System

Abstract

A system is provided.SOLUTION: The system includes an interaction means using a generation AI model for directly collecting feedback from a user, a storage means for storing the collected feedback, a natural language processing means for analyzing the stored feedback, a visualization means for visualizing an analysis result, and a notification means for notifying the analysis result and an improvement proposal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] User feedback is crucial in the development of modern products and services, and its collection and analysis are essential. However, current methods limit the collection of user feedback, and manual analysis is time-consuming and labor-intensive. This makes it difficult to identify quick and specific improvement measures. This invention aims to solve these issues by utilizing a generative AI model to efficiently and accurately collect feedback through user interactions and automatically analyze the results. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by the following means. Specifically, it provides a system including an interaction means using a generative AI model to directly collect feedback from users, a storage means for saving the collected feedback, a natural language processing means for analyzing the saved feedback, a visualization means for visualizing the analysis results, and a notification means for notifying the analysis results and improvement suggestions. Furthermore, it adds a statistical analysis means for identifying trends and patterns from the analysis results and provides a dashboard where managers and personnel can view and track the results, making it possible to quickly and effectively identify improvement measures for products and services.

[0006] A "generative AI model" is an artificial intelligence model that performs natural language processing through dialogue with users and collects and analyzes feedback.

[0007] "Interaction methods" refers to the methods and features used to gather opinions and feedback from users using generative AI models.

[0008] "Storage Means" refers to the database or storage system used to store and manage the collected User Feedback.

[0009] "Natural language processing means" refers to technologies and algorithms for analyzing the content of feedback and interpreting and classifying linguistic information.

[0010] "Visualization means" refers to the function of visually expressing the analysis results and providing them in the form of graphs or dashboards to make them easier for managers and staff to understand.

[0011] "Notification means" refers to telecommunications technologies and systems used to communicate analysis results and improvement suggestions to relevant parties.

[0012] "Statistical analysis procedures" are methods and techniques for statistically analyzing trends and patterns in collected feedback data.

[0013] A "dashboard" refers to a visual interface designed to allow managers and personnel to check and evaluate analysis results at a glance. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The system of the present invention is a system for collecting and analyzing user feedback using a generative AI model. This system operates among a server, a terminal, and a user, and is implemented in the following manner.

[0036] Interaction Phase (Feedback Collection)

[0037] server:

[0038] When a user accesses the server, the generative AI model is activated and a welcome message is sent to the user, such as "Tell us your opinion. What product / service is it about?" This prompts the user to provide feedback.

[0039] Device:

[0040] The terminal displays a welcome message and an input field for the user to enter their feedback, which is sent to the server in real time.

[0041] User:

[0042] Users enter their opinions and requests about the product or service and press the submit button. For example, they can enter feedback such as, "I think the design of this app is difficult to use."

[0043] Analysis phase (analysis of feedback)

[0044] server:

[0045] The server stores the received feedback in storage. It then analyzes the feedback using natural language processing. This analysis includes keyword extraction, sentiment analysis, and topic classification. For example, if the feedback "The button is small and difficult to tap" is analyzed, the keywords "button," "difficult to use," and "difficult to tap" are extracted.

[0046] server:

[0047] The analysis results can be used to identify common trends or patterns across multiple pieces of feedback, such as finding that a particular version of an app has multiple reports of the same issue, and then use this information to generate data that can be used to display the results in graphs or charts.

[0048] Device:

[0049] The terminal displays the analysis results in the form of a dashboard, allowing managers and product development teams to intuitively grasp trends and patterns in feedback.

[0050] Response and improvement phase (proposing improvements)

[0051] server:

[0052] Based on the analytical and statistical analysis results, the server uses a generative AI model to generate specific improvement suggestions, such as "increase the size of buttons" or "expand the tap area of ​​the user interface."

[0053] server:

[0054] The generated improvement proposals are notified to the person in charge via email or an intranet notification system.

[0055] Device:

[0056] The terminal provides an interface for managers and personnel to review improvement proposals, and also provides tools for tracking the progress of improvement work.

[0057] User (Administrator / Contact Person):

[0058] Managers and staff members implement specific improvement work based on the proposals. The progress of the improvement work is entered into the system, and the latest status is updated via the server.

[0059] Specific examples

[0060] For example, if user feedback about an app is that "the buttons are small and difficult to use" or "the colors are hard to see," the server collects, stores, and analyzes that feedback. Based on the analysis results, it generates improvement suggestions, such as "increase the button size" or "increase the color contrast," and notifies the relevant design team. The design team then uses these suggestions to revise the app's design and contribute to improving the user experience.

[0061] This system enables efficient collection and analysis of user feedback, enabling prompt and concrete improvement measures to be taken.

[0062] The processing flow will be explained below.

[0063] Step 1: User authentication

[0064] User:

[0065] Enter your username and password to log in to the system.

[0066] server:

[0067] Validates the entered credentials and authenticates the user. If successful, checks the user's access rights and loads the initial configuration information.

[0068] Step 2: Initiating a feedback dialogue

[0069] server:

[0070] Generate a welcome message and send it to the device, for example, "What product / service would you like to share your thoughts on?"

[0071] Device:

[0072] It displays a welcome message and an input field to prompt the user for input.

[0073] Step 3: Provide feedback

[0074] User:

[0075] Enter your opinions and requests regarding products and services and press the send button.

[0076] Device:

[0077] Send the feedback data entered by the user to the server.

[0078] Step 4: Gather feedback

[0079] server:

[0080] A generative AI model is used to analyze the content of user feedback and generate the next question, for example, "Which parts specifically did you find difficult to use?"

[0081] server:

[0082] Send the following question to the device:

[0083] Step 5: Ongoing dialogue

[0084] Device:

[0085] Displays the question sent by the server.

[0086] User:

[0087] Enter an answer to the question and submit. Example: "The buttons are small and difficult to tap."

[0088] Device:

[0089] The user's answer is sent to the server.

[0090] Step 6: Save your feedback

[0091] server:

[0092] The received feedback is stored in a database, including the user ID, date and time, and specific opinions.

[0093] Step 7: Perform text analysis

[0094] server:

[0095] The stored feedback data is analyzed using natural language processing tools, which include keyword extraction, sentiment analysis, and topic classification. For example, keywords such as "button," "difficult to use," and "difficult to tap" are detected.

[0096] Step 8: Identify trends and patterns

[0097] server:

[0098] Statistically process feedback from multiple users to identify common trends and patterns, aggregate the identified information, and generate visualizations in the form of reports.

[0099] Step 9: Visualize the results

[0100] Device:

[0101] Provide a dashboard that can be viewed by administrators and staff, displaying graphs and charts of analytical results. For example, show that a specific version has a lot of negative feedback about "button size."

[0102] Step 10: Generate improvement suggestions

[0103] server:

[0104] Based on the analysis results, a generative AI model is used to generate specific improvement suggestions, such as "increase the size of buttons" or "expand the tap area in the UI design."

[0105] Step 11: Implementing Notifications

[0106] server:

[0107] Proposals for improvement are communicated to the design and product development teams via email or an intranet notification system.

[0108] Step 12: Tracking Improvement Efforts

[0109] Device:

[0110] It provides an interface for managers and staff to review improvement proposals and track their progress. Once specific improvement work is initiated, the progress is updated in the system.

[0111] Step 13: Follow up on user feedback

[0112] server:

[0113] Once the improvements are complete, you can follow up by notifying users of the changes and asking for their feedback.

[0114] This allows you to automate and efficiently execute a series of processes, from collecting user feedback to analyzing it, visualizing the results, notifying improvement suggestions, and tracking improvement work.

[0115] Example 1

[0116] 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."

[0117] Conventional feedback collection systems face challenges in efficiently collecting and analyzing user feedback and quickly implementing improvement proposals. Specifically, the limited means of collecting feedback prevent users from fully incorporating their opinions, and the collected feedback must be analyzed manually, resulting in a long wait for improvement proposals. Furthermore, there is a lack of a way to visually and intuitively grasp the analysis results, and the system lacks a mechanism for effectively tracking the progress of improvement work.

[0118] 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.

[0119] In this invention, the server includes an interaction means using a generative AI model to directly collect feedback from users, a storage device means for saving the collected feedback, a natural language processing device means for analyzing the saved feedback, a statistical analysis device means for identifying common trends and patterns from multiple pieces of feedback, a display device means for visualizing the analysis results, a notification device means for notifying the analysis results and improvement proposals, a user interface means for allowing a manager or person in charge to check the improvement proposals, and a tool for tracking the progress of improvement work, thereby enabling efficient collection and analysis of user feedback and rapid implementation of improvement measures.

[0120] A "generative AI model" is an artificial intelligence model that generates natural language dialogue to collect feedback from users.

[0121] "Interaction means" refers to a means of directly interacting with the user using the generative AI model and obtaining feedback.

[0122] "Storage means" is a hardware or software device for storing collected feedback.

[0123] A "natural language processing means" is a device that performs natural language processing techniques used to analyze the stored feedback.

[0124] "Statistical analysis device means" refers to the statistical analysis techniques used to identify common trends and patterns from multiple feedbacks and the devices that perform them.

[0125] A "display device" is a hardware or software device used to visualize the results of an analysis.

[0126] The "notification device means" is a hardware or software device for notifying the person in charge of the analysis results and improvement suggestions.

[0127] The "user interface means" is a means for providing an interface for managers and staff members to check and operate improvement proposals.

[0128] "Tools" are software or hardware tools for tracking the progress of improvement efforts.

[0129] The present invention relates to a system for collecting and analyzing user feedback using a generative AI model. This system operates among a server, a terminal, and a user, and uses the following hardware and software:

[0130] The server launches a generative AI model (such as GPT-3 (registered trademark)) to collect feedback directly from users and asks for feedback through dialogue. When a user accesses the server, the server generates a welcome message saying, "Please tell us your opinion. What product / service is it about?" and sends it to the terminal.

[0131] The device displays this welcome message to the user and provides an input field for entering feedback. The user enters their feedback and presses the send button. Specifically, the user enters "The design of this app is difficult to use" and sends it.

[0132] The server stores the feedback received from the user in a storage device (e.g., an SQL database). The stored feedback is then analyzed using a natural language processing system (e.g., spaCy or NLTK). The analysis includes keyword extraction, sentiment analysis, and topic classification. For example, when analyzing the feedback "The button is small and difficult to tap," keywords such as "button," "difficult to use," and "difficult to tap" are extracted.

[0133] Based on the analysis results, the server uses statistical analysis tools (e.g., clustering algorithms or TF-IDF) to identify common trends and patterns among the multiple feedbacks. For example, it may discover that similar issues have been reported multiple times for a particular version of an app. Based on this information, the server visualizes the analysis results as graphs and charts using display tools (e.g., Matplotlib or D3.js).

[0134] The terminal displays the analysis results in the form of a dashboard, allowing managers and product development teams to intuitively grasp trends and patterns in feedback.

[0135] The server uses a generative AI model based on the analytical and statistical analysis results to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area of ​​the user interface" may be generated. The server then notifies the person in charge of these improvement suggestions using a notification device. Notification methods include email and intranet notification systems.

[0136] The terminal provides a user interface that allows managers and staff to check improvement proposals. It also provides tools for tracking the progress of improvement work. Managers and staff implement specific improvement work based on the proposals and enter their progress into the system, which updates the latest status.

[0137] Specific examples

[0138] For example, if user feedback about an app is that "the buttons are small and difficult to use" or "the colors are hard to see," the server collects, stores, and analyzes that feedback. Based on the analysis results, improvement suggestions such as "increase the button size" or "increase the color contrast" are generated and notified to the design team. The design team can then revise the app design based on the improvement suggestions, contributing to an improved user experience.

[0139] Prompt Sentence Examples

[0140] "I want to collect and analyze user feedback on a new app design. I want to know how the server, device, and user work together to identify specific issues."

[0141] This system enables efficient collection and analysis of user feedback, enabling prompt and concrete improvement measures to be taken.

[0142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0143] Step 1:

[0144] The server launches the generative AI model when a user accesses a specific URL and generates a welcome message.

[0145] Input: User's access request

[0146] Output: Welcome message ("What product / service would you like to hear about?")

[0147] Specific operation: When the server receives an HTTP request, it invokes a generative AI model (e.g., GPT-3) to generate a welcome message, embeds it in an HTML page, and sends it back to the user's browser.

[0148] Step 2:

[0149] The terminal displays an input field along with the welcome message received from the server.

[0150] Input: Welcome message from the server

[0151] Output: User feedback input interface

[0152] Specific operation: The terminal (user's browser) uses an HTML form and JavaScript (registered trademark) to display a text area where the user can enter feedback and a submit button.

[0153] Step 3:

[0154] The user inputs their opinions and requests regarding the product or service and presses the send button.

[0155] Input: User feedback (e.g., "The design of this app is difficult to use.")

[0156] Output: User-entered feedback data

[0157] Specific behavior: The user enters text in the feedback field and clicks the "Submit" button.

[0158] Step 4:

[0159] The server receives the feedback sent by the user and stores it in a database.

[0160] Input: Feedback data submitted by the user

[0161] Output: Feedback stored in a database

[0162] Specific operation: The server receives the feedback data and stores it in the SQL database using an INSERT statement.

[0163] Step 5:

[0164] The server analyzes the stored feedback using a natural language processing device.

[0165] Input: Saved feedback data

[0166] Output: Analysis results (keyword list, sentiment score, topic tags, etc.)

[0167] Specific operation: The server reads the saved feedback data, sends it to a natural language processing tool (e.g., spaCy or NLTK) via an API, and saves the returned analysis results back in the database.

[0168] Step 6:

[0169] The server performs statistical analysis based on the analysis results to identify common trends and patterns from the multiple feedbacks.

[0170] Input: Analysis results

[0171] Output: Statistical analysis results (identification of common trends and patterns)

[0172] Specific operation: The server uses algorithms such as k-means clustering and TF-IDF to extract commonalities in the feedback and perform statistical analysis.

[0173] Step 7:

[0174] The server generates graphs and charts to visualize the analysis results.

[0175] Input: Statistical analysis results

[0176] Output: Visualized data (graphs, charts, etc.)

[0177] Specific operation: The server uses visualization tools such as Matplotlib and D3.js to generate visualization data based on the feedback trend data.

[0178] Step 8:

[0179] The terminal displays the visualized data received from the server in dashboard format.

[0180] Input: Visualization data from the server

[0181] Output: Dashboard format display

[0182] Specific operation: The terminal (user's browser) displays an HTML page containing visualized data and a dashboard UI.

[0183] Step 9:

[0184] The server uses a generative AI model based on the analytical and statistical analysis results to generate specific improvement suggestions.

[0185] Input: Statistical analysis results

[0186] Output: Improvement suggestion (e.g. "Make the button size larger")

[0187] Specific operation: The server inputs the analysis results as prompt sentences into the generative AI model, and the AI ​​generates suggestions.

[0188] Step 10:

[0189] The server notifies the person in charge of the generated improvement proposal.

[0190] Input: Generated improvement suggestions

[0191] Output: Notification to responsible parties (via email or intranet notification system)

[0192] Specific operation: The server sends an email containing the proposal to the person in charge via the SMTP server or notifies them using the intranet notification API.

[0193] Step 11:

[0194] The device provides a UI for managers and staff to review improvement proposals, and also provides tools for tracking the progress of improvement work.

[0195] Input: Improvement suggestion notification from the server

[0196] Output: Display improvement suggestions to managers and staff and provide tracking tools

[0197] Specific operation: The terminal (user's browser) displays improvement proposals in list format and provides the person in charge with the ability to update the progress status.

[0198] Step 12:

[0199] Managers and staff members then carry out specific improvement work based on the suggestions. Progress is entered into the system, and the latest status is updated via the server.

[0200] Input: Improvement proposals, progress of improvement work

[0201] Output: Updated remediation status

[0202] Specific actions: Managers and staff enter the progress of improvement work into the tracking system and save the progress status in the database.

[0203] (Application example 1)

[0204] 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."

[0205] There is a lack of a way to efficiently collect user feedback on the experience of using autonomous vehicles, analyze it in real time, and quickly propose improvements. This poses a challenge, delaying the improvement of the service quality of autonomous vehicles. There is also a need for a smooth method of collecting feedback without disrupting the user experience.

[0206] 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.

[0207] In this invention, the server includes an interaction means using a generative AI model to directly collect feedback from users, a storage means for storing the collected feedback, a natural language processing means for analyzing the stored feedback, a display means for visualizing the analysis results, a notification means for notifying the analysis results and improvement suggestions, an input means for passengers of the autonomous vehicle to input feedback using a smartphone, a communication means for transmitting the feedback input by the passengers of the autonomous vehicle to the server in real time, and a generation means using a generative AI model to generate improvements based on the analysis results. This makes it possible to quickly collect and analyze user feedback in the autonomous vehicle and make appropriate improvement suggestions.

[0208] A "generative AI model" is a model that uses artificial intelligence to generate, analyze, and suggest user feedback.

[0209] "Interactive means" are means for communicating with users, such as collecting feedback.

[0210] "Storage means" means means for storing collected feedback.

[0211] "Natural language processing means" is a means for analyzing collected feedback, and involves performing keyword extraction, sentiment analysis, topic classification, etc.

[0212] The "display means" is a means for visually displaying the analysis results.

[0213] "Notification means" refers to the means for notifying the person in charge of the analysis results and improvement suggestions.

[0214] "Input means" refers to the smartphone interface that allows users to input feedback.

[0215] "Communication means" refers to a means for transmitting feedback from users to the server in real time.

[0216] The "generation means" is a means that uses a generative AI model to generate improvement proposals based on the analysis results.

[0217] An "autonomous vehicle" is a vehicle in which driving operations are automated.

[0218] The system according to the present invention includes the following elements in order to efficiently collect feedback from users of autonomous vehicles, analyze the feedback, and make appropriate improvement suggestions.

[0219] 1. Feedback gathering phase

[0220] The server sends a welcome message to the user via the smartphone application, such as "Tell us what you think! Tell us about your experience riding in a self-driving vehicle." This prompts the user to provide feedback.

[0221] The device (smartphone) displays a welcome message along with an input field to allow the user to enter feedback.

[0222] The user provides feedback by speaking or typing, for example, "I couldn't see the scenery from the window very well" or "The air conditioning was too strong and it was cold."

[0223] 2. Feedback analysis phase

[0224] The server stores the received feedback in a storage means (e.g., a database or a JSON file).

[0225] Next, the feedback is analyzed using natural language processing tools, such as a generative AI model (e.g., OpenAI's GPT-4®), to extract keywords from the feedback and perform sentiment analysis and topic classification.

[0226] The analysis results are saved as text. For example, from feedback such as "The air conditioning was too strong and it was cold," keywords such as "air conditioning" and "cold" are extracted.

[0227] 3. Response and Improvement Phase

[0228] The server uses a generative AI model based on the analysis results to generate specific improvement proposals, such as "improving the automatic adjustment function of the air conditioning system."

[0229] The improvement proposal will be notified to the responsible person via email or an intranet notification system.

[0230] The device (smartphone or tablet) displays the analysis results in a dashboard format, allowing managers and staff to check the results. Tools are also provided for tracking the progress of improvements.

[0231] Hardware and software used

[0232] Hardware: Servers, smartphones, network devices

[0233] Software: Python, Flask, OpenAI API (GPT-4)

[0234] Data processing and calculation

[0235] Feedback is collected using a smartphone app, and the input feedback is sent to a server in real time.

[0236] Feedback is stored on the server side, and a natural language processing engine (GPT-4) is used to extract keywords, analyze sentiment, and classify topics.

[0237] Common patterns and trends are identified from the analysis results, and specific improvement suggestions are generated using a generative AI model.

[0238] Finally, by notifying the person in charge of the improvement proposal, a prompt response can be made.

[0239] Examples and prompts

[0240] Specific examples

[0241] When a user enters feedback while riding in an autonomous vehicle, such as "I couldn't see the scenery from the window very well" or "The air conditioning was too strong and it was cold," the system collects and analyzes this in real time. As a result of the analysis, it generates suggestions such as "Improve the window brightness adjustment function" or "Improve the automatic air conditioning adjustment function" and notifies the person in charge. The person in charge can then directly improve the system based on these suggestions.

[0242] Prompt Sentence Examples

[0243] Analyze the following feedback:

[0244] ["I couldn't see the scenery from the window very well", "The air conditioning was too strong and it was cold"]

[0245] Generate improvement suggestions based on the following feedback analysis results:

[0246] ["Improve the window brightness adjustment function", "Improve the automatic air conditioning adjustment function"]

[0247] The present invention makes it possible to efficiently and quickly improve the user experience in autonomous vehicles.

[0248] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0249] Step 1:

[0250] Feedback collection

[0251] ---

[0252] Input: The user responds to the "Tell us what you think" welcome message displayed on the smartphone app.

[0253] Action: The user enters feedback and presses the submit button. For example, the user enters feedback such as "The view from the train window was not very clear."

[0254] Output: The feedback data entered by the user is sent to the server via the smartphone app.

[0255] Step 2:

[0256] Save your feedback

[0257] ---

[0258] Input: Feedback data submitted by the user

[0259] Behavior: The server stores the received feedback data in a storage medium (e.g., a database or a JSON file).

[0260] Output: Stored feedback data

[0261] Step 3:

[0262] Feedback Analysis

[0263] ---

[0264] Input: Stored feedback data

[0265] How it works: The server analyzes the feedback using natural language processing tools. Generative AI models such as GPT-4 are used to extract keywords, analyze sentiment, and classify topics. For example, from the feedback "The air conditioning was too strong and it was cold," it extracts keywords such as "air conditioning" and "cold."

[0266] Output: Analyzed feedback data (keywords and sentiment analysis results)

[0267] Step 4:

[0268] Visualization of analysis results

[0269] ---

[0270] Input: Parsed feedback data

[0271] How it works: The server uses the analysis results to visualize the results as graphs and charts, and processes the data so that it can be displayed in a dashboard format.

[0272] Output: Visualized analysis results (e.g., graphs, charts, etc.)

[0273] Step 5:

[0274] Generate improvement suggestions

[0275] ---

[0276] Input: Parsed feedback data

[0277] How it works: The server uses the generative AI model to generate specific improvement suggestions based on the analysis results, such as "improve the brightness adjustment function of window glass."

[0278] Output: Specific improvement suggestions

[0279] Step 6:

[0280] Notification of improvement proposals

[0281] ---

[0282] Input: Generated improvement suggestions

[0283] Behavior: The server notifies the person in charge of the generated improvement proposal, using email or an intranet notification system.

[0284] Output: Improvement suggestions notified to the person in charge

[0285] Step 7:

[0286] Review and implement improvement proposals

[0287] ---

[0288] Input: Improvement proposal notified to the person in charge

[0289] Action: The person in charge receives a notification, checks the proposal, and then implements the specific improvement work and enters the progress into the system. For example, the person in charge implements a proposal to "improve the automatic adjustment function of the air conditioning system."

[0290] Output: Progress of improvement work

[0291] In this way, data processing and calculations are carried out at each step, ultimately improving the service quality of autonomous vehicles.

[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] The system of the present invention combines a generative AI model, storage means, natural language processing means, visualization means, notification means, statistical analysis means, and an emotion engine to collect and analyze user feedback and automatically generate specific improvement proposals. This system operates among a server, terminals, and users.

[0294] Interaction Phase (Feedback Collection)

[0295] server:

[0296] When a user accesses the server, the generative AI model is activated and a welcome message is sent to the user, such as "Tell us your opinion. What product / service is it about?" This prompts the user to provide feedback.

[0297] Device:

[0298] The terminal displays a welcome message and input fields for the user to enter feedback, which is sent to the server in real time.

[0299] User:

[0300] Users enter their opinions and requests regarding products and services and press the submit button. For example, they can enter feedback such as, "I think the design of this app is difficult to use."

[0301] Analysis phase (analysis of feedback)

[0302] server:

[0303] The server stores the received feedback in storage. It then analyzes the feedback using natural language processing. This analysis includes keyword extraction, sentiment analysis, and topic classification. For example, if the feedback "The button is small and difficult to tap" is analyzed, the keywords "button," "difficult to use," and "difficult to tap" are extracted.

[0304] server:

[0305] Furthermore, an emotion engine is used to recognize user emotions, such as "dissatisfaction" or "irritation." This emotion data is used to assess the importance and urgency of feedback.

[0306] server:

[0307] The analysis results can be used to identify common trends and patterns across multiple pieces of feedback, such as finding that a particular version of an app is reporting a high number of "dissatisfied" and "irritated" users. This information can then be used to generate data that can be displayed as graphs or charts using visualization tools.

[0308] Device:

[0309] The device displays the analysis results in the form of a dashboard, allowing managers and product development teams to intuitively grasp feedback trends, patterns, and sentiment data.

[0310] Response and improvement phase (proposing improvements)

[0311] server:

[0312] The server uses a generative AI model to generate specific improvement suggestions based on the analytical and statistical analysis results. For example, suggestions might be made such as "increase the button size" or "expand the tap area in the UI design." Additionally, based on emotional data, it prioritizes the most urgent improvements.

[0313] server:

[0314] The generated improvement proposals are notified to the person in charge via email or an intranet notification system.

[0315] Device:

[0316] The terminal provides an interface for managers and personnel to review improvement proposals, and also provides tools for tracking the progress of improvement work.

[0317] User (Administrator / Contact Person):

[0318] Managers and staff members then carry out specific improvement work based on the proposals. The progress of the improvement work is entered into the system, and the latest status is updated via the server. The progress of the improvement work is also displayed on the dashboard, allowing all parties involved to understand the progress.

[0319] Specific examples

[0320] For example, if user feedback about a certain app is that "the buttons are small and difficult to use" or "the colors are hard to see," and the emotion engine detects "dissatisfaction" or "irritation," the server collects, stores, and analyzes that feedback. Based on the analysis results, improvement suggestions such as "increase the button size" or "increase the color contrast" are generated and notified to the design team in charge. The design team then uses the suggestions to revise the app's design and contribute to improving the user experience.

[0321] This system allows for efficient collection and analysis of user feedback and their emotions, enabling prompt and concrete improvement measures to be taken.

[0322] The processing flow will be explained below.

[0323] Step 1: User authentication

[0324] User:

[0325] Enter your username and password to log in to the system.

[0326] server:

[0327] Validates the entered credentials and authenticates the user. If successful, checks the user's access rights and loads the initial configuration information.

[0328] Step 2: Initiating a feedback dialogue

[0329] server:

[0330] Generate a welcome message and send it to the device, for example, "What product / service would you like to share your thoughts on?"

[0331] Device:

[0332] It displays a welcome message and an input field to prompt the user for input.

[0333] Step 3: Provide feedback

[0334] User:

[0335] Enter your opinions and requests regarding products and services and press the send button.

[0336] Device:

[0337] Send the feedback data entered by the user to the server.

[0338] Step 4: Receive and store feedback

[0339] server:

[0340] The received feedback data is stored in storage, including the user ID, date and time, and specific opinions.

[0341] Step 5: Continuing the Generative AI Model

[0342] server:

[0343] A generative AI model is used to analyze user feedback and generate the next question, for example, "Which parts specifically did you find difficult to use?"

[0344] server:

[0345] Send the following question to the device:

[0346] Step 6: Continue the conversation

[0347] Device:

[0348] Displays the question sent by the server.

[0349] User:

[0350] Enter an answer to the question and submit. Example: "The buttons are small and difficult to tap."

[0351] Device:

[0352] The user's answer is sent to the server.

[0353] Step 7: Collect emotion recognition data

[0354] server:

[0355] The emotion engine is used to recognize the user's emotions from the input feedback, for example, detecting emotions such as "dissatisfaction" or "irritation."

[0356] Step 8: Analyze feedback and incorporate sentiment data

[0357] server:

[0358] The collected feedback and sentiment data is analyzed using natural language processing tools, including keyword extraction, sentiment analysis, and topic classification. For example, keywords such as "button," "difficult to use," and "difficult to tap" are extracted.

[0359] server:

[0360] Emotional data is incorporated into the analysis results to assess the importance and urgency of feedback, and feedback with high importance is tagged as high priority.

[0361] Step 9: Identify trends and patterns

[0362] server:

[0363] Statistically process feedback from multiple users to identify common trends and patterns. For example, find out if a particular version of an app is generating a lot of frustration or irritation.

[0364] Step 10: Visualize the results

[0365] Device:

[0366] Provides a dashboard where administrators and staff can check the analysis results, displaying graphs and charts of the analysis results. Example: Showing that a specific version has a lot of negative feedback about "button size."

[0367] Step 11: Generate improvement suggestions

[0368] server:

[0369] Based on the results of analytical and statistical analysis, a generative AI model is used to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are created. Additionally, based on emotional data, the system prioritizes and presents particularly urgent improvement points.

[0370] Step 12: Notification of improvement proposals

[0371] server:

[0372] The generated improvement proposals are notified to the person in charge via email or an intranet notification system.

[0373] Step 13: Tracking Improvement Efforts

[0374] Device:

[0375] It provides an interface for managers and staff to review improvement proposals and track their progress. Once specific improvement work is initiated, the progress is updated in the system.

[0376] Step 14: Follow up on user feedback

[0377] server:

[0378] Once the improvements are complete, you can follow up by notifying users of the changes and asking for their feedback.

[0379] This allows for the automation and efficient execution of a series of processes, from collecting user feedback to recognizing emotions, analyzing them, visualizing the results, notifying improvement suggestions, and tracking improvement work.

[0380] Example 2

[0381] 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."

[0382] Conventional feedback collection systems have difficulty efficiently analyzing user feedback and automatically generating specific improvement proposals. Furthermore, due to a lack of emotion recognition and statistical trend analysis, they are unable to properly evaluate the importance and urgency of feedback. A system that can solve these issues and effectively utilize user feedback is needed.

[0383] 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.

[0384] In this invention, the server includes an interaction means using a generative AI model to directly collect feedback from users, a data storage means for storing the collected feedback, a natural language processing means for extracting keywords and classifying topics based on the stored feedback data, a sentiment analysis means for detecting sentiment in the analyzed feedback data, a data visualization means for visually displaying the analysis results, and a notification means for notifying the analysis results and improvement suggestions.

[0385] This makes it possible to efficiently collect and analyze feedback from users and quickly generate and communicate specific improvement suggestions, including emotional data.

[0386] A "generative AI model" is an artificial intelligence model that interprets user feedback in natural language and collects it in an interactive format.

[0387] "Data storage means" refers to a database system or storage system for storing and managing collected feedback data.

[0388] "Natural language processing means" refers to natural language processing technology for analyzing collected feedback data and performing keyword extraction and topic classification.

[0389] "Emotion analysis means" refers to a technique for detecting a user's emotions from the analyzed feedback data.

[0390] "Data visualization means" refers to tools and technologies that visually display the results of analyzed feedback data, making it easier for managers and staff to understand.

[0391] "Notification means" refers to a communication means for notifying the person in charge of the analysis results and generated improvement proposals.

[0392] "Statistical analysis methods" refers to statistical methods and techniques for identifying common trends or patterns from multiple feedback data.

[0393] "Dashboard" refers to the user interface that allows administrators and personnel to view and track analysis results.

[0394] The system of the present invention combines a generative AI model, data storage means, natural language processing means, sentiment analysis means, data visualization means, notification means, and statistical analysis means to collect and analyze user feedback and automatically generate specific improvement proposals. This system operates among a server, terminals, and users.

[0395] Collecting feedback

[0396] server:

[0397] The server activates the generative AI model when a user accesses the system and sends a welcome message, such as "Tell us your opinion. What product / service is it about?", which prompts the user to provide feedback.

[0398] Device:

[0399] The device displays the received welcome message and allows the user to enter feedback, which is sent to the server in real time.

[0400] User:

[0401] Users enter their opinions and requests regarding products and services and press the submit button. For example, they can enter feedback such as, "I think the design of this app is difficult to use."

[0402] Feedback analysis and sentiment analysis

[0403] server:

[0404] The server stores the received feedback in a data storage means, for example, a database system such as MySQL (registered trademark) or PostgreSQL.

[0405] Next, the feedback is analyzed using natural language processing tools (e.g., NLTK, spacy). This includes keyword extraction and topic classification. For example, if the feedback says, "The button is small and difficult to tap," the keywords "button," "small," and "difficult to tap" are extracted.

[0406] Additionally, sentiment analysis tools (e.g., BERT) are used to recognize user emotions. For example, emotions such as "dissatisfaction" and "irritation" are detected. This emotional data is used to assess the importance and urgency of the feedback.

[0407] Visualizing and notifying results

[0408] server:

[0409] Based on the analysis results, we use statistical analysis methods to identify common trends and patterns across multiple pieces of feedback, for example, finding that a particular version of an app is more likely to be "frustrated" or "irritated."

[0410] Next, data visualization tools (e.g., D3.js or Chart.js) are used to generate graphs and charts that display these results, allowing managers and product development teams to intuitively understand feedback trends, patterns, and sentiment data.

[0411] Device:

[0412] The terminal displays the visualized data sent from the server in the form of a dashboard, allowing managers and product development teams to intuitively grasp feedback trends, patterns, and sentiment data.

[0413] Generate and notify improvement suggestions

[0414] server:

[0415] The server uses a generative AI model (e.g., GPT-3) based on the analytical and statistical analysis results to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are generated. Additionally, based on emotional data, it prioritizes and presents particularly urgent improvement points.

[0416] Next, the generated improvement proposals are notified to the person in charge via a mail server or an intranet notification system.

[0417] Device:

[0418] The device will display a notification to allow the administrator or person in charge to check the improvement proposal, for example, through the email app or a dedicated notification app.

[0419] User (Administrator / Contact Person):

[0420] Managers and staff members then carry out specific improvement work based on the proposals. The progress of the improvement work is entered into the system, and the latest status is updated via the server. The progress of the improvement work is also displayed on the dashboard, allowing all parties involved to understand the progress.

[0421] Prompt Sentence Examples

[0422] Here are some examples of prompts to input to a generative AI model:

[0423] "After collecting user feedback on product X and performing sentiment analysis, what improvements would you suggest?"

[0424] "Analyze the negative feedback received from users of Service Y and identify specific areas for improvement."

[0425] This prompt allows the AI ​​model to quickly generate the necessary analysis and suggestions.

[0426] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0427] Step 1:

[0428] Feedback session begins

[0429] server:

[0430] When a user accesses the system, the server launches the generative AI model and sends a welcome message, such as "What product / service would you like to share your thoughts on?"

[0431] Input: User's access request

[0432] Output: Welcome message

[0433] Device:

[0434] The terminal displays the received welcome message on the user interface, along with a text box for entering feedback and a submit button.

[0435] Input: Welcome message sent by the server

[0436] Output: A welcome message and an input field.

[0437] Step 2:

[0438] Enter and submit feedback

[0439] User:

[0440] Users can enter their feedback into a text box on their device and press the submit button, for example, "I think the design of this app is difficult to use."

[0441] Input: Feedback

[0442] Output: Send feedback

[0443] Device:

[0444] The device sends the feedback entered by the user to the server in real time.

[0445] Input: User feedback

[0446] Output: Send feedback to the server

[0447] Step 3:

[0448] Save your feedback

[0449] server:

[0450] The server stores the received feedback in a storage means, for example, a database system such as MySQL or PostgreSQL.

[0451] Input: User feedback data

[0452] Output: Saving the feedback data to a database

[0453] Step 4:

[0454] Feedback Analysis

[0455] server:

[0456] The server uses natural language processing tools (e.g., NLTK, Spacy) to analyze the stored feedback data. This analysis includes keyword extraction and topic classification. For example, from the feedback "The button is small and difficult to tap," the keywords "button," "small," and "difficult to tap" are extracted.

[0457] Input: Stored feedback data

[0458] Output: Extracted keywords and topics

[0459] Step 5:

[0460] Conducting sentiment analysis

[0461] server:

[0462] The server performs sentiment analysis of the feedback using sentiment analysis tools (e.g., BERT). For example, emotions such as "dissatisfaction" and "irritation" are detected. This sentiment data is used to evaluate the importance and urgency of the feedback.

[0463] Input: Feedback data and extracted keywords

[0464] Output: Emotion data

[0465] Step 6:

[0466] Visualizing the results

[0467] server:

[0468] Based on the analysis results and sentiment analysis results, the server uses statistical analysis tools to identify trends and patterns, and generates visualized data using data visualization tools (e.g., D3.js or Chart.js), such as graphs and charts showing feedback trends.

[0469] Input: Analysis results and emotion data

[0470] Output: Visualized data (graphs and charts)

[0471] Device:

[0472] The terminal displays the visualized data sent from the server in the form of a dashboard, allowing managers and product development teams to understand feedback trends and sentiment data.

[0473] Input: Visualization data sent from the server

[0474] Output: Dashboard display

[0475] Step 7:

[0476] Generate improvement suggestions

[0477] server:

[0478] The server uses a generative AI model (e.g., GPT-3) based on the analytical and statistical analysis results to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are generated. Additionally, based on emotional data, it prioritizes and presents particularly urgent improvement points.

[0479] Input: Analysis and statistical analysis results

[0480] Output: Improvement suggestions

[0481] Step 8:

[0482] Notification of improvement proposals

[0483] server:

[0484] The server notifies the person in charge of the generated improvement proposals using a mail server or an intranet notification system.

[0485] Input: Improvement Suggestion

[0486] Output: Notification to the person in charge

[0487] Device:

[0488] The device will display a notification to allow the administrator or person in charge to check the improvement proposal, for example, through the email app or a dedicated notification app.

[0489] Input: Notification from the server

[0490] Output: Display notification

[0491] Step 9:

[0492] Review and implement the proposal

[0493] User (Administrator / Contact Person):

[0494] Managers and staff members review the proposals and implement specific improvement work. The progress of the improvement work is entered into the system, and the latest status is updated via the server. The progress of the improvement work is also displayed on the dashboard, allowing all parties involved to understand the progress.

[0495] Input: Improvement Suggestion

[0496] Output: Progress of the implemented improvement work

[0497] (Application example 2)

[0498] 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."

[0499] In recent years, many online shopping sites have been trying to improve their services by collecting and analyzing user feedback, but this process is often done manually, requiring time and effort. It is also difficult to centrally manage the content of feedback and generate quick and specific improvement proposals. In particular, there is a need for a method to efficiently process large amounts of feedback and visualize the analysis results in an easy-to-understand manner. An effective system to solve these challenges is needed.

[0500] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0501] In this invention, the server includes a dialogue means using a generative AI model, a data storage means for saving collected feedback, a natural language processing means for analyzing the saved feedback, an information visualization means for visualizing the analysis results, an information transmission means for notifying generated improvement suggestions, and an interface provision means for tracking the progress of the improvement suggestions, thereby enabling efficient collection and analysis of user feedback and prompt and specific improvement suggestions to be provided.

[0502] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and generates new data.

[0503] "Interaction means" refers to a means of communication between a user and a system.

[0504] "Data storage means" refers to means for accumulating and storing data such as feedback.

[0505] "Natural language processing means" refers to means for analyzing text data and extracting meaning.

[0506] "Information visualization means" refers to means for displaying analytical results in visual formats such as graphs and charts.

[0507] "Information transmission means" refers to a means for informing related parties of the generated improvement proposals.

[0508] The "interface providing means" is a means for providing an interface for a user to check and operate information.

[0509] "Data analysis means" refers to means for processing received data and extracting trends and patterns.

[0510] A "display device" is a device for displaying visualized information.

[0511] The system according to the present invention automates the collection and analysis of feedback and the generation of improvement proposals for an online shopping site. Specific embodiments of this system will be described below.

[0512] Feedback gathering phase

[0513] When a user accesses a shopping site, the server activates the generative AI model and sends a welcome message. This message prompts the user to provide feedback, and is displayed in the form of, "Tell us your opinion. What product / service is it about?" The device displays this welcome message along with an input field for the user, and the user enters their feedback through the interface. This input is sent to the server in real time.

[0514] Feedback Analysis Phase

[0515] The server stores the collected feedback in a database. Next, it uses natural language processing (NLTK) to analyze the text data and extract keywords. An emotion engine is also used in this process to understand the user's emotions. The emotion data is added to the analysis results and used to evaluate the importance and urgency. The analysis results are displayed visually using information visualization tools so that managers and development teams can review them.

[0516] Improvement proposal generation phase

[0517] The server uses a generative AI model (TENSORFLOW (registered trademark)) based on the analysis results and data analysis means to generate specific improvement proposals. For example, if the feedback includes an opinion that "the search function is difficult to use," a proposal to "improve the interface of the search function" is generated. The generated improvement proposals are notified to the person in charge via information transmission means (SendGrid, Slack API).

[0518] The progress of improvement proposals is tracked through an interface provided by the device, and managers and staff can use a dashboard to monitor improvement proposals and their progress across multiple metrics.

[0519] Specific examples

[0520] If a user provides feedback that the app's design is difficult to use, the generative AI model will generate specific suggestions for improvement, such as increasing the button size or expanding the tap area in the UI design. These suggestions will be notified to the design team, who will then take action.

[0521] Here is an example prompt:

[0522] Please provide your feedback:

[0523] I think the design of this app is difficult to use.

[0524] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0525] Step 1:

[0526] When a user accesses the online shopping site, the server launches the generative AI model and sends the user a welcome message prompting them to provide feedback. Specifically, the message "Please tell us your opinion. Which product / service is it about?" is displayed on the user's device. This message is a prompt to encourage the user to enter feedback.

[0527] Step 2:

[0528] The user inputs feedback according to the welcome message, and the device sends this input to the server in real time. For example, the user may enter feedback such as "The design of this app is difficult to use." This feedback becomes input data to the server.

[0529] Step 3:

[0530] The server stores the received feedback in a database, where the data is stored in its original form and is used for subsequent analysis.

[0531] Step 4:

[0532] The server analyzes the saved feedback using natural language processing (NLTK). Specifically, it extracts keywords from the text data and analyzes the user's emotions. This analysis evaluates the importance and urgency of the feedback content. For example, the keyword "difficult to use" can be used to detect user dissatisfaction or irritation.

[0533] Step 5:

[0534] The server visually displays the analysis results using information visualization tools. The analysis results are displayed on terminals in dashboard format so that administrators and development teams can review them. Graphs and charts are used to clarify trends and patterns in the data.

[0535] Step 6:

[0536] The server uses a generative AI model (TensorFlow) to generate specific improvement suggestions based on the analysis results. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are generated. In this process, important parts of the feedback are extracted and specific measures are proposed.

[0537] Step 7:

[0538] The generated improvement proposals are notified to the responsible person via information transmission methods (SendGrid or Slack API), such as email or internal messaging systems. The notification includes the priority of the improvement and the specific proposal content.

[0539] Step 8:

[0540] The device provides the manager or person in charge with an interface to track the content and progress of the improvement proposal. Using the dashboard, the manager or person in charge can check the progress of the improvement work in real time and take necessary actions.

[0541] 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.

[0542] 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.

[0543] 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.

[0544] [Second embodiment]

[0545] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0546] 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.

[0547] 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).

[0548] 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.

[0549] 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.

[0550] 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).

[0551] 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.

[0552] 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.

[0553] 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.

[0554] 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.

[0555] 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.

[0556] 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."

[0557] The system of the present invention is a system for collecting and analyzing user feedback using a generative AI model. This system operates among a server, a terminal, and a user, and is implemented in the following manner.

[0558] Interaction Phase (Feedback Collection)

[0559] server:

[0560] When a user accesses the server, the generative AI model is activated and a welcome message is sent to the user, such as "Tell us your opinion. What product / service is it about?" This prompts the user to provide feedback.

[0561] Device:

[0562] The terminal displays a welcome message and an input field for the user to enter their feedback, which is sent to the server in real time.

[0563] User:

[0564] Users enter their opinions and requests about the product or service and press the submit button. For example, they can enter feedback such as, "I think the design of this app is difficult to use."

[0565] Analysis phase (analysis of feedback)

[0566] server:

[0567] The server stores the received feedback in storage. It then analyzes the feedback using natural language processing. This analysis includes keyword extraction, sentiment analysis, and topic classification. For example, if the feedback "The button is small and difficult to tap" is analyzed, the keywords "button," "difficult to use," and "difficult to tap" are extracted.

[0568] server:

[0569] The analysis results can be used to identify common trends or patterns across multiple pieces of feedback, such as finding that a particular version of an app has multiple reports of the same issue, and then use this information to generate data that can be used to display the results in graphs or charts.

[0570] Device:

[0571] The terminal displays the analysis results in the form of a dashboard, allowing managers and product development teams to intuitively grasp trends and patterns in feedback.

[0572] Response and improvement phase (proposing improvements)

[0573] server:

[0574] Based on the analytical and statistical analysis results, the server uses a generative AI model to generate specific improvement suggestions, such as "increase the size of buttons" or "expand the tap area of ​​the user interface."

[0575] server:

[0576] The generated improvement proposals are notified to the person in charge via email or an intranet notification system.

[0577] Device:

[0578] The terminal provides an interface for managers and personnel to review improvement proposals, and also provides tools for tracking the progress of improvement work.

[0579] User (Administrator / Contact Person):

[0580] Managers and staff members implement specific improvement work based on the proposals. The progress of the improvement work is entered into the system, and the latest status is updated via the server.

[0581] Specific examples

[0582] For example, if user feedback about an app is that "the buttons are small and difficult to use" or "the colors are hard to see," the server collects, stores, and analyzes that feedback. Based on the analysis results, it generates improvement suggestions, such as "increase the button size" or "increase the color contrast," and notifies the relevant design team. The design team then uses these suggestions to revise the app's design and contribute to improving the user experience.

[0583] This system enables efficient collection and analysis of user feedback, enabling prompt and concrete improvement measures to be taken.

[0584] The processing flow will be explained below.

[0585] Step 1: User authentication

[0586] User:

[0587] Enter your username and password to log in to the system.

[0588] server:

[0589] Validates the entered credentials and authenticates the user. If successful, checks the user's access rights and loads the initial configuration information.

[0590] Step 2: Initiating a feedback dialogue

[0591] server:

[0592] Generate a welcome message and send it to the device, for example, "What product / service would you like to share your thoughts on?"

[0593] Device:

[0594] It displays a welcome message and an input field to prompt the user for input.

[0595] Step 3: Provide feedback

[0596] User:

[0597] Enter your opinions and requests regarding products and services and press the send button.

[0598] Device:

[0599] Send the feedback data entered by the user to the server.

[0600] Step 4: Gather feedback

[0601] server:

[0602] A generative AI model is used to analyze the content of user feedback and generate the next question, for example, "Which parts specifically did you find difficult to use?"

[0603] server:

[0604] Send the following question to the device:

[0605] Step 5: Ongoing dialogue

[0606] Device:

[0607] Displays the question sent by the server.

[0608] User:

[0609] Enter an answer to the question and submit. Example: "The buttons are small and difficult to tap."

[0610] Device:

[0611] The user's answer is sent to the server.

[0612] Step 6: Save your feedback

[0613] server:

[0614] The received feedback is stored in a database, including the user ID, date and time, and specific opinions.

[0615] Step 7: Perform text analysis

[0616] server:

[0617] The stored feedback data is analyzed using natural language processing tools, which include keyword extraction, sentiment analysis, and topic classification. For example, keywords such as "button," "difficult to use," and "difficult to tap" are detected.

[0618] Step 8: Identify trends and patterns

[0619] server:

[0620] Statistically process feedback from multiple users to identify common trends and patterns, aggregate the identified information, and generate visualizations in the form of reports.

[0621] Step 9: Visualize the results

[0622] Device:

[0623] Provide a dashboard that can be viewed by administrators and staff, displaying graphs and charts of analytical results. For example, show that a specific version has a lot of negative feedback about "button size."

[0624] Step 10: Generate improvement suggestions

[0625] server:

[0626] Based on the analysis results, a generative AI model is used to generate specific improvement suggestions, such as "increase the size of buttons" or "expand the tap area in the UI design."

[0627] Step 11: Implementing Notifications

[0628] server:

[0629] Proposals for improvement are communicated to the design and product development teams via email or an intranet notification system.

[0630] Step 12: Tracking Improvement Efforts

[0631] Device:

[0632] It provides an interface for managers and staff to review improvement proposals and track their progress. Once specific improvement work is initiated, the progress is updated in the system.

[0633] Step 13: Follow up on user feedback

[0634] server:

[0635] Once the improvements are complete, you can follow up by notifying users of the changes and asking for their feedback.

[0636] This allows you to automate and efficiently execute a series of processes, from collecting user feedback to analyzing it, visualizing the results, notifying improvement suggestions, and tracking improvement work.

[0637] Example 1

[0638] 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."

[0639] Conventional feedback collection systems face challenges in efficiently collecting and analyzing user feedback and quickly implementing improvement proposals. Specifically, the limited means of collecting feedback prevent users from fully incorporating their opinions, and the collected feedback must be analyzed manually, resulting in a long wait for improvement proposals. Furthermore, there is a lack of a way to visually and intuitively grasp the analysis results, and the system lacks a mechanism for effectively tracking the progress of improvement work.

[0640] 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.

[0641] In this invention, the server includes an interaction means using a generative AI model to directly collect feedback from users, a storage device means for saving the collected feedback, a natural language processing device means for analyzing the saved feedback, a statistical analysis device means for identifying common trends and patterns from multiple pieces of feedback, a display device means for visualizing the analysis results, a notification device means for notifying the analysis results and improvement proposals, a user interface means for allowing a manager or person in charge to check the improvement proposals, and a tool for tracking the progress of improvement work, thereby enabling efficient collection and analysis of user feedback and rapid implementation of improvement measures.

[0642] A "generative AI model" is an artificial intelligence model that generates natural language dialogue to collect feedback from users.

[0643] "Interaction means" refers to a means of directly interacting with the user using the generative AI model and obtaining feedback.

[0644] "Storage means" is a hardware or software device for storing collected feedback.

[0645] A "natural language processing means" is a device that performs natural language processing techniques used to analyze the stored feedback.

[0646] "Statistical analysis device means" refers to the statistical analysis techniques used to identify common trends and patterns from multiple feedbacks and the devices that perform them.

[0647] A "display device" is a hardware or software device used to visualize the results of an analysis.

[0648] The "notification device means" is a hardware or software device for notifying the person in charge of the analysis results and improvement suggestions.

[0649] The "user interface means" is a means for providing an interface for managers and staff members to check and operate improvement proposals.

[0650] "Tools" are software or hardware tools for tracking the progress of improvement efforts.

[0651] The present invention relates to a system for collecting and analyzing user feedback using a generative AI model. This system operates among a server, a terminal, and a user, and uses the following hardware and software:

[0652] The server launches a generative AI model (e.g., GPT-3) to collect feedback directly from users and asks for feedback through dialogue. When a user accesses the server, the server generates a welcome message saying, "Please tell us your opinion. What product / service is it about?" and sends it to the device.

[0653] The device displays this welcome message to the user and provides an input field for entering feedback. The user enters their feedback and presses the send button. Specifically, the user enters "The design of this app is difficult to use" and sends it.

[0654] The server stores the feedback received from the user in a storage device (e.g., an SQL database). The stored feedback is then analyzed using a natural language processing system (e.g., spaCy or NLTK). The analysis includes keyword extraction, sentiment analysis, and topic classification. For example, when analyzing the feedback "The button is small and difficult to tap," keywords such as "button," "difficult to use," and "difficult to tap" are extracted.

[0655] Based on the analysis results, the server uses statistical analysis tools (e.g., clustering algorithms or TF-IDF) to identify common trends and patterns among the multiple feedbacks. For example, it may discover that similar issues have been reported multiple times for a particular version of an app. Based on this information, the server visualizes the analysis results as graphs and charts using display tools (e.g., Matplotlib or D3.js).

[0656] The terminal displays the analysis results in the form of a dashboard, allowing managers and product development teams to intuitively grasp trends and patterns in feedback.

[0657] The server uses a generative AI model based on the analytical and statistical analysis results to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area of ​​the user interface" may be generated. The server then notifies the person in charge of these improvement suggestions using a notification device. Notification methods include email and intranet notification systems.

[0658] The terminal provides a user interface that allows managers and staff to check improvement proposals. It also provides tools for tracking the progress of improvement work. Managers and staff implement specific improvement work based on the proposals and enter their progress into the system, which updates the latest status.

[0659] Specific examples

[0660] For example, if user feedback about an app is that "the buttons are small and difficult to use" or "the colors are hard to see," the server collects, stores, and analyzes that feedback. Based on the analysis results, improvement suggestions such as "increase the button size" or "increase the color contrast" are generated and notified to the design team. The design team can then revise the app design based on the improvement suggestions, contributing to an improved user experience.

[0661] Prompt Sentence Examples

[0662] "I want to collect and analyze user feedback on a new app design. I want to know how the server, device, and user work together to identify specific issues."

[0663] This system enables efficient collection and analysis of user feedback, enabling prompt and concrete improvement measures to be taken.

[0664] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0665] Step 1:

[0666] The server launches the generative AI model when a user accesses a specific URL and generates a welcome message.

[0667] Input: User's access request

[0668] Output: Welcome message ("What product / service would you like to hear about?")

[0669] Specific operation: When the server receives an HTTP request, it invokes a generative AI model (e.g., GPT-3) to generate a welcome message, embeds it in an HTML page, and sends it back to the user's browser.

[0670] Step 2:

[0671] The terminal displays an input field along with the welcome message received from the server.

[0672] Input: Welcome message from the server

[0673] Output: User feedback input interface

[0674] Specific behavior: The device (user's browser) uses an HTML form and JavaScript to display a text area where the user can enter feedback and a submit button.

[0675] Step 3:

[0676] The user inputs their opinions and requests regarding the product or service and presses the send button.

[0677] Input: User feedback (e.g., "The design of this app is difficult to use.")

[0678] Output: User-entered feedback data

[0679] Specific behavior: The user enters text in the feedback field and clicks the "Submit" button.

[0680] Step 4:

[0681] The server receives the feedback sent by the user and stores it in a database.

[0682] Input: Feedback data submitted by the user

[0683] Output: Feedback stored in a database

[0684] Specific operation: The server receives the feedback data and stores it in the SQL database using an INSERT statement.

[0685] Step 5:

[0686] The server analyzes the stored feedback using a natural language processing device.

[0687] Input: Saved feedback data

[0688] Output: Analysis results (keyword list, sentiment score, topic tags, etc.)

[0689] Specific operation: The server reads the saved feedback data, sends it to a natural language processing tool (e.g., spaCy or NLTK) via an API, and saves the returned analysis results back in the database.

[0690] Step 6:

[0691] The server performs statistical analysis based on the analysis results to identify common trends and patterns from the multiple feedbacks.

[0692] Input: Analysis results

[0693] Output: Statistical analysis results (identification of common trends and patterns)

[0694] Specific operation: The server uses algorithms such as k-means clustering and TF-IDF to extract commonalities in the feedback and perform statistical analysis.

[0695] Step 7:

[0696] The server generates graphs and charts to visualize the analysis results.

[0697] Input: Statistical analysis results

[0698] Output: Visualized data (graphs, charts, etc.)

[0699] Specific operation: The server uses visualization tools such as Matplotlib and D3.js to generate visualization data based on the feedback trend data.

[0700] Step 8:

[0701] The terminal displays the visualized data received from the server in dashboard format.

[0702] Input: Visualization data from the server

[0703] Output: Dashboard format display

[0704] Specific operation: The terminal (user's browser) displays an HTML page containing visualized data and a dashboard UI.

[0705] Step 9:

[0706] The server uses a generative AI model based on the analytical and statistical analysis results to generate specific improvement suggestions.

[0707] Input: Statistical analysis results

[0708] Output: Improvement suggestion (e.g. "Make the button size larger")

[0709] Specific operation: The server inputs the analysis results as prompt sentences into the generative AI model, and the AI ​​generates suggestions.

[0710] Step 10:

[0711] The server notifies the person in charge of the generated improvement proposal.

[0712] Input: Generated improvement suggestions

[0713] Output: Notification to responsible parties (via email or intranet notification system)

[0714] Specific operation: The server sends an email containing the proposal to the person in charge via the SMTP server or notifies them using the intranet notification API.

[0715] Step 11:

[0716] The device provides a UI for managers and staff to review improvement proposals, and also provides tools for tracking the progress of improvement work.

[0717] Input: Improvement suggestion notification from the server

[0718] Output: Display improvement suggestions to managers and staff and provide tracking tools

[0719] Specific operation: The terminal (user's browser) displays improvement proposals in list format and provides the person in charge with the ability to update the progress status.

[0720] Step 12:

[0721] Managers and staff members then carry out specific improvement work based on the suggestions. Progress is entered into the system, and the latest status is updated via the server.

[0722] Input: Improvement proposals, progress of improvement work

[0723] Output: Updated remediation status

[0724] Specific actions: Managers and staff enter the progress of improvement work into the tracking system and save the progress status in the database.

[0725] (Application example 1)

[0726] 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."

[0727] There is a lack of a way to efficiently collect user feedback on the experience of using autonomous vehicles, analyze it in real time, and quickly propose improvements. This poses a challenge, delaying the improvement of the service quality of autonomous vehicles. There is also a need for a smooth method of collecting feedback without disrupting the user experience.

[0728] 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.

[0729] In this invention, the server includes an interaction means using a generative AI model to directly collect feedback from users, a storage means for storing the collected feedback, a natural language processing means for analyzing the stored feedback, a display means for visualizing the analysis results, a notification means for notifying the analysis results and improvement suggestions, an input means for passengers of the autonomous vehicle to input feedback using a smartphone, a communication means for transmitting the feedback input by the passengers of the autonomous vehicle to the server in real time, and a generation means using a generative AI model to generate improvements based on the analysis results. This makes it possible to quickly collect and analyze user feedback in the autonomous vehicle and make appropriate improvement suggestions.

[0730] A "generative AI model" is a model that uses artificial intelligence to generate, analyze, and suggest user feedback.

[0731] "Interactive means" are means for communicating with users, such as collecting feedback.

[0732] "Storage means" means means for storing collected feedback.

[0733] "Natural language processing means" is a means for analyzing collected feedback, and involves performing keyword extraction, sentiment analysis, topic classification, etc.

[0734] The "display means" is a means for visually displaying the analysis results.

[0735] "Notification means" refers to the means for notifying the person in charge of the analysis results and improvement suggestions.

[0736] "Input means" refers to the smartphone interface that allows users to input feedback.

[0737] "Communication means" refers to a means for transmitting feedback from users to the server in real time.

[0738] The "generation means" is a means that uses a generative AI model to generate improvement proposals based on the analysis results.

[0739] An "autonomous vehicle" is a vehicle in which driving operations are automated.

[0740] The system according to the present invention includes the following elements in order to efficiently collect feedback from users of autonomous vehicles, analyze the feedback, and make appropriate improvement suggestions.

[0741] 1. Feedback gathering phase

[0742] The server sends a welcome message to the user via the smartphone application, such as "Tell us what you think! Tell us about your experience riding in a self-driving vehicle." This prompts the user to provide feedback.

[0743] The device (smartphone) displays a welcome message along with an input field to allow the user to enter feedback.

[0744] The user provides feedback by speaking or typing, for example, "I couldn't see the scenery from the window very well" or "The air conditioning was too strong and it was cold."

[0745] 2. Feedback analysis phase

[0746] The server stores the received feedback in a storage means (e.g., a database or a JSON file).

[0747] Next, the feedback is analyzed using natural language processing tools, such as a generative AI model (e.g., OpenAI's GPT-4), to extract keywords from the feedback and perform sentiment analysis and topic classification.

[0748] The analysis results are saved as text. For example, from feedback such as "The air conditioning was too strong and it was cold," keywords such as "air conditioning" and "cold" are extracted.

[0749] 3. Response and Improvement Phase

[0750] The server uses a generative AI model based on the analysis results to generate specific improvement proposals, such as "improving the automatic adjustment function of the air conditioning system."

[0751] The improvement proposal will be notified to the responsible person via email or an intranet notification system.

[0752] The device (smartphone or tablet) displays the analysis results in a dashboard format, allowing managers and staff to check the results. Tools are also provided for tracking the progress of improvements.

[0753] Hardware and software used

[0754] Hardware: Servers, smartphones, network devices

[0755] Software: Python, Flask, OpenAI API (GPT-4)

[0756] Data processing and calculation

[0757] Feedback is collected using a smartphone app, and the input feedback is sent to a server in real time.

[0758] Feedback is stored on the server side, and a natural language processing engine (GPT-4) is used to extract keywords, analyze sentiment, and classify topics.

[0759] Common patterns and trends are identified from the analysis results, and specific improvement suggestions are generated using a generative AI model.

[0760] Finally, by notifying the person in charge of the improvement proposal, a prompt response can be made.

[0761] Examples and prompts

[0762] Specific examples

[0763] When a user enters feedback while riding in an autonomous vehicle, such as "I couldn't see the scenery from the window very well" or "The air conditioning was too strong and it was cold," the system collects and analyzes this in real time. As a result of the analysis, it generates suggestions such as "Improve the window brightness adjustment function" or "Improve the automatic air conditioning adjustment function" and notifies the person in charge. The person in charge can then directly improve the system based on these suggestions.

[0764] Prompt Sentence Examples

[0765] Analyze the following feedback:

[0766] ["I couldn't see the scenery from the window very well", "The air conditioning was too strong and it was cold"]

[0767] Generate improvement suggestions based on the following feedback analysis results:

[0768] ["Improve the window brightness adjustment function", "Improve the automatic air conditioning adjustment function"]

[0769] The present invention makes it possible to efficiently and quickly improve the user experience in autonomous vehicles.

[0770] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0771] Step 1:

[0772] Feedback collection

[0773] ---

[0774] Input: The user responds to the "Tell us what you think" welcome message displayed on the smartphone app.

[0775] Action: The user enters feedback and presses the submit button. For example, the user enters feedback such as "The view from the train window was not very clear."

[0776] Output: The feedback data entered by the user is sent to the server via the smartphone app.

[0777] Step 2:

[0778] Save your feedback

[0779] ---

[0780] Input: Feedback data submitted by the user

[0781] Behavior: The server stores the received feedback data in a storage medium (e.g., a database or a JSON file).

[0782] Output: Stored feedback data

[0783] Step 3:

[0784] Feedback Analysis

[0785] ---

[0786] Input: Stored feedback data

[0787] How it works: The server analyzes the feedback using natural language processing tools. Generative AI models such as GPT-4 are used to extract keywords, analyze sentiment, and classify topics. For example, from the feedback "The air conditioning was too strong and it was cold," it extracts keywords such as "air conditioning" and "cold."

[0788] Output: Analyzed feedback data (keywords and sentiment analysis results)

[0789] Step 4:

[0790] Visualization of analysis results

[0791] ---

[0792] Input: Parsed feedback data

[0793] How it works: The server uses the analysis results to visualize the results as graphs and charts, and processes the data so that it can be displayed in a dashboard format.

[0794] Output: Visualized analysis results (e.g., graphs, charts, etc.)

[0795] Step 5:

[0796] Generate improvement suggestions

[0797] ---

[0798] Input: Parsed feedback data

[0799] How it works: The server uses the generative AI model to generate specific improvement suggestions based on the analysis results, such as "improve the brightness adjustment function of window glass."

[0800] Output: Specific improvement suggestions

[0801] Step 6:

[0802] Notification of improvement proposals

[0803] ---

[0804] Input: Generated improvement suggestions

[0805] Behavior: The server notifies the person in charge of the generated improvement proposal, using email or an intranet notification system.

[0806] Output: Improvement suggestions notified to the person in charge

[0807] Step 7:

[0808] Review and implement improvement proposals

[0809] ---

[0810] Input: Improvement proposal notified to the person in charge

[0811] Action: The person in charge receives a notification, checks the proposal, and then implements the specific improvement work and enters the progress into the system. For example, the person in charge implements a proposal to "improve the automatic adjustment function of the air conditioning system."

[0812] Output: Progress of improvement work

[0813] In this way, data processing and calculations are carried out at each step, ultimately improving the service quality of autonomous vehicles.

[0814] 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.

[0815] The system of the present invention combines a generative AI model, storage means, natural language processing means, visualization means, notification means, statistical analysis means, and an emotion engine to collect and analyze user feedback and automatically generate specific improvement proposals. This system operates among a server, terminals, and users.

[0816] Interaction Phase (Feedback Collection)

[0817] server:

[0818] When a user accesses the server, the generative AI model is activated and a welcome message is sent to the user, such as "Tell us your opinion. What product / service is it about?" This prompts the user to provide feedback.

[0819] Device:

[0820] The terminal displays a welcome message and input fields for the user to enter feedback, which is sent to the server in real time.

[0821] User:

[0822] Users enter their opinions and requests regarding products and services and press the submit button. For example, they can enter feedback such as, "I think the design of this app is difficult to use."

[0823] Analysis phase (analysis of feedback)

[0824] server:

[0825] The server stores the received feedback in storage. It then analyzes the feedback using natural language processing. This analysis includes keyword extraction, sentiment analysis, and topic classification. For example, if the feedback "The button is small and difficult to tap" is analyzed, the keywords "button," "difficult to use," and "difficult to tap" are extracted.

[0826] server:

[0827] Furthermore, an emotion engine is used to recognize user emotions, such as "dissatisfaction" or "irritation." This emotion data is used to assess the importance and urgency of feedback.

[0828] server:

[0829] The analysis results can be used to identify common trends and patterns across multiple pieces of feedback, such as finding that a particular version of an app is reporting a high number of "dissatisfied" and "irritated" users. This information can then be used to generate data that can be displayed as graphs or charts using visualization tools.

[0830] Device:

[0831] The device displays the analysis results in the form of a dashboard, allowing managers and product development teams to intuitively grasp feedback trends, patterns, and sentiment data.

[0832] Response and improvement phase (proposing improvements)

[0833] server:

[0834] The server uses a generative AI model to generate specific improvement suggestions based on the analytical and statistical analysis results. For example, suggestions might be made such as "increase the button size" or "expand the tap area in the UI design." Additionally, based on emotional data, it prioritizes the most urgent improvements.

[0835] server:

[0836] The generated improvement proposals are notified to the person in charge via email or an intranet notification system.

[0837] Device:

[0838] The terminal provides an interface for managers and personnel to review improvement proposals, and also provides tools for tracking the progress of improvement work.

[0839] User (Administrator / Contact Person):

[0840] Managers and staff members then carry out specific improvement work based on the proposals. The progress of the improvement work is entered into the system, and the latest status is updated via the server. The progress of the improvement work is also displayed on the dashboard, allowing all parties involved to understand the progress.

[0841] Specific examples

[0842] For example, if user feedback about a certain app is that "the buttons are small and difficult to use" or "the colors are hard to see," and the emotion engine detects "dissatisfaction" or "irritation," the server collects, stores, and analyzes that feedback. Based on the analysis results, improvement suggestions such as "increase the button size" or "increase the color contrast" are generated and notified to the design team in charge. The design team then uses the suggestions to revise the app's design and contribute to improving the user experience.

[0843] This system allows for efficient collection and analysis of user feedback and their emotions, enabling prompt and concrete improvement measures to be taken.

[0844] The processing flow will be explained below.

[0845] Step 1: User authentication

[0846] User:

[0847] Enter your username and password to log in to the system.

[0848] server:

[0849] Validates the entered credentials and authenticates the user. If successful, checks the user's access rights and loads the initial configuration information.

[0850] Step 2: Initiating a feedback dialogue

[0851] server:

[0852] Generate a welcome message and send it to the device, for example, "What product / service would you like to share your thoughts on?"

[0853] Device:

[0854] It displays a welcome message and an input field to prompt the user for input.

[0855] Step 3: Provide feedback

[0856] User:

[0857] Enter your opinions and requests regarding products and services and press the send button.

[0858] Device:

[0859] Send the feedback data entered by the user to the server.

[0860] Step 4: Receive and store feedback

[0861] server:

[0862] The received feedback data is stored in storage, including the user ID, date and time, and specific opinions.

[0863] Step 5: Continuing the Generative AI Model

[0864] server:

[0865] A generative AI model is used to analyze user feedback and generate the next question, for example, "Which parts specifically did you find difficult to use?"

[0866] server:

[0867] Send the following question to the device:

[0868] Step 6: Continue the conversation

[0869] Device:

[0870] Displays the question sent by the server.

[0871] User:

[0872] Enter an answer to the question and submit. Example: "The buttons are small and difficult to tap."

[0873] Device:

[0874] The user's answer is sent to the server.

[0875] Step 7: Collect emotion recognition data

[0876] server:

[0877] The emotion engine is used to recognize the user's emotions from the input feedback, for example, detecting emotions such as "dissatisfaction" or "irritation."

[0878] Step 8: Analyze feedback and incorporate sentiment data

[0879] server:

[0880] The collected feedback and sentiment data is analyzed using natural language processing tools, including keyword extraction, sentiment analysis, and topic classification. For example, keywords such as "button," "difficult to use," and "difficult to tap" are extracted.

[0881] server:

[0882] Emotional data is incorporated into the analysis results to assess the importance and urgency of feedback, and feedback with high importance is tagged as high priority.

[0883] Step 9: Identify trends and patterns

[0884] server:

[0885] Statistically process feedback from multiple users to identify common trends and patterns. For example, find out if a particular version of an app is generating a lot of frustration or irritation.

[0886] Step 10: Visualize the results

[0887] Device:

[0888] Provides a dashboard where administrators and staff can check the analysis results, displaying graphs and charts of the analysis results. Example: Showing that a specific version has a lot of negative feedback about "button size."

[0889] Step 11: Generate improvement suggestions

[0890] server:

[0891] Based on the results of analytical and statistical analysis, a generative AI model is used to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are created. Additionally, based on emotional data, the system prioritizes and presents particularly urgent improvement points.

[0892] Step 12: Notification of improvement proposals

[0893] server:

[0894] The generated improvement proposals are notified to the person in charge via email or an intranet notification system.

[0895] Step 13: Tracking Improvement Efforts

[0896] Device:

[0897] It provides an interface for managers and staff to review improvement proposals and track their progress. Once specific improvement work is initiated, the progress is updated in the system.

[0898] Step 14: Follow up on user feedback

[0899] server:

[0900] Once the improvements are complete, you can follow up by notifying users of the changes and asking for their feedback.

[0901] This allows for the automation and efficient execution of a series of processes, from collecting user feedback to recognizing emotions, analyzing them, visualizing the results, notifying improvement suggestions, and tracking improvement work.

[0902] Example 2

[0903] 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."

[0904] Conventional feedback collection systems have difficulty efficiently analyzing user feedback and automatically generating specific improvement proposals. Furthermore, due to a lack of emotion recognition and statistical trend analysis, they are unable to properly evaluate the importance and urgency of feedback. A system that can solve these issues and effectively utilize user feedback is needed.

[0905] 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.

[0906] In this invention, the server includes an interaction means using a generative AI model to directly collect feedback from users, a data storage means for storing the collected feedback, a natural language processing means for extracting keywords and classifying topics based on the stored feedback data, a sentiment analysis means for detecting sentiment in the analyzed feedback data, a data visualization means for visually displaying the analysis results, and a notification means for notifying the analysis results and improvement suggestions.

[0907] This makes it possible to efficiently collect and analyze feedback from users and quickly generate and communicate specific improvement suggestions, including emotional data.

[0908] A "generative AI model" is an artificial intelligence model that interprets user feedback in natural language and collects it in an interactive format.

[0909] "Data storage means" refers to a database system or storage system for storing and managing collected feedback data.

[0910] "Natural language processing means" refers to natural language processing technology for analyzing collected feedback data and performing keyword extraction and topic classification.

[0911] "Emotion analysis means" refers to a technique for detecting a user's emotions from the analyzed feedback data.

[0912] "Data visualization means" refers to tools and technologies that visually display the results of analyzed feedback data, making it easier for managers and staff to understand.

[0913] "Notification means" refers to a communication means for notifying the person in charge of the analysis results and generated improvement proposals.

[0914] "Statistical analysis methods" refers to statistical methods and techniques for identifying common trends or patterns from multiple feedback data.

[0915] "Dashboard" refers to the user interface that allows administrators and personnel to view and track analysis results.

[0916] The system of the present invention combines a generative AI model, data storage means, natural language processing means, sentiment analysis means, data visualization means, notification means, and statistical analysis means to collect and analyze user feedback and automatically generate specific improvement proposals. This system operates among a server, terminals, and users.

[0917] Collecting feedback

[0918] server:

[0919] The server activates the generative AI model when a user accesses the system and sends a welcome message, such as "Tell us your opinion. What product / service is it about?", which prompts the user to provide feedback.

[0920] Device:

[0921] The device displays the received welcome message and allows the user to enter feedback, which is sent to the server in real time.

[0922] User:

[0923] Users enter their opinions and requests regarding products and services and press the submit button. For example, they can enter feedback such as, "I think the design of this app is difficult to use."

[0924] Feedback analysis and sentiment analysis

[0925] server:

[0926] The server stores the received feedback in a data storage means, for example, a database system such as MySQL or PostgreSQL.

[0927] Next, the feedback is analyzed using natural language processing tools (e.g., NLTK, spacy). This includes keyword extraction and topic classification. For example, if the feedback says, "The button is small and difficult to tap," the keywords "button," "small," and "difficult to tap" are extracted.

[0928] Additionally, sentiment analysis tools (e.g., BERT) are used to recognize user emotions. For example, emotions such as "dissatisfaction" and "irritation" are detected. This emotional data is used to assess the importance and urgency of the feedback.

[0929] Visualizing and notifying results

[0930] server:

[0931] Based on the analysis results, we use statistical analysis methods to identify common trends and patterns across multiple pieces of feedback, for example, finding that a particular version of an app is more likely to be "frustrated" or "irritated."

[0932] Next, data visualization tools (e.g., D3.js or Chart.js) are used to generate graphs and charts that display these results, allowing managers and product development teams to intuitively understand feedback trends, patterns, and sentiment data.

[0933] Device:

[0934] The terminal displays the visualized data sent from the server in the form of a dashboard, allowing managers and product development teams to intuitively grasp feedback trends, patterns, and sentiment data.

[0935] Generate and notify improvement suggestions

[0936] server:

[0937] The server uses a generative AI model (e.g., GPT-3) based on the analytical and statistical analysis results to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are generated. Additionally, based on emotional data, it prioritizes and presents particularly urgent improvement points.

[0938] Next, the generated improvement proposals are notified to the person in charge via a mail server or an intranet notification system.

[0939] Device:

[0940] The device will display a notification to allow the administrator or person in charge to check the improvement proposal, for example, through the email app or a dedicated notification app.

[0941] User (Administrator / Contact Person):

[0942] Managers and staff members then carry out specific improvement work based on the proposals. The progress of the improvement work is entered into the system, and the latest status is updated via the server. The progress of the improvement work is also displayed on the dashboard, allowing all parties involved to understand the progress.

[0943] Prompt Sentence Examples

[0944] Here are some examples of prompts to input to a generative AI model:

[0945] "After collecting user feedback on product X and performing sentiment analysis, what improvements would you suggest?"

[0946] "Analyze the negative feedback received from users of Service Y and identify specific areas for improvement."

[0947] This prompt allows the AI ​​model to quickly generate the necessary analysis and suggestions.

[0948] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0949] Step 1:

[0950] Feedback session begins

[0951] server:

[0952] When a user accesses the system, the server launches the generative AI model and sends a welcome message, such as "What product / service would you like to share your thoughts on?"

[0953] Input: User's access request

[0954] Output: Welcome message

[0955] Device:

[0956] The terminal displays the received welcome message on the user interface, along with a text box for entering feedback and a submit button.

[0957] Input: Welcome message sent by the server

[0958] Output: A welcome message and an input field.

[0959] Step 2:

[0960] Enter and submit feedback

[0961] User:

[0962] Users can enter their feedback into a text box on their device and press the submit button, for example, "I think the design of this app is difficult to use."

[0963] Input: Feedback

[0964] Output: Send feedback

[0965] Device:

[0966] The device sends the feedback entered by the user to the server in real time.

[0967] Input: User feedback

[0968] Output: Send feedback to the server

[0969] Step 3:

[0970] Save your feedback

[0971] server:

[0972] The server stores the received feedback in a storage means, for example, a database system such as MySQL or PostgreSQL.

[0973] Input: User feedback data

[0974] Output: Saving the feedback data to a database

[0975] Step 4:

[0976] Feedback Analysis

[0977] server:

[0978] The server uses natural language processing tools (e.g., NLTK, Spacy) to analyze the stored feedback data. This analysis includes keyword extraction and topic classification. For example, from the feedback "The button is small and difficult to tap," the keywords "button," "small," and "difficult to tap" are extracted.

[0979] Input: Stored feedback data

[0980] Output: Extracted keywords and topics

[0981] Step 5:

[0982] Conducting sentiment analysis

[0983] server:

[0984] The server performs sentiment analysis of the feedback using sentiment analysis tools (e.g., BERT). For example, emotions such as "dissatisfaction" and "irritation" are detected. This sentiment data is used to evaluate the importance and urgency of the feedback.

[0985] Input: Feedback data and extracted keywords

[0986] Output: Emotion data

[0987] Step 6:

[0988] Visualizing the results

[0989] server:

[0990] Based on the analysis results and sentiment analysis results, the server uses statistical analysis tools to identify trends and patterns, and generates visualized data using data visualization tools (e.g., D3.js or Chart.js), such as graphs and charts showing feedback trends.

[0991] Input: Analysis results and emotion data

[0992] Output: Visualized data (graphs and charts)

[0993] Device:

[0994] The terminal displays the visualized data sent from the server in the form of a dashboard, allowing managers and product development teams to understand feedback trends and sentiment data.

[0995] Input: Visualization data sent from the server

[0996] Output: Dashboard display

[0997] Step 7:

[0998] Generate improvement suggestions

[0999] server:

[1000] The server uses a generative AI model (e.g., GPT-3) based on the analytical and statistical analysis results to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are generated. Additionally, based on emotional data, it prioritizes and presents particularly urgent improvement points.

[1001] Input: Analysis and statistical analysis results

[1002] Output: Improvement suggestions

[1003] Step 8:

[1004] Notification of improvement proposals

[1005] server:

[1006] The server notifies the person in charge of the generated improvement proposals using a mail server or an intranet notification system.

[1007] Input: Improvement Suggestion

[1008] Output: Notification to the person in charge

[1009] Device:

[1010] The device will display a notification to allow the administrator or person in charge to check the improvement proposal, for example, through the email app or a dedicated notification app.

[1011] Input: Notification from the server

[1012] Output: Display notification

[1013] Step 9:

[1014] Review and implement the proposal

[1015] User (Administrator / Contact Person):

[1016] Managers and staff members review the proposals and implement specific improvement work. The progress of the improvement work is entered into the system, and the latest status is updated via the server. The progress of the improvement work is also displayed on the dashboard, allowing all parties involved to understand the progress.

[1017] Input: Improvement Suggestion

[1018] Output: Progress of the implemented improvement work

[1019] (Application example 2)

[1020] 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."

[1021] In recent years, many online shopping sites have been trying to improve their services by collecting and analyzing user feedback, but this process is often done manually, requiring time and effort. It is also difficult to centrally manage the content of feedback and generate quick and specific improvement proposals. In particular, there is a need for a method to efficiently process large amounts of feedback and visualize the analysis results in an easy-to-understand manner. An effective system to solve these challenges is needed.

[1022] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1023] In this invention, the server includes a dialogue means using a generative AI model, a data storage means for saving collected feedback, a natural language processing means for analyzing the saved feedback, an information visualization means for visualizing the analysis results, an information transmission means for notifying generated improvement suggestions, and an interface provision means for tracking the progress of the improvement suggestions, thereby enabling efficient collection and analysis of user feedback and prompt and specific improvement suggestions to be provided.

[1024] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and generates new data.

[1025] "Interaction means" refers to a means of communication between a user and a system.

[1026] "Data storage means" refers to means for accumulating and storing data such as feedback.

[1027] "Natural language processing means" refers to means for analyzing text data and extracting meaning.

[1028] "Information visualization means" refers to means for displaying analytical results in visual formats such as graphs and charts.

[1029] "Information transmission means" refers to a means for informing related parties of the generated improvement proposals.

[1030] The "interface providing means" is a means for providing an interface for a user to check and operate information.

[1031] "Data analysis means" refers to means for processing received data and extracting trends and patterns.

[1032] A "display device" is a device for displaying visualized information.

[1033] The system according to the present invention automates the collection and analysis of feedback and the generation of improvement proposals for an online shopping site. Specific embodiments of this system will be described below.

[1034] Feedback gathering phase

[1035] When a user accesses a shopping site, the server activates the generative AI model and sends a welcome message. This message prompts the user to provide feedback, and is displayed in the form of, "Tell us your opinion. What product / service is it about?" The device displays this welcome message along with an input field for the user, and the user enters their feedback through the interface. This input is sent to the server in real time.

[1036] Feedback Analysis Phase

[1037] The server stores the collected feedback in a database. Next, it uses natural language processing (NLTK) to analyze the text data and extract keywords. An emotion engine is also used in this process to understand the user's emotions. The emotion data is added to the analysis results and used to evaluate the importance and urgency. The analysis results are displayed visually using information visualization tools so that managers and development teams can review them.

[1038] Improvement proposal generation phase

[1039] The server uses a generative AI model (TensorFlow) to generate specific improvement proposals based on the analysis results and data analysis methods. For example, if the feedback includes a comment that the search function is difficult to use, a proposal to improve the search function interface will be generated. The generated improvement proposals are notified to the person in charge via information transmission methods (SendGrid, Slack API).

[1040] The progress of improvement proposals is tracked through an interface provided by the device, and managers and staff can use a dashboard to monitor improvement proposals and their progress across multiple metrics.

[1041] Specific examples

[1042] If a user provides feedback that the app's design is difficult to use, the generative AI model will generate specific suggestions for improvement, such as increasing the button size or expanding the tap area in the UI design. These suggestions will be notified to the design team, who will then take action.

[1043] Here is an example prompt:

[1044] Please provide your feedback:

[1045] I think the design of this app is difficult to use.

[1046] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1047] Step 1:

[1048] When a user accesses the online shopping site, the server launches the generative AI model and sends the user a welcome message prompting them to provide feedback. Specifically, the message "Please tell us your opinion. Which product / service is it about?" is displayed on the user's device. This message is a prompt to encourage the user to enter feedback.

[1049] Step 2:

[1050] The user inputs feedback according to the welcome message, and the device sends this input to the server in real time. For example, the user may enter feedback such as "The design of this app is difficult to use." This feedback becomes input data to the server.

[1051] Step 3:

[1052] The server stores the received feedback in a database, where the data is stored in its original form and is used for subsequent analysis.

[1053] Step 4:

[1054] The server analyzes the saved feedback using natural language processing (NLTK). Specifically, it extracts keywords from the text data and analyzes the user's emotions. This analysis evaluates the importance and urgency of the feedback content. For example, the keyword "difficult to use" can be used to detect user dissatisfaction or irritation.

[1055] Step 5:

[1056] The server visually displays the analysis results using information visualization tools. The analysis results are displayed on terminals in dashboard format so that administrators and development teams can review them. Graphs and charts are used to clarify trends and patterns in the data.

[1057] Step 6:

[1058] The server uses a generative AI model (TensorFlow) to generate specific improvement suggestions based on the analysis results. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are generated. In this process, important parts of the feedback are extracted and specific measures are proposed.

[1059] Step 7:

[1060] The generated improvement proposals are notified to the responsible person via information transmission methods (SendGrid or Slack API), such as email or internal messaging systems. The notification includes the priority of the improvement and the specific proposal content.

[1061] Step 8:

[1062] The device provides the manager or person in charge with an interface to track the content and progress of the improvement proposal. Using the dashboard, the manager or person in charge can check the progress of the improvement work in real time and take necessary actions.

[1063] 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.

[1064] 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.

[1065] 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.

[1066] [Third embodiment]

[1067] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1068] 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.

[1069] 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).

[1070] 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.

[1071] 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.

[1072] 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).

[1073] 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.

[1074] 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.

[1075] 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.

[1076] 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.

[1077] 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.

[1078] 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."

[1079] The system of the present invention is a system for collecting and analyzing user feedback using a generative AI model. This system operates among a server, a terminal, and a user, and is implemented in the following manner.

[1080] Interaction Phase (Feedback Collection)

[1081] server:

[1082] When a user accesses the server, the generative AI model is activated and a welcome message is sent to the user, such as "Tell us your opinion. What product / service is it about?" This prompts the user to provide feedback.

[1083] Device:

[1084] The terminal displays a welcome message and an input field for the user to enter their feedback, which is sent to the server in real time.

[1085] User:

[1086] Users enter their opinions and requests about the product or service and press the submit button. For example, they can enter feedback such as, "I think the design of this app is difficult to use."

[1087] Analysis phase (analysis of feedback)

[1088] server:

[1089] The server stores the received feedback in storage. It then analyzes the feedback using natural language processing. This analysis includes keyword extraction, sentiment analysis, and topic classification. For example, if the feedback "The button is small and difficult to tap" is analyzed, the keywords "button," "difficult to use," and "difficult to tap" are extracted.

[1090] server:

[1091] The analysis results can be used to identify common trends or patterns across multiple pieces of feedback, such as finding that a particular version of an app has multiple reports of the same issue, and then use this information to generate data that can be used to display the results in graphs or charts.

[1092] Device:

[1093] The terminal displays the analysis results in the form of a dashboard, allowing managers and product development teams to intuitively grasp trends and patterns in feedback.

[1094] Response and improvement phase (proposing improvements)

[1095] server:

[1096] Based on the analytical and statistical analysis results, the server uses a generative AI model to generate specific improvement suggestions, such as "increase the size of buttons" or "expand the tap area of ​​the user interface."

[1097] server:

[1098] The generated improvement proposals are notified to the person in charge via email or an intranet notification system.

[1099] Device:

[1100] The terminal provides an interface for managers and personnel to review improvement proposals, and also provides tools for tracking the progress of improvement work.

[1101] User (Administrator / Contact Person):

[1102] Managers and staff members implement specific improvement work based on the proposals. The progress of the improvement work is entered into the system, and the latest status is updated via the server.

[1103] Specific examples

[1104] For example, if user feedback about an app is that "the buttons are small and difficult to use" or "the colors are hard to see," the server collects, stores, and analyzes that feedback. Based on the analysis results, it generates improvement suggestions, such as "increase the button size" or "increase the color contrast," and notifies the relevant design team. The design team then uses these suggestions to revise the app's design and contribute to improving the user experience.

[1105] This system enables efficient collection and analysis of user feedback, enabling prompt and concrete improvement measures to be taken.

[1106] The processing flow will be explained below.

[1107] Step 1: User authentication

[1108] User:

[1109] Enter your username and password to log in to the system.

[1110] server:

[1111] Validates the entered credentials and authenticates the user. If successful, checks the user's access rights and loads the initial configuration information.

[1112] Step 2: Initiating a feedback dialogue

[1113] server:

[1114] Generate a welcome message and send it to the device, for example, "What product / service would you like to share your thoughts on?"

[1115] Device:

[1116] It displays a welcome message and an input field to prompt the user for input.

[1117] Step 3: Provide feedback

[1118] User:

[1119] Enter your opinions and requests regarding products and services and press the send button.

[1120] Device:

[1121] Send the feedback data entered by the user to the server.

[1122] Step 4: Gather feedback

[1123] server:

[1124] A generative AI model is used to analyze the content of user feedback and generate the next question, for example, "Which parts specifically did you find difficult to use?"

[1125] server:

[1126] Send the following question to the device:

[1127] Step 5: Ongoing dialogue

[1128] Device:

[1129] Displays the question sent by the server.

[1130] User:

[1131] Enter an answer to the question and submit. Example: "The buttons are small and difficult to tap."

[1132] Device:

[1133] The user's answer is sent to the server.

[1134] Step 6: Save your feedback

[1135] server:

[1136] The received feedback is stored in a database, including the user ID, date and time, and specific opinions.

[1137] Step 7: Perform text analysis

[1138] server:

[1139] The stored feedback data is analyzed using natural language processing tools, which include keyword extraction, sentiment analysis, and topic classification. For example, keywords such as "button," "difficult to use," and "difficult to tap" are detected.

[1140] Step 8: Identify trends and patterns

[1141] server:

[1142] Statistically process feedback from multiple users to identify common trends and patterns, aggregate the identified information, and generate visualizations in the form of reports.

[1143] Step 9: Visualize the results

[1144] Device:

[1145] Provide a dashboard that can be viewed by administrators and staff, displaying graphs and charts of analytical results. For example, show that a specific version has a lot of negative feedback about "button size."

[1146] Step 10: Generate improvement suggestions

[1147] server:

[1148] Based on the analysis results, a generative AI model is used to generate specific improvement suggestions, such as "increase the size of buttons" or "expand the tap area in the UI design."

[1149] Step 11: Implementing Notifications

[1150] server:

[1151] Proposals for improvement are communicated to the design and product development teams via email or an intranet notification system.

[1152] Step 12: Tracking Improvement Efforts

[1153] Device:

[1154] It provides an interface for managers and staff to review improvement proposals and track their progress. Once specific improvement work is initiated, the progress is updated in the system.

[1155] Step 13: Follow up on user feedback

[1156] server:

[1157] Once the improvements are complete, you can follow up by notifying users of the changes and asking for their feedback.

[1158] This allows you to automate and efficiently execute a series of processes, from collecting user feedback to analyzing it, visualizing the results, notifying improvement suggestions, and tracking improvement work.

[1159] Example 1

[1160] 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."

[1161] Conventional feedback collection systems face challenges in efficiently collecting and analyzing user feedback and quickly implementing improvement proposals. Specifically, the limited means of collecting feedback prevent users from fully incorporating their opinions, and the collected feedback must be analyzed manually, resulting in a long wait for improvement proposals. Furthermore, there is a lack of a way to visually and intuitively grasp the analysis results, and the system lacks a mechanism for effectively tracking the progress of improvement work.

[1162] 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.

[1163] In this invention, the server includes an interaction means using a generative AI model to directly collect feedback from users, a storage device means for saving the collected feedback, a natural language processing device means for analyzing the saved feedback, a statistical analysis device means for identifying common trends and patterns from multiple pieces of feedback, a display device means for visualizing the analysis results, a notification device means for notifying the analysis results and improvement proposals, a user interface means for allowing a manager or person in charge to check the improvement proposals, and a tool for tracking the progress of improvement work, thereby enabling efficient collection and analysis of user feedback and rapid implementation of improvement measures.

[1164] A "generative AI model" is an artificial intelligence model that generates natural language dialogue to collect feedback from users.

[1165] "Interaction means" refers to a means of directly interacting with the user using the generative AI model and obtaining feedback.

[1166] "Storage means" is a hardware or software device for storing collected feedback.

[1167] A "natural language processing means" is a device that performs natural language processing techniques used to analyze the stored feedback.

[1168] "Statistical analysis device means" refers to the statistical analysis techniques used to identify common trends and patterns from multiple feedbacks and the devices that perform them.

[1169] A "display device" is a hardware or software device used to visualize the results of an analysis.

[1170] The "notification device means" is a hardware or software device for notifying the person in charge of the analysis results and improvement suggestions.

[1171] The "user interface means" is a means for providing an interface for managers and staff members to check and operate improvement proposals.

[1172] "Tools" are software or hardware tools for tracking the progress of improvement efforts.

[1173] The present invention relates to a system for collecting and analyzing user feedback using a generative AI model. This system operates among a server, a terminal, and a user, and uses the following hardware and software:

[1174] The server launches a generative AI model (e.g., GPT-3) to collect feedback directly from users and asks for feedback through dialogue. When a user accesses the server, the server generates a welcome message saying, "Please tell us your opinion. What product / service is it about?" and sends it to the device.

[1175] The device displays this welcome message to the user and provides an input field for entering feedback. The user enters their feedback and presses the send button. Specifically, the user enters "The design of this app is difficult to use" and sends it.

[1176] The server stores the feedback received from the user in a storage device (e.g., an SQL database). The stored feedback is then analyzed using a natural language processing system (e.g., spaCy or NLTK). The analysis includes keyword extraction, sentiment analysis, and topic classification. For example, when analyzing the feedback "The button is small and difficult to tap," keywords such as "button," "difficult to use," and "difficult to tap" are extracted.

[1177] Based on the analysis results, the server uses statistical analysis tools (e.g., clustering algorithms or TF-IDF) to identify common trends and patterns among the multiple feedbacks. For example, it may discover that similar issues have been reported multiple times for a particular version of an app. Based on this information, the server visualizes the analysis results as graphs and charts using display tools (e.g., Matplotlib or D3.js).

[1178] The terminal displays the analysis results in the form of a dashboard, allowing managers and product development teams to intuitively grasp trends and patterns in feedback.

[1179] The server uses a generative AI model based on the analytical and statistical analysis results to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area of ​​the user interface" may be generated. The server then notifies the person in charge of these improvement suggestions using a notification device. Notification methods include email and intranet notification systems.

[1180] The terminal provides a user interface that allows managers and staff to check improvement proposals. It also provides tools for tracking the progress of improvement work. Managers and staff implement specific improvement work based on the proposals and enter their progress into the system, which updates the latest status.

[1181] Specific examples

[1182] For example, if user feedback about an app is that "the buttons are small and difficult to use" or "the colors are hard to see," the server collects, stores, and analyzes that feedback. Based on the analysis results, improvement suggestions such as "increase the button size" or "increase the color contrast" are generated and notified to the design team. The design team can then revise the app design based on the improvement suggestions, contributing to an improved user experience.

[1183] Prompt Sentence Examples

[1184] "I want to collect and analyze user feedback on a new app design. I want to know how the server, device, and user work together to identify specific issues."

[1185] This system enables efficient collection and analysis of user feedback, enabling prompt and concrete improvement measures to be taken.

[1186] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1187] Step 1:

[1188] The server launches the generative AI model when a user accesses a specific URL and generates a welcome message.

[1189] Input: User's access request

[1190] Output: Welcome message ("What product / service would you like to hear about?")

[1191] Specific operation: When the server receives an HTTP request, it invokes a generative AI model (e.g., GPT-3) to generate a welcome message, embeds it in an HTML page, and sends it back to the user's browser.

[1192] Step 2:

[1193] The terminal displays an input field along with the welcome message received from the server.

[1194] Input: Welcome message from the server

[1195] Output: User feedback input interface

[1196] Specific behavior: The device (user's browser) uses an HTML form and JavaScript to display a text area where the user can enter feedback and a submit button.

[1197] Step 3:

[1198] The user inputs their opinions and requests regarding the product or service and presses the send button.

[1199] Input: User feedback (e.g., "The design of this app is difficult to use.")

[1200] Output: User-entered feedback data

[1201] Specific behavior: The user enters text in the feedback field and clicks the "Submit" button.

[1202] Step 4:

[1203] The server receives the feedback sent by the user and stores it in a database.

[1204] Input: Feedback data submitted by the user

[1205] Output: Feedback stored in a database

[1206] Specific operation: The server receives the feedback data and stores it in the SQL database using an INSERT statement.

[1207] Step 5:

[1208] The server analyzes the stored feedback using a natural language processing device.

[1209] Input: Saved feedback data

[1210] Output: Analysis results (keyword list, sentiment score, topic tags, etc.)

[1211] Specific operation: The server reads the saved feedback data, sends it to a natural language processing tool (e.g., spaCy or NLTK) via an API, and saves the returned analysis results back in the database.

[1212] Step 6:

[1213] The server performs statistical analysis based on the analysis results to identify common trends and patterns from the multiple feedbacks.

[1214] Input: Analysis results

[1215] Output: Statistical analysis results (identification of common trends and patterns)

[1216] Specific operation: The server uses algorithms such as k-means clustering and TF-IDF to extract commonalities in the feedback and perform statistical analysis.

[1217] Step 7:

[1218] The server generates graphs and charts to visualize the analysis results.

[1219] Input: Statistical analysis results

[1220] Output: Visualized data (graphs, charts, etc.)

[1221] Specific operation: The server uses visualization tools such as Matplotlib and D3.js to generate visualization data based on the feedback trend data.

[1222] Step 8:

[1223] The terminal displays the visualized data received from the server in dashboard format.

[1224] Input: Visualization data from the server

[1225] Output: Dashboard format display

[1226] Specific operation: The terminal (user's browser) displays an HTML page containing visualized data and a dashboard UI.

[1227] Step 9:

[1228] The server uses a generative AI model based on the analytical and statistical analysis results to generate specific improvement suggestions.

[1229] Input: Statistical analysis results

[1230] Output: Improvement suggestion (e.g. "Make the button size larger")

[1231] Specific operation: The server inputs the analysis results as prompt sentences into the generative AI model, and the AI ​​generates suggestions.

[1232] Step 10:

[1233] The server notifies the person in charge of the generated improvement proposal.

[1234] Input: Generated improvement suggestions

[1235] Output: Notification to responsible parties (via email or intranet notification system)

[1236] Specific operation: The server sends an email containing the proposal to the person in charge via the SMTP server or notifies them using the intranet notification API.

[1237] Step 11:

[1238] The device provides a UI for managers and staff to review improvement proposals, and also provides tools for tracking the progress of improvement work.

[1239] Input: Improvement suggestion notification from the server

[1240] Output: Display improvement suggestions to managers and staff and provide tracking tools

[1241] Specific operation: The terminal (user's browser) displays improvement proposals in list format and provides the person in charge with the ability to update the progress status.

[1242] Step 12:

[1243] Managers and staff members then carry out specific improvement work based on the suggestions. Progress is entered into the system, and the latest status is updated via the server.

[1244] Input: Improvement proposals, progress of improvement work

[1245] Output: Updated remediation status

[1246] Specific actions: Managers and staff enter the progress of improvement work into the tracking system and save the progress status in the database.

[1247] (Application example 1)

[1248] 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."

[1249] There is a lack of a way to efficiently collect user feedback on the experience of using autonomous vehicles, analyze it in real time, and quickly propose improvements. This poses a challenge, delaying the improvement of the service quality of autonomous vehicles. There is also a need for a smooth method of collecting feedback without disrupting the user experience.

[1250] 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.

[1251] In this invention, the server includes an interaction means using a generative AI model to directly collect feedback from users, a storage means for storing the collected feedback, a natural language processing means for analyzing the stored feedback, a display means for visualizing the analysis results, a notification means for notifying the analysis results and improvement suggestions, an input means for passengers of the autonomous vehicle to input feedback using a smartphone, a communication means for transmitting the feedback input by the passengers of the autonomous vehicle to the server in real time, and a generation means using a generative AI model to generate improvements based on the analysis results. This makes it possible to quickly collect and analyze user feedback in the autonomous vehicle and make appropriate improvement suggestions.

[1252] A "generative AI model" is a model that uses artificial intelligence to generate, analyze, and suggest user feedback.

[1253] "Interactive means" are means for communicating with users, such as collecting feedback.

[1254] "Storage means" means means for storing collected feedback.

[1255] "Natural language processing means" is a means for analyzing collected feedback, and involves performing keyword extraction, sentiment analysis, topic classification, etc.

[1256] The "display means" is a means for visually displaying the analysis results.

[1257] "Notification means" refers to the means for notifying the person in charge of the analysis results and improvement suggestions.

[1258] "Input means" refers to the smartphone interface that allows users to input feedback.

[1259] "Communication means" refers to a means for transmitting feedback from users to the server in real time.

[1260] The "generation means" is a means that uses a generative AI model to generate improvement proposals based on the analysis results.

[1261] An "autonomous vehicle" is a vehicle in which driving operations are automated.

[1262] The system according to the present invention includes the following elements in order to efficiently collect feedback from users of autonomous vehicles, analyze the feedback, and make appropriate improvement suggestions.

[1263] 1. Feedback gathering phase

[1264] The server sends a welcome message to the user via the smartphone application, such as "Tell us what you think! Tell us about your experience riding in a self-driving vehicle." This prompts the user to provide feedback.

[1265] The device (smartphone) displays a welcome message along with an input field to allow the user to enter feedback.

[1266] The user provides feedback by speaking or typing, for example, "I couldn't see the scenery from the window very well" or "The air conditioning was too strong and it was cold."

[1267] 2. Feedback analysis phase

[1268] The server stores the received feedback in a storage means (e.g., a database or a JSON file).

[1269] Next, the feedback is analyzed using natural language processing tools, such as a generative AI model (e.g., OpenAI's GPT-4), to extract keywords from the feedback and perform sentiment analysis and topic classification.

[1270] The analysis results are saved as text. For example, from feedback such as "The air conditioning was too strong and it was cold," keywords such as "air conditioning" and "cold" are extracted.

[1271] 3. Response and Improvement Phase

[1272] The server uses a generative AI model based on the analysis results to generate specific improvement proposals, such as "improving the automatic adjustment function of the air conditioning system."

[1273] The improvement proposal will be notified to the responsible person via email or an intranet notification system.

[1274] The device (smartphone or tablet) displays the analysis results in a dashboard format, allowing managers and staff to check the results. Tools are also provided for tracking the progress of improvements.

[1275] Hardware and software used

[1276] Hardware: Servers, smartphones, network devices

[1277] Software: Python, Flask, OpenAI API (GPT-4)

[1278] Data processing and calculation

[1279] Feedback is collected using a smartphone app, and the input feedback is sent to a server in real time.

[1280] Feedback is stored on the server side, and a natural language processing engine (GPT-4) is used to extract keywords, analyze sentiment, and classify topics.

[1281] Common patterns and trends are identified from the analysis results, and specific improvement suggestions are generated using a generative AI model.

[1282] Finally, by notifying the person in charge of the improvement proposal, a prompt response can be made.

[1283] Examples and prompts

[1284] Specific examples

[1285] When a user enters feedback while riding in an autonomous vehicle, such as "I couldn't see the scenery from the window very well" or "The air conditioning was too strong and it was cold," the system collects and analyzes this in real time. As a result of the analysis, it generates suggestions such as "Improve the window brightness adjustment function" or "Improve the automatic air conditioning adjustment function" and notifies the person in charge. The person in charge can then directly improve the system based on these suggestions.

[1286] Prompt Sentence Examples

[1287] Analyze the following feedback:

[1288] ["I couldn't see the scenery from the window very well", "The air conditioning was too strong and it was cold"]

[1289] Generate improvement suggestions based on the following feedback analysis results:

[1290] ["Improve the window brightness adjustment function", "Improve the automatic air conditioning adjustment function"]

[1291] The present invention makes it possible to efficiently and quickly improve the user experience in autonomous vehicles.

[1292] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1293] Step 1:

[1294] Feedback collection

[1295] ---

[1296] Input: The user responds to the "Tell us what you think" welcome message displayed on the smartphone app.

[1297] Action: The user enters feedback and presses the submit button. For example, the user enters feedback such as "The view from the train window was not very clear."

[1298] Output: The feedback data entered by the user is sent to the server via the smartphone app.

[1299] Step 2:

[1300] Save your feedback

[1301] ---

[1302] Input: Feedback data submitted by the user

[1303] Behavior: The server stores the received feedback data in a storage medium (e.g., a database or a JSON file).

[1304] Output: Stored feedback data

[1305] Step 3:

[1306] Feedback Analysis

[1307] ---

[1308] Input: Stored feedback data

[1309] How it works: The server analyzes the feedback using natural language processing tools. Generative AI models such as GPT-4 are used to extract keywords, analyze sentiment, and classify topics. For example, from the feedback "The air conditioning was too strong and it was cold," it extracts keywords such as "air conditioning" and "cold."

[1310] Output: Analyzed feedback data (keywords and sentiment analysis results)

[1311] Step 4:

[1312] Visualization of analysis results

[1313] ---

[1314] Input: Parsed feedback data

[1315] How it works: The server uses the analysis results to visualize the results as graphs and charts, and processes the data so that it can be displayed in a dashboard format.

[1316] Output: Visualized analysis results (e.g., graphs, charts, etc.)

[1317] Step 5:

[1318] Generate improvement suggestions

[1319] ---

[1320] Input: Parsed feedback data

[1321] How it works: The server uses the generative AI model to generate specific improvement suggestions based on the analysis results, such as "improve the brightness adjustment function of window glass."

[1322] Output: Specific improvement suggestions

[1323] Step 6:

[1324] Notification of improvement proposals

[1325] ---

[1326] Input: Generated improvement suggestions

[1327] Behavior: The server notifies the person in charge of the generated improvement proposal, using email or an intranet notification system.

[1328] Output: Improvement suggestions notified to the person in charge

[1329] Step 7:

[1330] Review and implement improvement proposals

[1331] ---

[1332] Input: Improvement proposal notified to the person in charge

[1333] Action: The person in charge receives a notification, checks the proposal, and then implements the specific improvement work and enters the progress into the system. For example, the person in charge implements a proposal to "improve the automatic adjustment function of the air conditioning system."

[1334] Output: Progress of improvement work

[1335] In this way, data processing and calculations are carried out at each step, ultimately improving the service quality of autonomous vehicles.

[1336] 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.

[1337] The system of the present invention combines a generative AI model, storage means, natural language processing means, visualization means, notification means, statistical analysis means, and an emotion engine to collect and analyze user feedback and automatically generate specific improvement proposals. This system operates among a server, terminals, and users.

[1338] Interaction Phase (Feedback Collection)

[1339] server:

[1340] When a user accesses the server, the generative AI model is activated and a welcome message is sent to the user, such as "Tell us your opinion. What product / service is it about?" This prompts the user to provide feedback.

[1341] Device:

[1342] The terminal displays a welcome message and input fields for the user to enter feedback, which is sent to the server in real time.

[1343] User:

[1344] Users enter their opinions and requests regarding products and services and press the submit button. For example, they can enter feedback such as, "I think the design of this app is difficult to use."

[1345] Analysis phase (analysis of feedback)

[1346] server:

[1347] The server stores the received feedback in storage. It then analyzes the feedback using natural language processing. This analysis includes keyword extraction, sentiment analysis, and topic classification. For example, if the feedback "The button is small and difficult to tap" is analyzed, the keywords "button," "difficult to use," and "difficult to tap" are extracted.

[1348] server:

[1349] Furthermore, an emotion engine is used to recognize user emotions, such as "dissatisfaction" or "irritation." This emotion data is used to assess the importance and urgency of feedback.

[1350] server:

[1351] The analysis results can be used to identify common trends and patterns across multiple pieces of feedback, such as finding that a particular version of an app is reporting a high number of "dissatisfied" and "irritated" users. This information can then be used to generate data that can be displayed as graphs or charts using visualization tools.

[1352] Device:

[1353] The device displays the analysis results in the form of a dashboard, allowing managers and product development teams to intuitively grasp feedback trends, patterns, and sentiment data.

[1354] Response and improvement phase (proposing improvements)

[1355] server:

[1356] The server uses a generative AI model to generate specific improvement suggestions based on the analytical and statistical analysis results. For example, suggestions might be made such as "increase the button size" or "expand the tap area in the UI design." Additionally, based on emotional data, it prioritizes the most urgent improvements.

[1357] server:

[1358] The generated improvement proposals are notified to the person in charge via email or an intranet notification system.

[1359] Device:

[1360] The terminal provides an interface for managers and personnel to review improvement proposals, and also provides tools for tracking the progress of improvement work.

[1361] User (Administrator / Contact Person):

[1362] Managers and staff members then carry out specific improvement work based on the proposals. The progress of the improvement work is entered into the system, and the latest status is updated via the server. The progress of the improvement work is also displayed on the dashboard, allowing all parties involved to understand the progress.

[1363] Specific examples

[1364] For example, if user feedback about a certain app is that "the buttons are small and difficult to use" or "the colors are hard to see," and the emotion engine detects "dissatisfaction" or "irritation," the server collects, stores, and analyzes that feedback. Based on the analysis results, improvement suggestions such as "increase the button size" or "increase the color contrast" are generated and notified to the design team in charge. The design team then uses the suggestions to revise the app's design and contribute to improving the user experience.

[1365] This system allows for efficient collection and analysis of user feedback and their emotions, enabling prompt and concrete improvement measures to be taken.

[1366] The processing flow will be explained below.

[1367] Step 1: User authentication

[1368] User:

[1369] Enter your username and password to log in to the system.

[1370] server:

[1371] Validates the entered credentials and authenticates the user. If successful, checks the user's access rights and loads the initial configuration information.

[1372] Step 2: Initiating a feedback dialogue

[1373] server:

[1374] Generate a welcome message and send it to the device, for example, "What product / service would you like to share your thoughts on?"

[1375] Device:

[1376] It displays a welcome message and an input field to prompt the user for input.

[1377] Step 3: Provide feedback

[1378] User:

[1379] Enter your opinions and requests regarding products and services and press the send button.

[1380] Device:

[1381] Send the feedback data entered by the user to the server.

[1382] Step 4: Receive and store feedback

[1383] server:

[1384] The received feedback data is stored in storage, including the user ID, date and time, and specific opinions.

[1385] Step 5: Continuing the Generative AI Model

[1386] server:

[1387] A generative AI model is used to analyze user feedback and generate the next question, for example, "Which parts specifically did you find difficult to use?"

[1388] server:

[1389] Send the following question to the device:

[1390] Step 6: Continue the conversation

[1391] Device:

[1392] Displays the question sent by the server.

[1393] User:

[1394] Enter an answer to the question and submit. Example: "The buttons are small and difficult to tap."

[1395] Device:

[1396] The user's answer is sent to the server.

[1397] Step 7: Collect emotion recognition data

[1398] server:

[1399] The emotion engine is used to recognize the user's emotions from the input feedback, for example, detecting emotions such as "dissatisfaction" or "irritation."

[1400] Step 8: Analyze feedback and incorporate sentiment data

[1401] server:

[1402] The collected feedback and sentiment data is analyzed using natural language processing tools, including keyword extraction, sentiment analysis, and topic classification. For example, keywords such as "button," "difficult to use," and "difficult to tap" are extracted.

[1403] server:

[1404] Emotional data is incorporated into the analysis results to assess the importance and urgency of feedback, and feedback with high importance is tagged as high priority.

[1405] Step 9: Identify trends and patterns

[1406] server:

[1407] Statistically process feedback from multiple users to identify common trends and patterns. For example, find out if a particular version of an app is generating a lot of frustration or irritation.

[1408] Step 10: Visualize the results

[1409] Device:

[1410] Provides a dashboard where administrators and staff can check the analysis results, displaying graphs and charts of the analysis results. Example: Showing that a specific version has a lot of negative feedback about "button size."

[1411] Step 11: Generate improvement suggestions

[1412] server:

[1413] Based on the results of analytical and statistical analysis, a generative AI model is used to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are created. Additionally, based on emotional data, the system prioritizes and presents particularly urgent improvement points.

[1414] Step 12: Notification of improvement proposals

[1415] server:

[1416] The generated improvement proposals are notified to the person in charge via email or an intranet notification system.

[1417] Step 13: Tracking Improvement Efforts

[1418] Device:

[1419] It provides an interface for managers and staff to review improvement proposals and track their progress. Once specific improvement work is initiated, the progress is updated in the system.

[1420] Step 14: Follow up on user feedback

[1421] server:

[1422] Once the improvements are complete, you can follow up by notifying users of the changes and asking for their feedback.

[1423] This allows for the automation and efficient execution of a series of processes, from collecting user feedback to recognizing emotions, analyzing them, visualizing the results, notifying improvement suggestions, and tracking improvement work.

[1424] Example 2

[1425] 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."

[1426] Conventional feedback collection systems have difficulty efficiently analyzing user feedback and automatically generating specific improvement proposals. Furthermore, due to a lack of emotion recognition and statistical trend analysis, they are unable to properly evaluate the importance and urgency of feedback. A system that can solve these issues and effectively utilize user feedback is needed.

[1427] 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.

[1428] In this invention, the server includes an interaction means using a generative AI model to directly collect feedback from users, a data storage means for storing the collected feedback, a natural language processing means for extracting keywords and classifying topics based on the stored feedback data, a sentiment analysis means for detecting sentiment in the analyzed feedback data, a data visualization means for visually displaying the analysis results, and a notification means for notifying the analysis results and improvement suggestions.

[1429] This makes it possible to efficiently collect and analyze feedback from users and quickly generate and communicate specific improvement suggestions, including emotional data.

[1430] A "generative AI model" is an artificial intelligence model that interprets user feedback in natural language and collects it in an interactive format.

[1431] "Data storage means" refers to a database system or storage system for storing and managing collected feedback data.

[1432] "Natural language processing means" refers to natural language processing technology for analyzing collected feedback data and performing keyword extraction and topic classification.

[1433] "Emotion analysis means" refers to a technique for detecting a user's emotions from the analyzed feedback data.

[1434] "Data visualization means" refers to tools and technologies that visually display the results of analyzed feedback data, making it easier for managers and staff to understand.

[1435] "Notification means" refers to a communication means for notifying the person in charge of the analysis results and generated improvement proposals.

[1436] "Statistical analysis methods" refers to statistical methods and techniques for identifying common trends or patterns from multiple feedback data.

[1437] "Dashboard" refers to the user interface that allows administrators and personnel to view and track analysis results.

[1438] The system of the present invention combines a generative AI model, data storage means, natural language processing means, sentiment analysis means, data visualization means, notification means, and statistical analysis means to collect and analyze user feedback and automatically generate specific improvement proposals. This system operates among a server, terminals, and users.

[1439] Collecting feedback

[1440] server:

[1441] The server activates the generative AI model when a user accesses the system and sends a welcome message, such as "Tell us your opinion. What product / service is it about?", which prompts the user to provide feedback.

[1442] Device:

[1443] The device displays the received welcome message and allows the user to enter feedback, which is sent to the server in real time.

[1444] User:

[1445] Users enter their opinions and requests regarding products and services and press the submit button. For example, they can enter feedback such as, "I think the design of this app is difficult to use."

[1446] Feedback analysis and sentiment analysis

[1447] server:

[1448] The server stores the received feedback in a data storage means, for example, a database system such as MySQL or PostgreSQL.

[1449] Next, the feedback is analyzed using natural language processing tools (e.g., NLTK, spacy). This includes keyword extraction and topic classification. For example, if the feedback says, "The button is small and difficult to tap," the keywords "button," "small," and "difficult to tap" are extracted.

[1450] Additionally, sentiment analysis tools (e.g., BERT) are used to recognize user emotions. For example, emotions such as "dissatisfaction" and "irritation" are detected. This emotional data is used to assess the importance and urgency of the feedback.

[1451] Visualizing and notifying results

[1452] server:

[1453] Based on the analysis results, we use statistical analysis methods to identify common trends and patterns across multiple pieces of feedback, for example, finding that a particular version of an app is more likely to be "frustrated" or "irritated."

[1454] Next, data visualization tools (e.g., D3.js or Chart.js) are used to generate graphs and charts that display these results, allowing managers and product development teams to intuitively understand feedback trends, patterns, and sentiment data.

[1455] Device:

[1456] The terminal displays the visualized data sent from the server in the form of a dashboard, allowing managers and product development teams to intuitively grasp feedback trends, patterns, and sentiment data.

[1457] Generate and notify improvement suggestions

[1458] server:

[1459] The server uses a generative AI model (e.g., GPT-3) based on the analytical and statistical analysis results to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are generated. Additionally, based on emotional data, it prioritizes and presents particularly urgent improvement points.

[1460] Next, the generated improvement proposals are notified to the person in charge via a mail server or an intranet notification system.

[1461] Device:

[1462] The device will display a notification to allow the administrator or person in charge to check the improvement proposal, for example, through the email app or a dedicated notification app.

[1463] User (Administrator / Contact Person):

[1464] Managers and staff members then carry out specific improvement work based on the proposals. The progress of the improvement work is entered into the system, and the latest status is updated via the server. The progress of the improvement work is also displayed on the dashboard, allowing all parties involved to understand the progress.

[1465] Prompt Sentence Examples

[1466] Here are some examples of prompts to input to a generative AI model:

[1467] "After collecting user feedback on product X and performing sentiment analysis, what improvements would you suggest?"

[1468] "Analyze the negative feedback received from users of Service Y and identify specific areas for improvement."

[1469] This prompt allows the AI ​​model to quickly generate the necessary analysis and suggestions.

[1470] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1471] Step 1:

[1472] Feedback session begins

[1473] server:

[1474] When a user accesses the system, the server launches the generative AI model and sends a welcome message, such as "What product / service would you like to share your thoughts on?"

[1475] Input: User's access request

[1476] Output: Welcome message

[1477] Device:

[1478] The terminal displays the received welcome message on the user interface, along with a text box for entering feedback and a submit button.

[1479] Input: Welcome message sent by the server

[1480] Output: A welcome message and an input field.

[1481] Step 2:

[1482] Enter and submit feedback

[1483] User:

[1484] Users can enter their feedback into a text box on their device and press the submit button, for example, "I think the design of this app is difficult to use."

[1485] Input: Feedback

[1486] Output: Send feedback

[1487] Device:

[1488] The device sends the feedback entered by the user to the server in real time.

[1489] Input: User feedback

[1490] Output: Send feedback to the server

[1491] Step 3:

[1492] Save your feedback

[1493] server:

[1494] The server stores the received feedback in a storage means, for example, a database system such as MySQL or PostgreSQL.

[1495] Input: User feedback data

[1496] Output: Saving the feedback data to a database

[1497] Step 4:

[1498] Feedback Analysis

[1499] server:

[1500] The server uses natural language processing tools (e.g., NLTK, Spacy) to analyze the stored feedback data. This analysis includes keyword extraction and topic classification. For example, from the feedback "The button is small and difficult to tap," the keywords "button," "small," and "difficult to tap" are extracted.

[1501] Input: Stored feedback data

[1502] Output: Extracted keywords and topics

[1503] Step 5:

[1504] Conducting sentiment analysis

[1505] server:

[1506] The server performs sentiment analysis of the feedback using sentiment analysis tools (e.g., BERT). For example, emotions such as "dissatisfaction" and "irritation" are detected. This sentiment data is used to evaluate the importance and urgency of the feedback.

[1507] Input: Feedback data and extracted keywords

[1508] Output: Emotion data

[1509] Step 6:

[1510] Visualizing the results

[1511] server:

[1512] Based on the analysis results and sentiment analysis results, the server uses statistical analysis tools to identify trends and patterns, and generates visualized data using data visualization tools (e.g., D3.js or Chart.js), such as graphs and charts showing feedback trends.

[1513] Input: Analysis results and emotion data

[1514] Output: Visualized data (graphs and charts)

[1515] Device:

[1516] The terminal displays the visualized data sent from the server in the form of a dashboard, allowing managers and product development teams to understand feedback trends and sentiment data.

[1517] Input: Visualization data sent from the server

[1518] Output: Dashboard display

[1519] Step 7:

[1520] Generate improvement suggestions

[1521] server:

[1522] The server uses a generative AI model (e.g., GPT-3) based on the analytical and statistical analysis results to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are generated. Additionally, based on emotional data, it prioritizes and presents particularly urgent improvement points.

[1523] Input: Analysis and statistical analysis results

[1524] Output: Improvement suggestions

[1525] Step 8:

[1526] Notification of improvement proposals

[1527] server:

[1528] The server notifies the person in charge of the generated improvement proposals using a mail server or an intranet notification system.

[1529] Input: Improvement Suggestion

[1530] Output: Notification to the person in charge

[1531] Device:

[1532] The device will display a notification to allow the administrator or person in charge to check the improvement proposal, for example, through the email app or a dedicated notification app.

[1533] Input: Notification from the server

[1534] Output: Display notification

[1535] Step 9:

[1536] Review and implement the proposal

[1537] User (Administrator / Contact Person):

[1538] Managers and staff members review the proposals and implement specific improvement work. The progress of the improvement work is entered into the system, and the latest status is updated via the server. The progress of the improvement work is also displayed on the dashboard, allowing all parties involved to understand the progress.

[1539] Input: Improvement Suggestion

[1540] Output: Progress of the implemented improvement work

[1541] (Application example 2)

[1542] 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."

[1543] In recent years, many online shopping sites have been trying to improve their services by collecting and analyzing user feedback, but this process is often done manually, requiring time and effort. It is also difficult to centrally manage the content of feedback and generate quick and specific improvement proposals. In particular, there is a need for a method to efficiently process large amounts of feedback and visualize the analysis results in an easy-to-understand manner. An effective system to solve these challenges is needed.

[1544] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1545] In this invention, the server includes a dialogue means using a generative AI model, a data storage means for saving collected feedback, a natural language processing means for analyzing the saved feedback, an information visualization means for visualizing the analysis results, an information transmission means for notifying generated improvement suggestions, and an interface provision means for tracking the progress of the improvement suggestions, thereby enabling efficient collection and analysis of user feedback and prompt and specific improvement suggestions to be provided.

[1546] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and generates new data.

[1547] "Interaction means" refers to a means of communication between a user and a system.

[1548] "Data storage means" refers to means for accumulating and storing data such as feedback.

[1549] "Natural language processing means" refers to means for analyzing text data and extracting meaning.

[1550] "Information visualization means" refers to means for displaying analytical results in visual formats such as graphs and charts.

[1551] "Information transmission means" refers to a means for informing related parties of the generated improvement proposals.

[1552] The "interface providing means" is a means for providing an interface for a user to check and operate information.

[1553] "Data analysis means" refers to means for processing received data and extracting trends and patterns.

[1554] A "display device" is a device for displaying visualized information.

[1555] The system according to the present invention automates the collection and analysis of feedback and the generation of improvement proposals for an online shopping site. Specific embodiments of this system will be described below.

[1556] Feedback gathering phase

[1557] When a user accesses a shopping site, the server activates the generative AI model and sends a welcome message. This message prompts the user to provide feedback, and is displayed in the form of, "Tell us your opinion. What product / service is it about?" The device displays this welcome message along with an input field for the user, and the user enters their feedback through the interface. This input is sent to the server in real time.

[1558] Feedback Analysis Phase

[1559] The server stores the collected feedback in a database. Next, it uses natural language processing (NLTK) to analyze the text data and extract keywords. An emotion engine is also used in this process to understand the user's emotions. The emotion data is added to the analysis results and used to evaluate the importance and urgency. The analysis results are displayed visually using information visualization tools so that managers and development teams can review them.

[1560] Improvement proposal generation phase

[1561] The server uses a generative AI model (TensorFlow) to generate specific improvement proposals based on the analysis results and data analysis methods. For example, if the feedback includes a comment that the search function is difficult to use, a proposal to improve the search function interface will be generated. The generated improvement proposals are notified to the person in charge via information transmission methods (SendGrid, Slack API).

[1562] The progress of improvement proposals is tracked through an interface provided by the device, and managers and staff can use a dashboard to monitor improvement proposals and their progress across multiple metrics.

[1563] Specific examples

[1564] If a user provides feedback that the app's design is difficult to use, the generative AI model will generate specific suggestions for improvement, such as increasing the button size or expanding the tap area in the UI design. These suggestions will be notified to the design team, who will then take action.

[1565] Here is an example prompt:

[1566] Please provide your feedback:

[1567] I think the design of this app is difficult to use.

[1568] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1569] Step 1:

[1570] When a user accesses the online shopping site, the server launches the generative AI model and sends the user a welcome message prompting them to provide feedback. Specifically, the message "Please tell us your opinion. Which product / service is it about?" is displayed on the user's device. This message is a prompt to encourage the user to enter feedback.

[1571] Step 2:

[1572] The user inputs feedback according to the welcome message, and the device sends this input to the server in real time. For example, the user may enter feedback such as "The design of this app is difficult to use." This feedback becomes input data to the server.

[1573] Step 3:

[1574] The server stores the received feedback in a database, where the data is stored in its original form and is used for subsequent analysis.

[1575] Step 4:

[1576] The server analyzes the saved feedback using natural language processing (NLTK). Specifically, it extracts keywords from the text data and analyzes the user's emotions. This analysis evaluates the importance and urgency of the feedback content. For example, the keyword "difficult to use" can be used to detect user dissatisfaction or irritation.

[1577] Step 5:

[1578] The server visually displays the analysis results using information visualization tools. The analysis results are displayed on terminals in dashboard format so that administrators and development teams can review them. Graphs and charts are used to clarify trends and patterns in the data.

[1579] Step 6:

[1580] The server uses a generative AI model (TensorFlow) to generate specific improvement suggestions based on the analysis results. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are generated. In this process, important parts of the feedback are extracted and specific measures are proposed.

[1581] Step 7:

[1582] The generated improvement proposals are notified to the responsible person via information transmission methods (SendGrid or Slack API), such as email or internal messaging systems. The notification includes the priority of the improvement and the specific proposal content.

[1583] Step 8:

[1584] The device provides the manager or person in charge with an interface to track the content and progress of the improvement proposal. Using the dashboard, the manager or person in charge can check the progress of the improvement work in real time and take necessary actions.

[1585] 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.

[1586] 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.

[1587] 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.

[1588] [Fourth embodiment]

[1589] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1590] 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.

[1591] 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).

[1592] 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.

[1593] 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.

[1594] 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).

[1595] 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.

[1596] 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.

[1597] 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.

[1598] 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.

[1599] 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.

[1600] 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.

[1601] 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."

[1602] The system of the present invention is a system for collecting and analyzing user feedback using a generative AI model. This system operates among a server, a terminal, and a user, and is implemented in the following manner.

[1603] Interaction Phase (Feedback Collection)

[1604] server:

[1605] When a user accesses the server, the generative AI model is activated and a welcome message is sent to the user, such as "Tell us your opinion. What product / service is it about?" This prompts the user to provide feedback.

[1606] Device:

[1607] The terminal displays a welcome message and an input field for the user to enter their feedback, which is sent to the server in real time.

[1608] User:

[1609] Users enter their opinions and requests about the product or service and press the submit button. For example, they can enter feedback such as, "I think the design of this app is difficult to use."

[1610] Analysis phase (analysis of feedback)

[1611] server:

[1612] The server stores the received feedback in storage. It then analyzes the feedback using natural language processing. This analysis includes keyword extraction, sentiment analysis, and topic classification. For example, if the feedback "The button is small and difficult to tap" is analyzed, the keywords "button," "difficult to use," and "difficult to tap" are extracted.

[1613] server:

[1614] The analysis results can be used to identify common trends or patterns across multiple pieces of feedback, such as finding that a particular version of an app has multiple reports of the same issue, and then use this information to generate data that can be used to display the results in graphs or charts.

[1615] Device:

[1616] The terminal displays the analysis results in the form of a dashboard, allowing managers and product development teams to intuitively grasp trends and patterns in feedback.

[1617] Response and improvement phase (proposing improvements)

[1618] server:

[1619] Based on the analytical and statistical analysis results, the server uses a generative AI model to generate specific improvement suggestions, such as "increase the size of buttons" or "expand the tap area of ​​the user interface."

[1620] server:

[1621] The generated improvement proposals are notified to the person in charge via email or an intranet notification system.

[1622] Device:

[1623] The terminal provides an interface for managers and personnel to review improvement proposals, and also provides tools for tracking the progress of improvement work.

[1624] User (Administrator / Contact Person):

[1625] Managers and staff members implement specific improvement work based on the proposals. The progress of the improvement work is entered into the system, and the latest status is updated via the server.

[1626] Specific examples

[1627] For example, if user feedback about an app is that "the buttons are small and difficult to use" or "the colors are hard to see," the server collects, stores, and analyzes that feedback. Based on the analysis results, it generates improvement suggestions, such as "increase the button size" or "increase the color contrast," and notifies the relevant design team. The design team then uses these suggestions to revise the app's design and contribute to improving the user experience.

[1628] This system enables efficient collection and analysis of user feedback, enabling prompt and concrete improvement measures to be taken.

[1629] The processing flow will be explained below.

[1630] Step 1: User authentication

[1631] User:

[1632] Enter your username and password to log in to the system.

[1633] server:

[1634] Validates the entered credentials and authenticates the user. If successful, checks the user's access rights and loads the initial configuration information.

[1635] Step 2: Initiating a feedback dialogue

[1636] server:

[1637] Generate a welcome message and send it to the device, for example, "What product / service would you like to share your thoughts on?"

[1638] Device:

[1639] It displays a welcome message and an input field to prompt the user for input.

[1640] Step 3: Provide feedback

[1641] User:

[1642] Enter your opinions and requests regarding products and services and press the send button.

[1643] Device:

[1644] Send the feedback data entered by the user to the server.

[1645] Step 4: Gather feedback

[1646] server:

[1647] A generative AI model is used to analyze the content of user feedback and generate the next question, for example, "Which parts specifically did you find difficult to use?"

[1648] server:

[1649] Send the following question to the device:

[1650] Step 5: Ongoing dialogue

[1651] Device:

[1652] Displays the question sent by the server.

[1653] User:

[1654] Enter an answer to the question and submit. Example: "The buttons are small and difficult to tap."

[1655] Device:

[1656] The user's answer is sent to the server.

[1657] Step 6: Save your feedback

[1658] server:

[1659] The received feedback is stored in a database, including the user ID, date and time, and specific opinions.

[1660] Step 7: Perform text analysis

[1661] server:

[1662] The stored feedback data is analyzed using natural language processing tools, which include keyword extraction, sentiment analysis, and topic classification. For example, keywords such as "button," "difficult to use," and "difficult to tap" are detected.

[1663] Step 8: Identify trends and patterns

[1664] server:

[1665] Statistically process feedback from multiple users to identify common trends and patterns, aggregate the identified information, and generate visualizations in the form of reports.

[1666] Step 9: Visualize the results

[1667] Device:

[1668] Provide a dashboard that can be viewed by administrators and staff, displaying graphs and charts of analytical results. For example, show that a specific version has a lot of negative feedback about "button size."

[1669] Step 10: Generate improvement suggestions

[1670] server:

[1671] Based on the analysis results, a generative AI model is used to generate specific improvement suggestions, such as "increase the size of buttons" or "expand the tap area in the UI design."

[1672] Step 11: Implementing Notifications

[1673] server:

[1674] Proposals for improvement are communicated to the design and product development teams via email or an intranet notification system.

[1675] Step 12: Tracking Improvement Efforts

[1676] Device:

[1677] It provides an interface for managers and staff to review improvement proposals and track their progress. Once specific improvement work is initiated, the progress is updated in the system.

[1678] Step 13: Follow up on user feedback

[1679] server:

[1680] Once the improvements are complete, you can follow up by notifying users of the changes and asking for their feedback.

[1681] This allows you to automate and efficiently execute a series of processes, from collecting user feedback to analyzing it, visualizing the results, notifying improvement suggestions, and tracking improvement work.

[1682] Example 1

[1683] 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."

[1684] Conventional feedback collection systems face challenges in efficiently collecting and analyzing user feedback and quickly implementing improvement proposals. Specifically, the limited means of collecting feedback prevent users from fully incorporating their opinions, and the collected feedback must be analyzed manually, resulting in a long wait for improvement proposals. Furthermore, there is a lack of a way to visually and intuitively grasp the analysis results, and the system lacks a mechanism for effectively tracking the progress of improvement work.

[1685] 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.

[1686] In this invention, the server includes an interaction means using a generative AI model to directly collect feedback from users, a storage device means for saving the collected feedback, a natural language processing device means for analyzing the saved feedback, a statistical analysis device means for identifying common trends and patterns from multiple pieces of feedback, a display device means for visualizing the analysis results, a notification device means for notifying the analysis results and improvement proposals, a user interface means for allowing a manager or person in charge to check the improvement proposals, and a tool for tracking the progress of improvement work, thereby enabling efficient collection and analysis of user feedback and rapid implementation of improvement measures.

[1687] A "generative AI model" is an artificial intelligence model that generates natural language dialogue to collect feedback from users.

[1688] "Interaction means" refers to a means of directly interacting with the user using the generative AI model and obtaining feedback.

[1689] "Storage means" is a hardware or software device for storing collected feedback.

[1690] A "natural language processing means" is a device that performs natural language processing techniques used to analyze the stored feedback.

[1691] "Statistical analysis device means" refers to the statistical analysis techniques used to identify common trends and patterns from multiple feedbacks and the devices that perform them.

[1692] A "display device" is a hardware or software device used to visualize the results of an analysis.

[1693] The "notification device means" is a hardware or software device for notifying the person in charge of the analysis results and improvement suggestions.

[1694] The "user interface means" is a means for providing an interface for managers and staff members to check and operate improvement proposals.

[1695] "Tools" are software or hardware tools for tracking the progress of improvement efforts.

[1696] The present invention relates to a system for collecting and analyzing user feedback using a generative AI model. This system operates among a server, a terminal, and a user, and uses the following hardware and software:

[1697] The server launches a generative AI model (e.g., GPT-3) to collect feedback directly from users and asks for feedback through dialogue. When a user accesses the server, the server generates a welcome message saying, "Please tell us your opinion. What product / service is it about?" and sends it to the device.

[1698] The device displays this welcome message to the user and provides an input field for entering feedback. The user enters their feedback and presses the send button. Specifically, the user enters "The design of this app is difficult to use" and sends it.

[1699] The server stores the feedback received from the user in a storage device (e.g., an SQL database). The stored feedback is then analyzed using a natural language processing system (e.g., spaCy or NLTK). The analysis includes keyword extraction, sentiment analysis, and topic classification. For example, when analyzing the feedback "The button is small and difficult to tap," keywords such as "button," "difficult to use," and "difficult to tap" are extracted.

[1700] Based on the analysis results, the server uses statistical analysis tools (e.g., clustering algorithms or TF-IDF) to identify common trends and patterns among the multiple feedbacks. For example, it may discover that similar issues have been reported multiple times for a particular version of an app. Based on this information, the server visualizes the analysis results as graphs and charts using display tools (e.g., Matplotlib or D3.js).

[1701] The terminal displays the analysis results in the form of a dashboard, allowing managers and product development teams to intuitively grasp trends and patterns in feedback.

[1702] The server uses a generative AI model based on the analytical and statistical analysis results to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area of ​​the user interface" may be generated. The server then notifies the person in charge of these improvement suggestions using a notification device. Notification methods include email and intranet notification systems.

[1703] The terminal provides a user interface that allows managers and staff to check improvement proposals. It also provides tools for tracking the progress of improvement work. Managers and staff implement specific improvement work based on the proposals and enter their progress into the system, which updates the latest status.

[1704] Specific examples

[1705] For example, if user feedback about an app is that "the buttons are small and difficult to use" or "the colors are hard to see," the server collects, stores, and analyzes that feedback. Based on the analysis results, improvement suggestions such as "increase the button size" or "increase the color contrast" are generated and notified to the design team. The design team can then revise the app design based on the improvement suggestions, contributing to an improved user experience.

[1706] Prompt Sentence Examples

[1707] "I want to collect and analyze user feedback on a new app design. I want to know how the server, device, and user work together to identify specific issues."

[1708] This system enables efficient collection and analysis of user feedback, enabling prompt and concrete improvement measures to be taken.

[1709] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1710] Step 1:

[1711] The server launches the generative AI model when a user accesses a specific URL and generates a welcome message.

[1712] Input: User's access request

[1713] Output: Welcome message ("What product / service would you like to hear about?")

[1714] Specific operation: When the server receives an HTTP request, it invokes a generative AI model (e.g., GPT-3) to generate a welcome message, embeds it in an HTML page, and sends it back to the user's browser.

[1715] Step 2:

[1716] The terminal displays an input field along with the welcome message received from the server.

[1717] Input: Welcome message from the server

[1718] Output: User feedback input interface

[1719] Specific behavior: The device (user's browser) uses an HTML form and JavaScript to display a text area where the user can enter feedback and a submit button.

[1720] Step 3:

[1721] The user inputs their opinions and requests regarding the product or service and presses the send button.

[1722] Input: User feedback (e.g., "The design of this app is difficult to use.")

[1723] Output: User-entered feedback data

[1724] Specific behavior: The user enters text in the feedback field and clicks the "Submit" button.

[1725] Step 4:

[1726] The server receives the feedback sent by the user and stores it in a database.

[1727] Input: Feedback data submitted by the user

[1728] Output: Feedback stored in a database

[1729] Specific operation: The server receives the feedback data and stores it in the SQL database using an INSERT statement.

[1730] Step 5:

[1731] The server analyzes the stored feedback using a natural language processing device.

[1732] Input: Saved feedback data

[1733] Output: Analysis results (keyword list, sentiment score, topic tags, etc.)

[1734] Specific operation: The server reads the saved feedback data, sends it to a natural language processing tool (e.g., spaCy or NLTK) via an API, and saves the returned analysis results back in the database.

[1735] Step 6:

[1736] The server performs statistical analysis based on the analysis results to identify common trends and patterns from the multiple feedbacks.

[1737] Input: Analysis results

[1738] Output: Statistical analysis results (identification of common trends and patterns)

[1739] Specific operation: The server uses algorithms such as k-means clustering and TF-IDF to extract commonalities in the feedback and perform statistical analysis.

[1740] Step 7:

[1741] The server generates graphs and charts to visualize the analysis results.

[1742] Input: Statistical analysis results

[1743] Output: Visualized data (graphs, charts, etc.)

[1744] Specific operation: The server uses visualization tools such as Matplotlib and D3.js to generate visualization data based on the feedback trend data.

[1745] Step 8:

[1746] The terminal displays the visualized data received from the server in dashboard format.

[1747] Input: Visualization data from the server

[1748] Output: Dashboard format display

[1749] Specific operation: The terminal (user's browser) displays an HTML page containing visualized data and a dashboard UI.

[1750] Step 9:

[1751] The server uses a generative AI model based on the analytical and statistical analysis results to generate specific improvement suggestions.

[1752] Input: Statistical analysis results

[1753] Output: Improvement suggestion (e.g. "Make the button size larger")

[1754] Specific operation: The server inputs the analysis results as prompt sentences into the generative AI model, and the AI ​​generates suggestions.

[1755] Step 10:

[1756] The server notifies the person in charge of the generated improvement proposal.

[1757] Input: Generated improvement suggestions

[1758] Output: Notification to responsible parties (via email or intranet notification system)

[1759] Specific operation: The server sends an email containing the proposal to the person in charge via the SMTP server or notifies them using the intranet notification API.

[1760] Step 11:

[1761] The device provides a UI for managers and staff to review improvement proposals, and also provides tools for tracking the progress of improvement work.

[1762] Input: Improvement suggestion notification from the server

[1763] Output: Display improvement suggestions to managers and staff and provide tracking tools

[1764] Specific operation: The terminal (user's browser) displays improvement proposals in list format and provides the person in charge with the ability to update the progress status.

[1765] Step 12:

[1766] Managers and staff members then carry out specific improvement work based on the suggestions. Progress is entered into the system, and the latest status is updated via the server.

[1767] Input: Improvement proposals, progress of improvement work

[1768] Output: Updated remediation status

[1769] Specific actions: Managers and staff enter the progress of improvement work into the tracking system and save the progress status in the database.

[1770] (Application example 1)

[1771] 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."

[1772] There is a lack of a way to efficiently collect user feedback on the experience of using autonomous vehicles, analyze it in real time, and quickly propose improvements. This poses a challenge, delaying the improvement of the service quality of autonomous vehicles. There is also a need for a smooth method of collecting feedback without disrupting the user experience.

[1773] 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.

[1774] In this invention, the server includes an interaction means using a generative AI model to directly collect feedback from users, a storage means for storing the collected feedback, a natural language processing means for analyzing the stored feedback, a display means for visualizing the analysis results, a notification means for notifying the analysis results and improvement suggestions, an input means for passengers of the autonomous vehicle to input feedback using a smartphone, a communication means for transmitting the feedback input by the passengers of the autonomous vehicle to the server in real time, and a generation means using a generative AI model to generate improvements based on the analysis results. This makes it possible to quickly collect and analyze user feedback in the autonomous vehicle and make appropriate improvement suggestions.

[1775] A "generative AI model" is a model that uses artificial intelligence to generate, analyze, and suggest user feedback.

[1776] "Interactive means" are means for communicating with users, such as collecting feedback.

[1777] "Storage means" means means for storing collected feedback.

[1778] "Natural language processing means" is a means for analyzing collected feedback, and involves performing keyword extraction, sentiment analysis, topic classification, etc.

[1779] The "display means" is a means for visually displaying the analysis results.

[1780] "Notification means" refers to the means for notifying the person in charge of the analysis results and improvement suggestions.

[1781] "Input means" refers to the smartphone interface that allows users to input feedback.

[1782] "Communication means" refers to a means for transmitting feedback from users to the server in real time.

[1783] The "generation means" is a means that uses a generative AI model to generate improvement proposals based on the analysis results.

[1784] An "autonomous vehicle" is a vehicle in which driving operations are automated.

[1785] The system according to the present invention includes the following elements in order to efficiently collect feedback from users of autonomous vehicles, analyze the feedback, and make appropriate improvement suggestions.

[1786] 1. Feedback gathering phase

[1787] The server sends a welcome message to the user via the smartphone application, such as "Tell us what you think! Tell us about your experience riding in a self-driving vehicle." This prompts the user to provide feedback.

[1788] The device (smartphone) displays a welcome message along with an input field to allow the user to enter feedback.

[1789] The user provides feedback by speaking or typing, for example, "I couldn't see the scenery from the window very well" or "The air conditioning was too strong and it was cold."

[1790] 2. Feedback analysis phase

[1791] The server stores the received feedback in a storage means (e.g., a database or a JSON file).

[1792] Next, the feedback is analyzed using natural language processing tools, such as a generative AI model (e.g., OpenAI's GPT-4), to extract keywords from the feedback and perform sentiment analysis and topic classification.

[1793] The analysis results are saved as text. For example, from feedback such as "The air conditioning was too strong and it was cold," keywords such as "air conditioning" and "cold" are extracted.

[1794] 3. Response and Improvement Phase

[1795] The server uses a generative AI model based on the analysis results to generate specific improvement proposals, such as "improving the automatic adjustment function of the air conditioning system."

[1796] The improvement proposal will be notified to the responsible person via email or an intranet notification system.

[1797] The device (smartphone or tablet) displays the analysis results in a dashboard format, allowing managers and staff to check the results. Tools are also provided for tracking the progress of improvements.

[1798] Hardware and software used

[1799] Hardware: Servers, smartphones, network devices

[1800] Software: Python, Flask, OpenAI API (GPT-4)

[1801] Data processing and calculation

[1802] Feedback is collected using a smartphone app, and the input feedback is sent to a server in real time.

[1803] Feedback is stored on the server side, and a natural language processing engine (GPT-4) is used to extract keywords, analyze sentiment, and classify topics.

[1804] Common patterns and trends are identified from the analysis results, and specific improvement suggestions are generated using a generative AI model.

[1805] Finally, by notifying the person in charge of the improvement proposal, a prompt response can be made.

[1806] Examples and prompts

[1807] Specific examples

[1808] When a user enters feedback while riding in an autonomous vehicle, such as "I couldn't see the scenery from the window very well" or "The air conditioning was too strong and it was cold," the system collects and analyzes this in real time. As a result of the analysis, it generates suggestions such as "Improve the window brightness adjustment function" or "Improve the automatic air conditioning adjustment function" and notifies the person in charge. The person in charge can then directly improve the system based on these suggestions.

[1809] Prompt Sentence Examples

[1810] Analyze the following feedback:

[1811] ["I couldn't see the scenery from the window very well", "The air conditioning was too strong and it was cold"]

[1812] Generate improvement suggestions based on the following feedback analysis results:

[1813] ["Improve the window brightness adjustment function", "Improve the automatic air conditioning adjustment function"]

[1814] The present invention makes it possible to efficiently and quickly improve the user experience in autonomous vehicles.

[1815] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1816] Step 1:

[1817] Feedback collection

[1818] ---

[1819] Input: The user responds to the "Tell us what you think" welcome message displayed on the smartphone app.

[1820] Action: The user enters feedback and presses the submit button. For example, the user enters feedback such as "The view from the train window was not very clear."

[1821] Output: The feedback data entered by the user is sent to the server via the smartphone app.

[1822] Step 2:

[1823] Save your feedback

[1824] ---

[1825] Input: Feedback data submitted by the user

[1826] Behavior: The server stores the received feedback data in a storage medium (e.g., a database or a JSON file).

[1827] Output: Stored feedback data

[1828] Step 3:

[1829] Feedback Analysis

[1830] ---

[1831] Input: Stored feedback data

[1832] How it works: The server analyzes the feedback using natural language processing tools. Generative AI models such as GPT-4 are used to extract keywords, analyze sentiment, and classify topics. For example, from the feedback "The air conditioning was too strong and it was cold," it extracts keywords such as "air conditioning" and "cold."

[1833] Output: Analyzed feedback data (keywords and sentiment analysis results)

[1834] Step 4:

[1835] Visualization of analysis results

[1836] ---

[1837] Input: Parsed feedback data

[1838] How it works: The server uses the analysis results to visualize the results as graphs and charts, and processes the data so that it can be displayed in a dashboard format.

[1839] Output: Visualized analysis results (e.g., graphs, charts, etc.)

[1840] Step 5:

[1841] Generate improvement suggestions

[1842] ---

[1843] Input: Parsed feedback data

[1844] How it works: The server uses the generative AI model to generate specific improvement suggestions based on the analysis results, such as "improve the brightness adjustment function of window glass."

[1845] Output: Specific improvement suggestions

[1846] Step 6:

[1847] Notification of improvement proposals

[1848] ---

[1849] Input: Generated improvement suggestions

[1850] Behavior: The server notifies the person in charge of the generated improvement proposal, using email or an intranet notification system.

[1851] Output: Improvement suggestions notified to the person in charge

[1852] Step 7:

[1853] Confirmation and Implementation of Improvement Proposals

[1854] ---

[1855] Input: Improvement proposals notified to the person in charge

[1856] Operation: The person in charge receives the notification and checks the content of the proposal. Next, the person conducts specific improvement work and enters the progress status into the system. For example, implement a proposal to "improve the automatic adjustment function of the air conditioning system".

[1857] Output: Progress status of improvement work

[1858] In this way, data processing and calculations are performed at each step, and finally, the service quality of the autonomous driving vehicle is improved.

[1859] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[1860] The system according to the present invention combines a generative AI model, storage means, natural language processing means, visualization means, notification means, statistical analysis means, and an emotion engine to collect and analyze user feedback and automatically generate specific improvement proposals. This system operates among the server, the terminal, and the user.

[1861] Interaction Phase (Feedback Collection)

[1862] Server:

[1863] When the user accesses, the server activates the generative AI model and sends a welcome message to the user. For example, display a message such as "Please let us know your opinion. Which product / service is it about?" As a result, the user starts providing feedback.

[1864] Device:

[1865] The terminal displays a welcome message and input fields for the user to enter feedback, which is sent to the server in real time.

[1866] User:

[1867] Users enter their opinions and requests regarding products and services and press the submit button. For example, they can enter feedback such as, "I think the design of this app is difficult to use."

[1868] Analysis phase (analysis of feedback)

[1869] server:

[1870] The server stores the received feedback in storage. It then analyzes the feedback using natural language processing. This analysis includes keyword extraction, sentiment analysis, and topic classification. For example, if the feedback "The button is small and difficult to tap" is analyzed, the keywords "button," "difficult to use," and "difficult to tap" are extracted.

[1871] server:

[1872] Furthermore, an emotion engine is used to recognize user emotions, such as "dissatisfaction" or "irritation." This emotion data is used to assess the importance and urgency of feedback.

[1873] server:

[1874] The analysis results can be used to identify common trends and patterns across multiple pieces of feedback, such as finding that a particular version of an app is reporting a high number of "dissatisfied" and "irritated" users. This information can then be used to generate data that can be displayed as graphs or charts using visualization tools.

[1875] Device:

[1876] The device displays the analysis results in the form of a dashboard, allowing managers and product development teams to intuitively grasp feedback trends, patterns, and sentiment data.

[1877] Response and improvement phase (proposing improvements)

[1878] server:

[1879] The server uses a generative AI model to generate specific improvement suggestions based on the analytical and statistical analysis results. For example, suggestions might be made such as "increase the button size" or "expand the tap area in the UI design." Additionally, based on emotional data, it prioritizes the most urgent improvements.

[1880] server:

[1881] The generated improvement proposals are notified to the person in charge via email or an intranet notification system.

[1882] Device:

[1883] The terminal provides an interface for managers and personnel to review improvement proposals, and also provides tools for tracking the progress of improvement work.

[1884] User (Administrator / Contact Person):

[1885] Managers and staff members then carry out specific improvement work based on the proposals. The progress of the improvement work is entered into the system, and the latest status is updated via the server. The progress of the improvement work is also displayed on the dashboard, allowing all parties involved to understand the progress.

[1886] Specific examples

[1887] For example, if user feedback about a certain app is that "the buttons are small and difficult to use" or "the colors are hard to see," and the emotion engine detects "dissatisfaction" or "irritation," the server collects, stores, and analyzes that feedback. Based on the analysis results, improvement suggestions such as "increase the button size" or "increase the color contrast" are generated and notified to the design team in charge. The design team then uses the suggestions to revise the app's design and contribute to improving the user experience.

[1888] This system allows for efficient collection and analysis of user feedback and their emotions, enabling prompt and concrete improvement measures to be taken.

[1889] The processing flow will be explained below.

[1890] Step 1: User authentication

[1891] User:

[1892] Enter your username and password to log in to the system.

[1893] server:

[1894] Validates the entered credentials and authenticates the user. If successful, checks the user's access rights and loads the initial configuration information.

[1895] Step 2: Initiating a feedback dialogue

[1896] server:

[1897] Generate a welcome message and send it to the device, for example, "What product / service would you like to share your thoughts on?"

[1898] Device:

[1899] It displays a welcome message and an input field to prompt the user for input.

[1900] Step 3: Provide feedback

[1901] User:

[1902] Enter your opinions and requests regarding products and services and press the send button.

[1903] Device:

[1904] Send the feedback data entered by the user to the server.

[1905] Step 4: Receive and store feedback

[1906] server:

[1907] The received feedback data is stored in storage, including the user ID, date and time, and specific opinions.

[1908] Step 5: Continuing the Generative AI Model

[1909] server:

[1910] A generative AI model is used to analyze user feedback and generate the next question, for example, "Which parts specifically did you find difficult to use?"

[1911] server:

[1912] Send the following question to the device:

[1913] Step 6: Continue the conversation

[1914] Device:

[1915] Displays the question sent by the server.

[1916] User:

[1917] Enter an answer to the question and submit. Example: "The buttons are small and difficult to tap."

[1918] Device:

[1919] The user's answer is sent to the server.

[1920] Step 7: Collect emotion recognition data

[1921] server:

[1922] The emotion engine is used to recognize the user's emotions from the input feedback, for example, detecting emotions such as "dissatisfaction" or "irritation."

[1923] Step 8: Analyze feedback and incorporate sentiment data

[1924] server:

[1925] The collected feedback and sentiment data is analyzed using natural language processing tools, including keyword extraction, sentiment analysis, and topic classification. For example, keywords such as "button," "difficult to use," and "difficult to tap" are extracted.

[1926] server:

[1927] Emotional data is incorporated into the analysis results to assess the importance and urgency of feedback, and feedback with high importance is tagged as high priority.

[1928] Step 9: Identify trends and patterns

[1929] server:

[1930] Statistically process feedback from multiple users to identify common trends and patterns. For example, find out if a particular version of an app is generating a lot of frustration or irritation.

[1931] Step 10: Visualize the results

[1932] Device:

[1933] Provides a dashboard where administrators and staff can check the analysis results, displaying graphs and charts of the analysis results. Example: Showing that a specific version has a lot of negative feedback about "button size."

[1934] Step 11: Generate improvement suggestions

[1935] server:

[1936] Based on the results of analytical and statistical analysis, a generative AI model is used to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are created. Additionally, based on emotional data, the system prioritizes and presents particularly urgent improvement points.

[1937] Step 12: Notification of improvement proposals

[1938] server:

[1939] The generated improvement proposals are notified to the person in charge via email or an intranet notification system.

[1940] Step 13: Tracking Improvement Efforts

[1941] Device:

[1942] It provides an interface for managers and staff to review improvement proposals and track their progress. Once specific improvement work is initiated, the progress is updated in the system.

[1943] Step 14: Follow up on user feedback

[1944] server:

[1945] Once the improvements are complete, you can follow up by notifying users of the changes and asking for their feedback.

[1946] This allows for the automation and efficient execution of a series of processes, from collecting user feedback to recognizing emotions, analyzing them, visualizing the results, notifying improvement suggestions, and tracking improvement work.

[1947] Example 2

[1948] 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."

[1949] Conventional feedback collection systems have difficulty efficiently analyzing user feedback and automatically generating specific improvement proposals. Furthermore, due to a lack of emotion recognition and statistical trend analysis, they are unable to properly evaluate the importance and urgency of feedback. A system that can solve these issues and effectively utilize user feedback is needed.

[1950] 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.

[1951] In this invention, the server includes an interaction means using a generative AI model to directly collect feedback from users, a data storage means for storing the collected feedback, a natural language processing means for extracting keywords and classifying topics based on the stored feedback data, a sentiment analysis means for detecting sentiment in the analyzed feedback data, a data visualization means for visually displaying the analysis results, and a notification means for notifying the analysis results and improvement suggestions.

[1952] This makes it possible to efficiently collect and analyze feedback from users and quickly generate and communicate specific improvement suggestions, including emotional data.

[1953] A "generative AI model" is an artificial intelligence model that interprets user feedback in natural language and collects it in an interactive format.

[1954] "Data storage means" refers to a database system or storage system for storing and managing collected feedback data.

[1955] "Natural language processing means" refers to natural language processing technology for analyzing collected feedback data and performing keyword extraction and topic classification.

[1956] "Emotion analysis means" refers to a technique for detecting a user's emotions from the analyzed feedback data.

[1957] "Data visualization means" refers to tools and technologies that visually display the results of analyzed feedback data, making it easier for managers and staff to understand.

[1958] "Notification means" refers to a communication means for notifying the person in charge of the analysis results and generated improvement proposals.

[1959] "Statistical analysis methods" refers to statistical methods and techniques for identifying common trends or patterns from multiple feedback data.

[1960] "Dashboard" refers to the user interface that allows administrators and personnel to view and track analysis results.

[1961] The system of the present invention combines a generative AI model, data storage means, natural language processing means, sentiment analysis means, data visualization means, notification means, and statistical analysis means to collect and analyze user feedback and automatically generate specific improvement proposals. This system operates among a server, terminals, and users.

[1962] Collecting feedback

[1963] server:

[1964] The server activates the generative AI model when a user accesses the system and sends a welcome message, such as "Tell us your opinion. What product / service is it about?", which prompts the user to provide feedback.

[1965] Device:

[1966] The device displays the received welcome message and allows the user to enter feedback, which is sent to the server in real time.

[1967] User:

[1968] Users enter their opinions and requests regarding products and services and press the submit button. For example, they can enter feedback such as, "I think the design of this app is difficult to use."

[1969] Feedback analysis and sentiment analysis

[1970] server:

[1971] The server stores the received feedback in a data storage means, for example, a database system such as MySQL or PostgreSQL.

[1972] Next, the feedback is analyzed using natural language processing tools (e.g., NLTK, spacy). This includes keyword extraction and topic classification. For example, if the feedback says, "The button is small and difficult to tap," the keywords "button," "small," and "difficult to tap" are extracted.

[1973] Additionally, sentiment analysis tools (e.g., BERT) are used to recognize user emotions. For example, emotions such as "dissatisfaction" and "irritation" are detected. This emotional data is used to assess the importance and urgency of the feedback.

[1974] Visualizing and notifying results

[1975] server:

[1976] Based on the analysis results, we use statistical analysis methods to identify common trends and patterns across multiple pieces of feedback, for example, finding that a particular version of an app is more likely to be "frustrated" or "irritated."

[1977] Next, data visualization tools (e.g., D3.js or Chart.js) are used to generate graphs and charts that display these results, allowing managers and product development teams to intuitively understand feedback trends, patterns, and sentiment data.

[1978] Device:

[1979] The terminal displays the visualized data sent from the server in the form of a dashboard, allowing managers and product development teams to intuitively grasp feedback trends, patterns, and sentiment data.

[1980] Generate and notify improvement suggestions

[1981] server:

[1982] The server uses a generative AI model (e.g., GPT-3) based on the analytical and statistical analysis results to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are generated. Additionally, based on emotional data, it prioritizes and presents particularly urgent improvement points.

[1983] Next, the generated improvement proposals are notified to the person in charge via a mail server or an intranet notification system.

[1984] Device:

[1985] The device will display a notification to allow the administrator or person in charge to check the improvement proposal, for example, through the email app or a dedicated notification app.

[1986] User (Administrator / Contact Person):

[1987] Managers and staff members then carry out specific improvement work based on the proposals. The progress of the improvement work is entered into the system, and the latest status is updated via the server. The progress of the improvement work is also displayed on the dashboard, allowing all parties involved to understand the progress.

[1988] Prompt Sentence Examples

[1989] Here are some examples of prompts to input to a generative AI model:

[1990] "After collecting user feedback on product X and performing sentiment analysis, what improvements would you suggest?"

[1991] "Analyze the negative feedback received from users of Service Y and identify specific areas for improvement."

[1992] This prompt allows the AI ​​model to quickly generate the necessary analysis and suggestions.

[1993] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1994] Step 1:

[1995] Feedback session begins

[1996] server:

[1997] When a user accesses the system, the server launches the generative AI model and sends a welcome message, such as "What product / service would you like to share your thoughts on?"

[1998] Input: User's access request

[1999] Output: Welcome message

[2000] Device:

[2001] The terminal displays the received welcome message on the user interface, along with a text box for entering feedback and a submit button.

[2002] Input: Welcome message sent by the server

[2003] Output: A welcome message and an input field.

[2004] Step 2:

[2005] Enter and submit feedback

[2006] User:

[2007] Users can enter their feedback into a text box on their device and press the submit button, for example, "I think the design of this app is difficult to use."

[2008] Input: Feedback

[2009] Output: Send feedback

[2010] Device:

[2011] The device sends the feedback entered by the user to the server in real time.

[2012] Input: User feedback

[2013] Output: Send feedback to the server

[2014] Step 3:

[2015] Save your feedback

[2016] server:

[2017] The server stores the received feedback in a storage means, for example, a database system such as MySQL or PostgreSQL.

[2018] Input: User feedback data

[2019] Output: Saving the feedback data to a database

[2020] Step 4:

[2021] Feedback Analysis

[2022] server:

[2023] The server uses natural language processing tools (e.g., NLTK, Spacy) to analyze the stored feedback data. This analysis includes keyword extraction and topic classification. For example, from the feedback "The button is small and difficult to tap," the keywords "button," "small," and "difficult to tap" are extracted.

[2024] Input: Stored feedback data

[2025] Output: Extracted keywords and topics

[2026] Step 5:

[2027] Conducting sentiment analysis

[2028] server:

[2029] The server performs sentiment analysis of the feedback using sentiment analysis tools (e.g., BERT). For example, emotions such as "dissatisfaction" and "irritation" are detected. This sentiment data is used to evaluate the importance and urgency of the feedback.

[2030] Input: Feedback data and extracted keywords

[2031] Output: Emotion data

[2032] Step 6:

[2033] Visualizing the results

[2034] server:

[2035] Based on the analysis results and sentiment analysis results, the server uses statistical analysis tools to identify trends and patterns, and generates visualized data using data visualization tools (e.g., D3.js or Chart.js), such as graphs and charts showing feedback trends.

[2036] Input: Analysis results and emotion data

[2037] Output: Visualized data (graphs and charts)

[2038] Device:

[2039] The terminal displays the visualized data sent from the server in the form of a dashboard, allowing managers and product development teams to understand feedback trends and sentiment data.

[2040] Input: Visualization data sent from the server

[2041] Output: Dashboard display

[2042] Step 7:

[2043] Generate improvement suggestions

[2044] server:

[2045] The server uses a generative AI model (e.g., GPT-3) based on the analytical and statistical analysis results to generate specific improvement suggestions. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are generated. Additionally, based on emotional data, it prioritizes and presents particularly urgent improvement points.

[2046] Input: Analysis and statistical analysis results

[2047] Output: Improvement suggestions

[2048] Step 8:

[2049] Notification of improvement proposals

[2050] server:

[2051] The server notifies the person in charge of the generated improvement proposals using a mail server or an intranet notification system.

[2052] Input: Improvement Suggestion

[2053] Output: Notification to the person in charge

[2054] Device:

[2055] The device will display a notification to allow the administrator or person in charge to check the improvement proposal, for example, through the email app or a dedicated notification app.

[2056] Input: Notification from the server

[2057] Output: Display notification

[2058] Step 9:

[2059] Review and implement the proposal

[2060] User (Administrator / Contact Person):

[2061] Managers and staff members review the proposals and implement specific improvement work. The progress of the improvement work is entered into the system, and the latest status is updated via the server. The progress of the improvement work is also displayed on the dashboard, allowing all parties involved to understand the progress.

[2062] Input: Improvement Suggestion

[2063] Output: Progress of the implemented improvement work

[2064] (Application example 2)

[2065] 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."

[2066] In recent years, many online shopping sites have been trying to improve their services by collecting and analyzing user feedback, but this process is often done manually, requiring time and effort. It is also difficult to centrally manage the content of feedback and generate quick and specific improvement proposals. In particular, there is a need for a method to efficiently process large amounts of feedback and visualize the analysis results in an easy-to-understand manner. An effective system to solve these challenges is needed.

[2067] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2068] In this invention, the server includes a dialogue means using a generative AI model, a data storage means for saving collected feedback, a natural language processing means for analyzing the saved feedback, an information visualization means for visualizing the analysis results, an information transmission means for notifying generated improvement suggestions, and an interface provision means for tracking the progress of the improvement suggestions, thereby enabling efficient collection and analysis of user feedback and prompt and specific improvement suggestions to be provided.

[2069] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and generates new data.

[2070] "Interaction means" refers to a means of communication between a user and a system.

[2071] "Data storage means" refers to means for accumulating and storing data such as feedback.

[2072] "Natural language processing means" refers to means for analyzing text data and extracting meaning.

[2073] "Information visualization means" refers to means for displaying analytical results in visual formats such as graphs and charts.

[2074] "Information transmission means" refers to a means for informing related parties of the generated improvement proposals.

[2075] The "interface providing means" is a means for providing an interface for a user to check and operate information.

[2076] "Data analysis means" refers to means for processing received data and extracting trends and patterns.

[2077] A "display device" is a device for displaying visualized information.

[2078] The system according to the present invention automates the collection and analysis of feedback and the generation of improvement proposals for an online shopping site. Specific embodiments of this system will be described below.

[2079] Feedback gathering phase

[2080] When a user accesses a shopping site, the server activates the generative AI model and sends a welcome message. This message prompts the user to provide feedback, and is displayed in the form of, "Tell us your opinion. What product / service is it about?" The device displays this welcome message along with an input field for the user, and the user enters their feedback through the interface. This input is sent to the server in real time.

[2081] Feedback Analysis Phase

[2082] The server stores the collected feedback in a database. Next, it uses natural language processing (NLTK) to analyze the text data and extract keywords. An emotion engine is also used in this process to understand the user's emotions. The emotion data is added to the analysis results and used to evaluate the importance and urgency. The analysis results are displayed visually using information visualization tools so that managers and development teams can review them.

[2083] Improvement proposal generation phase

[2084] The server uses a generative AI model (TensorFlow) to generate specific improvement proposals based on the analysis results and data analysis methods. For example, if the feedback includes a comment that the search function is difficult to use, a proposal to improve the search function interface will be generated. The generated improvement proposals are notified to the person in charge via information transmission methods (SendGrid, Slack API).

[2085] The progress of improvement proposals is tracked through an interface provided by the device, and managers and staff can use a dashboard to monitor improvement proposals and their progress across multiple metrics.

[2086] Specific examples

[2087] If a user provides feedback that the app's design is difficult to use, the generative AI model will generate specific suggestions for improvement, such as increasing the button size or expanding the tap area in the UI design. These suggestions will be notified to the design team, who will then take action.

[2088] Here is an example prompt:

[2089] Please provide your feedback:

[2090] I think the design of this app is difficult to use.

[2091] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2092] Step 1:

[2093] When a user accesses the online shopping site, the server launches the generative AI model and sends the user a welcome message prompting them to provide feedback. Specifically, the message "Please tell us your opinion. Which product / service is it about?" is displayed on the user's device. This message is a prompt to encourage the user to enter feedback.

[2094] Step 2:

[2095] The user inputs feedback according to the welcome message, and the device sends this input to the server in real time. For example, the user may enter feedback such as "The design of this app is difficult to use." This feedback becomes input data to the server.

[2096] Step 3:

[2097] The server stores the received feedback in a database, where the data is stored in its original form and is used for subsequent analysis.

[2098] Step 4:

[2099] The server analyzes the saved feedback using natural language processing (NLTK). Specifically, it extracts keywords from the text data and analyzes the user's emotions. This analysis evaluates the importance and urgency of the feedback content. For example, the keyword "difficult to use" can be used to detect user dissatisfaction or irritation.

[2100] Step 5:

[2101] The server visually displays the analysis results using information visualization tools. The analysis results are displayed on terminals in dashboard format so that administrators and development teams can review them. Graphs and charts are used to clarify trends and patterns in the data.

[2102] Step 6:

[2103] The server uses a generative AI model (TensorFlow) to generate specific improvement suggestions based on the analysis results. For example, suggestions such as "increase the button size" or "expand the tap area in the UI design" are generated. In this process, important parts of the feedback are extracted and specific measures are proposed.

[2104] Step 7:

[2105] The generated improvement proposals are notified to the responsible person via information transmission methods (SendGrid or Slack API), such as email or internal messaging systems. The notification includes the priority of the improvement and the specific proposal content.

[2106] Step 8:

[2107] The device provides the manager or person in charge with an interface to track the content and progress of the improvement proposal. Using the dashboard, the manager or person in charge can check the progress of the improvement work in real time and take necessary actions.

[2108] 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.

[2109] 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.

[2110] 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.

[2111] 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.

[2112] 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.

[2113] 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.

[2114] 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).

[2115] 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.

[2116] 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."

[2117] 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.

[2118] 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).

[2119] 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.

[2120] 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.

[2121] 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.

[2122] 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.

[2123] 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.

[2124] 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.

[2125] 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.

[2126] 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.

[2127] 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.

[2128] 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.

[2129] The following is further disclosed regarding the above embodiment.

[2130] (Claim 1)

[2131] A means of interaction using generative AI models to collect direct user feedback;

[2132] a storage means for storing the collected feedback;

[2133] natural language processing means for analyzing the stored feedback;

[2134] a visualization means for visualizing the analysis results;

[2135] A system including a notification means for notifying analysis results and improvement suggestions.

[2136] (Claim 2)

[2137] 10. The system of claim 1, further comprising statistical analysis means for identifying trends and patterns from the analysis results.

[2138] (Claim 3)

[2139] The system according to claim 1, characterized in that the visualization means provides a dashboard for managers and personnel to view and track the visualized analysis results.

[2140] "Example 1"

[2141] (Claim 1)

[2142] A means of interaction using generative AI models to collect direct user feedback;

[2143] storage means for storing the collected feedback;

[2144] natural language processing means for analyzing the stored feedback;

[2145] statistical analysis means for identifying common trends or patterns from the plurality of feedbacks;

[2146] a display device for visualizing the analysis results;

[2147] a notification device means for notifying the analysis result and improvement suggestions;

[2148] a user interface means for allowing a manager or person in charge to confirm the improvement proposal;

[2149] A system that includes tools for tracking the progress of improvement work.

[2150] (Claim 2)

[2151] 10. The system according to claim 1, further comprising visualization means for generating visualization data that displays trends and patterns of the analysis results as graphs or charts.

[2152] (Claim 3)

[2153] The system according to claim 1, characterized in that the visualization means provides a dashboard for managers and personnel to view and track the visualized analysis results.

[2154] "Application Example 1"

[2155] (Claim 1)

[2156] A means of interaction using generative AI models to collect direct user feedback;

[2157] a storage means for storing the collected feedback;

[2158] natural language processing means for analyzing the stored feedback;

[2159] a display means for visualizing the analysis results;

[2160] a notification means for notifying the analysis results and improvement suggestions;

[2161] an input means for a passenger of the autonomous vehicle to input feedback using a smartphone;

[2162] a communication means for transmitting feedback input from a passenger of the autonomous vehicle to a server in real time;

[2163] A system that includes a generation means using a generative AI model to generate improvements based on the analysis results.

[2164] (Claim 2)

[2165] 10. The system of claim 1, further comprising statistical analysis means for identifying trends and patterns from the analysis results.

[2166] (Claim 3)

[2167] The system according to claim 1, characterized in that the display means provides a dashboard for managers and personnel to view and track the visualized analysis results.

[2168] "Example 2: Combining Emotion Engines"

[2169] (Claim 1)

[2170] A means of interaction using generative AI models to collect direct user feedback;

[2171] a data storage means for storing the collected feedback;

[2172] natural language processing means for extracting keywords and classifying topics based on the stored feedback data;

[2173] sentiment analysis means for detecting sentiment in the analyzed feedback data;

[2174] a data visualization means for visually displaying the analysis results;

[2175] A system including a notification means for notifying analysis results and improvement suggestions.

[2176] (Claim 2)

[2177] 10. The system of claim 1, further comprising statistical analysis means for statistically analyzing the analysis results to identify common trends or patterns.

[2178] (Claim 3)

[2179] The system according to claim 1, characterized in that the data visualization means provides a dashboard for managers and personnel to view and track the visualized analysis results.

[2180] "Application example 2 when combining emotion engines"

[2181] (Claim 1)

[2182] A dialogue method using generative AI models,

[2183] data storage means for storing the collected feedback;

[2184] natural language processing means for analyzing the stored feedback;

[2185] an information visualization means for visualizing the analysis results;

[2186] an information transmission means for notifying the generated improvement proposal;

[2187] The system includes a means for providing an interface for tracking the progress of improvement proposals.

[2188] (Claim 2)

[2189] 10. The system of claim 1, further comprising a data analysis means for identifying trends and patterns from the analysis results.

[2190] (Claim 3)

[2191] 2. The system according to claim 1, wherein the information visualization means provides a display device for managing and manipulating the visualized analysis results. [Explanation of symbols]

[2192] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of interaction using generative AI models to collect direct user feedback; a storage means for storing the collected feedback; natural language processing means for analyzing the stored feedback; a visualization means for visualizing the analysis results; A system including a notification means for notifying analysis results and improvement suggestions.

2. 10. The system of claim 1, further comprising statistical analysis means for identifying trends and patterns from the analysis results.

3. 2. The system according to claim 1, wherein the visualization means provides a dashboard for managers and personnel to view and track the visualized analysis results.

Images