System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving request data; means for analyzing the received data by natural language processing and classifying the request data into categories; means for generating specific solutions based on the classified request data; means for notifying appropriate parties of the generated solutions; and means for analyzing historical request data and solutions and automatically generating new suggestions.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] Conventional suggestion box systems are set up to accept requests and complaints from users, but they have the problem that processing them requires a lot of time and effort, making it difficult to quickly provide appropriate solutions. Furthermore, the collected request data cannot be effectively utilized, and new ideas and improvements cannot be automatically generated, so the original effect of the suggestion box cannot be fully realized. This invention aims to solve these problems and maximize the effect of the suggestion box by efficiently processing a huge number of requests and automatically generating new ideas. [Means for solving the problem]

[0005] This invention provides a system that includes a means for receiving request data, a means for analyzing the received data using natural language processing and categorizing the request data, a means for generating specific solutions based on the categorized request data, a means for notifying appropriate parties of the generated solutions, and a means for analyzing past request data and solutions and automatically generating new proposals. This system allows for rapid and accurate processing of user requests, providing efficient solutions, and maximizing the effectiveness of the suggestion box by periodically making new proposals. Furthermore, this system can provide more specific and feasible solutions by referencing past databases and examples from other companies. Furthermore, the generated solutions and new proposals are periodically notified and presented to the user, enabling continuous improvement.

[0006] "Request data" refers to information such as complaints and requests that users input through the suggestion box system.

[0007] The "receiving means" refers to a device or software that has the function of receiving and saving requested data from a user in the suggestion box system.

[0008] "Natural language processing" is a technology used by generative AI to analyze the content of requested data, analyzing text data to understand its meaning and classifying it into appropriate categories.

[0009] A "means for categorizing" is a device or software that has the function of automatically classifying the request data analyzed by the generation AI into specific categories.

[0010] "Means for generating solutions" refers to devices or software that have the functionality to allow the generation AI to automatically generate specific solutions based on categorized requirement data.

[0011] The "means for notifying a solution" refers to a device or software that has the function of quickly communicating the generated solution to the appropriate parties.

[0012] The "means for automatically generating new proposals" refers to devices or software that have the function of automatically proposing new ideas and improvements based on past requirement data and solutions.

[0013] "Stakeholders" are department personnel and managers who may be involved in implementing the generated solutions. [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 illustrating 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 cloud suggestion box + AI generation function system of this invention efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. Detailed embodiments of this system are described below.

[0036] System Overview:

[0037] Users input request data such as complaints and requests into the cloud suggestion box.

[0038] The terminal transmits the data entered by the user to the server in real time.

[0039] The server stores the received request data in a database and begins the analysis process.

[0040] Parsing and categorizing requirements data:

[0041] The server sends the saved request data to the generation AI for analysis.

[0042] Generative AI uses natural language processing (NLP) technology to analyze the content of requests and automatically classify them into specific categories, such as "internal facilities," "user interface," and "service improvement."

[0043] Auto-generation of solutions:

[0044] Generative AI generates specific solutions based on categorized requirements. During this process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, and time.

[0045] Solution Notification:

[0046] The server notifies the appropriate parties of the generated solution, for example, if the solution concerns internal facilities, it notifies the relevant administrative department personnel by email.

[0047] The user can quickly respond based on the notified solution.

[0048] Automatic generation of new suggestions:

[0049] Generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including proposals for new projects and ideas for improving business efficiency.

[0050] The server notifies the user or administrator of any new proposals generated and, if applicable, puts them into immediate implementation.

[0051] Examples:

[0052] For example, if a user submits a request to the suggestion box saying, "The conference room reservation system is difficult to use,"

[0053] The server stores this request data in a database and begins the analysis process.

[0054] The generative AI analyzes this data and categorizes it as a request related to "internal facilities."

[0055] The generative AI generates specific solutions such as "improving the UI of the conference room reservation system" and "creating a tutorial video for the reservation process."

[0056] The server notifies the company's system administration personnel of these solutions.

[0057] Users can be assured that the issues have been resolved with an improved system and new tutorials.

[0058] In this way, the Cloud Suggestion Box + Generative AI Function System can respond quickly and appropriately to user requests and achieve continuous improvement. It also automatically generates new ideas and suggestions on a regular basis and provides them to users, ensuring that they always receive the latest and best solutions.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] Users input their requests or complaints into the cloud suggestion box, and the input data is sent from the device to the server in real time.

[0062] Step 2:

[0063] Once the server receives the requested data, it stores it in a database, where it is added to a queue for analysis.

[0064] Step 3:

[0065] The server periodically checks the queue to see if there is new request data. If it finds new request data, it sends it to the generation AI.

[0066] Step 4:

[0067] The generative AI receives the request data and uses natural language processing (NLP) technology to analyze the content of the data, determining which category the request data belongs to.

[0068] Step 5:

[0069] The generation AI classifies the request data into appropriate categories based on the identified categories, such as "internal facilities," "user interface," and "service improvement."

[0070] Step 6:

[0071] The generative AI generates specific solutions based on categorized requirements data. During the generation process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, time, etc.

[0072] Step 7:

[0073] Once a solution is generated, the server notifies the appropriate parties of the solution. For example, if the solution concerns an internal facility, a notification is sent via email to the relevant administrative personnel.

[0074] Step 8:

[0075] Users can receive solutions notified by relevant parties and initiate the necessary response, which includes a concrete action plan, enabling rapid response.

[0076] Step 9:

[0077] The server receives and logs feedback from stakeholders to track the implementation of solutions, allowing you to see the effectiveness of the solutions.

[0078] Step 10:

[0079] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including ideas for new projects and business efficiency improvements.

[0080] Step 11:

[0081] Newly generated suggestions are notified to users and administrators via the server, and if applicable, they are immediately implemented for further improvement.

[0082] Example 1

[0083] 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."

[0084] The existing system lacked the process for efficiently collecting and analyzing user requests and complaints, automatically generating solutions, and notifying the appropriate parties. It also struggled to regularly provide users with continuous improvements and new proposals. This hindered the rapid resolution of problems and improved work efficiency.

[0085] 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.

[0086] In this invention, the server includes means for receiving request data, means for analyzing the received data using natural language processing and classifying the request data into categories, means for generating specific solutions based on the classified request data, means for analyzing past request data and solutions and automatically generating new proposals, means for notifying a person in charge of management or a user of the generated solutions and encouraging them to take action, and means for periodically notifying a user or a manager of new proposals and encouraging them to implement them. This makes it possible to efficiently collect and analyze requests and complaints from users and quickly provide specific solutions, as well as to periodically provide continuous improvements and new proposals.

[0087] "Request data" is information including complaints, requests, and other demands input by the user.

[0088] A "server" is a computer system that receives, stores, analyzes request data, and generates and notifies solutions.

[0089] A "terminal" is a device through which a user inputs request data and transmits it to a server.

[0090] "Generative AI" is an artificial intelligence system that uses natural language processing technology to analyze requirement data and automatically generate solutions and new proposals.

[0091] "Natural Language Processing (NLP)" is a technology that enables computers to understand, analyze, and generate human language.

[0092] "Category" is a classification category used by the generation AI to classify the request data analyzed.

[0093] A "solution" is a specific countermeasure or improvement that the generating AI proposes based on the required data.

[0094] "Notification" is the act of informing appropriate parties of solutions or proposals generated by generative AI.

[0095] "Proposals" are new improvement plans or ideas that the generative AI generates by analyzing past requirement data and solutions.

[0096] "Stakeholders" refer to the management personnel and users who should receive the generated solutions and proposals.

[0097] MODE FOR CARRYING OUT THE INVENTION

[0098] The cloud suggestion box + AI generation function system of this invention efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. Specific embodiments of this system are shown below.

[0099] System Overview

[0100] The system consists of four main components: the user, the terminal, the server, and the generating AI.

[0101] User: The user inputs complaints, requests, and other request data into the cloud suggestion box. For example, the user inputs a request such as "The conference room reservation system is difficult to use."

[0102] Terminal: The terminal transmits the data entered by the user to the server in real time. The terminal is a device such as a PC or smartphone that transmits data through a cloud-based input form or application.

[0103] Server: The server receives the requested data and stores it in a database, which then initiates the analysis process and sends it to the generation AI.

[0104] Generative AI: Generative AI uses natural language processing (NLP) techniques to analyze the received request data and classify it into specific categories. It then generates a specific solution based on the classified request data. The generated solution is returned to the server, which then notifies the appropriate parties.

[0105] Analyzing and categorizing requirements data

[0106] The server sends the saved request data to the generation AI, which begins analyzing it. The generation AI uses natural language processing technology to analyze the content of the request and automatically classify it into specific categories. These include categories such as "internal facilities," "user interface," and "service improvement." The generation AI uses generative AI models such as BERT and GPT, which are NLP techniques in general computer science.

[0107] Automatic solution generation

[0108] Generative AI generates specific solutions based on categorized requirements. During this process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, time, etc. Generative AI learns from past databases and cases to provide highly accurate solutions.

[0109] Solution Notification

[0110] The server then notifies the appropriate parties of the generated solution. For example, if the solution relates to internal facilities, it will notify the relevant management department via email or an internal notification system. The notification will also include specific steps and resources to be taken, allowing the parties involved to respond quickly.

[0111] Automatic generation of new proposals

[0112] The generative AI periodically analyzes past requirement data and solutions to automatically generate new proposals and improvements. These include proposals for new projects and ideas for improving business efficiency. The server notifies users and administrators of the new proposals and, if applicable, immediately implements them.

[0113] Specific examples

[0114] For example, if a user submits a request to the suggestion box saying, "The conference room reservation system is difficult to use,"

[0115] The server stores this request data in a database and begins the analysis process.

[0116] The generative AI analyzes this data and categorizes it as a request related to "internal facilities."

[0117] The generative AI generates specific solutions such as "improving the UI of the conference room reservation system" and "creating a tutorial video for the reservation process."

[0118] The server notifies the company's system administration personnel of these solutions.

[0119] Users can be assured that the issues have been resolved with an improved system and new tutorials.

[0120] Prompt Sentence Examples

[0121] If a user types "I want to improve the onboarding process for new employees":

[0122] The device sends this to the server.

[0123] The server sends the data to the generation AI, which then suggests simplifying the onboarding flow for new employees and introducing digital training content.

[0124] The server notifies the HR department.

[0125] The HR department implements the proposal and new employees are smoothly onboarded.

[0126] In this way, the cloud suggestion box + generative AI function system can respond quickly and appropriately to user requests and achieve continuous improvement. It also automatically generates new ideas and suggestions on a regular basis and provides them to users, ensuring that they always receive the latest and best solutions.

[0127] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0128] Step 1:

[0129] The user inputs the requested data into the input form of the cloud suggestion box. For example, the input requested data is "The conference room reservation system is difficult to use." This data is captured by the terminal.

[0130] Input: User request data (text format)

[0131] Output: The requested data entered is saved on the terminal.

[0132] Step 2:

[0133] The terminal transmits the request data input by the user to the server in real time. The terminal uses the HTTP POST method to transmit the request data to the server as a packet.

[0134] Input: Request data stored on the device

[0135] Output: Packet data sent to the server

[0136] Step 3:

[0137] The server receives the HTTP request, extracts the request data from the request body, and then executes an INSERT query to store this request data in the database.

[0138] Input: Packet data sent to the server

[0139] Output: Request data stored in the database

[0140] Step 4:

[0141] The server sends the saved request data to the generation AI and starts the analysis process. The request data is transferred to the generation AI through the API endpoint.

[0142] Input: Request data stored in the database

[0143] Output: Request data sent to the generating AI

[0144] Step 5:

[0145] Generative AI analyzes the received request data using natural language processing (NLP) techniques, typically using BERT or GPT models. This analysis performs semantic analysis of the text data and classifies it into specific categories.

[0146] Input: Request data sent to the generating AI

[0147] Output: Parsed category information (e.g., "In-house facilities")

[0148] Step 6:

[0149] Generative AI automatically generates solutions based on categorized requirements, referencing past success stories and database information to provide specific action plans.

[0150] Input: Parsed category information

[0151] Output: Generated solutions (e.g., "Improve the UI of the conference room reservation system," "Create a tutorial video for the reservation process")

[0152] Step 7:

[0153] The server notifies the appropriate parties of the generated solution. For example, if the solution is related to internal facilities, it notifies the relevant management department personnel via email or an internal notification system.

[0154] Input: Generated solution

[0155] Output: Notification to relevant parties (email and system notification)

[0156] Step 8:

[0157] Users receive notification and confirmation that the solution has been implemented. Users can use the improved system and see its effectiveness.

[0158] Input:Notification to interested parties

[0159] Output: User confirmation of solution and feedback

[0160] Step 9:

[0161] Generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals, including new project proposals and ideas for improving business efficiency.

[0162] Input: Past request data and solutions

[0163] Output: New proposal (e.g., "Remote work optimization proposal")

[0164] Step 10:

[0165] The server notifies the user or administrator of any new suggestions that are generated and, if applicable, implements them immediately.

[0166] Input: New proposal

[0167] Output: Notification and action recommendation to users and administrators

[0168] These are the specific processing steps of the cloud suggestion box + generative AI function system, which enables a quick and appropriate response to user requests.

[0169] (Application example 1)

[0170] 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."

[0171] Traditionally, processing customer feedback and requests in brick-and-mortar stores has been inefficient and difficult to respond to promptly. In particular, it has been difficult for the person receiving the feedback to quickly find a solution, and continuous improvement and the generation of new proposals have been insufficient. For these reasons, there is a need to improve customer satisfaction and streamline store operations.

[0172] 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.

[0173] In this invention, the server includes means for receiving request data, means for analyzing the received data using natural language processing and classifying the request data into categories, means for sending customer feedback from the physical store to a cloud suggestion box in real time via a smartphone app, means for generating specific solutions based on the classified request data, means for notifying appropriate parties of the generated solutions, and means for analyzing past request data and solutions and automatically generating new proposals. This enables rapid processing of customer feedback, improved operational efficiency of the physical store, continuous improvement, and the automatic generation of new proposals.

[0174] "Request Data" means feedback or request information collected from users.

[0175] "Natural language processing" is a technology that allows computers to understand and analyze natural language used by humans.

[0176] A "category" is a grouping based on a certain common attribute or theme.

[0177] A "smartphone app" is a software application that runs on a mobile information terminal.

[0178] A "cloud suggestion box" is a system that stores data on the Internet and allows users to enter requests and feedback.

[0179] A "server" is a computer device that stores, manages, and analyzes data over a network.

[0180] A "solution" is a specific method or policy for solving a particular problem.

[0181] "Stakeholders" are people or departments with responsibilities related to a particular issue or situation.

[0182] A "proposal" is a new idea or plan for improvement for a specific problem.

[0183] To implement the present invention, a system including a server, a terminal, and a user is used. The configuration and operation procedure of this system will be described in detail below.

[0184] System Configuration

[0185] 1. Hardware and Software

[0186] Server: This is the central computer that stores data, analyzes it, and generates solutions. This server must have high computing power and be equipped with natural language processing (NLP) technology. Specifically, cloud platforms such as Google Cloud, Amazon Web Services (AWS), and Microsoft Azure can be used.

[0187] Terminal: A smartphone or tablet device that transmits user feedback to the server in real time. The smartphone app is installed on the terminal.

[0188] software:

[0189] Smartphone app: A feedback collection and notification application that allows users to enter feedback and receive notifications.

[0190] Generative AI model: A data analysis technology with natural language processing and generative AI functions. Specifically, OpenAI's GPT-3 is one example.

[0191] Operating Procedure

[0192] 1. Gathering feedback

[0193] Customers use a smartphone app to enter feedback and requests about physical stores, such as "the shelves are hard to find."

[0194] 2. Data transmission and storage

[0195] The device sends the input feedback in real time to the cloud suggestion box, which runs on cloud platforms such as Google Cloud and AWS.

[0196] 3. Data Analysis and Classification

[0197] The server receives the transmitted data and analyzes the feedback using natural language processing techniques.

[0198] The analyzed data is sent to a generative AI model and automatically classified into specific categories (e.g., "product placement" or "service improvement").

[0199] 4. Generating concrete solutions

[0200] The server uses a generative AI model to generate specific solutions based on the categorized feedback, including a concrete implementation plan and required resources, budget, and time.

[0201] 5. Notification of Solution

[0202] The server notifies the appropriate parties of the generated solution, who can then receive it via a smartphone app.

[0203] 6. Automatic generation of new proposals

[0204] The server analyzes past feedback and solutions and periodically generates new suggestions and improvements automatically, facilitating continuous improvement of the entire system.

[0205] Specific examples

[0206] For example, if a user uses a smartphone app to send feedback that "the product shelves are difficult to understand," the process proceeds as follows:

[0207] Example prompt: "Please provide a specific solution to improve the request for confusing shelves."

[0208] The server receives this feedback, automatically analyzes it, and categorizes it into categories such as "product placement."

[0209] Using a generative AI model, it generates specific solution suggestions such as "color-coding shelf labels and installing guide signs in each section."

[0210] The solution will be communicated to store managers and implemented promptly.

[0211] Through the above-described operational procedure, the present invention can be implemented, thereby improving the efficiency of feedback processing in physical stores and customer satisfaction.

[0212] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0213] Step 1:

[0214] The user enters feedback into the smartphone app. For example, the user might enter "The product shelves are difficult to find" and submit this feedback. The entered data is sent from the user's device to the server.

[0215] Step 2:

[0216] The device receives feedback from users and sends it to the Cloud Suggestion Box in real time. The Cloud Suggestion Box uses cloud platforms such as Google Cloud and AWS. The data processing performed here involves converting the input feedback into an appropriate format such as JSON. The output is data stored in the Cloud Suggestion Box.

[0217] Step 3:

[0218] The server receives and stores feedback from the cloud suggestion box. The server then analyzes the feedback data using natural language processing (NLP) techniques. NLP processing includes text tokenization and grammar analysis. The input is the stored feedback data, and the output is the analyzed text information.

[0219] Step 4:

[0220] The server sends the analyzed feedback data to a generative AI model, which classifies it into a specific category. For example, natural language processing can be used to classify feedback related to "product placement." The input is the analyzed text information, and the output is the categorized data.

[0221] Step 5:

[0222] The server uses the generative AI model to generate specific solutions based on feedback categorized into specific categories. For example, the prompt "Please provide a specific solution to improve the requirement that product shelves are difficult to understand" is used to input data into the generative AI model, and an output solution is obtained. The data processing performed here is the generation of a solution by the AI ​​model.

[0223] Step 6:

[0224] The server notifies the appropriate parties of the generated solution. Notifications are sent via a smartphone app, email, or other means. For example, a solution such as "color-code shelf labels and install guide signs in each section" is sent to the manager of a physical store. The input is the generated solution, and the output is a notification message to the relevant parties.

[0225] Step 7:

[0226] The server periodically analyzes past feedback and solutions and automatically generates new suggestions and improvements. It periodically retrains the generative AI model, using past data to gain new insights. The input is past feedback and solution data, and the output is newly generated suggestions.

[0227] Specific actions at each step ensure that user feedback is handled quickly and effectively, ensuring that brick-and-mortar store operations are constantly optimized.

[0228] 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.

[0229] The system of this invention, which combines a cloud suggestion box with a generative AI function and an emotion engine, efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. It is also capable of recognizing user emotions and adjusting the solution generation process based on those emotions. A detailed embodiment of this system is shown below.

[0230] System Overview:

[0231] Users input request data such as complaints and requests into the cloud suggestion box.

[0232] The terminal transmits the data entered by the user to the server in real time.

[0233] The server stores the received request data in a database and begins the analysis process.

[0234] Sentiment Analysis:

[0235] The server sends the request data to the emotion engine and analyzes the user's emotion contained in the data.

[0236] The emotion engine uses text analysis technology to recognize emotions in request data and classify them into categories such as "anger," "joy," and "sadness."

[0237] The server also stores the emotion data detected by the emotion engine.

[0238] Parsing and categorizing requirements data:

[0239] The server sends the request data stored along with the emotion data to the generation AI for analysis.

[0240] Generative AI uses natural language processing (NLP) technology to analyze the content of requests and automatically classify them into specific categories, such as "internal facilities," "user interface," and "service improvement."

[0241] Auto-generation of solutions:

[0242] The generative AI generates specific solutions based on categorized requirements and sentiment data. During this process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, and time.

[0243] If the emotion data indicates "anger," the generated solution requires a rapid response and may include customer service intervention.

[0244] Solution Notification:

[0245] The server notifies the appropriate parties of the generated solution. For example, if the solution concerns an internal facility, a notification is sent via email to the relevant administrative department.

[0246] The user can quickly respond based on the notified solution.

[0247] Emotional notifications:

[0248] The server notifies the participants of the details, including the user's emotions detected by the emotion engine, so that the participants can also take the emotion data into account when implementing a solution.

[0249] Automatic generation of new suggestions:

[0250] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including ideas for new projects and business efficiency improvements.

[0251] The server notifies the user or administrator of any new proposals generated and, if applicable, puts them into immediate implementation.

[0252] Examples:

[0253] For example, if a user posts a request to the suggestion box saying, "The conference room reservation system is difficult to use," and the user expresses anger in the request,

[0254] The server stores this request data and emotion data in a database and starts the analysis process.

[0255] The generation AI analyzes the request data and categorizes it as a request related to "internal facilities."

[0256] Generative AI takes emotional data into account and generates quick and effective solutions, such as "improving the UI of the conference room booking system" or "creating a tutorial video for the booking process."

[0257] The server notifies the user's "anger" emotion data along with a solution to the relevant person in charge of the management department.

[0258] Users can be assured that the issues have been resolved with an improved system and new tutorials.

[0259] In this way, a system that combines a cloud suggestion box, generative AI functions, and an emotion engine can respond quickly and appropriately to user requests and provide solutions that take the user's emotions into consideration. Furthermore, by automatically generating new ideas and suggestions on a regular basis and providing them to users, it is possible to always provide the latest and best solutions.

[0260] The processing flow will be explained below.

[0261] Step 1:

[0262] Users input their requests or complaints into the cloud suggestion box, and the input data is sent from the device to the server in real time.

[0263] Step 2:

[0264] Once the server receives the requested data, it stores it in a database, where it is added to a queue for analysis.

[0265] Step 3:

[0266] The server periodically checks the queue for new request data, and if it finds new request data, it sends it to the emotion engine.

[0267] Step 4:

[0268] The emotion engine receives the request data and analyzes the emotion using text analysis technology, generating emotion data such as "anger," "joy," and "sadness" as the analysis result.

[0269] Step 5:

[0270] The emotion engine sends the generated emotion data to the server, which stores the emotion data together with the request data in a database.

[0271] Step 6:

[0272] The server sends the saved request data and emotion data to the generation AI for analysis.

[0273] Step 7:

[0274] The generative AI uses natural language processing (NLP) technology to analyze the content of the request data and automatically classify it into specific categories, such as "internal facilities," "user interface," and "service improvement."

[0275] Step 8:

[0276] The generative AI generates specific solutions based on categorized requirements and sentiment data, referencing past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, time, etc.

[0277] Step 9:

[0278] The generative AI takes emotion data into account and adjusts the urgency of the solution and specific countermeasures. For example, if emotion data of "anger" is detected, a quick response is required.

[0279] Step 10:

[0280] The generated solution is then communicated to the appropriate parties via the server. For example, if the solution relates to internal facilities, a notification is sent via email to the relevant administrative department.

[0281] Step 11:

[0282] The server also notifies the parties involved of the user's emotion data detected by the emotion engine, so that the parties involved can implement solutions taking the user's emotions into consideration.

[0283] Step 12:

[0284] Users can receive solutions notified by relevant parties and initiate the necessary response, which includes a concrete action plan, enabling rapid response.

[0285] Step 13:

[0286] The server receives and logs feedback from stakeholders to track the implementation of solutions, allowing you to see the effectiveness of the solutions.

[0287] Step 14:

[0288] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including new project proposals and ideas for improving business efficiency.

[0289] Step 15:

[0290] Newly generated suggestions are notified to users and administrators via the server, and if applicable, they are immediately implemented for further improvement.

[0291] Example 2

[0292] 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."

[0293] Conventional systems lacked the ability to efficiently analyze user request data and automatically generate and notify optimal solutions. Furthermore, there were no systems that could take user emotions into consideration or automatically generate new proposals. This created the risk of lowering user satisfaction and led to problems with appropriate improvement measures not being implemented quickly.

[0294] 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.

[0295] In this invention, the server includes means for receiving request data and emotion data, means for analyzing the received request data and emotion data using natural language processing and categorizing the request data, means for generating specific solutions based on the analysis results including the emotion data, means for notifying appropriate parties of the generated solutions and emotion data, and means for analyzing past request data and solutions and automatically generating new proposals. This makes it possible to provide effective and prompt solutions that take user emotions into consideration, thereby improving user satisfaction and generating new improvement proposals.

[0296] "Request data" refers to information collected from users, such as complaints, requests, and suggestions.

[0297] "Emotion data" refers to information that classifies the user's emotions contained in the request data.

[0298] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0299] A "category" is a classification to which the analyzed request data belongs, and refers to a specific theme or content.

[0300] "Solutions" refer to specific problem-solving techniques and proposals that are generated based on the analyzed requirement data and emotion data.

[0301] "Stakeholders" refers to the individuals or departments who are notified of the generated solutions and are responsible for implementing the response.

[0302] A "database" refers to a system that systematically stores and manages information such as requirements data, emotion data, and past solutions.

[0303] "New proposals" refer to proposals for improvements or new projects that are generated based on past requirements data and solutions.

[0304] The system of this invention, which combines a cloud suggestion box, a generative AI function, and an emotion engine, efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. It is also capable of recognizing user emotions and adjusting the solution generation process based on them.

[0305] System configuration

[0306] Users use devices such as PCs or smartphones to input complaints, requests, and other request data into the cloud suggestion box.

[0307] The terminal transmits the data entered by the user to the server in real time. The terminal communicates with the server via an internet connection using the HTTPS protocol.

[0308] The server uses a database (e.g., MySQL, PostgreSQL) to store the received request data, and then begins the analysis process.

[0309] Data analysis

[0310] The server sends the request data to an emotion engine (e.g., NLP API, machine learning model) and analyzes the user's emotions contained in the data.

[0311] The emotion engine uses text analysis technology to recognize emotions in request data and classify them into categories such as "anger," "joy," and "sadness."

[0312] The server stores the emotion data generated by the emotion engine in a database.

[0313] Categorizing requirements data and generating solutions

[0314] The server then sends the request data, along with the emotion data, to the AI ​​for analysis. The AI ​​then uses natural language processing to analyze the request and classify it into specific categories, such as "internal facilities," "user interface," and "service improvement."

[0315] The generative AI generates specific solutions based on categorized requests and sentiment data. It references past success stories and case studies from other organizations to build solutions that include specific implementation plans, required resources, budgets, and time. Examples of solutions include "improving the UI of the conference room reservation system" and "creating a tutorial video for the reservation process."

[0316] Notification of solutions and sentiment data

[0317] The server notifies the appropriate parties of the generated solution. For example, if the solution concerns an internal facility, a notification is sent via email to the relevant administrative department.

[0318] The user can quickly respond based on the solution. The user checks the notified solution and implements it according to the instructions.

[0319] Automatic generation of new proposals

[0320] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including ideas for new projects and business efficiency improvements.

[0321] The server notifies the user or administrator of any new proposals generated and, if applicable, puts them into immediate implementation.

[0322] Specific examples

[0323] For example, a user may submit a request to the suggestion box saying, "The conference room reservation system is difficult to use," and may include the emotion of "anger" in the request.

[0324] The server stores this request data and emotion data in a database and starts the analysis process.

[0325] The server sends the data to the emotion engine for emotion analysis.

[0326] The generation AI analyzes the request data and categorizes it as a request related to "internal facilities."

[0327] The generative AI takes emotional data into account and generates solutions such as "improving the UI of the conference room reservation system" or "creating a tutorial video for the reservation process."

[0328] The server notifies the user's "anger" emotion data along with the solution to the relevant person in charge of the management department.

[0329] Users will find that their issues have been resolved with an improved system and new tutorials.

[0330] Prompt Sentence Examples

[0331] "Generate a specific solution based on the user's request data that 'the conference room reservation system is difficult to use' and the emotion data of 'anger' analyzed by the emotion engine."

[0332] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0333] Step 1:

[0334] The user inputs the request data into the cloud suggestion box.

[0335] Users use devices such as PCs or smartphones to enter request data in text format via a web interface or mobile application. The input at this stage is specific, such as a problem, request, or suggestion. For example, a user might enter, "The conference room reservation system is difficult to use."

[0336] Step 2:

[0337] The terminal transmits the input request data to the server.

[0338] The terminal formats the request data and sends it to the server over an Internet connection using the HTTPS protocol. The input to this step is the raw request data entered by the user, and the output is the data packet received by the server.

[0339] Step 3:

[0340] The server stores the received data in a database and starts the analysis process.

[0341] The server stores the received request data in a database (e.g., MySQL, PostgreSQL). Based on the stored request data, it moves to the next process for analysis. The input of this step is the received request data, and the output is the data stored in the database.

[0342] Step 4:

[0343] The server sends the request data to the emotion engine for emotion analysis.

[0344] The server sends the request data to an emotion engine (e.g., a natural language processing API). The emotion engine uses text analysis technology to analyze emotions in the request data and classify them into categories such as "anger," "joy," and "sadness." The input of this step is the request data, and the output is the analyzed emotion data.

[0345] Step 5:

[0346] The server stores the sentiment analysis data in a database.

[0347] The server stores the emotion data generated by the emotion engine in a database. This forms a pair of request data and emotion data. The input of this step is the analyzed emotion data, and the output is the emotion data stored in the database.

[0348] Step 6:

[0349] The server sends the data to the generating AI, which categorizes the request.

[0350] The server sends the request data and related emotion data to the generation AI, which uses natural language processing technology to analyze the request content and classify it into specific categories such as "internal facilities," "user interface," and "service improvement." The input for this step is the request data and emotion data, and the output is categorized request data.

[0351] Step 7:

[0352] Generative AI generates specific solutions.

[0353] The generative AI generates specific solutions based on the categorized requirements and sentiment data. It references past success stories and case studies from other organizations to build solutions that include specific details such as an implementation plan, required resources, budget, and time. The input for this step is the categorized requirements data and sentiment data, and the output is a specific solution.

[0354] Step 8:

[0355] The server notifies the generated solution and sentiment data to the participants.

[0356] The server sends the generated solution and emotion data to the appropriate parties via email or system notification. For example, if the solution is related to internal facilities, the relevant administrative department personnel will be notified. The input of this step is the solution and emotion data, and the output is a notification to the parties involved.

[0357] Step 9:

[0358] The user implements the solution.

[0359] The user takes prompt action based on the notified solution. Implement the instructed solution and check whether the problem has been resolved. The input of this step is the notified solution, and the output is the implemented action and its result.

[0360] Step 10:

[0361] The server periodically generates and announces new proposals.

[0362] The server periodically analyzes past requirement data and solutions to generate new proposals and improvements. These proposals include new project proposals and ideas for improving business efficiency. It notifies users and administrators of the new proposals and, if applicable, implements them immediately. The inputs to this step are past data and solutions, and the output is new proposals.

[0363] (Application example 2)

[0364] 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."

[0365] Modern commercial facilities and service industries are required to process customer feedback quickly and accurately and respond on the spot. It is also important to understand customer emotions and respond accordingly. However, current systems do not process feedback in real time, making it difficult to properly grasp customer emotions. In addition, there is a lack of systems that provide concrete solutions that allow staff to quickly adjust their response methods on the spot. This leads to a decline in customer satisfaction and a deterioration in service quality.

[0366] 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.

[0367] In this invention, the server includes means for receiving request data, means for analyzing the received data using natural language processing and categorizing the request data, means for generating specific solutions based on the categorized request data, means for notifying appropriate parties of the generated solutions, means for analyzing past request data and solutions and automatically generating new proposals, means for analyzing user feedback in real time and providing improvements based on the analysis results, means for analyzing emotions in the feedback using an emotion engine and adjusting the solution generation based on the emotion data, and means for notifying staff via a notification device of the analysis results and the generated solutions. This enables customer feedback to be analyzed quickly and in real time, appropriate solutions to be provided, and responses that take customer emotions into consideration. Furthermore, by having staff adjust their response methods on the spot, customer satisfaction and service quality can be improved.

[0368] "Request data" is information such as feedback or requests provided by a user.

[0369] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0370] A "category" is a concept for classifying request data into a specific group or category.

[0371] A "solution" is a specific action or response that should be taken to address a particular problem.

[0372] "Generative AI" is an artificial intelligence system that uses machine learning technology to automatically generate solutions and proposals.

[0373] "Stakeholders" are individuals or departments responsible for implementing the generated solutions.

[0374] A "database" is a system for systematically managing and storing information.

[0375] An "emotion engine" is an algorithm or technology for analyzing and identifying emotions from text data.

[0376] "Emotion data" is information about emotions extracted from user feedback.

[0377] A "device" is an appliance or piece of equipment for displaying or receiving information.

[0378] "Improvements" are suggestions or solutions to improve the current situation.

[0379] "Real-time" means that data processing and responses occur almost immediately.

[0380] The present invention is a system for quickly and accurately processing user feedback and providing improvements. The system mainly uses smart glasses, a cloud server, a generative AI model, an emotion engine, and a database.

[0381] The system first receives user feedback via smart glasses, such as Google Glass, which collects feedback via voice and touch input.

[0382] The requested data is sent in real time to a cloud server, which uses, for example, AWS (Amazon Web Services) and stores the received data in a database (such as Amazon RDS).

[0383] The cloud server then sends the request data to an emotion engine, which analyzes the emotion data using algorithms such as IBM Watson Tone Analyzer, to identify emotions (e.g., anger, joy, sadness, etc.) in the request data.

[0384] Once the emotion data has been analyzed, the cloud server sends the request data and emotion data to a generative AI model (e.g., OpenAI GPT-3) to generate a specific solution. The generative AI model then references past data and examples to automatically generate the optimal solution.

[0385] The cloud server notifies the smart glasses of the generated solutions, and the smart glasses' built-in notification system allows staff to check the analysis results of the feedback and areas for improvement in real time.

[0386] For example, if a user receives feedback that they have been waiting a long time at the cash register, the following process will be performed.

[0387] 1. Receive feedback through smart glasses that "The cashier is slow and the wait is long."

[0388] 2. This request data is sent to the cloud server and stored in a database.

[0389] 3. The emotion engine analyzes the emotion of "anger" and sends the emotion data to the cloud server.

[0390] 4. The generative AI model generates solutions based on emotion data and requirement data.

[0391] An example of a prompt is as follows:

[0392] "User feedback: The checkout is slow and the wait is long."

[0393] "Emotion data: Anger"

[0394] "Solution: Open another register as soon as possible, and offer a coupon to customers who are waiting."

[0395] 5. The generated solution is sent to the smart glasses, allowing staff to quickly adjust their response on the spot.

[0396] In this way, this system can improve the quality of service by analyzing user feedback in real time and providing appropriate solutions according to the situation.

[0397] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0398] Step 1:

[0399] The user inputs feedback through the smart glasses.

[0400] Input: Feedback data from voice or touch input

[0401] Output: Generate feedback data

[0402] The smart glasses receive the user's feedback and prepare to send this data to a cloud server.

[0403] Step 2:

[0404] The smart glasses send the feedback data to a cloud server.

[0405] Input: Feedback data

[0406] Output: Feedback data sent to the cloud server

[0407] The cloud server stores the received feedback data in a database.

[0408] Step 3:

[0409] The server sends the feedback data to the emotion engine for emotion analysis.

[0410] Input: Feedback data

[0411] Output: Parsed emotion data

[0412] The emotion engine analyzes the emotions contained in the feedback data and generates emotion data such as "anger," "joy," and "sadness."

[0413] Step 4:

[0414] The server sends feedback data, including emotion data, to the generative AI model.

[0415] Input: Feedback data, emotion data

[0416] Output: Input data to a generative AI model

[0417] The generative AI model creates and analyzes prompts based on the data it receives to generate optimal solutions.

[0418] Step 5:

[0419] A generative AI model generates specific solutions based on requirement data and emotion data.

[0420] Input: Prompt sentence (input based on request data and emotion data)

[0421] Output: Generated solution

[0422] The generative AI model references past data and case studies, and integrates requirement data and emotional data to automatically generate specific solutions.

[0423] Step 6:

[0424] The server notifies the device (smart glasses) of the generated solution.

[0425] Input: Generated solution

[0426] Output: Notification information to the device

[0427] The smart glasses receive this notification information and display the contents to the staff.

[0428] Step 7:

[0429] Staff adjust their response on the spot based on solutions displayed through smart glasses.

[0430] Input: Solution displayed on smart glasses

[0431] Output: Improved response

[0432] Staff can check the solutions displayed on the smart glasses and take prompt action based on them.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] [Second embodiment]

[0437] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0438] 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.

[0439] 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).

[0440] 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.

[0441] 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.

[0442] 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).

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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."

[0449] The cloud suggestion box + AI generation function system of this invention efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. Detailed embodiments of this system are described below.

[0450] System Overview:

[0451] Users input request data such as complaints and requests into the cloud suggestion box.

[0452] The terminal transmits the data entered by the user to the server in real time.

[0453] The server stores the received request data in a database and begins the analysis process.

[0454] Parsing and categorizing requirements data:

[0455] The server sends the saved request data to the generation AI for analysis.

[0456] Generative AI uses natural language processing (NLP) technology to analyze the content of requests and automatically classify them into specific categories, such as "internal facilities," "user interface," and "service improvement."

[0457] Auto-generation of solutions:

[0458] Generative AI generates specific solutions based on categorized requirements. During this process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, and time.

[0459] Solution Notification:

[0460] The server notifies the appropriate parties of the generated solution, for example, if the solution concerns internal facilities, it notifies the relevant administrative department personnel by email.

[0461] The user can quickly respond based on the notified solution.

[0462] Automatic generation of new suggestions:

[0463] Generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including proposals for new projects and ideas for improving business efficiency.

[0464] The server notifies the user or administrator of any new proposals generated and, if applicable, puts them into immediate implementation.

[0465] Examples:

[0466] For example, if a user submits a request to the suggestion box saying, "The conference room reservation system is difficult to use,"

[0467] The server stores this request data in a database and begins the analysis process.

[0468] The generative AI analyzes this data and categorizes it as a request related to "internal facilities."

[0469] The generative AI generates specific solutions such as "improving the UI of the conference room reservation system" and "creating a tutorial video for the reservation process."

[0470] The server notifies the company's system administration personnel of these solutions.

[0471] Users can be assured that the issues have been resolved with an improved system and new tutorials.

[0472] In this way, the Cloud Suggestion Box + Generative AI Function System can respond quickly and appropriately to user requests and achieve continuous improvement. It also automatically generates new ideas and suggestions on a regular basis and provides them to users, ensuring that they always receive the latest and best solutions.

[0473] The processing flow will be explained below.

[0474] Step 1:

[0475] Users input their requests or complaints into the cloud suggestion box, and the input data is sent from the device to the server in real time.

[0476] Step 2:

[0477] Once the server receives the requested data, it stores it in a database, where it is added to a queue for analysis.

[0478] Step 3:

[0479] The server periodically checks the queue to see if there is new request data. If it finds new request data, it sends it to the generation AI.

[0480] Step 4:

[0481] The generative AI receives the request data and uses natural language processing (NLP) technology to analyze the content of the data, determining which category the request data belongs to.

[0482] Step 5:

[0483] The generation AI classifies the request data into appropriate categories based on the identified categories, such as "internal facilities," "user interface," and "service improvement."

[0484] Step 6:

[0485] The generative AI generates specific solutions based on categorized requirements data. During the generation process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, time, etc.

[0486] Step 7:

[0487] Once a solution is generated, the server notifies the appropriate parties of the solution. For example, if the solution concerns an internal facility, a notification is sent via email to the relevant administrative personnel.

[0488] Step 8:

[0489] Users can receive solutions notified by relevant parties and initiate the necessary response, which includes a concrete action plan, enabling rapid response.

[0490] Step 9:

[0491] The server receives and logs feedback from stakeholders to track the implementation of solutions, allowing you to see the effectiveness of the solutions.

[0492] Step 10:

[0493] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including ideas for new projects and business efficiency improvements.

[0494] Step 11:

[0495] Newly generated suggestions are notified to users and administrators via the server, and if applicable, they are immediately implemented for further improvement.

[0496] Example 1

[0497] 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."

[0498] The existing system lacked the process for efficiently collecting and analyzing user requests and complaints, automatically generating solutions, and notifying the appropriate parties. It also struggled to regularly provide users with continuous improvements and new proposals. This hindered the rapid resolution of problems and improved work efficiency.

[0499] 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.

[0500] In this invention, the server includes means for receiving request data, means for analyzing the received data using natural language processing and classifying the request data into categories, means for generating specific solutions based on the classified request data, means for analyzing past request data and solutions and automatically generating new proposals, means for notifying a person in charge of management or a user of the generated solutions and encouraging them to take action, and means for periodically notifying a user or a manager of new proposals and encouraging them to implement them. This makes it possible to efficiently collect and analyze requests and complaints from users and quickly provide specific solutions, as well as to periodically provide continuous improvements and new proposals.

[0501] "Request data" is information including complaints, requests, and other demands input by the user.

[0502] A "server" is a computer system that receives, stores, analyzes request data, and generates and notifies solutions.

[0503] A "terminal" is a device through which a user inputs request data and transmits it to a server.

[0504] "Generative AI" is an artificial intelligence system that uses natural language processing technology to analyze requirement data and automatically generate solutions and new proposals.

[0505] "Natural Language Processing (NLP)" is a technology that enables computers to understand, analyze, and generate human language.

[0506] "Category" is a classification category used by the generation AI to classify the request data analyzed.

[0507] A "solution" is a specific countermeasure or improvement that the generating AI proposes based on the required data.

[0508] "Notification" is the act of informing appropriate parties of solutions or proposals generated by generative AI.

[0509] "Proposals" are new improvement plans or ideas that the generative AI generates by analyzing past requirement data and solutions.

[0510] "Stakeholders" refer to the management personnel and users who should receive the generated solutions and proposals.

[0511] MODE FOR CARRYING OUT THE INVENTION

[0512] The cloud suggestion box + AI generation function system of this invention efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. Specific embodiments of this system are shown below.

[0513] System Overview

[0514] The system consists of four main components: the user, the terminal, the server, and the generating AI.

[0515] User: The user inputs complaints, requests, and other request data into the cloud suggestion box. For example, the user inputs a request such as "The conference room reservation system is difficult to use."

[0516] Terminal: The terminal transmits the data entered by the user to the server in real time. The terminal is a device such as a PC or smartphone that transmits data through a cloud-based input form or application.

[0517] Server: The server receives the requested data and stores it in a database, which then initiates the analysis process and sends it to the generation AI.

[0518] Generative AI: Generative AI uses natural language processing (NLP) techniques to analyze the received request data and classify it into specific categories. It then generates a specific solution based on the classified request data. The generated solution is returned to the server, which then notifies the appropriate parties.

[0519] Analyzing and categorizing requirements data

[0520] The server sends the saved request data to the generation AI, which begins analyzing it. The generation AI uses natural language processing technology to analyze the content of the request and automatically classify it into specific categories. These include categories such as "internal facilities," "user interface," and "service improvement." The generation AI uses generative AI models such as BERT and GPT, which are NLP techniques in general computer science.

[0521] Automatic solution generation

[0522] Generative AI generates specific solutions based on categorized requirements. During this process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, time, etc. Generative AI learns from past databases and cases to provide highly accurate solutions.

[0523] Solution Notification

[0524] The server then notifies the appropriate parties of the generated solution. For example, if the solution relates to internal facilities, it will notify the relevant management department via email or an internal notification system. The notification will also include specific steps and resources to be taken, allowing the parties involved to respond quickly.

[0525] Automatic generation of new proposals

[0526] The generative AI periodically analyzes past requirement data and solutions to automatically generate new proposals and improvements. These include proposals for new projects and ideas for improving business efficiency. The server notifies users and administrators of the new proposals and, if applicable, immediately implements them.

[0527] Specific examples

[0528] For example, if a user submits a request to the suggestion box saying, "The conference room reservation system is difficult to use,"

[0529] The server stores this request data in a database and begins the analysis process.

[0530] The generative AI analyzes this data and categorizes it as a request related to "internal facilities."

[0531] The generative AI generates specific solutions such as "improving the UI of the conference room reservation system" and "creating a tutorial video for the reservation process."

[0532] The server notifies the company's system administration personnel of these solutions.

[0533] Users can be assured that the issues have been resolved with an improved system and new tutorials.

[0534] Prompt Sentence Examples

[0535] If a user types "I want to improve the onboarding process for new employees":

[0536] The device sends this to the server.

[0537] The server sends the data to the generation AI, which then suggests simplifying the onboarding flow for new employees and introducing digital training content.

[0538] The server notifies the HR department.

[0539] The HR department implements the proposal and new employees are smoothly onboarded.

[0540] In this way, the cloud suggestion box + generative AI function system can respond quickly and appropriately to user requests and achieve continuous improvement. It also automatically generates new ideas and suggestions on a regular basis and provides them to users, ensuring that they always receive the latest and best solutions.

[0541] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0542] Step 1:

[0543] The user inputs the requested data into the input form of the cloud suggestion box. For example, the input requested data is "The conference room reservation system is difficult to use." This data is captured by the terminal.

[0544] Input: User request data (text format)

[0545] Output: The requested data entered is saved on the terminal.

[0546] Step 2:

[0547] The terminal transmits the request data input by the user to the server in real time. The terminal uses the HTTP POST method to transmit the request data to the server as a packet.

[0548] Input: Request data stored on the device

[0549] Output: Packet data sent to the server

[0550] Step 3:

[0551] The server receives the HTTP request, extracts the request data from the request body, and then executes an INSERT query to store this request data in the database.

[0552] Input: Packet data sent to the server

[0553] Output: Request data stored in the database

[0554] Step 4:

[0555] The server sends the saved request data to the generation AI and starts the analysis process. The request data is transferred to the generation AI through the API endpoint.

[0556] Input: Request data stored in the database

[0557] Output: Request data sent to the generating AI

[0558] Step 5:

[0559] Generative AI analyzes the received request data using natural language processing (NLP) techniques, typically using BERT or GPT models. This analysis performs semantic analysis of the text data and classifies it into specific categories.

[0560] Input: Request data sent to the generating AI

[0561] Output: Parsed category information (e.g., "In-house facilities")

[0562] Step 6:

[0563] Generative AI automatically generates solutions based on categorized requirements, referencing past success stories and database information to provide specific action plans.

[0564] Input: Parsed category information

[0565] Output: Generated solutions (e.g., "Improve the UI of the conference room reservation system," "Create a tutorial video for the reservation process")

[0566] Step 7:

[0567] The server notifies the appropriate parties of the generated solution. For example, if the solution is related to internal facilities, it notifies the relevant management department personnel via email or an internal notification system.

[0568] Input: Generated solution

[0569] Output: Notification to relevant parties (email and system notification)

[0570] Step 8:

[0571] Users receive notification and confirmation that the solution has been implemented. Users can use the improved system and see its effectiveness.

[0572] Input:Notification to interested parties

[0573] Output: User confirmation of solution and feedback

[0574] Step 9:

[0575] Generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals, including new project proposals and ideas for improving business efficiency.

[0576] Input: Past request data and solutions

[0577] Output: New proposal (e.g., "Remote work optimization proposal")

[0578] Step 10:

[0579] The server notifies the user or administrator of any new suggestions that are generated and, if applicable, implements them immediately.

[0580] Input: New proposal

[0581] Output: Notification and action recommendation to users and administrators

[0582] These are the specific processing steps of the cloud suggestion box + generative AI function system, which enables a quick and appropriate response to user requests.

[0583] (Application example 1)

[0584] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0585] Traditionally, processing customer feedback and requests in brick-and-mortar stores has been inefficient and difficult to respond to promptly. In particular, it has been difficult for the person receiving the feedback to quickly find a solution, and continuous improvement and the generation of new proposals have been insufficient. For these reasons, there is a need to improve customer satisfaction and streamline store operations.

[0586] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0587] In this invention, the server includes means for receiving request data, means for analyzing the received data using natural language processing and classifying the request data into categories, means for sending customer feedback from the physical store to a cloud suggestion box in real time via a smartphone app, means for generating specific solutions based on the classified request data, means for notifying appropriate parties of the generated solutions, and means for analyzing past request data and solutions and automatically generating new proposals. This enables rapid processing of customer feedback, improved operational efficiency of the physical store, continuous improvement, and the automatic generation of new proposals.

[0588] "Request Data" means feedback or request information collected from users.

[0589] "Natural language processing" is a technology that allows computers to understand and analyze natural language used by humans.

[0590] A "category" is a grouping based on a certain common attribute or theme.

[0591] A "smartphone app" is a software application that runs on a mobile information terminal.

[0592] A "cloud suggestion box" is a system that stores data on the Internet and allows users to enter requests and feedback.

[0593] A "server" is a computer device that stores, manages, and analyzes data over a network.

[0594] A "solution" is a specific method or policy for solving a particular problem.

[0595] "Stakeholders" are people or departments with responsibilities related to a particular issue or situation.

[0596] A "proposal" is a new idea or plan for improvement for a specific problem.

[0597] To implement the present invention, a system including a server, a terminal, and a user is used. The configuration and operation procedure of this system will be described in detail below.

[0598] System Configuration

[0599] 1. Hardware and Software

[0600] Server: This is the central computer that stores data, analyzes it, and generates solutions. This server must have high computing power and be equipped with natural language processing (NLP) technology. Specifically, cloud platforms such as Google Cloud, Amazon Web Services (AWS), and Microsoft Azure can be used.

[0601] Terminal: A smartphone or tablet device that transmits user feedback to the server in real time. The smartphone app is installed on the terminal.

[0602] software:

[0603] Smartphone app: A feedback collection and notification application that allows users to enter feedback and receive notifications.

[0604] Generative AI model: A data analysis technology with natural language processing and generative AI functions. Specifically, OpenAI's GPT-3 is one example.

[0605] Operating Procedure

[0606] 1. Gathering feedback

[0607] Customers use a smartphone app to enter feedback and requests about physical stores, such as "the shelves are hard to find."

[0608] 2. Data transmission and storage

[0609] The device sends the input feedback in real time to the cloud suggestion box, which runs on cloud platforms such as Google Cloud and AWS.

[0610] 3. Data Analysis and Classification

[0611] The server receives the transmitted data and analyzes the feedback using natural language processing techniques.

[0612] The analyzed data is sent to a generative AI model and automatically classified into specific categories (e.g., "product placement" or "service improvement").

[0613] 4. Generating concrete solutions

[0614] The server uses a generative AI model to generate specific solutions based on the categorized feedback, including a concrete implementation plan and required resources, budget, and time.

[0615] 5. Notification of Solution

[0616] The server notifies the appropriate parties of the generated solution, who can then receive it via a smartphone app.

[0617] 6. Automatic generation of new proposals

[0618] The server analyzes past feedback and solutions and periodically generates new suggestions and improvements automatically, facilitating continuous improvement of the entire system.

[0619] Specific examples

[0620] For example, if a user uses a smartphone app to send feedback that "the product shelves are difficult to understand," the process proceeds as follows:

[0621] Example prompt: "Please provide a specific solution to improve the request for confusing shelves."

[0622] The server receives this feedback, automatically analyzes it, and categorizes it into categories such as "product placement."

[0623] Using a generative AI model, it generates specific solution suggestions such as "color-coding shelf labels and installing guide signs in each section."

[0624] The solution will be communicated to store managers and implemented promptly.

[0625] Through the above-described operational procedure, the present invention can be implemented, thereby improving the efficiency of feedback processing in physical stores and customer satisfaction.

[0626] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0627] Step 1:

[0628] The user enters feedback into the smartphone app. For example, the user might enter "The product shelves are difficult to find" and submit this feedback. The entered data is sent from the user's device to the server.

[0629] Step 2:

[0630] The device receives feedback from users and sends it to the Cloud Suggestion Box in real time. The Cloud Suggestion Box uses cloud platforms such as Google Cloud and AWS. The data processing performed here involves converting the input feedback into an appropriate format such as JSON. The output is data stored in the Cloud Suggestion Box.

[0631] Step 3:

[0632] The server receives and stores feedback from the cloud suggestion box. The server then analyzes the feedback data using natural language processing (NLP) techniques. NLP processing includes text tokenization and grammar analysis. The input is the stored feedback data, and the output is the analyzed text information.

[0633] Step 4:

[0634] The server sends the analyzed feedback data to a generative AI model, which classifies it into a specific category. For example, natural language processing can be used to classify feedback related to "product placement." The input is the analyzed text information, and the output is the categorized data.

[0635] Step 5:

[0636] The server uses the generative AI model to generate specific solutions based on feedback categorized into specific categories. For example, the prompt "Please provide a specific solution to improve the requirement that product shelves are difficult to understand" is used to input data into the generative AI model, and an output solution is obtained. The data processing performed here is the generation of a solution by the AI ​​model.

[0637] Step 6:

[0638] The server notifies the appropriate parties of the generated solution. Notifications are sent via a smartphone app, email, or other means. For example, a solution such as "color-code shelf labels and install guide signs in each section" is sent to the manager of a physical store. The input is the generated solution, and the output is a notification message to the relevant parties.

[0639] Step 7:

[0640] The server periodically analyzes past feedback and solutions and automatically generates new suggestions and improvements. It periodically retrains the generative AI model, using past data to gain new insights. The input is past feedback and solution data, and the output is newly generated suggestions.

[0641] Specific actions at each step ensure that user feedback is handled quickly and effectively, ensuring that brick-and-mortar store operations are constantly optimized.

[0642] 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.

[0643] The system of this invention, which combines a cloud suggestion box with a generative AI function and an emotion engine, efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. It is also capable of recognizing user emotions and adjusting the solution generation process based on those emotions. A detailed embodiment of this system is shown below.

[0644] System Overview:

[0645] Users input request data such as complaints and requests into the cloud suggestion box.

[0646] The terminal transmits the data entered by the user to the server in real time.

[0647] The server stores the received request data in a database and begins the analysis process.

[0648] Sentiment Analysis:

[0649] The server sends the request data to the emotion engine and analyzes the user's emotion contained in the data.

[0650] The emotion engine uses text analysis technology to recognize emotions in request data and classify them into categories such as "anger," "joy," and "sadness."

[0651] The server also stores the emotion data detected by the emotion engine.

[0652] Parsing and categorizing requirements data:

[0653] The server sends the request data stored along with the emotion data to the generation AI for analysis.

[0654] Generative AI uses natural language processing (NLP) technology to analyze the content of requests and automatically classify them into specific categories, such as "internal facilities," "user interface," and "service improvement."

[0655] Auto-generation of solutions:

[0656] The generative AI generates specific solutions based on categorized requirements and sentiment data. During this process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, and time.

[0657] If the emotion data indicates "anger," the generated solution requires a rapid response and may include customer service intervention.

[0658] Solution Notification:

[0659] The server notifies the appropriate parties of the generated solution. For example, if the solution concerns an internal facility, a notification is sent via email to the relevant administrative department.

[0660] The user can quickly respond based on the notified solution.

[0661] Emotional notifications:

[0662] The server notifies the participants of the details, including the user's emotions detected by the emotion engine, so that the participants can also take the emotion data into account when implementing a solution.

[0663] Automatic generation of new suggestions:

[0664] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including ideas for new projects and business efficiency improvements.

[0665] The server notifies the user or administrator of any new proposals generated and, if applicable, puts them into immediate implementation.

[0666] Examples:

[0667] For example, if a user posts a request to the suggestion box saying, "The conference room reservation system is difficult to use," and the user expresses anger in the request,

[0668] The server stores this request data and emotion data in a database and starts the analysis process.

[0669] The generation AI analyzes the request data and categorizes it as a request related to "internal facilities."

[0670] Generative AI takes emotional data into account and generates quick and effective solutions, such as "improving the UI of the conference room booking system" or "creating a tutorial video for the booking process."

[0671] The server notifies the user's "anger" emotion data along with a solution to the relevant person in charge of the management department.

[0672] Users can be assured that the issues have been resolved with an improved system and new tutorials.

[0673] In this way, a system that combines a cloud suggestion box, generative AI functions, and an emotion engine can respond quickly and appropriately to user requests and provide solutions that take the user's emotions into consideration. Furthermore, by automatically generating new ideas and suggestions on a regular basis and providing them to users, it is possible to always provide the latest and best solutions.

[0674] The processing flow will be explained below.

[0675] Step 1:

[0676] Users input their requests or complaints into the cloud suggestion box, and the input data is sent from the device to the server in real time.

[0677] Step 2:

[0678] Once the server receives the requested data, it stores it in a database, where it is added to a queue for analysis.

[0679] Step 3:

[0680] The server periodically checks the queue for new request data, and if it finds new request data, it sends it to the emotion engine.

[0681] Step 4:

[0682] The emotion engine receives the request data and analyzes the emotion using text analysis technology, generating emotion data such as "anger," "joy," and "sadness" as the analysis result.

[0683] Step 5:

[0684] The emotion engine sends the generated emotion data to the server, which stores the emotion data together with the request data in a database.

[0685] Step 6:

[0686] The server sends the saved request data and emotion data to the generation AI for analysis.

[0687] Step 7:

[0688] The generative AI uses natural language processing (NLP) technology to analyze the content of the request data and automatically classify it into specific categories, such as "internal facilities," "user interface," and "service improvement."

[0689] Step 8:

[0690] The generative AI generates specific solutions based on categorized requirements and sentiment data, referencing past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, time, etc.

[0691] Step 9:

[0692] The generative AI takes emotion data into account and adjusts the urgency of the solution and specific countermeasures. For example, if emotion data of "anger" is detected, a quick response is required.

[0693] Step 10:

[0694] The generated solution is then communicated to the appropriate parties via the server. For example, if the solution relates to internal facilities, a notification is sent via email to the relevant administrative department.

[0695] Step 11:

[0696] The server also notifies the parties involved of the user's emotion data detected by the emotion engine, so that the parties involved can implement solutions taking the user's emotions into consideration.

[0697] Step 12:

[0698] Users can receive solutions notified by relevant parties and initiate the necessary response, which includes a concrete action plan, enabling rapid response.

[0699] Step 13:

[0700] The server receives and logs feedback from stakeholders to track the implementation of solutions, allowing you to see the effectiveness of the solutions.

[0701] Step 14:

[0702] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including new project proposals and ideas for improving business efficiency.

[0703] Step 15:

[0704] Newly generated suggestions are notified to users and administrators via the server, and if applicable, they are immediately implemented for further improvement.

[0705] Example 2

[0706] 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."

[0707] Conventional systems lacked the ability to efficiently analyze user request data and automatically generate and notify optimal solutions. Furthermore, there were no systems that could take user emotions into consideration or automatically generate new proposals. This created the risk of lowering user satisfaction and led to problems with appropriate improvement measures not being implemented quickly.

[0708] 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.

[0709] In this invention, the server includes means for receiving request data and emotion data, means for analyzing the received request data and emotion data using natural language processing and categorizing the request data, means for generating specific solutions based on the analysis results including the emotion data, means for notifying appropriate parties of the generated solutions and emotion data, and means for analyzing past request data and solutions and automatically generating new proposals. This makes it possible to provide effective and prompt solutions that take user emotions into consideration, thereby improving user satisfaction and generating new improvement proposals.

[0710] "Request data" refers to information collected from users, such as complaints, requests, and suggestions.

[0711] "Emotion data" refers to information that classifies the user's emotions contained in the request data.

[0712] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0713] A "category" is a classification to which the analyzed request data belongs, and refers to a specific theme or content.

[0714] "Solutions" refer to specific problem-solving techniques and proposals that are generated based on the analyzed requirement data and emotion data.

[0715] "Stakeholders" refers to the individuals or departments who are notified of the generated solutions and are responsible for implementing the response.

[0716] A "database" refers to a system that systematically stores and manages information such as requirements data, emotion data, and past solutions.

[0717] "New proposals" refer to proposals for improvements or new projects that are generated based on past requirements data and solutions.

[0718] The system of this invention, which combines a cloud suggestion box, a generative AI function, and an emotion engine, efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. It is also capable of recognizing user emotions and adjusting the solution generation process based on them.

[0719] System configuration

[0720] Users use devices such as PCs or smartphones to input complaints, requests, and other request data into the cloud suggestion box.

[0721] The terminal transmits the data entered by the user to the server in real time. The terminal communicates with the server via an internet connection using the HTTPS protocol.

[0722] The server uses a database (e.g., MySQL, PostgreSQL) to store the received request data, and then begins the analysis process.

[0723] Data analysis

[0724] The server sends the request data to an emotion engine (e.g., NLP API, machine learning model) and analyzes the user's emotions contained in the data.

[0725] The emotion engine uses text analysis technology to recognize emotions in request data and classify them into categories such as "anger," "joy," and "sadness."

[0726] The server stores the emotion data generated by the emotion engine in a database.

[0727] Categorizing requirements data and generating solutions

[0728] The server then sends the request data, along with the emotion data, to the AI ​​for analysis. The AI ​​then uses natural language processing to analyze the request and classify it into specific categories, such as "internal facilities," "user interface," and "service improvement."

[0729] The generative AI generates specific solutions based on categorized requests and sentiment data. It references past success stories and case studies from other organizations to build solutions that include specific implementation plans, required resources, budgets, and time. Examples of solutions include "improving the UI of the conference room reservation system" and "creating a tutorial video for the reservation process."

[0730] Notification of solutions and sentiment data

[0731] The server notifies the appropriate parties of the generated solution. For example, if the solution concerns an internal facility, a notification is sent via email to the relevant administrative department.

[0732] The user can quickly respond based on the solution. The user checks the notified solution and implements it according to the instructions.

[0733] Automatic generation of new proposals

[0734] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including ideas for new projects and business efficiency improvements.

[0735] The server notifies the user or administrator of any new proposals generated and, if applicable, puts them into immediate implementation.

[0736] Specific examples

[0737] For example, a user may submit a request to the suggestion box saying, "The conference room reservation system is difficult to use," and may include the emotion of "anger" in the request.

[0738] The server stores this request data and emotion data in a database and starts the analysis process.

[0739] The server sends the data to the emotion engine for emotion analysis.

[0740] The generation AI analyzes the request data and categorizes it as a request related to "internal facilities."

[0741] The generative AI takes emotional data into account and generates solutions such as "improving the UI of the conference room reservation system" or "creating a tutorial video for the reservation process."

[0742] The server notifies the user's "anger" emotion data along with the solution to the relevant person in charge of the management department.

[0743] Users will find that their issues have been resolved with an improved system and new tutorials.

[0744] Prompt Sentence Examples

[0745] "Generate a specific solution based on the user's request data that 'the conference room reservation system is difficult to use' and the emotion data of 'anger' analyzed by the emotion engine."

[0746] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0747] Step 1:

[0748] The user inputs the request data into the cloud suggestion box.

[0749] Users use devices such as PCs or smartphones to enter request data in text format via a web interface or mobile application. The input at this stage is specific, such as a problem, request, or suggestion. For example, a user might enter, "The conference room reservation system is difficult to use."

[0750] Step 2:

[0751] The terminal transmits the input request data to the server.

[0752] The terminal formats the request data and sends it to the server over an Internet connection using the HTTPS protocol. The input to this step is the raw request data entered by the user, and the output is the data packet received by the server.

[0753] Step 3:

[0754] The server stores the received data in a database and starts the analysis process.

[0755] The server stores the received request data in a database (e.g., MySQL, PostgreSQL). Based on the stored request data, it moves to the next process for analysis. The input of this step is the received request data, and the output is the data stored in the database.

[0756] Step 4:

[0757] The server sends the request data to the emotion engine for emotion analysis.

[0758] The server sends the request data to an emotion engine (e.g., a natural language processing API). The emotion engine uses text analysis technology to analyze emotions in the request data and classify them into categories such as "anger," "joy," and "sadness." The input of this step is the request data, and the output is the analyzed emotion data.

[0759] Step 5:

[0760] The server stores the sentiment analysis data in a database.

[0761] The server stores the emotion data generated by the emotion engine in a database. This forms a pair of request data and emotion data. The input of this step is the analyzed emotion data, and the output is the emotion data stored in the database.

[0762] Step 6:

[0763] The server sends the data to the generating AI, which categorizes the request.

[0764] The server sends the request data and related emotion data to the generation AI, which uses natural language processing technology to analyze the request content and classify it into specific categories such as "internal facilities," "user interface," and "service improvement." The input for this step is the request data and emotion data, and the output is categorized request data.

[0765] Step 7:

[0766] Generative AI generates specific solutions.

[0767] The generative AI generates specific solutions based on the categorized requirements and sentiment data. It references past success stories and case studies from other organizations to build solutions that include specific details such as an implementation plan, required resources, budget, and time. The input for this step is the categorized requirements data and sentiment data, and the output is a specific solution.

[0768] Step 8:

[0769] The server notifies the generated solution and sentiment data to the participants.

[0770] The server sends the generated solution and emotion data to the appropriate parties via email or system notification. For example, if the solution is related to internal facilities, the relevant administrative department personnel will be notified. The input of this step is the solution and emotion data, and the output is a notification to the parties involved.

[0771] Step 9:

[0772] The user implements the solution.

[0773] The user takes prompt action based on the notified solution. Implement the instructed solution and check whether the problem has been resolved. The input of this step is the notified solution, and the output is the implemented action and its result.

[0774] Step 10:

[0775] The server periodically generates and announces new proposals.

[0776] The server periodically analyzes past requirement data and solutions to generate new proposals and improvements. These proposals include new project proposals and ideas for improving business efficiency. It notifies users and administrators of the new proposals and, if applicable, implements them immediately. The inputs to this step are past data and solutions, and the output is new proposals.

[0777] (Application example 2)

[0778] 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."

[0779] Modern commercial facilities and service industries are required to process customer feedback quickly and accurately and respond on the spot. It is also important to understand customer emotions and respond accordingly. However, current systems do not process feedback in real time, making it difficult to properly grasp customer emotions. In addition, there is a lack of systems that provide concrete solutions that allow staff to quickly adjust their response methods on the spot. This leads to a decline in customer satisfaction and a deterioration in service quality.

[0780] 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.

[0781] In this invention, the server includes means for receiving request data, means for analyzing the received data using natural language processing and categorizing the request data, means for generating specific solutions based on the categorized request data, means for notifying appropriate parties of the generated solutions, means for analyzing past request data and solutions and automatically generating new proposals, means for analyzing user feedback in real time and providing improvements based on the analysis results, means for analyzing emotions in the feedback using an emotion engine and adjusting the solution generation based on the emotion data, and means for notifying staff via a notification device of the analysis results and the generated solutions. This enables customer feedback to be analyzed quickly and in real time, appropriate solutions to be provided, and responses that take customer emotions into consideration. Furthermore, by having staff adjust their response methods on the spot, customer satisfaction and service quality can be improved.

[0782] "Request data" is information such as feedback or requests provided by a user.

[0783] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0784] A "category" is a concept for classifying request data into a specific group or category.

[0785] A "solution" is a specific action or response that should be taken to address a particular problem.

[0786] "Generative AI" is an artificial intelligence system that uses machine learning technology to automatically generate solutions and proposals.

[0787] "Stakeholders" are individuals or departments responsible for implementing the generated solutions.

[0788] A "database" is a system for systematically managing and storing information.

[0789] An "emotion engine" is an algorithm or technology for analyzing and identifying emotions from text data.

[0790] "Emotion data" is information about emotions extracted from user feedback.

[0791] A "device" is an appliance or piece of equipment for displaying or receiving information.

[0792] "Improvements" are suggestions or solutions to improve the current situation.

[0793] "Real-time" means that data processing and responses occur almost immediately.

[0794] The present invention is a system for quickly and accurately processing user feedback and providing improvements. The system mainly uses smart glasses, a cloud server, a generative AI model, an emotion engine, and a database.

[0795] The system first receives user feedback via smart glasses, such as Google Glass, which collects feedback via voice and touch input.

[0796] The requested data is sent in real time to a cloud server, which uses, for example, AWS (Amazon Web Services) and stores the received data in a database (such as Amazon RDS).

[0797] The cloud server then sends the request data to an emotion engine, which analyzes the emotion data using algorithms such as IBM Watson Tone Analyzer, to identify emotions (e.g., anger, joy, sadness, etc.) in the request data.

[0798] Once the emotion data has been analyzed, the cloud server sends the request data and emotion data to a generative AI model (e.g., OpenAI GPT-3) to generate a specific solution. The generative AI model then references past data and examples to automatically generate the optimal solution.

[0799] The cloud server notifies the smart glasses of the generated solutions, and the smart glasses' built-in notification system allows staff to check the analysis results of the feedback and areas for improvement in real time.

[0800] For example, if a user receives feedback that they have been waiting a long time at the cash register, the following process will be performed.

[0801] 1. Receive feedback through smart glasses that "The cashier is slow and the wait is long."

[0802] 2. This request data is sent to the cloud server and stored in a database.

[0803] 3. The emotion engine analyzes the emotion of "anger" and sends the emotion data to the cloud server.

[0804] 4. The generative AI model generates solutions based on emotion data and requirement data.

[0805] An example of a prompt is as follows:

[0806] "User feedback: The checkout is slow and the wait is long."

[0807] "Emotion data: Anger"

[0808] "Solution: Open another register as soon as possible, and offer a coupon to customers who are waiting."

[0809] 5. The generated solution is sent to the smart glasses, allowing staff to quickly adjust their response on the spot.

[0810] In this way, this system can improve the quality of service by analyzing user feedback in real time and providing appropriate solutions according to the situation.

[0811] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0812] Step 1:

[0813] The user inputs feedback through the smart glasses.

[0814] Input: Feedback data from voice or touch input

[0815] Output: Generate feedback data

[0816] The smart glasses receive the user's feedback and prepare to send this data to a cloud server.

[0817] Step 2:

[0818] The smart glasses send the feedback data to a cloud server.

[0819] Input: Feedback data

[0820] Output: Feedback data sent to the cloud server

[0821] The cloud server stores the received feedback data in a database.

[0822] Step 3:

[0823] The server sends the feedback data to the emotion engine for emotion analysis.

[0824] Input: Feedback data

[0825] Output: Parsed emotion data

[0826] The emotion engine analyzes the emotions contained in the feedback data and generates emotion data such as "anger," "joy," and "sadness."

[0827] Step 4:

[0828] The server sends feedback data, including emotion data, to the generative AI model.

[0829] Input: Feedback data, emotion data

[0830] Output: Input data to a generative AI model

[0831] The generative AI model creates and analyzes prompts based on the data it receives to generate optimal solutions.

[0832] Step 5:

[0833] A generative AI model generates specific solutions based on requirement data and emotion data.

[0834] Input: Prompt sentence (input based on request data and emotion data)

[0835] Output: Generated solution

[0836] The generative AI model references past data and case studies, and integrates requirement data and emotional data to automatically generate specific solutions.

[0837] Step 6:

[0838] The server notifies the device (smart glasses) of the generated solution.

[0839] Input: Generated solution

[0840] Output: Notification information to the device

[0841] The smart glasses receive this notification information and display the contents to the staff.

[0842] Step 7:

[0843] Staff adjust their response on the spot based on solutions displayed through smart glasses.

[0844] Input: Solution displayed on smart glasses

[0845] Output: Improved response

[0846] Staff can check the solutions displayed on the smart glasses and take prompt action based on them.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] [Third embodiment]

[0851] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0852] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0853] 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).

[0854] 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.

[0855] 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.

[0856] 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).

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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."

[0863] The cloud suggestion box + AI generation function system of this invention efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. Detailed embodiments of this system are described below.

[0864] System Overview:

[0865] Users input request data such as complaints and requests into the cloud suggestion box.

[0866] The terminal transmits the data entered by the user to the server in real time.

[0867] The server stores the received request data in a database and begins the analysis process.

[0868] Parsing and categorizing requirements data:

[0869] The server sends the saved request data to the generation AI for analysis.

[0870] Generative AI uses natural language processing (NLP) technology to analyze the content of requests and automatically classify them into specific categories, such as "internal facilities," "user interface," and "service improvement."

[0871] Auto-generation of solutions:

[0872] Generative AI generates specific solutions based on categorized requirements. During this process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, and time.

[0873] Solution Notification:

[0874] The server notifies the appropriate parties of the generated solution, for example, if the solution concerns internal facilities, it notifies the relevant administrative department personnel by email.

[0875] The user can quickly respond based on the notified solution.

[0876] Automatic generation of new suggestions:

[0877] Generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including proposals for new projects and ideas for improving business efficiency.

[0878] The server notifies the user or administrator of any new proposals generated and, if applicable, puts them into immediate implementation.

[0879] Examples:

[0880] For example, if a user submits a request to the suggestion box saying, "The conference room reservation system is difficult to use,"

[0881] The server stores this request data in a database and begins the analysis process.

[0882] The generative AI analyzes this data and categorizes it as a request related to "internal facilities."

[0883] The generative AI generates specific solutions such as "improving the UI of the conference room reservation system" and "creating a tutorial video for the reservation process."

[0884] The server notifies the company's system administration personnel of these solutions.

[0885] Users can be assured that the issues have been resolved with an improved system and new tutorials.

[0886] In this way, the Cloud Suggestion Box + Generative AI Function System can respond quickly and appropriately to user requests and achieve continuous improvement. It also automatically generates new ideas and suggestions on a regular basis and provides them to users, ensuring that they always receive the latest and best solutions.

[0887] The processing flow will be explained below.

[0888] Step 1:

[0889] Users input their requests or complaints into the cloud suggestion box, and the input data is sent from the device to the server in real time.

[0890] Step 2:

[0891] Once the server receives the requested data, it stores it in a database, where it is added to a queue for analysis.

[0892] Step 3:

[0893] The server periodically checks the queue to see if there is new request data. If it finds new request data, it sends it to the generation AI.

[0894] Step 4:

[0895] The generative AI receives the request data and uses natural language processing (NLP) technology to analyze the content of the data, determining which category the request data belongs to.

[0896] Step 5:

[0897] The generation AI classifies the request data into appropriate categories based on the identified categories, such as "internal facilities," "user interface," and "service improvement."

[0898] Step 6:

[0899] The generative AI generates specific solutions based on categorized requirements data. During the generation process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, time, etc.

[0900] Step 7:

[0901] Once a solution is generated, the server notifies the appropriate parties of the solution. For example, if the solution concerns an internal facility, a notification is sent via email to the relevant administrative personnel.

[0902] Step 8:

[0903] Users can receive solutions notified by relevant parties and initiate the necessary response, which includes a concrete action plan, enabling rapid response.

[0904] Step 9:

[0905] The server receives and logs feedback from stakeholders to track the implementation of solutions, allowing you to see the effectiveness of the solutions.

[0906] Step 10:

[0907] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including ideas for new projects and business efficiency improvements.

[0908] Step 11:

[0909] Newly generated suggestions are notified to users and administrators via the server, and if applicable, they are immediately implemented for further improvement.

[0910] Example 1

[0911] 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."

[0912] The existing system lacked the process for efficiently collecting and analyzing user requests and complaints, automatically generating solutions, and notifying the appropriate parties. It also struggled to regularly provide users with continuous improvements and new proposals. This hindered the rapid resolution of problems and improved work efficiency.

[0913] 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.

[0914] In this invention, the server includes means for receiving request data, means for analyzing the received data using natural language processing and classifying the request data into categories, means for generating specific solutions based on the classified request data, means for analyzing past request data and solutions and automatically generating new proposals, means for notifying a person in charge of management or a user of the generated solutions and encouraging them to take action, and means for periodically notifying a user or a manager of new proposals and encouraging them to implement them. This makes it possible to efficiently collect and analyze requests and complaints from users and quickly provide specific solutions, as well as to periodically provide continuous improvements and new proposals.

[0915] "Request data" is information including complaints, requests, and other demands input by the user.

[0916] A "server" is a computer system that receives, stores, analyzes request data, and generates and notifies solutions.

[0917] A "terminal" is a device through which a user inputs request data and transmits it to a server.

[0918] "Generative AI" is an artificial intelligence system that uses natural language processing technology to analyze requirement data and automatically generate solutions and new proposals.

[0919] "Natural Language Processing (NLP)" is a technology that enables computers to understand, analyze, and generate human language.

[0920] "Category" is a classification category used by the generation AI to classify the request data analyzed.

[0921] A "solution" is a specific countermeasure or improvement that the generating AI proposes based on the required data.

[0922] "Notification" is the act of informing appropriate parties of solutions or proposals generated by generative AI.

[0923] "Proposals" are new improvement plans or ideas that the generative AI generates by analyzing past requirement data and solutions.

[0924] "Stakeholders" refer to the management personnel and users who should receive the generated solutions and proposals.

[0925] MODE FOR CARRYING OUT THE INVENTION

[0926] The cloud suggestion box + AI generation function system of this invention efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. Specific embodiments of this system are shown below.

[0927] System Overview

[0928] The system consists of four main components: the user, the terminal, the server, and the generating AI.

[0929] User: The user inputs complaints, requests, and other request data into the cloud suggestion box. For example, the user inputs a request such as "The conference room reservation system is difficult to use."

[0930] Terminal: The terminal transmits the data entered by the user to the server in real time. The terminal is a device such as a PC or smartphone that transmits data through a cloud-based input form or application.

[0931] Server: The server receives the requested data and stores it in a database, which then initiates the analysis process and sends it to the generation AI.

[0932] Generative AI: Generative AI uses natural language processing (NLP) techniques to analyze the received request data and classify it into specific categories. It then generates a specific solution based on the classified request data. The generated solution is returned to the server, which then notifies the appropriate parties.

[0933] Analyzing and categorizing requirements data

[0934] The server sends the saved request data to the generation AI, which begins analyzing it. The generation AI uses natural language processing technology to analyze the content of the request and automatically classify it into specific categories. These include categories such as "internal facilities," "user interface," and "service improvement." The generation AI uses generative AI models such as BERT and GPT, which are NLP techniques in general computer science.

[0935] Automatic solution generation

[0936] Generative AI generates specific solutions based on categorized requirements. During this process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, time, etc. Generative AI learns from past databases and cases to provide highly accurate solutions.

[0937] Solution Notification

[0938] The server then notifies the appropriate parties of the generated solution. For example, if the solution relates to internal facilities, it will notify the relevant management department via email or an internal notification system. The notification will also include specific steps and resources to be taken, allowing the parties involved to respond quickly.

[0939] Automatic generation of new proposals

[0940] The generative AI periodically analyzes past requirement data and solutions to automatically generate new proposals and improvements. These include proposals for new projects and ideas for improving business efficiency. The server notifies users and administrators of the new proposals and, if applicable, immediately implements them.

[0941] Specific examples

[0942] For example, if a user submits a request to the suggestion box saying, "The conference room reservation system is difficult to use,"

[0943] The server stores this request data in a database and begins the analysis process.

[0944] The generative AI analyzes this data and categorizes it as a request related to "internal facilities."

[0945] The generative AI generates specific solutions such as "improving the UI of the conference room reservation system" and "creating a tutorial video for the reservation process."

[0946] The server notifies the company's system administration personnel of these solutions.

[0947] Users can be assured that the issues have been resolved with an improved system and new tutorials.

[0948] Prompt Sentence Examples

[0949] If a user types "I want to improve the onboarding process for new employees":

[0950] The device sends this to the server.

[0951] The server sends the data to the generation AI, which then suggests simplifying the onboarding flow for new employees and introducing digital training content.

[0952] The server notifies the HR department.

[0953] The HR department implements the proposal and new employees are smoothly onboarded.

[0954] In this way, the cloud suggestion box + generative AI function system can respond quickly and appropriately to user requests and achieve continuous improvement. It also automatically generates new ideas and suggestions on a regular basis and provides them to users, ensuring that they always receive the latest and best solutions.

[0955] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0956] Step 1:

[0957] The user inputs the requested data into the input form of the cloud suggestion box. For example, the input requested data is "The conference room reservation system is difficult to use." This data is captured by the terminal.

[0958] Input: User request data (text format)

[0959] Output: The requested data entered is saved on the terminal.

[0960] Step 2:

[0961] The terminal transmits the request data input by the user to the server in real time. The terminal uses the HTTP POST method to transmit the request data to the server as a packet.

[0962] Input: Request data stored on the device

[0963] Output: Packet data sent to the server

[0964] Step 3:

[0965] The server receives the HTTP request, extracts the request data from the request body, and then executes an INSERT query to store this request data in the database.

[0966] Input: Packet data sent to the server

[0967] Output: Request data stored in the database

[0968] Step 4:

[0969] The server sends the saved request data to the generation AI and starts the analysis process. The request data is transferred to the generation AI through the API endpoint.

[0970] Input: Request data stored in the database

[0971] Output: Request data sent to the generating AI

[0972] Step 5:

[0973] Generative AI analyzes the received request data using natural language processing (NLP) techniques, typically using BERT or GPT models. This analysis performs semantic analysis of the text data and classifies it into specific categories.

[0974] Input: Request data sent to the generating AI

[0975] Output: Parsed category information (e.g., "In-house facilities")

[0976] Step 6:

[0977] Generative AI automatically generates solutions based on categorized requirements, referencing past success stories and database information to provide specific action plans.

[0978] Input: Parsed category information

[0979] Output: Generated solutions (e.g., "Improve the UI of the conference room reservation system," "Create a tutorial video for the reservation process")

[0980] Step 7:

[0981] The server notifies the appropriate parties of the generated solution. For example, if the solution is related to internal facilities, it notifies the relevant management department personnel via email or an internal notification system.

[0982] Input: Generated solution

[0983] Output: Notification to relevant parties (email and system notification)

[0984] Step 8:

[0985] Users receive notification and confirmation that the solution has been implemented. Users can use the improved system and see its effectiveness.

[0986] Input:Notification to interested parties

[0987] Output: User confirmation of solution and feedback

[0988] Step 9:

[0989] Generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals, including new project proposals and ideas for improving business efficiency.

[0990] Input: Past request data and solutions

[0991] Output: New proposal (e.g., "Remote work optimization proposal")

[0992] Step 10:

[0993] The server notifies the user or administrator of any new suggestions that are generated and, if applicable, implements them immediately.

[0994] Input: New proposal

[0995] Output: Notification and action recommendation to users and administrators

[0996] These are the specific processing steps of the cloud suggestion box + generative AI function system, which enables a quick and appropriate response to user requests.

[0997] (Application example 1)

[0998] 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."

[0999] Traditionally, processing customer feedback and requests in brick-and-mortar stores has been inefficient and difficult to respond to promptly. In particular, it has been difficult for the person receiving the feedback to quickly find a solution, and continuous improvement and the generation of new proposals have been insufficient. For these reasons, there is a need to improve customer satisfaction and streamline store operations.

[1000] 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.

[1001] In this invention, the server includes means for receiving request data, means for analyzing the received data using natural language processing and classifying the request data into categories, means for sending customer feedback from the physical store to a cloud suggestion box in real time via a smartphone app, means for generating specific solutions based on the classified request data, means for notifying appropriate parties of the generated solutions, and means for analyzing past request data and solutions and automatically generating new proposals. This enables rapid processing of customer feedback, improved operational efficiency of the physical store, continuous improvement, and the automatic generation of new proposals.

[1002] "Request Data" means feedback or request information collected from users.

[1003] "Natural language processing" is a technology that allows computers to understand and analyze natural language used by humans.

[1004] A "category" is a grouping based on a certain common attribute or theme.

[1005] A "smartphone app" is a software application that runs on a mobile information terminal.

[1006] A "cloud suggestion box" is a system that stores data on the Internet and allows users to enter requests and feedback.

[1007] A "server" is a computer device that stores, manages, and analyzes data over a network.

[1008] A "solution" is a specific method or policy for solving a particular problem.

[1009] "Stakeholders" are people or departments with responsibilities related to a particular issue or situation.

[1010] A "proposal" is a new idea or plan for improvement for a specific problem.

[1011] To implement the present invention, a system including a server, a terminal, and a user is used. The configuration and operation procedure of this system will be described in detail below.

[1012] System Configuration

[1013] 1. Hardware and Software

[1014] Server: This is the central computer that stores data, analyzes it, and generates solutions. This server must have high computing power and be equipped with natural language processing (NLP) technology. Specifically, cloud platforms such as Google Cloud, Amazon Web Services (AWS), and Microsoft Azure can be used.

[1015] Terminal: A smartphone or tablet device that transmits user feedback to the server in real time. The smartphone app is installed on the terminal.

[1016] software:

[1017] Smartphone app: A feedback collection and notification application that allows users to enter feedback and receive notifications.

[1018] Generative AI model: A data analysis technology with natural language processing and generative AI functions. Specifically, OpenAI's GPT-3 is one example.

[1019] Operating Procedure

[1020] 1. Gathering feedback

[1021] Customers use a smartphone app to enter feedback and requests about physical stores, such as "the shelves are hard to find."

[1022] 2. Data transmission and storage

[1023] The device sends the input feedback in real time to the cloud suggestion box, which runs on cloud platforms such as Google Cloud and AWS.

[1024] 3. Data Analysis and Classification

[1025] The server receives the transmitted data and analyzes the feedback using natural language processing techniques.

[1026] The analyzed data is sent to a generative AI model and automatically classified into specific categories (e.g., "product placement" or "service improvement").

[1027] 4. Generating concrete solutions

[1028] The server uses a generative AI model to generate specific solutions based on the categorized feedback, including a concrete implementation plan and required resources, budget, and time.

[1029] 5. Notification of Solution

[1030] The server notifies the appropriate parties of the generated solution, who can then receive it via a smartphone app.

[1031] 6. Automatic generation of new proposals

[1032] The server analyzes past feedback and solutions and periodically generates new suggestions and improvements automatically, facilitating continuous improvement of the entire system.

[1033] Specific examples

[1034] For example, if a user uses a smartphone app to send feedback that "the product shelves are difficult to understand," the process proceeds as follows:

[1035] Example prompt: "Please provide a specific solution to improve the request for confusing shelves."

[1036] The server receives this feedback, automatically analyzes it, and categorizes it into categories such as "product placement."

[1037] Using a generative AI model, it generates specific solution suggestions such as "color-coding shelf labels and installing guide signs in each section."

[1038] The solution will be communicated to store managers and implemented promptly.

[1039] Through the above-described operational procedure, the present invention can be implemented, thereby improving the efficiency of feedback processing in physical stores and customer satisfaction.

[1040] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1041] Step 1:

[1042] The user enters feedback into the smartphone app. For example, the user might enter "The product shelves are difficult to find" and submit this feedback. The entered data is sent from the user's device to the server.

[1043] Step 2:

[1044] The device receives feedback from users and sends it to the Cloud Suggestion Box in real time. The Cloud Suggestion Box uses cloud platforms such as Google Cloud and AWS. The data processing performed here involves converting the input feedback into an appropriate format such as JSON. The output is data stored in the Cloud Suggestion Box.

[1045] Step 3:

[1046] The server receives and stores feedback from the cloud suggestion box. The server then analyzes the feedback data using natural language processing (NLP) techniques. NLP processing includes text tokenization and grammar analysis. The input is the stored feedback data, and the output is the analyzed text information.

[1047] Step 4:

[1048] The server sends the analyzed feedback data to a generative AI model, which classifies it into a specific category. For example, natural language processing can be used to classify feedback related to "product placement." The input is the analyzed text information, and the output is the categorized data.

[1049] Step 5:

[1050] The server uses the generative AI model to generate specific solutions based on feedback categorized into specific categories. For example, the prompt "Please provide a specific solution to improve the requirement that product shelves are difficult to understand" is used to input data into the generative AI model, and an output solution is obtained. The data processing performed here is the generation of a solution by the AI ​​model.

[1051] Step 6:

[1052] The server notifies the appropriate parties of the generated solution. Notifications are sent via a smartphone app, email, or other means. For example, a solution such as "color-code shelf labels and install guide signs in each section" is sent to the manager of a physical store. The input is the generated solution, and the output is a notification message to the relevant parties.

[1053] Step 7:

[1054] The server periodically analyzes past feedback and solutions and automatically generates new suggestions and improvements. It periodically retrains the generative AI model, using past data to gain new insights. The input is past feedback and solution data, and the output is newly generated suggestions.

[1055] Specific actions at each step ensure that user feedback is handled quickly and effectively, ensuring that brick-and-mortar store operations are constantly optimized.

[1056] 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.

[1057] The system of this invention, which combines a cloud suggestion box with a generative AI function and an emotion engine, efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. It is also capable of recognizing user emotions and adjusting the solution generation process based on those emotions. A detailed embodiment of this system is shown below.

[1058] System Overview:

[1059] Users input request data such as complaints and requests into the cloud suggestion box.

[1060] The terminal transmits the data entered by the user to the server in real time.

[1061] The server stores the received request data in a database and begins the analysis process.

[1062] Sentiment Analysis:

[1063] The server sends the request data to the emotion engine and analyzes the user's emotion contained in the data.

[1064] The emotion engine uses text analysis technology to recognize emotions in request data and classify them into categories such as "anger," "joy," and "sadness."

[1065] The server also stores the emotion data detected by the emotion engine.

[1066] Parsing and categorizing requirements data:

[1067] The server sends the request data stored along with the emotion data to the generation AI for analysis.

[1068] Generative AI uses natural language processing (NLP) technology to analyze the content of requests and automatically classify them into specific categories, such as "internal facilities," "user interface," and "service improvement."

[1069] Auto-generation of solutions:

[1070] The generative AI generates specific solutions based on categorized requirements and sentiment data. During this process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, and time.

[1071] If the emotion data indicates "anger," the generated solution requires a rapid response and may include customer service intervention.

[1072] Solution Notification:

[1073] The server notifies the appropriate parties of the generated solution. For example, if the solution concerns an internal facility, a notification is sent via email to the relevant administrative department.

[1074] The user can quickly respond based on the notified solution.

[1075] Emotional notifications:

[1076] The server notifies the participants of the details, including the user's emotions detected by the emotion engine, so that the participants can also take the emotion data into account when implementing a solution.

[1077] Automatic generation of new suggestions:

[1078] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including ideas for new projects and business efficiency improvements.

[1079] The server notifies the user or administrator of any new proposals generated and, if applicable, puts them into immediate implementation.

[1080] Examples:

[1081] For example, if a user posts a request to the suggestion box saying, "The conference room reservation system is difficult to use," and the user expresses anger in the request,

[1082] The server stores this request data and emotion data in a database and starts the analysis process.

[1083] The generation AI analyzes the request data and categorizes it as a request related to "internal facilities."

[1084] Generative AI takes emotional data into account and generates quick and effective solutions, such as "improving the UI of the conference room booking system" or "creating a tutorial video for the booking process."

[1085] The server notifies the user's "anger" emotion data along with a solution to the relevant person in charge of the management department.

[1086] Users can be assured that the issues have been resolved with an improved system and new tutorials.

[1087] In this way, a system that combines a cloud suggestion box, generative AI functions, and an emotion engine can respond quickly and appropriately to user requests and provide solutions that take the user's emotions into consideration. Furthermore, by automatically generating new ideas and suggestions on a regular basis and providing them to users, it is possible to always provide the latest and best solutions.

[1088] The processing flow will be explained below.

[1089] Step 1:

[1090] Users input their requests or complaints into the cloud suggestion box, and the input data is sent from the device to the server in real time.

[1091] Step 2:

[1092] Once the server receives the requested data, it stores it in a database, where it is added to a queue for analysis.

[1093] Step 3:

[1094] The server periodically checks the queue for new request data, and if it finds new request data, it sends it to the emotion engine.

[1095] Step 4:

[1096] The emotion engine receives the request data and analyzes the emotion using text analysis technology, generating emotion data such as "anger," "joy," and "sadness" as the analysis result.

[1097] Step 5:

[1098] The emotion engine sends the generated emotion data to the server, which stores the emotion data together with the request data in a database.

[1099] Step 6:

[1100] The server sends the saved request data and emotion data to the generation AI for analysis.

[1101] Step 7:

[1102] The generative AI uses natural language processing (NLP) technology to analyze the content of the request data and automatically classify it into specific categories, such as "internal facilities," "user interface," and "service improvement."

[1103] Step 8:

[1104] The generative AI generates specific solutions based on categorized requirements and sentiment data, referencing past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, time, etc.

[1105] Step 9:

[1106] The generative AI takes emotion data into account and adjusts the urgency of the solution and specific countermeasures. For example, if emotion data of "anger" is detected, a quick response is required.

[1107] Step 10:

[1108] The generated solution is then communicated to the appropriate parties via the server. For example, if the solution relates to internal facilities, a notification is sent via email to the relevant administrative department.

[1109] Step 11:

[1110] The server also notifies the parties involved of the user's emotion data detected by the emotion engine, so that the parties involved can implement solutions taking the user's emotions into consideration.

[1111] Step 12:

[1112] Users can receive solutions notified by relevant parties and initiate the necessary response, which includes a concrete action plan, enabling rapid response.

[1113] Step 13:

[1114] The server receives and logs feedback from stakeholders to track the implementation of solutions, allowing you to see the effectiveness of the solutions.

[1115] Step 14:

[1116] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including new project proposals and ideas for improving business efficiency.

[1117] Step 15:

[1118] Newly generated suggestions are notified to users and administrators via the server, and if applicable, they are immediately implemented for further improvement.

[1119] Example 2

[1120] 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."

[1121] Conventional systems lacked the ability to efficiently analyze user request data and automatically generate and notify optimal solutions. Furthermore, there were no systems that could take user emotions into consideration or automatically generate new proposals. This created the risk of lowering user satisfaction and led to problems with appropriate improvement measures not being implemented quickly.

[1122] 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.

[1123] In this invention, the server includes means for receiving request data and emotion data, means for analyzing the received request data and emotion data using natural language processing and categorizing the request data, means for generating specific solutions based on the analysis results including the emotion data, means for notifying appropriate parties of the generated solutions and emotion data, and means for analyzing past request data and solutions and automatically generating new proposals. This makes it possible to provide effective and prompt solutions that take user emotions into consideration, thereby improving user satisfaction and generating new improvement proposals.

[1124] "Request data" refers to information collected from users, such as complaints, requests, and suggestions.

[1125] "Emotion data" refers to information that classifies the user's emotions contained in the request data.

[1126] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[1127] A "category" is a classification to which the analyzed request data belongs, and refers to a specific theme or content.

[1128] "Solutions" refer to specific problem-solving techniques and proposals that are generated based on the analyzed requirement data and emotion data.

[1129] "Stakeholders" refers to the individuals or departments who are notified of the generated solutions and are responsible for implementing the response.

[1130] A "database" refers to a system that systematically stores and manages information such as requirements data, emotion data, and past solutions.

[1131] "New proposals" refer to proposals for improvements or new projects that are generated based on past requirements data and solutions.

[1132] The system of this invention, which combines a cloud suggestion box, a generative AI function, and an emotion engine, efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. It is also capable of recognizing user emotions and adjusting the solution generation process based on them.

[1133] System configuration

[1134] Users use devices such as PCs or smartphones to input complaints, requests, and other request data into the cloud suggestion box.

[1135] The terminal transmits the data entered by the user to the server in real time. The terminal communicates with the server via an internet connection using the HTTPS protocol.

[1136] The server uses a database (e.g., MySQL, PostgreSQL) to store the received request data, and then begins the analysis process.

[1137] Data analysis

[1138] The server sends the request data to an emotion engine (e.g., NLP API, machine learning model) and analyzes the user's emotions contained in the data.

[1139] The emotion engine uses text analysis technology to recognize emotions in request data and classify them into categories such as "anger," "joy," and "sadness."

[1140] The server stores the emotion data generated by the emotion engine in a database.

[1141] Categorizing requirements data and generating solutions

[1142] The server then sends the request data, along with the emotion data, to the AI ​​for analysis. The AI ​​then uses natural language processing to analyze the request and classify it into specific categories, such as "internal facilities," "user interface," and "service improvement."

[1143] The generative AI generates specific solutions based on categorized requests and sentiment data. It references past success stories and case studies from other organizations to build solutions that include specific implementation plans, required resources, budgets, and time. Examples of solutions include "improving the UI of the conference room reservation system" and "creating a tutorial video for the reservation process."

[1144] Notification of solutions and sentiment data

[1145] The server notifies the appropriate parties of the generated solution. For example, if the solution concerns an internal facility, a notification is sent via email to the relevant administrative department.

[1146] The user can quickly respond based on the solution. The user checks the notified solution and implements it according to the instructions.

[1147] Automatic generation of new proposals

[1148] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including ideas for new projects and business efficiency improvements.

[1149] The server notifies the user or administrator of any new proposals generated and, if applicable, puts them into immediate implementation.

[1150] Specific examples

[1151] For example, a user may submit a request to the suggestion box saying, "The conference room reservation system is difficult to use," and may include the emotion of "anger" in the request.

[1152] The server stores this request data and emotion data in a database and starts the analysis process.

[1153] The server sends the data to the emotion engine for emotion analysis.

[1154] The generation AI analyzes the request data and categorizes it as a request related to "internal facilities."

[1155] The generative AI takes emotional data into account and generates solutions such as "improving the UI of the conference room reservation system" or "creating a tutorial video for the reservation process."

[1156] The server notifies the user's "anger" emotion data along with the solution to the relevant person in charge of the management department.

[1157] Users will find that their issues have been resolved with an improved system and new tutorials.

[1158] Prompt Sentence Examples

[1159] "Generate a specific solution based on the user's request data that 'the conference room reservation system is difficult to use' and the emotion data of 'anger' analyzed by the emotion engine."

[1160] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1161] Step 1:

[1162] The user inputs the request data into the cloud suggestion box.

[1163] Users use devices such as PCs or smartphones to enter request data in text format via a web interface or mobile application. The input at this stage is specific, such as a problem, request, or suggestion. For example, a user might enter, "The conference room reservation system is difficult to use."

[1164] Step 2:

[1165] The terminal transmits the input request data to the server.

[1166] The terminal formats the request data and sends it to the server over an Internet connection using the HTTPS protocol. The input to this step is the raw request data entered by the user, and the output is the data packet received by the server.

[1167] Step 3:

[1168] The server stores the received data in a database and starts the analysis process.

[1169] The server stores the received request data in a database (e.g., MySQL, PostgreSQL). Based on the stored request data, it moves to the next process for analysis. The input of this step is the received request data, and the output is the data stored in the database.

[1170] Step 4:

[1171] The server sends the request data to the emotion engine for emotion analysis.

[1172] The server sends the request data to an emotion engine (e.g., a natural language processing API). The emotion engine uses text analysis technology to analyze emotions in the request data and classify them into categories such as "anger," "joy," and "sadness." The input of this step is the request data, and the output is the analyzed emotion data.

[1173] Step 5:

[1174] The server stores the sentiment analysis data in a database.

[1175] The server stores the emotion data generated by the emotion engine in a database. This forms a pair of request data and emotion data. The input of this step is the analyzed emotion data, and the output is the emotion data stored in the database.

[1176] Step 6:

[1177] The server sends the data to the generating AI, which categorizes the request.

[1178] The server sends the request data and related emotion data to the generation AI, which uses natural language processing technology to analyze the request content and classify it into specific categories such as "internal facilities," "user interface," and "service improvement." The input for this step is the request data and emotion data, and the output is categorized request data.

[1179] Step 7:

[1180] Generative AI generates specific solutions.

[1181] The generative AI generates specific solutions based on the categorized requirements and sentiment data. It references past success stories and case studies from other organizations to build solutions that include specific details such as an implementation plan, required resources, budget, and time. The input for this step is the categorized requirements data and sentiment data, and the output is a specific solution.

[1182] Step 8:

[1183] The server notifies the generated solution and sentiment data to the participants.

[1184] The server sends the generated solution and emotion data to the appropriate parties via email or system notification. For example, if the solution is related to internal facilities, the relevant administrative department personnel will be notified. The input of this step is the solution and emotion data, and the output is a notification to the parties involved.

[1185] Step 9:

[1186] The user implements the solution.

[1187] The user takes prompt action based on the notified solution. Implement the instructed solution and check whether the problem has been resolved. The input of this step is the notified solution, and the output is the implemented action and its result.

[1188] Step 10:

[1189] The server periodically generates and announces new proposals.

[1190] The server periodically analyzes past requirement data and solutions to generate new proposals and improvements. These proposals include new project proposals and ideas for improving business efficiency. It notifies users and administrators of the new proposals and, if applicable, implements them immediately. The inputs to this step are past data and solutions, and the output is new proposals.

[1191] (Application example 2)

[1192] 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."

[1193] Modern commercial facilities and service industries are required to process customer feedback quickly and accurately and respond on the spot. It is also important to understand customer emotions and respond accordingly. However, current systems do not process feedback in real time, making it difficult to properly grasp customer emotions. In addition, there is a lack of systems that provide concrete solutions that allow staff to quickly adjust their response methods on the spot. This leads to a decline in customer satisfaction and a deterioration in service quality.

[1194] 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.

[1195] In this invention, the server includes means for receiving request data, means for analyzing the received data using natural language processing and categorizing the request data, means for generating specific solutions based on the categorized request data, means for notifying appropriate parties of the generated solutions, means for analyzing past request data and solutions and automatically generating new proposals, means for analyzing user feedback in real time and providing improvements based on the analysis results, means for analyzing emotions in the feedback using an emotion engine and adjusting the solution generation based on the emotion data, and means for notifying staff via a notification device of the analysis results and the generated solutions. This enables customer feedback to be analyzed quickly and in real time, appropriate solutions to be provided, and responses that take customer emotions into consideration. Furthermore, by having staff adjust their response methods on the spot, customer satisfaction and service quality can be improved.

[1196] "Request data" is information such as feedback or requests provided by a user.

[1197] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[1198] A "category" is a concept for classifying request data into a specific group or category.

[1199] A "solution" is a specific action or response that should be taken to address a particular problem.

[1200] "Generative AI" is an artificial intelligence system that uses machine learning technology to automatically generate solutions and proposals.

[1201] "Stakeholders" are individuals or departments responsible for implementing the generated solutions.

[1202] A "database" is a system for systematically managing and storing information.

[1203] An "emotion engine" is an algorithm or technology for analyzing and identifying emotions from text data.

[1204] "Emotion data" is information about emotions extracted from user feedback.

[1205] A "device" is an appliance or piece of equipment for displaying or receiving information.

[1206] "Improvements" are suggestions or solutions to improve the current situation.

[1207] "Real-time" means that data processing and responses occur almost immediately.

[1208] The present invention is a system for quickly and accurately processing user feedback and providing improvements. The system mainly uses smart glasses, a cloud server, a generative AI model, an emotion engine, and a database.

[1209] The system first receives user feedback via smart glasses, such as Google Glass, which collects feedback via voice and touch input.

[1210] The requested data is sent in real time to a cloud server, which uses, for example, AWS (Amazon Web Services) and stores the received data in a database (such as Amazon RDS).

[1211] The cloud server then sends the request data to an emotion engine, which analyzes the emotion data using algorithms such as IBM Watson Tone Analyzer, to identify emotions (e.g., anger, joy, sadness, etc.) in the request data.

[1212] Once the emotion data has been analyzed, the cloud server sends the request data and emotion data to a generative AI model (e.g., OpenAI GPT-3) to generate a specific solution. The generative AI model then references past data and examples to automatically generate the optimal solution.

[1213] The cloud server notifies the smart glasses of the generated solutions, and the smart glasses' built-in notification system allows staff to check the analysis results of the feedback and areas for improvement in real time.

[1214] For example, if a user receives feedback that they have been waiting a long time at the cash register, the following process will be performed.

[1215] 1. Receive feedback through smart glasses that "The cashier is slow and the wait is long."

[1216] 2. This request data is sent to the cloud server and stored in a database.

[1217] 3. The emotion engine analyzes the emotion of "anger" and sends the emotion data to the cloud server.

[1218] 4. The generative AI model generates solutions based on emotion data and requirement data.

[1219] An example of a prompt is as follows:

[1220] "User feedback: The checkout is slow and the wait is long."

[1221] "Emotion data: Anger"

[1222] "Solution: Open another register as soon as possible, and offer a coupon to customers who are waiting."

[1223] 5. The generated solution is sent to the smart glasses, allowing staff to quickly adjust their response on the spot.

[1224] In this way, this system can improve the quality of service by analyzing user feedback in real time and providing appropriate solutions according to the situation.

[1225] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1226] Step 1:

[1227] The user inputs feedback through the smart glasses.

[1228] Input: Feedback data from voice or touch input

[1229] Output: Generate feedback data

[1230] The smart glasses receive the user's feedback and prepare to send this data to a cloud server.

[1231] Step 2:

[1232] The smart glasses send the feedback data to a cloud server.

[1233] Input: Feedback data

[1234] Output: Feedback data sent to the cloud server

[1235] The cloud server stores the received feedback data in a database.

[1236] Step 3:

[1237] The server sends the feedback data to the emotion engine for emotion analysis.

[1238] Input: Feedback data

[1239] Output: Parsed emotion data

[1240] The emotion engine analyzes the emotions contained in the feedback data and generates emotion data such as "anger," "joy," and "sadness."

[1241] Step 4:

[1242] The server sends feedback data, including emotion data, to the generative AI model.

[1243] Input: Feedback data, emotion data

[1244] Output: Input data to a generative AI model

[1245] The generative AI model creates and analyzes prompts based on the data it receives to generate optimal solutions.

[1246] Step 5:

[1247] A generative AI model generates specific solutions based on requirement data and emotion data.

[1248] Input: Prompt sentence (input based on request data and emotion data)

[1249] Output: Generated solution

[1250] The generative AI model references past data and case studies, and integrates requirement data and emotional data to automatically generate specific solutions.

[1251] Step 6:

[1252] The server notifies the device (smart glasses) of the generated solution.

[1253] Input: Generated solution

[1254] Output: Notification information to the device

[1255] The smart glasses receive this notification information and display the contents to the staff.

[1256] Step 7:

[1257] Staff adjust their response on the spot based on solutions displayed through smart glasses.

[1258] Input: Solution displayed on smart glasses

[1259] Output: Improved response

[1260] Staff can check the solutions displayed on the smart glasses and take prompt action based on them.

[1261] 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.

[1262] 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.

[1263] 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.

[1264] [Fourth embodiment]

[1265] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1266] 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.

[1267] 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).

[1268] 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.

[1269] 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.

[1270] 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).

[1271] 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.

[1272] 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.

[1273] 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.

[1274] 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.

[1275] 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.

[1276] 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.

[1277] 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."

[1278] The cloud suggestion box + AI generation function system of this invention efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. Detailed embodiments of this system are described below.

[1279] System Overview:

[1280] Users input request data such as complaints and requests into the cloud suggestion box.

[1281] The terminal transmits the data entered by the user to the server in real time.

[1282] The server stores the received request data in a database and begins the analysis process.

[1283] Parsing and categorizing requirements data:

[1284] The server sends the saved request data to the generation AI for analysis.

[1285] Generative AI uses natural language processing (NLP) technology to analyze the content of requests and automatically classify them into specific categories, such as "internal facilities," "user interface," and "service improvement."

[1286] Auto-generation of solutions:

[1287] Generative AI generates specific solutions based on categorized requirements. During this process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, and time.

[1288] Solution Notification:

[1289] The server notifies the appropriate parties of the generated solution, for example, if the solution concerns internal facilities, it notifies the relevant administrative department personnel by email.

[1290] The user can quickly respond based on the notified solution.

[1291] Automatic generation of new suggestions:

[1292] Generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including proposals for new projects and ideas for improving business efficiency.

[1293] The server notifies the user or administrator of any new proposals generated and, if applicable, puts them into immediate implementation.

[1294] Examples:

[1295] For example, if a user submits a request to the suggestion box saying, "The conference room reservation system is difficult to use,"

[1296] The server stores this request data in a database and begins the analysis process.

[1297] The generative AI analyzes this data and categorizes it as a request related to "internal facilities."

[1298] The generative AI generates specific solutions such as "improving the UI of the conference room reservation system" and "creating a tutorial video for the reservation process."

[1299] The server notifies the company's system administration personnel of these solutions.

[1300] Users can be assured that the issues have been resolved with an improved system and new tutorials.

[1301] In this way, the Cloud Suggestion Box + Generative AI Function System can respond quickly and appropriately to user requests and achieve continuous improvement. It also automatically generates new ideas and suggestions on a regular basis and provides them to users, ensuring that they always receive the latest and best solutions.

[1302] The processing flow will be explained below.

[1303] Step 1:

[1304] Users input their requests or complaints into the cloud suggestion box, and the input data is sent from the device to the server in real time.

[1305] Step 2:

[1306] Once the server receives the requested data, it stores it in a database, where it is added to a queue for analysis.

[1307] Step 3:

[1308] The server periodically checks the queue to see if there is new request data. If it finds new request data, it sends it to the generation AI.

[1309] Step 4:

[1310] The generative AI receives the request data and uses natural language processing (NLP) technology to analyze the content of the data, determining which category the request data belongs to.

[1311] Step 5:

[1312] The generation AI classifies the request data into appropriate categories based on the identified categories, such as "internal facilities," "user interface," and "service improvement."

[1313] Step 6:

[1314] The generative AI generates specific solutions based on categorized requirements data. During the generation process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, time, etc.

[1315] Step 7:

[1316] Once a solution is generated, the server notifies the appropriate parties of the solution. For example, if the solution concerns an internal facility, a notification is sent via email to the relevant administrative personnel.

[1317] Step 8:

[1318] Users can receive solutions notified by relevant parties and initiate the necessary response, which includes a concrete action plan, enabling rapid response.

[1319] Step 9:

[1320] The server receives and logs feedback from stakeholders to track the implementation of solutions, allowing you to see the effectiveness of the solutions.

[1321] Step 10:

[1322] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including ideas for new projects and business efficiency improvements.

[1323] Step 11:

[1324] Newly generated suggestions are notified to users and administrators via the server, and if applicable, they are immediately implemented for further improvement.

[1325] Example 1

[1326] 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."

[1327] The existing system lacked the process for efficiently collecting and analyzing user requests and complaints, automatically generating solutions, and notifying the appropriate parties. It also struggled to regularly provide users with continuous improvements and new proposals. This hindered the rapid resolution of problems and improved work efficiency.

[1328] 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.

[1329] In this invention, the server includes means for receiving request data, means for analyzing the received data using natural language processing and classifying the request data into categories, means for generating specific solutions based on the classified request data, means for analyzing past request data and solutions and automatically generating new proposals, means for notifying a person in charge of management or a user of the generated solutions and encouraging them to take action, and means for periodically notifying a user or a manager of new proposals and encouraging them to implement them. This makes it possible to efficiently collect and analyze requests and complaints from users and quickly provide specific solutions, as well as to periodically provide continuous improvements and new proposals.

[1330] "Request data" is information including complaints, requests, and other demands input by the user.

[1331] A "server" is a computer system that receives, stores, analyzes request data, and generates and notifies solutions.

[1332] A "terminal" is a device through which a user inputs request data and transmits it to a server.

[1333] "Generative AI" is an artificial intelligence system that uses natural language processing technology to analyze requirement data and automatically generate solutions and new proposals.

[1334] "Natural Language Processing (NLP)" is a technology that enables computers to understand, analyze, and generate human language.

[1335] "Category" is a classification category used by the generation AI to classify the request data analyzed.

[1336] A "solution" is a specific countermeasure or improvement that the generating AI proposes based on the required data.

[1337] "Notification" is the act of informing appropriate parties of solutions or proposals generated by generative AI.

[1338] "Proposals" are new improvement plans or ideas that the generative AI generates by analyzing past requirement data and solutions.

[1339] "Stakeholders" refer to the management personnel and users who should receive the generated solutions and proposals.

[1340] MODE FOR CARRYING OUT THE INVENTION

[1341] The cloud suggestion box + AI generation function system of this invention efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. Specific embodiments of this system are shown below.

[1342] System Overview

[1343] The system consists of four main components: the user, the terminal, the server, and the generating AI.

[1344] User: The user inputs complaints, requests, and other request data into the cloud suggestion box. For example, the user inputs a request such as "The conference room reservation system is difficult to use."

[1345] Terminal: The terminal transmits the data entered by the user to the server in real time. The terminal is a device such as a PC or smartphone that transmits data through a cloud-based input form or application.

[1346] Server: The server receives the requested data and stores it in a database, which then initiates the analysis process and sends it to the generation AI.

[1347] Generative AI: Generative AI uses natural language processing (NLP) techniques to analyze the received request data and classify it into specific categories. It then generates a specific solution based on the classified request data. The generated solution is returned to the server, which then notifies the appropriate parties.

[1348] Analyzing and categorizing requirements data

[1349] The server sends the saved request data to the generation AI, which begins analyzing it. The generation AI uses natural language processing technology to analyze the content of the request and automatically classify it into specific categories. These include categories such as "internal facilities," "user interface," and "service improvement." The generation AI uses generative AI models such as BERT and GPT, which are NLP techniques in general computer science.

[1350] Automatic solution generation

[1351] Generative AI generates specific solutions based on categorized requirements. During this process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, time, etc. Generative AI learns from past databases and cases to provide highly accurate solutions.

[1352] Solution Notification

[1353] The server then notifies the appropriate parties of the generated solution. For example, if the solution relates to internal facilities, it will notify the relevant management department via email or an internal notification system. The notification will also include specific steps and resources to be taken, allowing the parties involved to respond quickly.

[1354] Automatic generation of new proposals

[1355] The generative AI periodically analyzes past requirement data and solutions to automatically generate new proposals and improvements. These include proposals for new projects and ideas for improving business efficiency. The server notifies users and administrators of the new proposals and, if applicable, immediately implements them.

[1356] Specific examples

[1357] For example, if a user submits a request to the suggestion box saying, "The conference room reservation system is difficult to use,"

[1358] The server stores this request data in a database and begins the analysis process.

[1359] The generative AI analyzes this data and categorizes it as a request related to "internal facilities."

[1360] The generative AI generates specific solutions such as "improving the UI of the conference room reservation system" and "creating a tutorial video for the reservation process."

[1361] The server notifies the company's system administration personnel of these solutions.

[1362] Users can be assured that the issues have been resolved with an improved system and new tutorials.

[1363] Prompt Sentence Examples

[1364] If a user types "I want to improve the onboarding process for new employees":

[1365] The device sends this to the server.

[1366] The server sends the data to the generation AI, which then suggests simplifying the onboarding flow for new employees and introducing digital training content.

[1367] The server notifies the HR department.

[1368] The HR department implements the proposal and new employees are smoothly onboarded.

[1369] In this way, the cloud suggestion box + generative AI function system can respond quickly and appropriately to user requests and achieve continuous improvement. It also automatically generates new ideas and suggestions on a regular basis and provides them to users, ensuring that they always receive the latest and best solutions.

[1370] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1371] Step 1:

[1372] The user inputs the requested data into the input form of the cloud suggestion box. For example, the input requested data is "The conference room reservation system is difficult to use." This data is captured by the terminal.

[1373] Input: User request data (text format)

[1374] Output: The requested data entered is saved on the terminal.

[1375] Step 2:

[1376] The terminal transmits the request data input by the user to the server in real time. The terminal uses the HTTP POST method to transmit the request data to the server as a packet.

[1377] Input: Request data stored on the device

[1378] Output: Packet data sent to the server

[1379] Step 3:

[1380] The server receives the HTTP request, extracts the request data from the request body, and then executes an INSERT query to store this request data in the database.

[1381] Input: Packet data sent to the server

[1382] Output: Request data stored in the database

[1383] Step 4:

[1384] The server sends the saved request data to the generation AI and starts the analysis process. The request data is transferred to the generation AI through the API endpoint.

[1385] Input: Request data stored in the database

[1386] Output: Request data sent to the generating AI

[1387] Step 5:

[1388] Generative AI analyzes the received request data using natural language processing (NLP) techniques, typically using BERT or GPT models. This analysis performs semantic analysis of the text data and classifies it into specific categories.

[1389] Input: Request data sent to the generating AI

[1390] Output: Parsed category information (e.g., "In-house facilities")

[1391] Step 6:

[1392] Generative AI automatically generates solutions based on categorized requirements, referencing past success stories and database information to provide specific action plans.

[1393] Input: Parsed category information

[1394] Output: Generated solutions (e.g., "Improve the UI of the conference room reservation system," "Create a tutorial video for the reservation process")

[1395] Step 7:

[1396] The server notifies the appropriate parties of the generated solution. For example, if the solution is related to internal facilities, it notifies the relevant management department personnel via email or an internal notification system.

[1397] Input: Generated solution

[1398] Output: Notification to relevant parties (email and system notification)

[1399] Step 8:

[1400] Users receive notification and confirmation that the solution has been implemented. Users can use the improved system and see its effectiveness.

[1401] Input:Notification to interested parties

[1402] Output: User confirmation of solution and feedback

[1403] Step 9:

[1404] Generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals, including new project proposals and ideas for improving business efficiency.

[1405] Input: Past request data and solutions

[1406] Output: New proposal (e.g., "Remote work optimization proposal")

[1407] Step 10:

[1408] The server notifies the user or administrator of any new suggestions that are generated and, if applicable, implements them immediately.

[1409] Input: New proposal

[1410] Output: Notification and action recommendation to users and administrators

[1411] These are the specific processing steps of the cloud suggestion box + generative AI function system, which enables a quick and appropriate response to user requests.

[1412] (Application example 1)

[1413] 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."

[1414] Traditionally, processing customer feedback and requests in brick-and-mortar stores has been inefficient and difficult to respond to promptly. In particular, it has been difficult for the person receiving the feedback to quickly find a solution, and continuous improvement and the generation of new proposals have been insufficient. For these reasons, there is a need to improve customer satisfaction and streamline store operations.

[1415] 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.

[1416] In this invention, the server includes means for receiving request data, means for analyzing the received data using natural language processing and classifying the request data into categories, means for sending customer feedback from the physical store to a cloud suggestion box in real time via a smartphone app, means for generating specific solutions based on the classified request data, means for notifying appropriate parties of the generated solutions, and means for analyzing past request data and solutions and automatically generating new proposals. This enables rapid processing of customer feedback, improved operational efficiency of the physical store, continuous improvement, and the automatic generation of new proposals.

[1417] "Request Data" means feedback or request information collected from users.

[1418] "Natural language processing" is a technology that allows computers to understand and analyze natural language used by humans.

[1419] A "category" is a grouping based on a certain common attribute or theme.

[1420] A "smartphone app" is a software application that runs on a mobile information terminal.

[1421] A "cloud suggestion box" is a system that stores data on the Internet and allows users to enter requests and feedback.

[1422] A "server" is a computer device that stores, manages, and analyzes data over a network.

[1423] A "solution" is a specific method or policy for solving a particular problem.

[1424] "Stakeholders" are people or departments with responsibilities related to a particular issue or situation.

[1425] A "proposal" is a new idea or plan for improvement for a specific problem.

[1426] To implement the present invention, a system including a server, a terminal, and a user is used. The configuration and operation procedure of this system will be described in detail below.

[1427] System Configuration

[1428] 1. Hardware and Software

[1429] Server: This is the central computer that stores data, analyzes it, and generates solutions. This server must have high computing power and be equipped with natural language processing (NLP) technology. Specifically, cloud platforms such as Google Cloud, Amazon Web Services (AWS), and Microsoft Azure can be used.

[1430] Terminal: A smartphone or tablet device that transmits user feedback to the server in real time. The smartphone app is installed on the terminal.

[1431] software:

[1432] Smartphone app: A feedback collection and notification application that allows users to enter feedback and receive notifications.

[1433] Generative AI model: A data analysis technology with natural language processing and generative AI functions. Specifically, OpenAI's GPT-3 is one example.

[1434] Operating Procedure

[1435] 1. Gathering feedback

[1436] Customers use a smartphone app to enter feedback and requests about physical stores, such as "the shelves are hard to find."

[1437] 2. Data transmission and storage

[1438] The device sends the input feedback in real time to the cloud suggestion box, which runs on cloud platforms such as Google Cloud and AWS.

[1439] 3. Data Analysis and Classification

[1440] The server receives the transmitted data and analyzes the feedback using natural language processing techniques.

[1441] The analyzed data is sent to a generative AI model and automatically classified into specific categories (e.g., "product placement" or "service improvement").

[1442] 4. Generating concrete solutions

[1443] The server uses a generative AI model to generate specific solutions based on the categorized feedback, including a concrete implementation plan and required resources, budget, and time.

[1444] 5. Notification of Solution

[1445] The server notifies the appropriate parties of the generated solution, who can then receive it via a smartphone app.

[1446] 6. Automatic generation of new proposals

[1447] The server analyzes past feedback and solutions and periodically generates new suggestions and improvements automatically, facilitating continuous improvement of the entire system.

[1448] Specific examples

[1449] For example, if a user uses a smartphone app to send feedback that "the product shelves are difficult to understand," the process proceeds as follows:

[1450] Example prompt: "Please provide a specific solution to improve the request for confusing shelves."

[1451] The server receives this feedback, automatically analyzes it, and categorizes it into categories such as "product placement."

[1452] Using a generative AI model, it generates specific solution suggestions such as "color-coding shelf labels and installing guide signs in each section."

[1453] The solution will be communicated to store managers and implemented promptly.

[1454] Through the above-described operational procedure, the present invention can be implemented, thereby improving the efficiency of feedback processing in physical stores and customer satisfaction.

[1455] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1456] Step 1:

[1457] The user enters feedback into the smartphone app. For example, the user might enter "The product shelves are difficult to find" and submit this feedback. The entered data is sent from the user's device to the server.

[1458] Step 2:

[1459] The device receives feedback from users and sends it to the Cloud Suggestion Box in real time. The Cloud Suggestion Box uses cloud platforms such as Google Cloud and AWS. The data processing performed here involves converting the input feedback into an appropriate format such as JSON. The output is data stored in the Cloud Suggestion Box.

[1460] Step 3:

[1461] The server receives and stores feedback from the cloud suggestion box. The server then analyzes the feedback data using natural language processing (NLP) techniques. NLP processing includes text tokenization and grammar analysis. The input is the stored feedback data, and the output is the analyzed text information.

[1462] Step 4:

[1463] The server sends the analyzed feedback data to a generative AI model, which classifies it into a specific category. For example, natural language processing can be used to classify feedback related to "product placement." The input is the analyzed text information, and the output is the categorized data.

[1464] Step 5:

[1465] The server uses the generative AI model to generate specific solutions based on feedback categorized into specific categories. For example, the prompt "Please provide a specific solution to improve the requirement that product shelves are difficult to understand" is used to input data into the generative AI model, and an output solution is obtained. The data processing performed here is the generation of a solution by the AI ​​model.

[1466] Step 6:

[1467] The server notifies the appropriate parties of the generated solution. Notifications are sent via a smartphone app, email, or other means. For example, a solution such as "color-code shelf labels and install guide signs in each section" is sent to the manager of a physical store. The input is the generated solution, and the output is a notification message to the relevant parties.

[1468] Step 7:

[1469] The server periodically analyzes past feedback and solutions and automatically generates new suggestions and improvements. It periodically retrains the generative AI model, using past data to gain new insights. The input is past feedback and solution data, and the output is newly generated suggestions.

[1470] Specific actions at each step ensure that user feedback is handled quickly and effectively, ensuring that brick-and-mortar store operations are constantly optimized.

[1471] 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.

[1472] The system of this invention, which combines a cloud suggestion box with a generative AI function and an emotion engine, efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. It is also capable of recognizing user emotions and adjusting the solution generation process based on those emotions. A detailed embodiment of this system is shown below.

[1473] System Overview:

[1474] Users input request data such as complaints and requests into the cloud suggestion box.

[1475] The terminal transmits the data entered by the user to the server in real time.

[1476] The server stores the received request data in a database and begins the analysis process.

[1477] Sentiment Analysis:

[1478] The server sends the request data to the emotion engine and analyzes the user's emotion contained in the data.

[1479] The emotion engine uses text analysis technology to recognize emotions in request data and classify them into categories such as "anger," "joy," and "sadness."

[1480] The server also stores the emotion data detected by the emotion engine.

[1481] Parsing and categorizing requirements data:

[1482] The server sends the request data stored along with the emotion data to the generation AI for analysis.

[1483] Generative AI uses natural language processing (NLP) technology to analyze the content of requests and automatically classify them into specific categories, such as "internal facilities," "user interface," and "service improvement."

[1484] Auto-generation of solutions:

[1485] The generative AI generates specific solutions based on categorized requirements and sentiment data. During this process, it references past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, and time.

[1486] If the emotion data indicates "anger," the generated solution requires a rapid response and may include customer service intervention.

[1487] Solution Notification:

[1488] The server notifies the appropriate parties of the generated solution. For example, if the solution concerns an internal facility, a notification is sent via email to the relevant administrative department.

[1489] The user can quickly respond based on the notified solution.

[1490] Emotional notifications:

[1491] The server notifies the participants of the details, including the user's emotions detected by the emotion engine, so that the participants can also take the emotion data into account when implementing a solution.

[1492] Automatic generation of new suggestions:

[1493] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including ideas for new projects and business efficiency improvements.

[1494] The server notifies the user or administrator of any new proposals generated and, if applicable, puts them into immediate implementation.

[1495] Examples:

[1496] For example, if a user posts a request to the suggestion box saying, "The conference room reservation system is difficult to use," and the user expresses anger in the request,

[1497] The server stores this request data and emotion data in a database and starts the analysis process.

[1498] The generation AI analyzes the request data and categorizes it as a request related to "internal facilities."

[1499] Generative AI takes emotional data into account and generates quick and effective solutions, such as "improving the UI of the conference room booking system" or "creating a tutorial video for the booking process."

[1500] The server notifies the user's "anger" emotion data along with a solution to the relevant person in charge of the management department.

[1501] Users can be assured that the issues have been resolved with an improved system and new tutorials.

[1502] In this way, a system that combines a cloud suggestion box, generative AI functions, and an emotion engine can respond quickly and appropriately to user requests and provide solutions that take the user's emotions into consideration. Furthermore, by automatically generating new ideas and suggestions on a regular basis and providing them to users, it is possible to always provide the latest and best solutions.

[1503] The processing flow will be explained below.

[1504] Step 1:

[1505] Users input their requests or complaints into the cloud suggestion box, and the input data is sent from the device to the server in real time.

[1506] Step 2:

[1507] Once the server receives the requested data, it stores it in a database, where it is added to a queue for analysis.

[1508] Step 3:

[1509] The server periodically checks the queue for new request data, and if it finds new request data, it sends it to the emotion engine.

[1510] Step 4:

[1511] The emotion engine receives the request data and analyzes the emotion using text analysis technology, generating emotion data such as "anger," "joy," and "sadness" as the analysis result.

[1512] Step 5:

[1513] The emotion engine sends the generated emotion data to the server, which stores the emotion data together with the request data in a database.

[1514] Step 6:

[1515] The server sends the saved request data and emotion data to the generation AI for analysis.

[1516] Step 7:

[1517] The generative AI uses natural language processing (NLP) technology to analyze the content of the request data and automatically classify it into specific categories, such as "internal facilities," "user interface," and "service improvement."

[1518] Step 8:

[1519] The generative AI generates specific solutions based on categorized requirements and sentiment data, referencing past success stories and case studies from other companies to build solutions that include specific implementation plans, required resources, budgets, time, etc.

[1520] Step 9:

[1521] The generative AI takes emotion data into account and adjusts the urgency of the solution and specific countermeasures. For example, if emotion data of "anger" is detected, a quick response is required.

[1522] Step 10:

[1523] The generated solution is then communicated to the appropriate parties via the server. For example, if the solution relates to internal facilities, a notification is sent via email to the relevant administrative department.

[1524] Step 11:

[1525] The server also notifies the parties involved of the user's emotion data detected by the emotion engine, so that the parties involved can implement solutions taking the user's emotions into consideration.

[1526] Step 12:

[1527] Users can receive solutions notified by relevant parties and initiate the necessary response, which includes a concrete action plan, enabling rapid response.

[1528] Step 13:

[1529] The server receives and logs feedback from stakeholders to track the implementation of solutions, allowing you to see the effectiveness of the solutions.

[1530] Step 14:

[1531] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including new project proposals and ideas for improving business efficiency.

[1532] Step 15:

[1533] Newly generated suggestions are notified to users and administrators via the server, and if applicable, they are immediately implemented for further improvement.

[1534] Example 2

[1535] 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."

[1536] Conventional systems lacked the ability to efficiently analyze user request data and automatically generate and notify optimal solutions. Furthermore, there were no systems that could take user emotions into consideration or automatically generate new proposals. This created the risk of lowering user satisfaction and led to problems with appropriate improvement measures not being implemented quickly.

[1537] 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.

[1538] In this invention, the server includes means for receiving request data and emotion data, means for analyzing the received request data and emotion data using natural language processing and categorizing the request data, means for generating specific solutions based on the analysis results including the emotion data, means for notifying appropriate parties of the generated solutions and emotion data, and means for analyzing past request data and solutions and automatically generating new proposals. This makes it possible to provide effective and prompt solutions that take user emotions into consideration, thereby improving user satisfaction and generating new improvement proposals.

[1539] "Request data" refers to information collected from users, such as complaints, requests, and suggestions.

[1540] "Emotion data" refers to information that classifies the user's emotions contained in the request data.

[1541] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[1542] A "category" is a classification to which the analyzed request data belongs, and refers to a specific theme or content.

[1543] "Solutions" refer to specific problem-solving techniques and proposals that are generated based on the analyzed requirement data and emotion data.

[1544] "Stakeholders" refers to the individuals or departments who are notified of the generated solutions and are responsible for implementing the response.

[1545] A "database" refers to a system that systematically stores and manages information such as requirements data, emotion data, and past solutions.

[1546] "New proposals" refer to proposals for improvements or new projects that are generated based on past requirements data and solutions.

[1547] The system of this invention, which combines a cloud suggestion box, a generative AI function, and an emotion engine, efficiently processes request data from users, automatically generates and notifies specific solutions, and automatically generates new proposals. It is also capable of recognizing user emotions and adjusting the solution generation process based on them.

[1548] System configuration

[1549] Users use devices such as PCs or smartphones to input complaints, requests, and other request data into the cloud suggestion box.

[1550] The terminal transmits the data entered by the user to the server in real time. The terminal communicates with the server via an internet connection using the HTTPS protocol.

[1551] The server uses a database (e.g., MySQL, PostgreSQL) to store the received request data, and then begins the analysis process.

[1552] Data analysis

[1553] The server sends the request data to an emotion engine (e.g., NLP API, machine learning model) and analyzes the user's emotions contained in the data.

[1554] The emotion engine uses text analysis technology to recognize emotions in request data and classify them into categories such as "anger," "joy," and "sadness."

[1555] The server stores the emotion data generated by the emotion engine in a database.

[1556] Categorizing requirements data and generating solutions

[1557] The server then sends the request data, along with the emotion data, to the AI ​​for analysis. The AI ​​then uses natural language processing to analyze the request and classify it into specific categories, such as "internal facilities," "user interface," and "service improvement."

[1558] The generative AI generates specific solutions based on categorized requests and sentiment data. It references past success stories and case studies from other organizations to build solutions that include specific implementation plans, required resources, budgets, and time. Examples of solutions include "improving the UI of the conference room reservation system" and "creating a tutorial video for the reservation process."

[1559] Notification of solutions and sentiment data

[1560] The server notifies the appropriate parties of the generated solution. For example, if the solution concerns an internal facility, a notification is sent via email to the relevant administrative department.

[1561] The user can quickly respond based on the solution. The user checks the notified solution and implements it according to the instructions.

[1562] Automatic generation of new proposals

[1563] The generative AI periodically analyzes past requirements data and solutions to automatically generate new proposals and improvements, including ideas for new projects and business efficiency improvements.

[1564] The server notifies the user or administrator of any new proposals generated and, if applicable, puts them into immediate implementation.

[1565] Specific examples

[1566] For example, a user may submit a request to the suggestion box saying, "The conference room reservation system is difficult to use," and may include the emotion of "anger" in the request.

[1567] The server stores this request data and emotion data in a database and starts the analysis process.

[1568] The server sends the data to the emotion engine for emotion analysis.

[1569] The generation AI analyzes the request data and categorizes it as a request related to "internal facilities."

[1570] The generative AI takes emotional data into account and generates solutions such as "improving the UI of the conference room reservation system" or "creating a tutorial video for the reservation process."

[1571] The server notifies the user's "anger" emotion data along with the solution to the relevant person in charge of the management department.

[1572] Users will find that their issues have been resolved with an improved system and new tutorials.

[1573] Prompt Sentence Examples

[1574] "Generate a specific solution based on the user's request data that 'the conference room reservation system is difficult to use' and the emotion data of 'anger' analyzed by the emotion engine."

[1575] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1576] Step 1:

[1577] The user inputs the request data into the cloud suggestion box.

[1578] Users use devices such as PCs or smartphones to enter request data in text format via a web interface or mobile application. The input at this stage is specific, such as a problem, request, or suggestion. For example, a user might enter, "The conference room reservation system is difficult to use."

[1579] Step 2:

[1580] The terminal transmits the input request data to the server.

[1581] The terminal formats the request data and sends it to the server over an Internet connection using the HTTPS protocol. The input to this step is the raw request data entered by the user, and the output is the data packet received by the server.

[1582] Step 3:

[1583] The server stores the received data in a database and starts the analysis process.

[1584] The server stores the received request data in a database (e.g., MySQL, PostgreSQL). Based on the stored request data, it moves to the next process for analysis. The input of this step is the received request data, and the output is the data stored in the database.

[1585] Step 4:

[1586] The server sends the request data to the emotion engine for emotion analysis.

[1587] The server sends the request data to an emotion engine (e.g., a natural language processing API). The emotion engine uses text analysis technology to analyze emotions in the request data and classify them into categories such as "anger," "joy," and "sadness." The input of this step is the request data, and the output is the analyzed emotion data.

[1588] Step 5:

[1589] The server stores the sentiment analysis data in a database.

[1590] The server stores the emotion data generated by the emotion engine in a database. This forms a pair of request data and emotion data. The input of this step is the analyzed emotion data, and the output is the emotion data stored in the database.

[1591] Step 6:

[1592] The server sends the data to the generating AI, which categorizes the request.

[1593] The server sends the request data and related emotion data to the generation AI, which uses natural language processing technology to analyze the request content and classify it into specific categories such as "internal facilities," "user interface," and "service improvement." The input for this step is the request data and emotion data, and the output is categorized request data.

[1594] Step 7:

[1595] Generative AI generates specific solutions.

[1596] The generative AI generates specific solutions based on the categorized requirements and sentiment data. It references past success stories and case studies from other organizations to build solutions that include specific details such as an implementation plan, required resources, budget, and time. The input for this step is the categorized requirements data and sentiment data, and the output is a specific solution.

[1597] Step 8:

[1598] The server notifies the generated solution and sentiment data to the participants.

[1599] The server sends the generated solution and emotion data to the appropriate parties via email or system notification. For example, if the solution is related to internal facilities, the relevant administrative department personnel will be notified. The input of this step is the solution and emotion data, and the output is a notification to the parties involved.

[1600] Step 9:

[1601] The user implements the solution.

[1602] The user takes prompt action based on the notified solution. Implement the instructed solution and check whether the problem has been resolved. The input of this step is the notified solution, and the output is the implemented action and its result.

[1603] Step 10:

[1604] The server periodically generates and announces new proposals.

[1605] The server periodically analyzes past requirement data and solutions to generate new proposals and improvements. These proposals include new project proposals and ideas for improving business efficiency. It notifies users and administrators of the new proposals and, if applicable, implements them immediately. The inputs to this step are past data and solutions, and the output is new proposals.

[1606] (Application example 2)

[1607] 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."

[1608] Modern commercial facilities and service industries are required to process customer feedback quickly and accurately and respond on the spot. It is also important to understand customer emotions and respond accordingly. However, current systems do not process feedback in real time, making it difficult to properly grasp customer emotions. In addition, there is a lack of systems that provide concrete solutions that allow staff to quickly adjust their response methods on the spot. This leads to a decline in customer satisfaction and a deterioration in service quality.

[1609] 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.

[1610] In this invention, the server includes means for receiving request data, means for analyzing the received data using natural language processing and categorizing the request data, means for generating specific solutions based on the categorized request data, means for notifying appropriate parties of the generated solutions, means for analyzing past request data and solutions and automatically generating new proposals, means for analyzing user feedback in real time and providing improvements based on the analysis results, means for analyzing emotions in the feedback using an emotion engine and adjusting the solution generation based on the emotion data, and means for notifying staff via a notification device of the analysis results and the generated solutions. This enables customer feedback to be analyzed quickly and in real time, appropriate solutions to be provided, and responses that take customer emotions into consideration. Furthermore, by having staff adjust their response methods on the spot, customer satisfaction and service quality can be improved.

[1611] "Request data" is information such as feedback or requests provided by a user.

[1612] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[1613] A "category" is a concept for classifying request data into a specific group or category.

[1614] A "solution" is a specific action or response that should be taken to address a particular problem.

[1615] "Generative AI" is an artificial intelligence system that uses machine learning technology to automatically generate solutions and proposals.

[1616] "Stakeholders" are individuals or departments responsible for implementing the generated solutions.

[1617] A "database" is a system for systematically managing and storing information.

[1618] An "emotion engine" is an algorithm or technology for analyzing and identifying emotions from text data.

[1619] "Emotion data" is information about emotions extracted from user feedback.

[1620] A "device" is an appliance or piece of equipment for displaying or receiving information.

[1621] "Improvements" are suggestions or solutions to improve the current situation.

[1622] "Real-time" means that data processing and responses occur almost immediately.

[1623] The present invention is a system for quickly and accurately processing user feedback and providing improvements. The system mainly uses smart glasses, a cloud server, a generative AI model, an emotion engine, and a database.

[1624] The system first receives user feedback via smart glasses, such as Google Glass, which collects feedback via voice and touch input.

[1625] The requested data is sent in real time to a cloud server, which uses, for example, AWS (Amazon Web Services) and stores the received data in a database (such as Amazon RDS).

[1626] The cloud server then sends the request data to an emotion engine, which analyzes the emotion data using algorithms such as IBM Watson Tone Analyzer, to identify emotions (e.g., anger, joy, sadness, etc.) in the request data.

[1627] Once the emotion data has been analyzed, the cloud server sends the request data and emotion data to a generative AI model (e.g., OpenAI GPT-3) to generate a specific solution. The generative AI model then references past data and examples to automatically generate the optimal solution.

[1628] The cloud server notifies the smart glasses of the generated solutions, and the smart glasses' built-in notification system allows staff to check the analysis results of the feedback and areas for improvement in real time.

[1629] For example, if a user receives feedback that they have been waiting a long time at the cash register, the following process will be performed.

[1630] 1. Receive feedback through smart glasses that "The cashier is slow and the wait is long."

[1631] 2. This request data is sent to the cloud server and stored in a database.

[1632] 3. The emotion engine analyzes the emotion of "anger" and sends the emotion data to the cloud server.

[1633] 4. The generative AI model generates solutions based on emotion data and requirement data.

[1634] An example of a prompt is as follows:

[1635] "User feedback: The checkout is slow and the wait is long."

[1636] "Emotion data: Anger"

[1637] "Solution: Open another register as soon as possible, and offer a coupon to customers who are waiting."

[1638] 5. The generated solution is sent to the smart glasses, allowing staff to quickly adjust their response on the spot.

[1639] In this way, this system can improve the quality of service by analyzing user feedback in real time and providing appropriate solutions according to the situation.

[1640] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1641] Step 1:

[1642] The user inputs feedback through the smart glasses.

[1643] Input: Feedback data from voice or touch input

[1644] Output: Generate feedback data

[1645] The smart glasses receive the user's feedback and prepare to send this data to a cloud server.

[1646] Step 2:

[1647] The smart glasses send the feedback data to a cloud server.

[1648] Input: Feedback data

[1649] Output: Feedback data sent to the cloud server

[1650] The cloud server stores the received feedback data in a database.

[1651] Step 3:

[1652] The server sends the feedback data to the emotion engine for emotion analysis.

[1653] Input: Feedback data

[1654] Output: Parsed emotion data

[1655] The emotion engine analyzes the emotions contained in the feedback data and generates emotion data such as "anger," "joy," and "sadness."

[1656] Step 4:

[1657] The server sends feedback data, including emotion data, to the generative AI model.

[1658] Input: Feedback data, emotion data

[1659] Output: Input data to a generative AI model

[1660] The generative AI model creates and analyzes prompts based on the data it receives to generate optimal solutions.

[1661] Step 5:

[1662] A generative AI model generates specific solutions based on requirement data and emotion data.

[1663] Input: Prompt sentence (input based on request data and emotion data)

[1664] Output: Generated solution

[1665] The generative AI model references past data and case studies, and integrates requirement data and emotional data to automatically generate specific solutions.

[1666] Step 6:

[1667] The server notifies the device (smart glasses) of the generated solution.

[1668] Input: Generated solution

[1669] Output: Notification information to the device

[1670] The smart glasses receive this notification information and display the contents to the staff.

[1671] Step 7:

[1672] Staff adjust their response on the spot based on solutions displayed through smart glasses.

[1673] Input: Solution displayed on smart glasses

[1674] Output: Improved response

[1675] Staff can check the solutions displayed on the smart glasses and take prompt action based on them.

[1676] 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.

[1677] 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.

[1678] 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.

[1679] 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.

[1680] 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.

[1681] 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.

[1682] 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).

[1683] 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.

[1684] 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."

[1685] 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.

[1686] 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).

[1687] 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.

[1688] 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.

[1689] 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.

[1690] 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.

[1691] 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.

[1692] 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.

[1693] 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.

[1694] 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.

[1695] 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.

[1696] 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.

[1697] The following is further disclosed regarding the above embodiment.

[1698] (Claim 1)

[1699] means for receiving request data;

[1700] means for analyzing the received data by natural language processing and classifying the requested data into categories;

[1701] a means for generating specific solutions based on the classified requirements data;

[1702] A means of communicating generated solutions to appropriate parties;

[1703] A system that includes a means for analyzing past requirements data and solutions and automatically generating new proposals.

[1704] (Claim 2)

[1705] 2. The system according to claim 1, further comprising means for referring to a past database and examples from other companies when analyzing requirement data and generating solutions.

[1706] (Claim 3)

[1707] 10. The system of claim 1, further comprising means for periodically notifying and presenting generated solutions and new suggestions to the user.

[1708] "Example 1"

[1709] (Claim 1)

[1710] means for receiving request data;

[1711] means for analyzing the received data by natural language processing and classifying the requested data into categories;

[1712] a means for generating specific solutions based on the classified requirements data;

[1713] A means of communicating generated solutions to appropriate parties;

[1714] A means for analyzing past requirement data and solutions and automatically generating new proposals;

[1715] A means for notifying the generated solution to a person in charge of management or a user and urging them to take action;

[1716] A method to periodically notify users and administrators of new proposals and encourage their implementation;

[1717] A system including:

[1718] (Claim 2)

[1719] 10. The system of claim 1, further comprising means for referencing past databases and cases when analyzing requirements data and generating solutions.

[1720] (Claim 3)

[1721] 10. The system of claim 1, further comprising means for periodically notifying and presenting generated solutions and new suggestions to the user.

[1722] "Application Example 1"

[1723] (Claim 1)

[1724] means for receiving request data;

[1725] means for analyzing the received data by natural language processing and classifying the requested data into categories;

[1726] A means to send customer feedback from physical stores to a cloud suggestion box in real time via a smartphone app,

[1727] a means for generating specific solutions based on the classified requirements data;

[1728] A means of communicating generated solutions to appropriate parties;

[1729] A system that includes a means for analyzing past requirements data and solutions and automatically generating new proposals.

[1730] (Claim 2)

[1731] 2. The system according to claim 1, further comprising means for referring to a past database and examples from other companies when analyzing requirement data and generating solutions.

[1732] (Claim 3)

[1733] 10. The system of claim 1, further comprising means for periodically notifying and presenting generated solutions and new suggestions to the user.

[1734] "Example 2: Combining Emotion Engines"

[1735] (Claim 1)

[1736] means for receiving request data and emotion data;

[1737] means for analyzing the received request data and emotion data by natural language processing and classifying the request data into categories;

[1738] A means for generating specific solutions based on the analysis results including emotion data;

[1739] a means of communicating the generated solutions and sentiment data to appropriate stakeholders;

[1740] A system that includes a means for analyzing past requirements data and solutions and automatically generating new proposals.

[1741] (Claim 2)

[1742] 10. The system of claim 1, further comprising means for referencing past databases and examples from other organizations when analyzing requirements data and generating solutions.

[1743] (Claim 3)

[1744] 10. The system of claim 1, further comprising means for periodically notifying and presenting generated solutions and new suggestions to the user.

[1745] "Application example 2 when combining emotion engines"

[1746] (Claim 1)

[1747] means for receiving request data;

[1748] means for analyzing the received data by natural language processing and classifying the requested data into categories;

[1749] a means for generating specific solutions based on the classified requirements data;

[1750] A means of communicating generated solutions to appropriate parties;

[1751] A means for analyzing past requirement data and solutions and automatically generating new proposals;

[1752] A means to analyze user feedback in real time and provide improvements based on the analysis results;

[1753] means for analyzing emotions in the feedback using an emotion engine and adjusting solution generation based on the emotion data;

[1754] A system that includes a means of notifying staff through a device to communicate the results of the analysis and the solutions generated.

[1755] (Claim 2)

[1756] 2. The system according to claim 1, further comprising means for referring to a past database and examples from other companies when analyzing requirement data and generating solutions.

[1757] (Claim 3)

[1758] 10. The system of claim 1, further comprising means for periodically notifying and presenting generated solutions and new suggestions to the user. [Explanation of symbols]

[1759] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving request data; means for analyzing the received data by natural language processing and classifying the requested data into categories; a means for generating specific solutions based on the classified requirements data; A means of communicating generated solutions to appropriate parties; A system that includes a means for analyzing past requirements data and solutions and automatically generating new proposals.

2. 2. The system according to claim 1, further comprising means for referring to a past database and examples of other companies when analyzing the requirements data and generating a solution.

3. 10. The system of claim 1, further comprising means for periodically notifying and presenting generated solutions and new suggestions to the user.

Images