feedback in a timely manner. This problem results in a poor user experience and reduces customer satisfaction.

[1776] 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.

[1777] In this invention, the server includes means for collecting feedback from users, means for analyzing the collected feedback and extracting problems and requests, means for generating proposals based on the extracted information, means for notifying the user of the proposals based on the analyzed feedback, and means for automatically generating responses to inquiries from users. This makes it possible to consistently and effectively perform processes from collecting feedback to analyzing it, generating proposals, and providing appropriate customer support.

[1778] "User" refers to a person or entity that uses the system.

[1779] "Feedback" refers to information such as opinions, problems, and requests provided by users.

[1780] "Means for collecting" refers to the methods and devices for receiving and storing feedback from users.

[1781] "Means for analyzing" refers to a method or device for analyzing collected feedback information and identifying problems or needs.

[1782] "Extraction means" refers to a method or device for extracting from the data the problems and needs obtained through analysis.

[1783] "Means for generating proposals" refers to a method or apparatus that generates solutions or proposals based on the extracted information.

[1784] The term "means for automatically generating a response to an inquiry" refers to a method or device for automatically generating a response appropriate to the content of a user's inquiry.

[1785] "Means for notifying" refers to a method or device for notifying the user of the generated suggestions.

[1786] "Database" refers to a system for systematically storing and managing data such as feedback information and analysis results.

[1787] "Structured data" refers to data that has been organized and stored in a specific format as a result of analyzed feedback.

[1788] The present invention relates to a system for effectively collecting user feedback and providing customer support on an online shopping site. This system includes means for collecting user feedback in real time, analyzing it to identify problems and requests, generating appropriate suggestions, and notifying the users. It also includes means for automatically generating responses to user inquiries.

[1789] The system operates as follows.

[1790] 1. Gathering feedback

[1791] The user provides feedback through a smartphone app. When the user types in "I'm not satisfied with the product I recently purchased. I'd like to return it," the device receives the feedback and sends it to the server in real time.

[1792] 2. Saving your feedback

[1793] The server stores the received feedback in a database. For example, feedback such as "I'm not happy with the product I recently purchased and would like to return it" is recorded in the database.

[1794] 3. Feedback Analysis

[1795] The server periodically retrieves new feedback data from the database and performs text analysis using a generative AI model to extract problems and requests such as "dissatisfaction" and "returns" from the feedback.

[1796] Hardware / Software used

[1797] Server: A server that stores and analyzes data

[1798] Generative AI models: used to perform text analysis

[1799] 4. Proposal Generation

[1800] The server generates a suggestion based on the parsed information, for example, "We're sorry for your inconvenience. Please see below for return procedures." and notifies the user.

[1801] 5. Response to inquiries

[1802] If a user makes a separate inquiry, the server uses the generative AI model to generate an appropriate response based on past data and FAQs. For example, in response to the inquiry, "How do I process a return?", the server generates a response saying, "Please follow the steps below to process a return," and notifies the user.

[1803] Hardware / Software used

[1804] Server: A system for processing query data.

[1805] Generative AI models: used to generate appropriate responses

[1806] Specific examples

[1807] User feedback: "My recently purchased smartphone runs out of battery quickly."

[1808] Analysis result: Battery-related issues

[1809] Suggestion: "To save battery, we recommend lowering your screen brightness and closing apps you're not using."

[1810] Inquiry prompt: "How do I process a return?"

[1811] This system will improve the user experience on online shopping sites and increase customer satisfaction.

[1812] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1813] Step 1:

[1814] The user enters feedback through a smartphone app. For example, the user provides feedback such as, "I'm not satisfied with the product I recently purchased. I'd like to return it." This becomes input data.

[1815] Step 2:

[1816] The terminal obtains the input feedback and transmits it to the server in real time, where the input data is the raw feedback information and the output data is the feedback information transmitted to the server.

[1817] Step 3:

[1818] The server stores the received feedback information in a database, where the input data is the feedback information sent from the terminal and the output data is the feedback entry stored in the database.

[1819] Step 4:

[1820] The server periodically retrieves new feedback data from the database, where the input data is the feedback information in the database and the output data is the feedback data for analysis.

[1821] Step 5:

[1822] The server uses a generative AI model to analyze the feedback data and extract problems and requests. The input data is the feedback data, and the output data is the extracted problems and requests. Specifically, it uses a text analysis algorithm to identify keywords in the feedback.

[1823] Step 6:

[1824] The server uses a generative AI model to generate a proposal based on the extracted information. The input data are the extracted problems and requests, and the output data is the generated proposal. For example, a proposal might be generated that says, "We apologize for the inconvenience. Please see below for the return procedure."

[1825] Step 7:

[1826] The server notifies the user of the generated proposal. The input data is the generated proposal, and the output data is the notification sent to the user. The user receives the proposal notification through their terminal.

[1827] Step 8:

[1828] When a user makes an inquiry, for example, they input, "Please tell me how to process a return." This is the input data.

[1829] Step 9:

[1830] The terminal sends the query to the server. The input data is the user's query, and the output data is the query information sent to the server.

[1831] Step 10:

[1832] The server uses the generative AI model to generate an automated response to the inquiry. The input data is the inquiry information, and the output data is the generated response. For example, it generates a response such as, "Please follow the steps below to process your return."

[1833] Step 11:

[1834] The server sends the generated response to the user. The input data is the generated response, and the output data is the reply sent to the user. The user receives the reply through their terminal.

[1835] 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.

[1836] This invention relates to a system that effectively collects and analyzes feedback and inquiries from users, recognizes their emotions, and then generates appropriate suggestions and responses. This system is characterized by a combination of the processing flow and emotion engine described below.

[1837] System configuration and operation

[1838] 1. Feedback collection and emotion recognition:

[1839] Users enter their issues and feedback through the chatbot.

[1840] Example: User types, "My app crashes so often. It's really frustrating."

[1841] The device receives user feedback in real time and recognizes the user's emotions using an emotion engine.

[1842] The emotion engine identifies the emotion "anger" from the user's input text.

[1843] The device transmits the feedback content and the recognized emotion information to the server as data.

[1844] Example: Send feedback to the server as "frequent crashes" or "angry."

[1845] 2. Feedback storage and analysis:

[1846] The server stores the received feedback in a dedicated feedback database.

[1847] Example: Adding entries to the feedback database for "frequent crashes" and "angry."

[1848] The server periodically retrieves new feedback data from the database and analyzes it using the generative AI model.

[1849] Example: Schedule a job to retrieve new feedback data every hour, and the generative AI model will analyze and extract "frequent crashes" and "anger."

[1850] 3. Save the analysis results and generate suggestions:

[1851] The server stores the results of the parsed feedback as structured data.

[1852] Example: Save the extracted keywords "frequent crashes" and "anger" in the error log.

[1853] The server uses an emotion engine to request a generative AI model to make suggestions based on the user's emotions.

[1854] The emotion engine provides the emotion information of "anger" to the generative AI model, which then generates suggestions based on that information.

[1855] 4. Proposal Review and Notification:

[1856] The server reviews the generated proposals and selects the most appropriate one.

[1857] Example: Select "Quick log collection procedure to identify the cause of a crash" from the suggestions.

[1858] The server stores the selected suggestions in a database and notifies the user if necessary.

[1859] Example: Add the selected suggestion to the "suggestion list" and notify relevant users.

[1860] 5. Receiving and responding to inquiries:

[1861] A user submits a query using a chatbot or support form.

[1862] Example: User types, "I want to reset my password. I'm having so much trouble."

[1863] The terminal transmits the inquiry to the server.

[1864] Example: Send the inquiry "Password reset" and "Confused" to the server.

[1865] The server receives the query content through the emotion engine and sends it to the generative AI model.

[1866] Example: The inquiry content "Password reset" and "Confused" are input into the generative AI model.

[1867] A generative AI model generates responses based on past inquiry data and FAQs, while an emotion engine adjusts the appropriate tone.

[1868] Example: The emotion engine generates a "kind and polite" response to the "confused" emotion.

[1869] The server sends the generated response to the terminal and sends it back to the user.

[1870] Example: The generated "password reset procedure" is sent to the terminal and the message "Don't worry, you can reset your password by following the steps" is displayed on the user screen.

[1871] In this way, it is possible to respond to user feedback and inquiries quickly and appropriately according to their emotions. In particular, by combining an emotion engine, it is possible to recognize the user's emotions and adjust suggestions and responses based on those emotions, further improving the user experience. As a specific example, if a user gives feedback such as "The app crashes frequently. It's really frustrating," the system can collect and analyze that feedback, recognize the emotion of "anger," and propose a quick solution to identify the cause of the crash. This allows the user's problems to be resolved quickly and increases their emotional satisfaction.

[1872] The processing flow will be explained below.

[1873] Step 1:

[1874] Users enter their issues and feedback through the chatbot.

[1875] Example: User types, "My app crashes so often. It's really frustrating."

[1876] Step 2:

[1877] The device receives user feedback in real time and recognizes the user's emotions using an emotion engine.

[1878] The emotion engine identifies the emotion "anger" from the user's input text.

[1879] Step 3:

[1880] The device transmits the feedback content and the recognized emotion information to the server as data.

[1881] Example: Send feedback to the server as "frequent crashes" or "angry."

[1882] Step 4:

[1883] The server stores the received feedback in a dedicated feedback database.

[1884] Example: Adding entries to the feedback database for "frequent crashes" and "angry."

[1885] Step 5:

[1886] The server periodically retrieves new feedback data from the database.

[1887] Example: Schedule a job to retrieve new feedback data every hour.

[1888] Step 6:

[1889] The generative AI model uses text analysis algorithms to extract issues and requests from within the feedback.

[1890] Example: A generative AI model extracts keywords such as "frequent crashes," "after update," and "anger."

[1891] Step 7:

[1892] The server stores the analysis results and emotional information as structured data in an error log or user suggestion list.

[1893] Example: Save the extracted keywords "frequent crashes" and "anger" in the error log.

[1894] Step 8:

[1895] The server uses the saved analysis results to input data based on the user's needs into the generative AI model.

[1896] Example: The analysis results "frequent crashes," "after update," and "anger" are input into the generative AI model.

[1897] Step 9:

[1898] The generative AI model generates suggestions using analysis results, past data, or inference algorithms, where an emotion engine takes into account the user's emotional information.

[1899] Example: A generative AI model generates "log collection procedures to identify the cause of a crash," and an emotion engine adds polite language to correspond to "anger."

[1900] Step 10:

[1901] The server reviews the generated proposals and selects the most appropriate one.

[1902] Example: Select "Quick log collection procedure to identify the cause of a crash" from the suggestions.

[1903] Step 11:

[1904] The server stores the selected suggestions in a database and notifies the user if necessary.

[1905] Example: Add the suggestion to the "Suggestion List" and notify relevant users.

[1906] Step 12:

[1907] A user submits a query using a chatbot or support form.

[1908] Example: User types, "I want to reset my password. I'm having so much trouble."

[1909] Step 13:

[1910] The terminal transmits the inquiry to the server.

[1911] Example: Send the inquiry "Password reset" and "Confused" to the server.

[1912] Step 14:

[1913] The server receives the query and sends it to the generative AI model.

[1914] Example: The inquiry content "Password reset" and "Confused" are input into the generative AI model.

[1915] Step 15:

[1916] A generative AI model generates appropriate responses based on past inquiry data and FAQs, while an emotion engine adjusts the appropriate tone.

[1917] Example: A generative AI model generates "password reset instructions," and an emotion engine adds a "kind and polite" response to "confusion."

[1918] Step 16:

[1919] The server sends the generated response to the terminal and sends it back to the user.

[1920] Example: The generated "password reset procedure" is sent to the terminal and the message "Don't worry, you can reset your password by following the steps" is displayed on the user screen.

[1921] Example 2

[1922] 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."

[1923] Conventional feedback collection systems have been limited to simple text analysis and quantitative data collection without considering user emotions, making it difficult to respond appropriately to the user's psychological state. As a result, they have not been able to sufficiently improve the user experience or quickly resolve problems. A new system that can solve this problem and quickly provide suggestions and responses that correspond to the user's emotions is needed.

[1924] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1925] In this invention, the server includes means for receiving feedback from a user in real time and recognizing emotions, means for transmitting the recognized emotion information and the feedback content as data, means for saving the received feedback in a database, means for periodically updating the saved data and analyzing it using a generative AI model, means for saving the analysis results as structured data, means for generating suggestions based on the analysis results, and means for generating automatic responses in response to user inquiries, thereby enabling prompt and appropriate suggestions and responses that take the user's emotions into consideration.

[1926] "Feedback" refers to information such as opinions, problem reports, and requests provided by users.

[1927] "Emotion recognition" is the process of analyzing a user's input text and identifying the emotions contained within it.

[1928] "Emotion information" is information about emotions (e.g., anger, confusion, joy, etc.) identified from the analyzed feedback.

[1929] A "database" is a system for storing collected feedback and analysis results in a structured format.

[1930] A "generative AI model" is an artificial intelligence technology that generates appropriate suggestions and responses based on user feedback and inquiries.

[1931] "Structured data" is data that has a specific format or structure and can be efficiently stored and managed in a database.

[1932] "Suggestions" are specific instructions for action or solutions provided to the user based on the analysis results and emotional information.

[1933] An "automated response" is an automatically generated answer to a user's inquiry, created by a generative AI model.

[1934] "Analysis" is the process of examining the collected feedback in detail and extracting and evaluating problems and requests.

[1935] "Real-time" refers to the timeline in which user feedback and inquiries are processed and responded to immediately after they are entered.

[1936] This invention relates to a system that effectively collects and analyzes feedback and inquiries from users, recognizes their emotions, and then generates appropriate suggestions and responses. This system is characterized by a combination of the processing flow and emotion engine described below.

[1937] This system is primarily composed of a server and a user device. Specific hardware features include a high-performance cloud server for the server and a PC or smartphone for the user device. The software uses an emotion engine (e.g., Azure Cognitive Services or IBM Watson) and a generative AI model (e.g., OpenAI's GPT-3).

[1938] Feedback collection and emotion recognition

[1939] Users use their devices to input their problems and feedback through the chatbot. For example, a user might type, "My app keeps crashing. It's really frustrating."

[1940] The device receives this user feedback in real time and uses an emotion engine to recognize the user's emotions. The device then calls a text analysis API to identify the emotion "anger" from the input text.

[1941] The device sends the feedback content and the recognized emotion information to the server as data. Specifically, the feedback content "frequent crashes" and the emotion "anger" are sent to the server in JSON format.

[1942] Feedback storage and analysis

[1943] The server stores the received feedback in a dedicated feedback database (e.g. MySQL or MongoDB). The server adds a new entry to the feedback database and saves the data.

[1944] The server uses a job scheduler (e.g., a Cron job) to periodically retrieve new feedback data from the database and analyze it using the generative AI model. This allows the server to retrieve and analyze new feedback data every hour.

[1945] Saving analysis results and generating proposals

[1946] The server stores the analyzed feedback results as structured data. The analysis results received from the generative AI model are stored in an error log database in JSON format.

[1947] The server uses the emotion engine to request a generative AI model to make a suggestion based on the user's emotion. The server provides the emotion information "anger" to the generative AI model, which then generates a suggestion: "Procedures for rapid log collection to identify the cause of the crash."

[1948] Proposal review and notification

[1949] The server reviews the generated proposals, selects the most appropriate proposal, adds the proposals to a list, and selects the best proposal either manually or through an automated process.

[1950] The server saves the selected suggestion in a database and notifies the user if necessary. The server saves the selected suggestion in a "suggestion list" and calls the notification API to send a message to the user.

[1951] Receiving and responding to inquiries

[1952] A user submits a query using a support form or chatbot. For example, they type, "I want to reset my password. I'm having a really hard time."

[1953] The device sends this inquiry to the server. The device sends the inquiry "Password reset" and the emotion "Confused" in JSON format to the server.

[1954] The server receives the inquiry via the emotion engine and sends it to the generative AI model, which then references the FAQ database and generates "password reset instructions" in a "friendly and polite" tone.

[1955] The server sends the generated response to the terminal and returns it to the user. It also sends the generated "password reset procedure" to the terminal and displays on the user's screen, "Don't worry, you can reset your password by following the steps."

[1956] Prompt Sentence Examples

[1957] "Please explain how the system responds when users give feedback that the app crashes too frequently."

[1958] "Could you please elaborate on how the system responds when a user is having trouble resetting their password?"

[1959] In this way, it is possible to respond to user feedback and inquiries quickly and appropriately according to their emotions, and this system is expected to significantly improve the user experience.

[1960] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1961] Step 1:

[1962] A user enters feedback using a chatbot.

[1963] Specific operation: The user opens the chatbot screen on a PC or smartphone and enters their problem or feedback. For example, they enter text such as, "The app keeps crashing. It's really frustrating."

[1964] Input: Text data entered by the user.

[1965] Output: Raw feedback data received on the user's device.

[1966] Step 2:

[1967] The device receives feedback in real time and recognizes emotions using an emotion engine.

[1968] Specific operation: The terminal sends the input text data to a text analysis API (e.g., an emotion engine) to analyze the emotion. The emotion engine identifies emotion information (e.g., "anger") from the text.

[1969] Input: Feedback text from the user.

[1970] Output: Identified emotion information (e.g., "anger").

[1971] Step 3:

[1972] The device transmits the feedback content and emotional information to the server as data.

[1973] Specific operation: The device converts the feedback content "frequent crashes" and emotional information "anger" into JSON format and sends it to the server.

[1974] Input: Feedback text and accompanying sentiment information.

[1975] Output: The JSON data sent to the server.

[1976] Step 4:

[1977] The server stores the received feedback in a feedback database.

[1978] Specific behavior: The server extracts the received JSON data, creates a new entry in the database, and saves it.

[1979] Input: JSON data sent from the terminal.

[1980] Output: A new feedback entry in the database.

[1981] Step 5:

[1982] The server periodically collects feedback data and analyzes it using a generative AI model.

[1983] How it works: The server uses a job scheduler (e.g., a Cron job) to retrieve new feedback from the database every hour, and sends it to the generative AI model for analysis. The generative AI model then analyzes the feedback in detail to identify problems and requests.

[1984] Input: New feedback data in the database.

[1985] Output: Analysis results from the generative AI model.

[1986] Step 6:

[1987] The server stores the analysis results as structured data.

[1988] Specific operation: The server stores the analysis results received from the generative AI model in JSON format in the error log database.

[1989] Input: Analysis results from a generative AI model.

[1990] Output: Analysis results stored as structured data.

[1991] Step 7:

[1992] The server utilizes an emotion engine to generate suggestions according to the user's emotions.

[1993] Specific operation: The server provides the emotional information "anger" to the generative AI model, and based on that, generates a suggestion for "quick log collection procedures to identify the cause of the crash."

[1994] Input: User emotion information and analysis results.

[1995] Output: Sentiment-based suggestions.

[1996] Step 8:

[1997] The server reviews the generated proposals and selects the most appropriate one.

[1998] What happens: The server adds the generated suggestions to a list and then selects the best suggestion either manually or through an automated process.

[1999] Input: Multiple proposals from a generative AI model.

[2000] Output: The selected best proposal.

[2001] Step 9:

[2002] The server stores the selected suggestions in a database and notifies the user if necessary.

[2003] Specific behavior: The server saves the selected suggestion in a "suggestion list" and calls the notification API to send a message to the user.

[2004] Input: Selected suggestion.

[2005] Output: Suggestions stored in database and notification to user.

[2006] Step 10:

[2007] A user submits a query using a support form or chatbot.

[2008] Specific action: For example, type "I want to reset my password. I'm having a really hard time."

[2009] Input: User query text.

[2010] Output: The raw query data received at the terminal.

[2011] Step 11:

[2012] The terminal transmits the inquiry to the server.

[2013] Specific operation: The device sends the inquiry "Password reset" and emotional information "Confused" in JSON format to the server.

[2014] Input: User inquiry and emotional information.

[2015] Output: The JSON data sent to the server.

[2016] Step 12:

[2017] The server receives the query via the emotion engine and sends it to the generative AI model.

[2018] Specific operation: The server analyzes the content through the emotion engine, sends the query content to the generative AI model, and generates a response.

[2019] Input: JSON data sent from the terminal.

[2020] Output: Response generated by the generative AI model.

[2021] Step 13:

[2022] A generative AI model generates responses based on past inquiry data and FAQs, while an emotion engine adjusts the appropriate tone.

[2023] Specific operation: The generative AI model refers to a database of FAQs and creates "password reset instructions" in a "friendly and polite" tone.

[2024] Input: Past inquiry data and current inquiry details.

[2025] Output: A response generated in a "friendly and polite" tone.

[2026] Step 14:

[2027] The server sends the generated response to the terminal and sends it back to the user.

[2028] Specific operation: The generated response content is sent to the terminal in JSON format, and the terminal displays "Don't worry, you can reset your password by following the steps" on the chat screen.

[2029] Input: The response from the generative AI model.

[2030] Output: The response message that is displayed on the user's terminal.

[2031] (Application example 2)

[2032] 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."

[2033] Conventional feedback collection and analysis systems do not adequately consider the emotional information in the feedback provided by users, resulting in the problem of not being able to provide appropriate suggestions or responses based on the user's actual emotional state. Furthermore, while there is a demand for fast, emotionally sensitive responses to user inquiries, there is currently no system that can adequately meet this demand.

[2034] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting feedback from users, means for analyzing the collected feedback to extract problems and requests and recognize the user's emotions, means for generating suggestions based on the extracted information and the recognized emotions, and means for automatically generating responses to inquiries from users. This makes it possible to analyze and suggest feedback based on the user's emotions, and to respond to user inquiries quickly and with consideration for the user's emotions.

[2035] "Means for collecting user feedback" refers to a device or process for collecting information such as opinions, impressions, and problems that users provide to the system.

[2036] "Means for analyzing collected feedback, extracting problems and requests, and recognizing user emotions" refers to a device or process for processing collected feedback data, analyzing user emotions, and identifying problems and requests contained in the feedback.

[2037] "Means for generating suggestions based on extracted information and recognized emotions" refers to a device or process that uses the information obtained through the analysis and the user's emotional information to generate appropriate suggestions or solutions for the user.

[2038] The "means for automatically generating a response to a user's inquiry" refers to a device or process for automatically creating and providing a response to the content of a user's inquiry.

[2039] "Means for storing collected feedback in a database" refers to a device or process for storing collected feedback data in a database for easy later access.

[2040] "Means for storing structured data including emotional information of the analyzed feedback data" refers to a device or process for structuring the feedback data including the emotional information obtained by the analysis and storing it in a database.

[2041] "Means for a generative AI model to analyze based on emotions and generate appropriate suggestions or responses based on prompts" refers to a device or process that allows a generative AI model to analyze based on a user's emotional information and generate appropriate suggestions or responses based on specific instructions (prompts).

[2042] In this invention, the configuration and operation for realizing a system that effectively collects and analyzes user feedback and makes appropriate suggestions and responses based on the user's emotional information will be described below.

[2043] 1. Collecting User Feedback

[2044] Users submit feedback using a smartphone application, which is provided as text input and includes, for example, "I didn't enjoy the movie that was recently released. I'm a little annoyed. Is there a more exciting movie out there?"

[2045] 2. Emotion recognition

[2046] The device analyzes the collected feedback in real time using a natural language processing library (e.g., spaCy) and an emotion recognition engine (e.g., an emotion analysis tool using an NLP model), thereby identifying emotions such as "irritation" from the user's feedback.

[2047] 3. Data storage

[2048] The device sends the feedback data along with the emotion information recognized by the device to the server, which then stores it in a database (e.g., MongoDB), where the feedback and associated emotion information are stored as structured data.

[2049] 4. Analysis and proposal generation

[2050] The server periodically retrieves feedback data from the database and analyzes it using a generative AI model (e.g., GPT-4). Based on the information and emotional information extracted through the analysis, the generative AI model creates and executes prompts to generate appropriate suggestions and solutions.

[2051] 5. Notice to Users

[2052] The generated suggestions and responses are sent to the user's terminal by the server, and the user receives them through the application. For example, in response to feedback such as "The recent movie was not interesting," a suggestion such as "Suggestion: Please check out the following for more exciting movies" may be made.

[2053] Specifically, this includes the following steps:

[2054] The user enters feedback such as, "The movie that was recently released wasn't interesting. I'm a little annoyed. Are there any more exciting movies?"

[2055] The device recognizes the emotion as "irritation" and sends feedback to the server.

[2056] The server stores the feedback and emotional information in a database, and the generative AI model generates appropriate suggestions.

[2057] The suggestion is notified to the user as "Suggestion: Check out the following for more exciting movies."

[2058] Hardware and software used:

[2059] Smartphone (Android, iOS)

[2060] Natural language processing library (spaCy)

[2061] Emotion recognition engine (NLP model)

[2062] Database (MongoDB)

[2063] Generative AI model (GPT-4)

[2064] This allows for analysis and suggestion of feedback based on the user's emotions, enabling fast and emotionally sensitive responses to queries.

[2065] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2066] Step 1:

[2067] The user inputs feedback into the smartphone application. For example, the input might be, "The movie that was recently released wasn't interesting. I'm a little annoyed. Is there a more exciting movie?" The input text data is sent to the device.

[2068] Step 2:

[2069] The device analyzes the collected feedback text using a natural language processing library (e.g., spaCy) and an emotion recognition engine (e.g., an emotion analysis tool using an NLP model). It receives the feedback text as input and identifies the emotion as "irritation" from the content of the text.

[2070] Step 3:

[2071] The device sends the analyzed emotion information and feedback data to the server, which stores the received feedback data and emotion information in a database (e.g., MongoDB). The data is stored in a structured format.

[2072] Step 4:

[2073] The server reads new feedback data from the database according to a regular schedule and analyzes it using a generative AI model (e.g., GPT-4). The generative AI model uses the feedback text and emotional information as input, and generates necessary information and suggestions based on that. For example, analysis is performed based on a prompt sentence corresponding to the emotion "irritation."

[2074] Step 5:

[2075] The generative AI model outputs suggestions and solutions, which are then reviewed by the server, which selects the most appropriate suggestion and makes adjustments as needed. The selected suggestion or solution is then stored as structured data.

[2076] Step 6:

[2077] The server notifies the generated suggestion to the user's device. The device receives the suggestion and displays it to the user. For example, "Suggestion: Check out the following for more exciting movies."

[2078] Step 7:

[2079] When a user submits a new inquiry, the inquiry is sent to the server in a similar manner and analyzed by the emotion recognition and generative AI model. An appropriate response is then generated and notified to the user. For example, if the issue is not resolved, a response such as "Don't worry, we'll contact our support team" is displayed.

[2080] As a result, a system is constructed that can provide appropriate suggestions and responses based on emotions in response to user feedback and inquiries.

[2081] 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.

[2082] 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.

[2083] 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.

[2084] 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.

[2085] 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.

[2086] 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.

[2087] 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).

[2088] 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.

[2089] 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."

[2090] 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.

[2091] 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).

[2092] 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.

[2093] 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.

[2094] 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.

[2095] 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.

[2096] 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.

[2097] 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.

[2098] 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.

[2099] 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.

[2100] 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.

[2101] 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.

[2102] The following is further disclosed regarding the above embodiment.

[2103] (Claim 1)

[2104] a means for collecting feedback from users;

[2105] A means of analyzing the collected feedback and extracting problems and requests,

[2106] means for generating suggestions based on the extracted information;

[2107] means for automatically generating responses to user queries;

[2108] A system including:

[2109] (Claim 2)

[2110] 10. The system of claim 1, further comprising means for storing the collected feedback in a database.

[2111] (Claim 3)

[2112] 10. The system of claim 1, further comprising means for storing the results of the parsed feedback as structured data.

[2113] (Claim 4)

[2114] 10. The system of claim 1, further comprising means for reviewing the generated suggestions and selecting the best suggestion.

[2115] (Claim 5)

[2116] A means to analyze user inquiries and generate responses based on past data and FAQs,

[2117] 10. The system of claim 1, further comprising means for transmitting the generated response to a user.

[2118] (Claim 6)

[2119] 10. The system of claim 1, further comprising means for periodically analyzing the collected feedback.

[2120] (Claim 7)

[2121] 10. The system of claim 1, further comprising means for notifying the user of the generated suggestions.

[2122] (Claim 8)

[2123] 10. The system of claim 1, further comprising means for taking into account historical data and market trends when generating proposals.

[2124] "Example 1"

[2125] (Claim 1)

[2126] a means for collecting feedback from users;

[2127] means for transmitting the collected feedback to a server in real time;

[2128] a means for storing the collected feedback in a database;

[2129] a means of periodically retrieving the stored feedback; and

[2130] A means of inputting and analyzing feedback obtained from the database into a generative AI model;

[2131] means for storing the results of the parsed feedback as structured data;

[2132] means for generating recommendations based on the analysis results;

[2133] means for selecting the generated suggestions and notifying the user as appropriate;

[2134] means for generating an appropriate response to a user query;

[2135] A system including:

[2136] (Claim 2)

[2137] 10. The system of claim 1, further comprising means for generating recommendations using a generative AI model based on the stored analysis results.

[2138] (Claim 3)

[2139] 10. The system of claim 1, further comprising means for receiving a user query and generating an appropriate response using the generative AI model.

[2140] "Application Example 1"

[2141] (Claim 1)

[2142] a means for collecting feedback from users;

[2143] A means of analyzing the collected feedback and extracting problems and requests,

[2144] means for generating suggestions based on the extracted information;

[2145] means for automatically generating responses to user queries;

[2146] a means for notifying the user of suggestions based on the analyzed feedback;

[2147] A system including:

[2148] (Claim 2)

[2149] 10. The system of claim 1, further comprising means for storing the collected feedback in a database.

[2150] (Claim 3)

[2151] 10. The system of claim 1, further comprising means for storing the results of the parsed feedback as structured data.

[2152] "Example 2: Combining Emotion Engines"

[2153] (Claim 1)

[2154] a means for collecting feedback from users;

[2155] A means of receiving collected feedback in real time and recognizing emotions;

[2156] a means for transmitting the recognized emotion information and feedback content as data;

[2157] a means of storing the received feedback in a database;

[2158] A means to periodically update the stored data and analyze it using a generative AI model; and

[2159] A means for storing the analysis results as structured data;

[2160] means for generating recommendations based on the analysis results;

[2161] means for generating an automatic response in response to a user inquiry;

[2162] A system including:

[2163] (Claim 2)

[2164] 10. The system of claim 1, further comprising means for storing the collected feedback in a database.

[2165] (Claim 3)

[2166] 10. The system of claim 1, further comprising means for storing the results of the parsed feedback as structured data.

[2167] "Application example 2 when combining emotion engines"

[2168] (Claim 1)

[2169] a means for collecting feedback from users;

[2170] A means for analyzing the collected feedback, extracting problems and requests, and recognizing user emotions;

[2171] means for generating suggestions based on the extracted information and the recognized sentiment;

[2172] means for automatically generating responses to user queries;

[2173] A system including:

[2174] (Claim 2)

[2175] a means for storing the collected feedback in a database;

[2176] 10. The system of claim 1, further comprising means for storing structured data including emotion information of the parsed feedback data.

[2177] (Claim 3)

[2178] 10. The system of claim 1, further comprising means for the generative AI model to analyze based on emotion and generate appropriate suggestions or responses based on the prompt sentence. [Explanation of symbols]

[2179] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting feedback from users; A means of analyzing the collected feedback and extracting problems and requests, means for generating suggestions based on the extracted information; means for automatically generating responses to user queries; A system including:

2. 10. The system of claim 1, further comprising means for storing the collected feedback in a database.

3. The system of claim 1 , further comprising means for storing the results of the analyzed feedback as structured data.

4. 10. The system of claim 1, further comprising means for reviewing the generated proposals and selecting the best proposal.

5. A means to analyze user inquiries and generate responses based on past data and FAQs, 10. The system of claim 1, further comprising means for transmitting the generated response to a user.

6. 10. The system of claim 1, further comprising means for periodically analyzing the collected feedback.

7. 10. The system of claim 1, further comprising means for notifying the user of the generated suggestions.

8. 10. The system of claim 1, further comprising means for taking into account historical data and market trends when generating proposals.

Images