system

Abstract

We provide the system. [Solution] A means of receiving input from the user, A means for preprocessing the received input data, A means for applying natural language processing to preprocessed data to analyze keywords and sentiment, A database matching means for comparing with past data and searching for related information, A means of generating feedback based on the information obtained, A system including means for providing generated feedback to the user.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional process of business management and improvement plan presentation, it is often carried out manually, and there is a problem of lacking efficiency and speed. Also, it is very difficult to process a large amount of information at once and generate useful feedback based on it. As a result, delays in business improvement and the provision of inaccurate feedback are inevitable. Therefore, there is a need for a system that can efficiently and quickly provide feedback based on user input and promote business improvement.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data to analyze keywords and sentiment, means for comparing with past data and retrieving relevant information from a database, means for generating feedback based on the obtained information, and means for providing the generated feedback to the user. This system enables users to obtain quick and accurate feedback, thereby improving the efficiency and effectiveness of their work.

[0006] A "user" is an individual or organization that uses a system and inputs information.

[0007] "Means for receiving input" refers to interfaces and mechanisms for capturing data such as text and audio from users.

[0008] "Means for pre-processing input data" refers to functions that perform processing to prepare received data into a format that is easy to analyze, and specifically includes spell checking and removal of unnecessary characters.

[0009] "Natural language processing" is a technology that analyzes human language and converts it into a format that computers can understand.

[0010] "Tokenization" is the process of dividing text into words or phrases.

[0011] "Part-of-speech tagging" is the process of assigning a tag to each token to identify its part of speech (noun, verb, adjective, etc.).

[0012] "Named entity recognition" is a technology that extracts specific important keywords (such as names of people, places, and organizations) from text.

[0013] "Sentiment analysis" is a technique for analyzing the emotional tendencies (positive, negative, neutral) of text.

[0014] A "database" is a system for systematically storing historical data and information.

[0015] A "database matching means" is a means that has the function of searching for related information in a database based on the analyzed data and obtaining matching data.

[0016] "Feedback" refers to information such as advice, opinions, and suggestions for improvement provided in response to user input.

[0017] "Means for generating feedback" refers to functions that create feedback to be provided to users based on collected and analyzed information.

[0018] "Means of delivery" refers to the interfaces and mechanisms for transmitting generated feedback and information to the user. [Brief explanation of the drawing]

[0019] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8]It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

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

[0022] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Further, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0027] [First Embodiment]

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

[0029] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0032] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0036] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0039] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0040] Modes for carrying out the invention

[0041] This invention is a system that provides efficient and rapid feedback based on user input, thereby promoting business improvement. A specific embodiment of this system is described below.

[0042] System Overview

[0043] This system allows users to input work-related issues and questions using a terminal, and the server processes that information to provide appropriate feedback and improvement suggestions. The system consists of the following main components:

[0044] 1. Terminal

[0045] 2. Server

[0046] 3. Database

[0047] This section describes the detailed components and their functions.

[0048] terminal

[0049] The terminal has an interface that receives user input and sends that input to the server. The system starts processing when the user enters tasks or questions in text format into the terminal.

[0050] server

[0051] The server receives the input data sent from the terminal and performs the following processing:

[0052] 1. Preprocessing of input data

[0053] It cleans up text data by performing spell checks and removing unnecessary characters.

[0054] 2. Natural Language Processing

[0055] The pre-processed data is subjected to tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis to analyze the meaning of the input data.

[0056] 3. Database matching

[0057] By cross-referencing with past data and searching for relevant information, it becomes possible to find similar cases and useful information.

[0058] 4. Generating Feedback

[0059] Based on the matching results, feedback and improvement suggestions for the user are generated.

[0060] 5. Responding to the user

[0061] The generated feedback is sent to the device and displayed to the user.

[0062] database

[0063] The database stores past issues, feedback, and related data. The server refers to this database to search for information relevant to user input.

[0064] Specific example

[0065] The following explains how the system works based on specific cases.

[0066] Example 1: Organizing business challenges

[0067] User: "I need you to identify the reason why the new project is behind schedule."

[0068] Terminal: Receives user input and sends it to the server.

[0069] server:

[0070] Preprocessing of input data: Perform a spell check and clean up phrases like "Please identify the reason why the new project is behind schedule."

[0071] Natural language processing: Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("project," "progress," "delay," "cause") and sentiment (negative).

[0072] Database matching: Search the database to find similar past issues and feedback.

[0073] Feedback generation: Generate common causes of delays (e.g., resource shortages, scheduling issues) and suggestions for improvement.

[0074] User response: Feedback is sent to the device, and the device displays it to the user.

[0075] Terminal: "Common causes of project delays include resource shortages and scheduling problems. Specifically, please consider the following improvement suggestions."

[0076] 1. Resource reallocation

[0077] 2. Implementation of progress management tools

[0078] 3. Hold regular progress review meetings.

[0079] In this way, this system analyzes the business challenges entered by users and provides quick and accurate feedback, thereby supporting the efficiency and improvement of business operations.

[0080] The following describes the processing flow.

[0081] Step 1:

[0082] Users type work-related issues or questions into their terminals and send them as text. For example, they might type, "I need help identifying the reason why the new project is behind schedule."

[0083] Step 2:

[0084] The terminal receives input data from the user. The received data is sent to the server in its original form.

[0085] Step 3:

[0086] The server preprocesses the data received from the terminal. Specifically, it cleans up the text by performing a spell check and removing unnecessary characters and symbols.

[0087] Step 4:

[0088] The server applies natural language processing (NLP) to the pre-processed text data. This step involves the following specific processes:

[0089] Tokenization: Dividing text into words or phrases.

[0090] Part-of-speech tagging: Assigns part-of-speech information to each token.

[0091] Named Entity Recognition (NER): Extracts important keywords (e.g., "project," "progress," "delay," etc.).

[0092] Sentiment Analysis: Analyzes the overall sentiment of the text and determines whether it is positive, negative, or neutral.

[0093] Step 5:

[0094] The server uses NLP results to compare them with an internal database. It searches for relevant past cases and feedback and retrieves relevant information from the database. This matching is performed using SQL queries, etc.

[0095] Step 6:

[0096] The server generates feedback and improvement suggestions for the user based on information retrieved from the database. Here, an AI algorithm operates to construct appropriate feedback based on highly relevant information.

[0097] Step 7:

[0098] The server sends the generated feedback to the terminal. The terminal receives this feedback and displays it to the user.

[0099] Step 8:

[0100] We review the feedback received from users and decide on the next course of action based on it. For example, we consider and implement specific improvement measures such as "reallocating resources" or "implementing progress management tools."

[0101] (Example 1)

[0102] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0103] Traditional business improvement systems have faced challenges in providing rapid and efficient feedback to user input. In particular, insufficient pre-processing of text data, natural language processing, and cross-referencing with historical data often result in inadequate feedback. Furthermore, the lack of emotional analysis meant that feedback tailored to user needs could not be provided.

[0104] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0105] In this invention, the server includes means for preprocessing received input data, means for applying natural language processing to the preprocessed data and analyzing keywords and sentiment, means for comparing with past data and retrieving relevant information from a database, means for generating feedback using a generative model based on the obtained information, and means for providing the generated feedback to the user. This makes it possible to provide rapid and accurate feedback to user input.

[0106] A "user" refers to an individual or organization that uses the system to input business-related issues or questions.

[0107] "Means of receiving" refers to the interface and method by which the system takes in data entered by the user.

[0108] "Preprocessing methods" refer to the processes and techniques used to prepare received text data into a format that is easy to analyze, such as by performing spell checks and removing unnecessary characters.

[0109] "Natural language processing" refers to techniques that analyze text data using methods such as tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis to understand its meaning and sentiment.

[0110] "Database matching means" refers to the process and system for a system to compare past data with current input data and retrieve relevant information.

[0111] A "generative model" refers to an algorithm or system that automatically generates appropriate feedback or suggestions from input data, such as a generative AI model.

[0112] "Means of generating feedback" refers to the processes and technologies for creating feedback and suggestions to provide to users, based on database matching results and the output of generative models.

[0113] "Means of providing feedback" refers to the interface and methods for communicating generated feedback and suggestions to users.

[0114] Modes for carrying out the invention

[0115] This invention is a system that provides efficient and rapid feedback based on user input, thereby promoting business improvement. In this system, users input work-related issues and questions using a terminal, and a server processes this information to provide appropriate feedback and improvement suggestions. A specific embodiment of this system is described below.

[0116] System Overview

[0117] This system consists of the following main components:

[0118] 1. Terminal

[0119] 2. Server

[0120] 3. Database

[0121] terminal

[0122] The terminal has an interface that receives user input and sends that input to the server. The system starts processing when the user enters tasks or questions in text format into the terminal. Specifically, a web browser or dedicated application is used as the user interface, and the input data is sent to the server via an HTTP POST request.

[0123] server

[0124] The server receives the input data sent from the terminal and performs the following processing:

[0125] 1. Preprocessing of input data

[0126] Use spell-checking tools (e.g., Hunspell) or regular expressions to remove unnecessary characters and correct spelling mistakes.

[0127] 2. Natural Language Processing

[0128] Preprocessed data is subjected to tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis using natural language processing tools (e.g., NLTK, Spacy). This allows for the analysis of the meaning and sentiment of the input data.

[0129] 3. Database matching

[0130] The server queries its internal database to retrieve historical data and related information. Relational database systems (e.g., MySQL®) or NoSQL databases (e.g., MongoDB) are used.

[0131] 4. Generating Feedback

[0132] Based on the acquired information, a generative AI model (e.g., OpenAI's GPT-3®) is used to generate feedback and improvement suggestions.

[0133] 5. Responding to the user

[0134] The generated feedback is sent to the device and displayed to the user.

[0135] database

[0136] The database stores past challenges, feedback, and related data. The server references this database and performs appropriate matching to retrieve information relevant to the user's input.

[0137] Specific example

[0138] The following explains how the system works based on specific cases.

[0139] Example 1: Organizing business challenges

[0140] User: "I need you to identify the reason why the new project is behind schedule."

[0141] Terminal: Receives user input and sends it to the server.

[0142] server:

[0143] Preprocessing of input data: Perform a spell check and clean up phrases like "Please identify the reason why the new project is behind schedule."

[0144] Natural language processing: Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("project," "progress," "delay," "cause") and sentiment (negative).

[0145] Database matching: Search the database to find similar past issues and feedback.

[0146] Feedback generation: Generate common causes of delays (e.g., resource shortages, scheduling issues) and suggestions for improvement.

[0147] Responding to the user: Send feedback to the device and display it to the user.

[0148] Terminal:

[0149] Common causes of project delays include resource shortages and scheduling problems. Specifically, please consider the following improvement suggestions.

[0150] 1. Resource reallocation

[0151] 2. Implementation of progress management tools

[0152] 3. Hold regular progress review meetings.

[0153] In this way, this system analyzes the business challenges entered by users and provides quick and accurate feedback, thereby supporting the efficiency and improvement of business operations.

[0154] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0155] Program processing steps

[0156] Step 1:

[0157] The user enters a work-related issue or question into the text input field on the terminal. For example, "I need help identifying the reason why the new project is behind schedule."

[0158] Input: User's text input

[0159] Output: Raw text data

[0160] Step 2:

[0161] The terminal sends the raw text data received from the user to the server. An HTTP POST request is used for this transmission.

[0162] Input: Raw text data

[0163] Output: HTTP POST request to the server

[0164] Step 3:

[0165] The server preprocesses the received raw text data, performing tasks such as spell checking (e.g., using Hunspel) and removing unwanted characters (e.g., using regular expressions).

[0166] Input: Raw text data

[0167] Data processing:

[0168] Spell check: Corrects spelling mistakes

[0169] Removing unwanted characters: Using regular expressions to remove noise.

[0170] Output: Cleaned-up text data

[0171] Step 4:

[0172] The server performs natural language processing on the cleaned text data. First, it uses tokenization to split the text into lists of words (e.g., NLTK). Next, it performs part-of-speech tagging, named entity recognition (e.g., Spacy), and sentiment analysis.

[0173] Input: Cleaned-up text data

[0174] Data processing:

[0175] Tokenization: Dividing into words or phrases

[0176] Part-of-speech tagging: Adding a part of speech to each word.

[0177] Named entity recognition: Identifying important entities.

[0178] Sentiment analysis: Analyzing the sentiment of text

[0179] Output: Analyzed data (keywords, entities, sentiment)

[0180] Step 5:

[0181] The server queries the database based on the analyzed data to retrieve relevant information. It uses a relational database system (e.g., MySQL) or a NoSQL database (e.g., MongoDB). It prioritizes retrieving past similar cases and feedback information.

[0182] Input: Analyzed data (keywords, entities, sentiment)

[0183] Data Calculation: Database Queries

[0184] Keyword matching, filtering

[0185] Extraction of similar information

[0186] Output: Related Information

[0187] Step 6:

[0188] The server generates feedback based on relevant information. It uses a generative AI model (e.g., OpenAI's GPT-3) to generate appropriate improvement suggestions and answers.

[0189] Input: Related Information

[0190] Data calculation:

[0191] Prompt input to the generative model

[0192] Feedback generation based on the model's output

[0193] Output: Generated feedback

[0194] Step 7:

[0195] The server sends the generated feedback to the terminal. It uses an HTTP POST request to send the feedback data.

[0196] Input: Generated feedback

[0197] Output: HTTP POST request to the terminal

[0198] Step 8:

[0199] The terminal displays feedback received from the server on the user interface. Users can review this feedback and use it to improve their work.

[0200] Input: Feedback received from the server

[0201] Output: Display of feedback

[0202] The above details the processing steps in this system. Each step involves specific data processing and calculations, ultimately providing the user with useful feedback.

[0203] (Application Example 1)

[0204] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0205] In conventional systems, providing rapid and accurate feedback on user input data was a challenge. In particular, in factory settings, real-time analysis and useful feedback are required, but existing systems struggled to meet these demands.

[0206] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0207] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data and analyzing keywords and sentiment, means for comparing with past data and searching for relevant information in a database, means for generating feedback based on the obtained information, means for providing the generated feedback to the user, means for using a generative AI model to generate new feedback based on the analysis results, and means for generating prompt sentences and inputting them into the generative AI model. This enables the provision of quick and accurate feedback to user input, thereby improving the efficiency and effectiveness of operations.

[0208] A "user" is an individual or group that utilizes the system and is responsible for providing input data.

[0209] "Input data" refers to text or other forms of data provided by the user.

[0210] "Preprocessing" refers to the process of cleaning up input data and converting it into a format suitable for natural language processing.

[0211] "Natural language processing" is a technology that analyzes text data to understand its meaning and extract keywords, emotions, and other relevant information.

[0212] "Keywords" refer to particularly important words or phrases from the input data provided by the user.

[0213] "Emotion" refers to the emotional elements and tone contained in the input data, and is the subject of analysis.

[0214] A "database" is a collection of information that stores past data and feedback to facilitate searching.

[0215] "Database matching" refers to the process of comparing input data with existing data in a database and retrieving related information.

[0216] "Feedback" refers to information such as advice and suggestions for improvement that a system provides to the user.

[0217] A "generative AI model" is an algorithm or framework that uses artificial intelligence to automatically generate new feedback and prompts.

[0218] A "prompt statement" is an instruction or initial statement given to a generative AI model, which the model uses to generate a response.

[0219] A "system" is the set of components that receive, process, and provide feedback from a user.

[0220] This invention is implemented as a robotic system within a factory. Specific embodiments are described below.

[0221] System Overview

[0222] This system receives user input and provides quick and appropriate feedback based on it. The system consists of terminals, a server, and a database.

[0223] terminal

[0224] Users use devices such as smartphones, tablets, and smart glasses to input and submit work-related tasks and questions. The device is responsible for sending the input data to the server.

[0225] server

[0226] The server receives the input data and performs the following processing:

[0227] 1. Preprocessing

[0228] The server preprocesses the input data received from the user, removing unnecessary characters and performing spell checks.

[0229] 2. Natural Language Processing

[0230] Natural language processing is applied to the pre-processed data to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. This allows for the analysis of keywords and sentiment.

[0231] 3. Database matching

[0232] The server searches the database and retrieves relevant information from past issues and feedback. It uses TF-IDF and cosine similarity to prioritize and extract the most relevant information.

[0233] 4. Use of Generative AI Models

[0234] Based on the analysis results, prompt sentences are generated and input into a generation AI model (e.g., OpenAI GPT-3). The model then generates new feedback.

[0235] 5. Providing feedback

[0236] The server sends the generated feedback back to the terminal and provides it to the user.

[0237] database

[0238] The database stores past issues, feedback, and related data. The server references this database to search for information relevant to user input.

[0239] Specific example

[0240] The following is an example of how this system works:

[0241] User

[0242] A factory worker enters the message, "Please identify the cause of the production line delay."

[0243] terminal

[0244] Input is received via smartphone or smart glasses and sent to the server.

[0245] server

[0246] Perform a spell check and cleaning to tidy up the phrase "Please identify the cause of the production line delay."

[0247] Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("production line," "delay," "cause") and sentiment (negative).

[0248] The database is searched, and similar cases are found based on past feedback. TF-IDF and cosine similarity are used to prioritize and extract the most relevant information.

[0249] The system provides feedback via a generative AI model, such as, "Possible causes of production line delays include machine malfunctions and labor shortages. Please consider the following improvement measures: strengthen machine inspection and maintenance, reallocate personnel, and revise the production schedule."

[0250] Example of a prompt

[0251] User question: Please identify the cause of the production line delay.

[0252] Please provide suggestions for improvement based on past feedback.

[0253] This allows the system to provide quick and accurate feedback to user input, supporting the streamlining and improvement of operations.

[0254] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0255] Step 1:

[0256] Users input work-related issues and questions using a device (smartphone or smart glasses). The input data is collected by the device. An example of input data is, "Please identify the cause of the delay on the production line."

[0257] Step 2:

[0258] The terminal sends the input data to the server. At this time, the input data is passed to the server in its original text format.

[0259] Step 3:

[0260] The server preprocesses the received input data. Preprocessing includes spell checking and removal of unnecessary characters. For example, it cleans up the sentence "Please identify the cause of the production line delay" by removing spelling mistakes and unnecessary spaces.

[0261] Step 4:

[0262] The server applies natural language processing to the pre-processed data. Specifically, it performs tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. In this step, keywords ("production line," "delay," "cause") and sentiment (negative) are extracted.

[0263] Step 5:

[0264] The server searches the database based on the results of natural language processing. The database contains past issues and feedback information. Using TF-IDF and cosine similarity, the most relevant information is extracted preferentially. This search yields relevant past feedback.

[0265] Step 6:

[0266] The server generates prompt messages based on the analysis results and inputs them into a generating AI model (e.g., OpenAI GPT-3). An example of such a prompt message is: "User question: Please identify the cause of the production line delay. Please provide improvement suggestions based on past feedback."

[0267] Step 7:

[0268] The AI ​​model generates new feedback based on the prompt text. This feedback will include specific improvement suggestions. For example, it might generate: "The delay in the production line may be due to machine failure or labor shortage. Please consider the following improvement suggestions: strengthen machine inspection and maintenance, reallocate personnel, and revise the production schedule."

[0269] Step 8:

[0270] The server sends the generated feedback back to the terminal. The terminal displays the feedback to the user. This allows the user to immediately receive specific suggestions for improvement.

[0271] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0272] Mode for Carrying Out the Invention

[0273] This invention is a system that provides efficient and rapid feedback based on user input, and particularly includes an emotion engine that recognizes the user's emotions and reflects them in the feedback. Specific embodiments of this system will be described below.

[0274] Overview of the Entire System

[0275] This system allows users to input business-related issues and questions using a terminal, and the server processes them and provides appropriate feedback and improvement suggestions. It also incorporates an emotion engine that recognizes the user's emotions and utilizes this information in the feedback. This system is mainly composed of the following components.

[0276] 1. Terminal

[0277] 2. Server

[0278] 3. Database

[0279] 4. Emotion Engine

[0280] The detailed components and their functions will be described.

[0281] Terminal

[0282] The terminal has an interface that receives the user's input and transmits the input to the server. When the user inputs and transmits business-related issues and questions in text form to the terminal, the processing of the system is initiated.

[0283] Server

[0284] The server receives the input data transmitted from the terminal and performs the following processing.

[0285] 1. Pretreatment of Input Data

[0286] Perform spell checking and remove unnecessary characters to clean up the text data.

[0287] 2. Natural Language Processing

[0288] Perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis on the preprocessed data to analyze the meaning and sentiment state of the input data.

[0289] 3. Sentiment Engine

[0290] Determine the user's sentiment state based on the sentiment analysis results of the text. Adjust the feedback content based on the determined sentiment state (e.g., positive, negative, neutral).

[0291] 4. Matching with the Database

[0292] Match with past data and search for relevant information. This allows us to find similar cases and useful information.

[0293] 5. Generation of Feedback

[0294] Generate feedback and improvement suggestions for the user based on the local data and the results of the sentiment engine.

[0295] 6. Response to the User

[0296] Send the generated feedback to the terminal and display it to the user.

[0297] Database

[0298] The database stores past issues, feedback, related data, and sentiment states. The server refers to this database to search for information related to the user's input.

[0299] Sentiment Engine

[0300] The sentiment engine performs sentiment analysis as part of natural language processing to determine the user's sentiment state. For example, if the input text shows a negative sentiment, the feedback is adjusted based on that information to provide a more appropriate and empathetic response.

[0301] Specific Example

[0302] The operation of the system will be described below based on a specific case.

[0303] Example 1: Sorting out business issues

[0304] User: "I want to identify the reasons for the delay in the progress of the new project."

[0305] Terminal: Receives the user's input and sends it to the server.

[0306] Server:

[0307] Preprocessing of input data: Perform spell checking and clean up "I want to identify the reasons for the delay in the progress of the new project."

[0308] Natural language processing: Perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis, and extract keywords ("project", "progress", "delay", "reason") and sentiment (negative).

[0309] Sentiment engine: Based on the sentiment analysis result of the text, determine that the user's sentiment state is negative.

[0310] Verification with the database: Search the database to find similar past issues and feedback.

[0311] Generation of feedback: Generate general causes of delays (such as lack of resources, problems with schedule management, etc.) and improvement plans, and provide empathetic feedback considering the results of the sentiment engine.

[0312] User response: Feedback is sent to the device, and the device displays it to the user.

[0313] Terminal: "Regarding project delays, resource shortages and scheduling issues are likely the most common causes. Please consider the following improvement suggestions:"

[0314] 1. Resource reallocation

[0315] 2. Implementation of progress management tools

[0316] 3. Hold regular progress review meetings.

[0317] In this way, this system, which incorporates an emotion engine, supports the efficiency and improvement of business operations by providing more appropriate feedback that takes user emotions into consideration.

[0318] The following describes the processing flow.

[0319] Step 1:

[0320] Users type work-related issues or questions into their terminals and send them as text. For example, they might type, "I need help identifying the reason why the new project is behind schedule."

[0321] Step 2:

[0322] The terminal receives input data from the user and sends that data to the server.

[0323] Step 3:

[0324] The server preprocesses the data received from the terminal. Specifically, it cleans up the text by performing a spell check and removing unnecessary characters and symbols.

[0325] Step 4:

[0326] The server applies natural language processing (NLP) to the pre-processed data. This step involves the following specific processes:

[0327] Tokenization: Divides input text into words and phrases.

[0328] Part-of-speech tagging: Assign part-of-speech information to each token (e.g., noun, verb, adjective, etc.).

[0329] Named Entity Recognition (NER): Extracts important keywords (e.g., "project," "progress," "delay").

[0330] Sentiment Analysis: Analyzes the emotional tendencies of the entire text to determine whether it is positive, negative, or neutral.

[0331] Step 5:

[0332] The server uses an emotion engine to determine the user's emotional state based on the sentiment analysis results (e.g., if the text indicates a negative emotion, the state is determined to be "negative").

[0333] Step 6:

[0334] The server adjusts the feedback based on the user's emotional state. Specifically, it modifies the feedback to take the user's emotional state into consideration.

[0335] Step 7:

[0336] The server compares the NLP results and the emotion engine results with an internal database. It searches for relevant past cases and feedback and retrieves relevant information from the database.

[0337] Step 8:

[0338] The server generates feedback and improvement suggestions for users based on information obtained from the database. In particular, it creates empathetic feedback that takes into account the user's emotional state.

[0339] Step 9:

[0340] The server sends the generated feedback to the terminal. The terminal receives this feedback and displays it to the user.

[0341] Step 10:

[0342] We review the feedback received from users and decide on the next course of action based on it. For example, we consider and implement specific improvement measures such as "reallocating resources" or "implementing progress management tools."

[0343] (Example 2)

[0344] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0345] Traditional feedback systems often fail to consider user emotions and provide only formulaic responses, leading to decreased user satisfaction and inefficient problem-solving. Furthermore, it's difficult to retrieve relevant information from past data and incorporate it into feedback, potentially resulting in inadequate advice.

[0346] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0347] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data to analyze keywords and emotions, means for determining the emotional state based on the analyzed data, database matching means for comparing with past data and retrieving related information, means for generating feedback based on the obtained information and emotional state, and means for providing the generated feedback to the user. This makes it possible to quickly provide appropriate and empathetic feedback that takes the user's emotions into consideration, thereby improving user satisfaction and the efficiency of problem solving.

[0348] A "user" refers to an entity that uses this system to input information and receive feedback.

[0349] "Input data" refers to the text information that a user provides to the system.

[0350] "Preprocessing" refers to the process of performing cleansing operations on received input data, such as spell checking and removing unnecessary characters.

[0351] "Natural language processing" refers to processes performed on text data, such as tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[0352] "Keywords" are important words or phrases extracted from the input data.

[0353] "Emotion" refers to the user's emotional state (e.g., positive, negative, neutral) analyzed from the input data.

[0354] An "emotion engine" refers to a system component that determines the user's emotional state based on input data and adjusts the feedback accordingly.

[0355] A "database" refers to an information storage system for accumulating past issues, feedback, and related data.

[0356] "Database matching means" refers to a function for comparing and searching received input data with information stored in the database.

[0357] "Feedback" refers to information such as advice, suggestions, and answers provided to the user based on input data and analysis results.

[0358] A "generative AI model" refers to a technology model that utilizes artificial intelligence to perform natural language processing based on input data and generate appropriate responses.

[0359] This invention is a system that provides efficient and rapid feedback based on user input, and in particular includes an emotion engine that recognizes the user's emotions and reflects them in the feedback. A specific embodiment for this system is shown below.

[0360] System Configuration

[0361] This system consists of the following main components:

[0362] 1. Terminal

[0363] 2. Server

[0364] 3. Database

[0365] 4. Emotional Engine

[0366] terminal

[0367] A terminal is a device with an interface that receives user input and sends that input to a server. System processing begins when the user inputs and sends work-related tasks or questions in text format to the terminal. Terminals can take the form of personal computers, smartphones, tablets, etc.

[0368] server

[0369] The server receives the input data sent from the terminal and performs the following processing:

[0370] 1. Preprocessing of input data

[0371] The software used is the open-source spell checker library "pyspellchecker".

[0372] 2. Natural Language Processing (NLP)

[0373] The pre-processed data will undergo tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. Specifically, natural language processing libraries such as "SpaCy" and "NLTK" will be used.

[0374] 3. Emotional Engine

[0375] "VADER" and "TextBlob" are used to determine the user's emotional state based on the sentiment analysis results.

[0376] 4. Database matching

[0377] Search existing databases to find similar past cases and related information. For this purpose, use database management systems (DBMS) such as "PostgreSQL" or "MongoDB".

[0378] 5. Generating Feedback

[0379] Using a generative AI model (for example, "GPT-4®"), feedback and improvement suggestions are generated for the user based on the available data and the results of the emotion engine.

[0380] 6. Responding to the user

[0381] The generated feedback is sent to the device and displayed to the user.

[0382] database

[0383] The database is used to store past challenges, feedback, related data, and emotional states. The server can refer to this database to retrieve information related to user input.

[0384] Emotional Engine

[0385] The emotion engine performs sentiment analysis as part of natural language processing and has the function of determining the user's emotional state. For example, if the input text indicates a negative emotion, it adjusts the feedback based on that information and provides an empathetic response.

[0386] Specific example

[0387] The following are examples of specific system operations:

[0388] Example: Organizing business issues

[0389] User: "I need you to identify the reason why the new project is behind schedule."

[0390] Terminal: Receives user input and sends it to the server.

[0391] server:

[0392] Input data preprocessing: Perform spell checking using "pyspellchecker".

[0393] Natural language processing: We use "SpaCy" to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[0394] The emotion engine "VADER" is used to determine the emotion of the text as "negative".

[0395] Database matching: Search the "PostgreSQL" database to find similar issues and feedback from the past.

[0396] Feedback generation: Using "GPT-4," feedback that takes user emotions into consideration is generated.

[0397] Response to user: Send feedback to the device, and the device will display it to the user: "Regarding the project's progress delays, resource shortages and scheduling issues are likely the most common causes. Please consider the following improvements: 1. Reallocate resources 2. Implement progress management tools 3. Hold regular progress review meetings"

[0398] Example of a prompt

[0399] Examples of prompt statements used as generative AI models (e.g., GPT-4):

[0400] In response to the user's question, "Please identify the reasons why the progress of the new project is behind schedule," generate emotionally sensitive feedback. The feedback should include concrete, actionable improvement suggestions and reflect the user's emotional state.

[0401] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0402] Step 1:

[0403] The user enters the information.

[0404] Users input work-related issues or questions into the terminal in text format. For example, they might input, "I need help identifying the reason why the new project is behind schedule." The input data is saved to the terminal in text format.

[0405] Step 2:

[0406] The terminal sends the input to the server.

[0407] The terminal sends user input data to the server in real time. The data is sent in JSON format using the HTTP or WebSockets protocol. The input data arrives at the server.

[0408] Step 3:

[0409] The server preprocesses the input data.

[0410] The server preprocesses the input data it receives. This preprocessing includes spell checking and removal of unnecessary characters. For example, it uses the "pyspellchecker" library to perform spell checking and clean the input data. The preprocessed data is obtained in a clean text format.

[0411] Step 4:

[0412] The server processes the input data using natural language processing.

[0413] The server performs natural language processing (NLP) on pre-processed data. Using tools like "SpaCy" and "NLTK," it performs tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. For example, for the text "Reasons why the progress of the new project is behind schedule," it extracts keywords ("project," "progress," "delay," "cause") and obtains a sentiment analysis result (negative). This provides the analyzed text data and sentiment state.

[0414] Step 5:

[0415] The server uses an emotion engine to perform sentiment analysis.

[0416] The server uses an emotion engine to determine the user's emotional state based on the results of natural language processing. It extracts the emotional state from the analyzed data using libraries such as "VADER" and "TextBlob". For example, the text data "Reasons why the new project is behind schedule" might be determined to be negative. The emotional state is then output as either positive, negative, or neutral.

[0417] Step 6:

[0418] The server checks the database.

[0419] The server searches for relevant past information in the database based on the analyzed data and emotional state. It uses databases such as PostgreSQL or MongoDB to search for relevant past issues and feedback. For example, it retrieves data related to "project progress delays" from the past and uses that to obtain useful information. The search extracts the most relevant data.

[0420] Step 7:

[0421] The server generates feedback.

[0422] The server generates feedback for the user, taking into account relevant information and emotional states acquired by the server. A generative AI model (e.g., GPT-4) is used here. For example, it might generate feedback that includes specific suggestions, such as, "Regarding project delays, resource shortages and scheduling problems are likely common causes." The generated feedback is provided in text format.

[0423] Step 8:

[0424] The server sends feedback to the terminal.

[0425] The server sends the generated feedback to the terminal. The data is sent again using the HTTP or WebSockets protocol in JSON format. The feedback arrives at the terminal.

[0426] Step 9:

[0427] The device displays feedback to the user.

[0428] The device displays the feedback it has received to the user. For example, it might display a message on the screen saying, "Regarding project delays, resource shortages and scheduling problems are likely the most common causes. Please consider the following improvements: 1. Reallocate resources 2. Implement a progress management tool 3. Hold regular progress review meetings." The user is then able to review the feedback.

[0429] The above is a detailed explanation of the processing steps of this system.

[0430] (Application Example 2)

[0431] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0432] In physical stores, it is essential to efficiently collect customer feedback and provide appropriate responses based on their emotional state. In particular, prompt and appropriate responses to negative feedback are crucial for improving customer satisfaction. Furthermore, utilizing past feedback data to propose more effective improvement measures is vital. The current system does not adequately consider emotional states when providing feedback, and this needs improvement.

[0433] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0434] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data and analyzing keywords and emotions, means for comparing with past data and retrieving relevant information from a database, means for adjusting feedback based on the user's emotional state, means for generating feedback based on the obtained information, and means for providing the generated feedback to the user and presenting empathetic responses according to their emotional state. This makes it possible to provide efficient and appropriate feedback that takes into account the emotional state of customers in physical stores.

[0435] "Means of receiving user input" refers to devices or interfaces that allow users to input feedback or questions in text format using a terminal and receive that data.

[0436] "Methods for preprocessing received input data" refer to methods of preparing text data received from users for analysis by performing spell checks, removing unnecessary characters, and other similar actions.

[0437] "Means for applying natural language processing to pre-processed data to analyze keywords and sentiment" refers to a technology that analyzes pre-processed text data through tokenization, part-of-speech tagging, named entity recognition, sentiment analysis, etc., to determine important keywords and the user's emotional state.

[0438] A "database matching means for comparing with past data and searching for related information" is a method for comparing user input data with accumulated past data to search for similar cases or relevant information.

[0439] "Means of adjusting feedback based on the user's emotional state" refers to technologies that appropriately modify the content and expression of feedback provided based on the analyzed user's emotional state (e.g., positive, negative, neutral).

[0440] "Means of generating feedback based on acquired information" refers to methods of creating specific feedback and improvement suggestions for users based on relevant information obtained from a database and the results of an analysis of their emotional state.

[0441] "A means of providing generated feedback to the user and offering empathetic responses according to their emotional state" refers to a method of communicating generated feedback to the user and responding using empathetic language, especially to users in negative emotional states.

[0442] System Overview

[0443] This invention constructs a system that collects customer feedback in physical stores and provides appropriate responses based on the customer's emotional state. The system receives user input and performs preprocessing, natural language processing, sentiment analysis, database matching, feedback generation, and presentation.

[0444] Detailed system configuration

[0445] 1. Hardware Configuration

[0446] Terminal:

[0447] A smartphone, smart glasses, or head-mounted display.

[0448] These devices are used by users to input feedback in text format.

[0449] server:

[0450] Responsible for receiving, processing, analyzing, and generating feedback.

[0451] A backend server with the necessary software installed.

[0452] Database:

[0453] A database for storing past feedback, customer information, and past countermeasures.

[0454] 2. Software Configuration

[0455] Natural language processing libraries:

[0456] We use NLP libraries such as SpaCy and NLTK to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[0457] Emotional engine:

[0458] A software module that analyzes the emotional state of user input text and determines its emotional state, such as positive, negative, or neutral.

[0459] Application Server:

[0460] The feedback processing logic is executed, and feedback is generated using a generative AI model. Frameworks such as Django and Flask can be used.

[0461] Database management system:

[0462] We use database management systems such as MySQL and PostgreSQL to manage past feedback and customer information.

[0463] System operation example

[0464] Feedback input process

[0465] Customers use their smartphones or smart glasses to enter feedback such as: "The service was slow. The wait time was too long."

[0466] Server Processing Flow

[0467] 1. Preprocessing of input data:

[0468] The server receives feedback from users and performs spell checking and removes unnecessary characters.

[0469] 2. Natural Language Processing:

[0470] The pre-processed text data is tokenized, tagged with parts of speech, recognized as a named entity, and subjected to sentiment analysis to extract keywords (e.g., "service," "slow," "waiting time") and sentiment states (e.g., negative).

[0471] 3. Database matching:

[0472] Based on the extracted keywords and emotional states, the system searches a past feedback database to retrieve highly relevant information.

[0473] 4. Feedback generation:

[0474] Using a generative AI model, we generate empathetic feedback for customers by comparing it with past feedback and considering their emotional state.

[0475] Example: We will take your feedback into consideration and strive to improve the speed of our service. We will offer you a special discount on your next visit.

[0476] Introduction of specific examples

[0477] Examples of prompt statements include the following:

[0478] "The service was slow. The wait time was too long."

[0479] The server processes this input, uses an emotion engine to determine negative emotions, matches it with relevant information in the database, and then generates empathetic feedback.

[0480] By combining these components, it becomes possible to efficiently process customer feedback in physical stores and respond based on their emotional state.

[0481] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0482] Step 1:

[0483] Users enter feedback using their devices.

[0484] Input: Users enter feedback in text format (e.g., "The service was slow. The wait time was too long.").

[0485] Output: Feedback data input from the terminal.

[0486] Specific operation: The user enters feedback in text format using a device such as a smartphone or smart glasses. The device then sends this input data to the server.

[0487] Step 2:

[0488] The server preprocesses the input data it receives.

[0489] Input: Feedback data sent from the device.

[0490] Output: Pre-processed, clean text data.

[0491] Specific operation: The server preprocesses the received feedback data by performing spell checks and removing unnecessary characters, preparing it for analysis.

[0492] Step 3:

[0493] The server applies natural language processing to the pre-processed data to analyze keywords and sentiment.

[0494] Input: Pre-processed, clean text data.

[0495] Output: Analyzed keywords and emotional states.

[0496] Specific operation: The server uses an NLP library (e.g., SpaCy, NLTK) to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis, and extracts keywords (e.g., "service," "slow," "wait time") and sentiment states (e.g., negative).

[0497] Step 4:

[0498] The server performs database matching based on the analyzed data.

[0499] Input: Analyzed keywords and emotional state.

[0500] Output: Related information in the database.

[0501] Specific operation: The server searches the database management system (e.g., MySQL, PostgreSQL) and retrieves relevant information from past feedback data. This allows it to collect similar cases and relevant information.

[0502] Step 5:

[0503] The server generates feedback based on the information it receives.

[0504] Input: Relevant information retrieved from the database, analyzed emotional state.

[0505] Output: Generated feedback.

[0506] Specific operation: The server utilizes a generative AI model, taking into account emotional states and database information to generate feedback to provide to the user. For example, it might create an empathetic message in response to a negative emotional state.

[0507] Step 6:

[0508] The server sends the generated feedback to the terminal and provides it to the user.

[0509] Input: Generated feedback.

[0510] Output: A feedback message that the user can see on their device.

[0511] Specific operation: The server sends the generated feedback message to the terminal, which then displays it to the user. This allows the user to receive an appropriate response based on their emotional state.

[0512] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0513] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0514] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0515] [Second Embodiment]

[0516] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0517] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0518] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0519] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0520] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0521] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0522] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0523] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0524] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0525] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0526] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0527] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0528] Modes for carrying out the invention

[0529] This invention is a system that provides efficient and rapid feedback based on user input, thereby promoting business improvement. A specific embodiment of this system is described below.

[0530] System Overview

[0531] This system allows users to input work-related issues and questions using a terminal, and the server processes that information to provide appropriate feedback and improvement suggestions. The system consists of the following main components:

[0532] 1. Terminal

[0533] 2. Server

[0534] 3. Database

[0535] This section describes the detailed components and their functions.

[0536] terminal

[0537] The terminal has an interface that receives user input and sends that input to the server. The system starts processing when the user enters tasks or questions in text format into the terminal.

[0538] server

[0539] The server receives the input data sent from the terminal and performs the following processing:

[0540] 1. Preprocessing of input data

[0541] It cleans up text data by performing spell checks and removing unnecessary characters.

[0542] 2. Natural Language Processing

[0543] The pre-processed data is subjected to tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis to analyze the meaning of the input data.

[0544] 3. Database matching

[0545] By cross-referencing with past data and searching for relevant information, it becomes possible to find similar cases and useful information.

[0546] 4. Generating Feedback

[0547] Based on the matching results, feedback and improvement suggestions for the user are generated.

[0548] 5. Responding to the user

[0549] The generated feedback is sent to the device and displayed to the user.

[0550] database

[0551] The database stores past issues, feedback, and related data. The server refers to this database to search for information relevant to user input.

[0552] Specific example

[0553] The following explains how the system works based on specific cases.

[0554] Example 1: Organizing business challenges

[0555] User: "I need you to identify the reason why the new project is behind schedule."

[0556] Terminal: Receives user input and sends it to the server.

[0557] server:

[0558] Preprocessing of input data: Perform a spell check and clean up phrases like "Please identify the reason why the new project is behind schedule."

[0559] Natural language processing: Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("project," "progress," "delay," "cause") and sentiment (negative).

[0560] Database matching: Search the database to find similar past issues and feedback.

[0561] Feedback generation: Generate common causes of delays (e.g., resource shortages, scheduling issues) and suggestions for improvement.

[0562] User response: Feedback is sent to the device, and the device displays it to the user.

[0563] Terminal: "Common causes of project delays include resource shortages and scheduling problems. Specifically, please consider the following improvement suggestions."

[0564] 1. Resource reallocation

[0565] 2. Implementation of progress management tools

[0566] 3. Hold regular progress review meetings.

[0567] In this way, this system analyzes the business challenges entered by users and provides quick and accurate feedback, thereby supporting the efficiency and improvement of business operations.

[0568] The following describes the processing flow.

[0569] Step 1:

[0570] Users type work-related issues or questions into their terminals and send them as text. For example, they might type, "I need help identifying the reason why the new project is behind schedule."

[0571] Step 2:

[0572] The terminal receives input data from the user. The received data is sent to the server in its original form.

[0573] Step 3:

[0574] The server preprocesses the data received from the terminal. Specifically, it cleans up the text by performing a spell check and removing unnecessary characters and symbols.

[0575] Step 4:

[0576] The server applies natural language processing (NLP) to the pre-processed text data. This step involves the following specific processes:

[0577] Tokenization: Dividing text into words or phrases.

[0578] Part-of-speech tagging: Assigns part-of-speech information to each token.

[0579] Named Entity Recognition (NER): Extracts important keywords (e.g., "project," "progress," "delay," etc.).

[0580] Sentiment Analysis: Analyzes the overall sentiment of the text and determines whether it is positive, negative, or neutral.

[0581] Step 5:

[0582] The server uses NLP results to compare them with an internal database. It searches for relevant past cases and feedback and retrieves relevant information from the database. This matching is performed using SQL queries, etc.

[0583] Step 6:

[0584] The server generates feedback and improvement suggestions for the user based on information retrieved from the database. Here, an AI algorithm operates to construct appropriate feedback based on highly relevant information.

[0585] Step 7:

[0586] The server sends the generated feedback to the terminal. The terminal receives this feedback and displays it to the user.

[0587] Step 8:

[0588] We review the feedback received from users and decide on the next course of action based on it. For example, we consider and implement specific improvement measures such as "reallocating resources" or "implementing progress management tools."

[0589] (Example 1)

[0590] Next, we will describe Example 1. 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."

[0591] Traditional business improvement systems have faced challenges in providing rapid and efficient feedback to user input. In particular, insufficient pre-processing of text data, natural language processing, and cross-referencing with historical data often result in inadequate feedback. Furthermore, the lack of emotional analysis meant that feedback tailored to user needs could not be provided.

[0592] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0593] In this invention, the server includes means for preprocessing received input data, means for applying natural language processing to the preprocessed data and analyzing keywords and sentiment, means for comparing with past data and retrieving relevant information from a database, means for generating feedback using a generative model based on the obtained information, and means for providing the generated feedback to the user. This makes it possible to provide rapid and accurate feedback to user input.

[0594] A "user" refers to an individual or organization that uses the system to input business-related issues or questions.

[0595] "Means of receiving" refers to the interface and method by which the system takes in data entered by the user.

[0596] "Preprocessing methods" refer to the processes and techniques used to prepare received text data into a format that is easy to analyze, such as by performing spell checks and removing unnecessary characters.

[0597] "Natural language processing" refers to techniques that analyze text data using methods such as tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis to understand its meaning and sentiment.

[0598] "Database matching means" refers to the process and system for a system to compare past data with current input data and retrieve relevant information.

[0599] A "generative model" refers to an algorithm or system that automatically generates appropriate feedback or suggestions from input data, such as a generative AI model.

[0600] "Means of generating feedback" refers to the processes and technologies for creating feedback and suggestions to provide to users, based on database matching results and the output of generative models.

[0601] "Means of providing feedback" refers to the interface and methods for communicating generated feedback and suggestions to users.

[0602] Modes for carrying out the invention

[0603] This invention is a system that provides efficient and rapid feedback based on user input, thereby promoting business improvement. In this system, users input work-related issues and questions using a terminal, and a server processes this information to provide appropriate feedback and improvement suggestions. A specific embodiment of this system is described below.

[0604] System Overview

[0605] This system consists of the following main components:

[0606] 1. Terminal

[0607] 2. Server

[0608] 3. Database

[0609] terminal

[0610] The terminal has an interface that receives user input and sends that input to the server. The system starts processing when the user enters tasks or questions in text format into the terminal. Specifically, a web browser or dedicated application is used as the user interface, and the input data is sent to the server via an HTTP POST request.

[0611] server

[0612] The server receives the input data sent from the terminal and performs the following processing:

[0613] 1. Preprocessing of input data

[0614] Use spell-checking tools (e.g., Hunspell) or regular expressions to remove unnecessary characters and correct spelling mistakes.

[0615] 2. Natural Language Processing

[0616] Preprocessed data is subjected to tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis using natural language processing tools (e.g., NLTK, Spacy). This allows for the analysis of the meaning and sentiment of the input data.

[0617] 3. Database matching

[0618] The server queries its internal database to retrieve historical data and related information. Relational database systems (e.g., MySQL) or NoSQL databases (e.g., MongoDB) are used.

[0619] 4. Generating Feedback

[0620] Based on the acquired information, a generative AI model (e.g., OpenAI's GPT-3) is used to generate feedback and improvement suggestions.

[0621] 5. Responding to the user

[0622] The generated feedback is sent to the device and displayed to the user.

[0623] database

[0624] The database stores past challenges, feedback, and related data. The server references this database and performs appropriate matching to retrieve information relevant to the user's input.

[0625] Specific example

[0626] The following explains how the system works based on specific cases.

[0627] Example 1: Organizing business challenges

[0628] User: "I need you to identify the reason why the new project is behind schedule."

[0629] Terminal: Receives user input and sends it to the server.

[0630] server:

[0631] Preprocessing of input data: Perform a spell check and clean up phrases like "Please identify the reason why the new project is behind schedule."

[0632] Natural language processing: Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("project," "progress," "delay," "cause") and sentiment (negative).

[0633] Database matching: Search the database to find similar past issues and feedback.

[0634] Feedback generation: Generate common causes of delays (e.g., resource shortages, scheduling issues) and suggestions for improvement.

[0635] Responding to the user: Send feedback to the device and display it to the user.

[0636] Terminal:

[0637] Common causes of project delays include resource shortages and scheduling problems. Specifically, please consider the following improvement suggestions.

[0638] 1. Resource reallocation

[0639] 2. Implementation of progress management tools

[0640] 3. Hold regular progress review meetings.

[0641] In this way, this system analyzes the business challenges entered by users and provides quick and accurate feedback, thereby supporting the efficiency and improvement of business operations.

[0642] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0643] Program processing steps

[0644] Step 1:

[0645] The user enters a work-related issue or question into the text input field on the terminal. For example, "I need help identifying the reason why the new project is behind schedule."

[0646] Input: User's text input

[0647] Output: Raw text data

[0648] Step 2:

[0649] The terminal sends the raw text data received from the user to the server. An HTTP POST request is used for this transmission.

[0650] Input: Raw text data

[0651] Output: HTTP POST request to the server

[0652] Step 3:

[0653] The server preprocesses the received raw text data, performing tasks such as spell checking (e.g., using Hunspel) and removing unwanted characters (e.g., using regular expressions).

[0654] Input: Raw text data

[0655] Data processing:

[0656] Spell check: Corrects spelling mistakes

[0657] Removing unwanted characters: Using regular expressions to remove noise.

[0658] Output: Cleaned-up text data

[0659] Step 4:

[0660] The server performs natural language processing on the cleaned text data. First, it uses tokenization to split the text into lists of words (e.g., NLTK). Next, it performs part-of-speech tagging, named entity recognition (e.g., Spacy), and sentiment analysis.

[0661] Input: Cleaned-up text data

[0662] Data processing:

[0663] Tokenization: Dividing into words or phrases

[0664] Part-of-speech tagging: Adding a part of speech to each word.

[0665] Named entity recognition: Identifying important entities.

[0666] Sentiment analysis: Analyzing the sentiment of text

[0667] Output: Analyzed data (keywords, entities, sentiment)

[0668] Step 5:

[0669] The server queries the database based on the analyzed data to retrieve relevant information. It uses a relational database system (e.g., MySQL) or a NoSQL database (e.g., MongoDB). It prioritizes retrieving past similar cases and feedback information.

[0670] Input: Analyzed data (keywords, entities, sentiment)

[0671] Data Calculation: Database Queries

[0672] Keyword matching, filtering

[0673] Extraction of similar information

[0674] Output: Related Information

[0675] Step 6:

[0676] The server generates feedback based on relevant information. It uses a generative AI model (e.g., OpenAI's GPT-3) to generate appropriate improvement suggestions and answers.

[0677] Input: Related Information

[0678] Data calculation:

[0679] Prompt input to the generative model

[0680] Feedback generation based on the model's output

[0681] Output: Generated feedback

[0682] Step 7:

[0683] The server sends the generated feedback to the terminal. It uses an HTTP POST request to send the feedback data.

[0684] Input: Generated feedback

[0685] Output: HTTP POST request to the terminal

[0686] Step 8:

[0687] The terminal displays feedback received from the server on the user interface. Users can review this feedback and use it to improve their work.

[0688] Input: Feedback received from the server

[0689] Output: Display of feedback

[0690] The above details the processing steps in this system. Each step involves specific data processing and calculations, ultimately providing the user with useful feedback.

[0691] (Application Example 1)

[0692] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0693] In conventional systems, providing rapid and accurate feedback on user input data was a challenge. In particular, in factory settings, real-time analysis and useful feedback are required, but existing systems struggled to meet these demands.

[0694] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0695] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data and analyzing keywords and sentiment, means for comparing with past data and searching for relevant information in a database, means for generating feedback based on the obtained information, means for providing the generated feedback to the user, means for using a generative AI model to generate new feedback based on the analysis results, and means for generating prompt sentences and inputting them into the generative AI model. This enables the provision of quick and accurate feedback to user input, thereby improving the efficiency and effectiveness of operations.

[0696] A "user" is an individual or group that utilizes the system and is responsible for providing input data.

[0697] "Input data" refers to text or other forms of data provided by the user.

[0698] "Preprocessing" refers to the process of cleaning up input data and converting it into a format suitable for natural language processing.

[0699] "Natural language processing" is a technology that analyzes text data to understand its meaning and extract keywords, emotions, and other relevant information.

[0700] "Keywords" refer to particularly important words or phrases from the input data provided by the user.

[0701] "Emotion" refers to the emotional elements and tone contained in the input data, and is the subject of analysis.

[0702] A "database" is a collection of information that stores past data and feedback to facilitate searching.

[0703] "Database matching" refers to the process of comparing input data with existing data in a database and retrieving related information.

[0704] "Feedback" refers to information such as advice and suggestions for improvement that a system provides to the user.

[0705] A "generative AI model" is an algorithm or framework that uses artificial intelligence to automatically generate new feedback and prompts.

[0706] A "prompt statement" is an instruction or initial statement given to a generative AI model, which the model uses to generate a response.

[0707] A "system" is the set of components that receive, process, and provide feedback from a user.

[0708] This invention is implemented as a robotic system within a factory. Specific embodiments are described below.

[0709] System Overview

[0710] This system receives user input and provides quick and appropriate feedback based on it. The system consists of terminals, a server, and a database.

[0711] terminal

[0712] Users use devices such as smartphones, tablets, and smart glasses to input and submit work-related tasks and questions. The device is responsible for sending the input data to the server.

[0713] server

[0714] The server receives the input data and performs the following processing:

[0715] 1. Preprocessing

[0716] The server preprocesses the input data received from the user, removing unnecessary characters and performing spell checks.

[0717] 2. Natural Language Processing

[0718] Natural language processing is applied to the pre-processed data to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. This allows for the analysis of keywords and sentiment.

[0719] 3. Database matching

[0720] The server searches the database and retrieves relevant information from past issues and feedback. It uses TF-IDF and cosine similarity to prioritize and extract the most relevant information.

[0721] 4. Use of Generative AI Models

[0722] Based on the analysis results, prompt sentences are generated and input into a generation AI model (e.g., OpenAI GPT-3). The model then generates new feedback.

[0723] 5. Providing feedback

[0724] The server sends the generated feedback back to the terminal and provides it to the user.

[0725] database

[0726] The database stores past issues, feedback, and related data. The server references this database to search for information relevant to user input.

[0727] Specific example

[0728] The following is an example of how this system works:

[0729] User

[0730] A factory worker enters the message, "Please identify the cause of the production line delay."

[0731] terminal

[0732] Input is received via smartphone or smart glasses and sent to the server.

[0733] server

[0734] Perform a spell check and cleaning to tidy up the phrase "Please identify the cause of the production line delay."

[0735] Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("production line," "delay," "cause") and sentiment (negative).

[0736] The database is searched, and similar cases are found based on past feedback. TF-IDF and cosine similarity are used to prioritize and extract the most relevant information.

[0737] The system provides feedback via a generative AI model, such as, "Possible causes of production line delays include machine malfunctions and labor shortages. Please consider the following improvement measures: strengthen machine inspection and maintenance, reallocate personnel, and revise the production schedule."

[0738] Example of a prompt

[0739] User question: Please identify the cause of the production line delay.

[0740] Please provide suggestions for improvement based on past feedback.

[0741] This allows the system to provide quick and accurate feedback to user input, supporting the streamlining and improvement of operations.

[0742] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0743] Step 1:

[0744] Users input work-related issues and questions using a device (smartphone or smart glasses). The input data is collected by the device. An example of input data is, "Please identify the cause of the delay on the production line."

[0745] Step 2:

[0746] The terminal sends the input data to the server. At this time, the input data is passed to the server in its original text format.

[0747] Step 3:

[0748] The server preprocesses the received input data. Preprocessing includes spell checking and removal of unnecessary characters. For example, it cleans up the sentence "Please identify the cause of the production line delay" by removing spelling mistakes and unnecessary spaces.

[0749] Step 4:

[0750] The server applies natural language processing to the pre-processed data. Specifically, it performs tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. In this step, keywords ("production line," "delay," "cause") and sentiment (negative) are extracted.

[0751] Step 5:

[0752] The server searches the database based on the results of natural language processing. The database contains past issues and feedback information. Using TF-IDF and cosine similarity, the most relevant information is extracted preferentially. This search yields relevant past feedback.

[0753] Step 6:

[0754] The server generates prompt messages based on the analysis results and inputs them into a generating AI model (e.g., OpenAI GPT-3). An example of such a prompt message is: "User question: Please identify the cause of the production line delay. Please provide improvement suggestions based on past feedback."

[0755] Step 7:

[0756] The AI ​​model generates new feedback based on the prompt text. This feedback will include specific improvement suggestions. For example, it might generate: "The delay in the production line may be due to machine failure or labor shortage. Please consider the following improvement suggestions: strengthen machine inspection and maintenance, reallocate personnel, and revise the production schedule."

[0757] Step 8:

[0758] The server sends the generated feedback back to the terminal. The terminal displays the feedback to the user. This allows the user to immediately receive specific suggestions for improvement.

[0759] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0760] Modes for carrying out the invention

[0761] This invention is a system that provides efficient and rapid feedback based on user input, and in particular includes an emotion engine that recognizes the user's emotions and reflects them in the feedback. Specific embodiments of this system are described below.

[0762] System Overview

[0763] This system allows users to input work-related issues and questions using a terminal, and the server processes this information to provide appropriate feedback and improvement suggestions. It also incorporates an emotion engine that recognizes user emotions and utilizes that information in the feedback. This system primarily consists of the following components:

[0764] 1. Terminal

[0765] 2. Server

[0766] 3. Database

[0767] 4. Emotional Engine

[0768] This section describes the detailed components and their functions.

[0769] terminal

[0770] The terminal has an interface that receives user input and sends that input to the server. The system starts processing when the user enters and sends work-related tasks or questions in text format to the terminal.

[0771] server

[0772] The server receives the input data sent from the terminal and performs the following processing:

[0773] 1. Preprocessing of input data

[0774] It cleans up text data by performing spell checks and removing unnecessary characters.

[0775] 2. Natural Language Processing

[0776] The pre-processed data is subjected to tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis to analyze the meaning and emotional state of the input data.

[0777] 3. Emotional Engine

[0778] The system determines the user's emotional state based on the sentiment analysis results of the text. The feedback content is then adjusted based on the determined emotional state (e.g., positive, negative, neutral).

[0779] 4. Database matching

[0780] By cross-referencing with past data and searching for relevant information, it becomes possible to find similar cases and useful information.

[0781] 5. Generating Feedback

[0782] Based on the available data and the results from the emotion engine, it generates feedback and improvement suggestions to provide to the user.

[0783] 6. Responding to the user

[0784] The generated feedback is sent to the device and displayed to the user.

[0785] database

[0786] The database stores past challenges, feedback, related data, and emotional states. The server refers to this database to retrieve information relevant to user input.

[0787] Emotional Engine

[0788] The emotion engine performs sentiment analysis as part of natural language processing to determine the user's emotional state. For example, if the input text indicates a negative emotion, it adjusts the feedback based on that information to provide a more appropriate and empathetic response.

[0789] Specific example

[0790] The following explains how the system works based on specific cases.

[0791] Example 1: Organizing business challenges

[0792] User: "I need you to identify the reason why the new project is behind schedule."

[0793] Terminal: Receives user input and sends it to the server.

[0794] server:

[0795] Preprocessing of input data: Perform a spell check and clean up phrases like "Please identify the reason why the new project is behind schedule."

[0796] Natural language processing: Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("project," "progress," "delay," "cause") and sentiment (negative).

[0797] Emotion Engine: Based on the sentiment analysis results of the text, it determines that the user's emotional state is negative.

[0798] Database matching: Search the database to find similar past issues and feedback.

[0799] Feedback generation: Generate common causes of delays (e.g., resource shortages, scheduling problems) and suggestions for improvement, and provide empathetic feedback considering the results of the emotion engine.

[0800] User response: Feedback is sent to the device, and the device displays it to the user.

[0801] Terminal: "Regarding project delays, resource shortages and scheduling issues are likely the most common causes. Please consider the following improvement suggestions:"

[0802] 1. Resource reallocation

[0803] 2. Implementation of progress management tools

[0804] 3. Hold regular progress review meetings.

[0805] In this way, this system, which incorporates an emotion engine, supports the efficiency and improvement of business operations by providing more appropriate feedback that takes user emotions into consideration.

[0806] The following describes the processing flow.

[0807] Step 1:

[0808] Users type work-related issues or questions into their terminals and send them as text. For example, they might type, "I need help identifying the reason why the new project is behind schedule."

[0809] Step 2:

[0810] The terminal receives input data from the user and sends that data to the server.

[0811] Step 3:

[0812] The server preprocesses the data received from the terminal. Specifically, it cleans up the text by performing a spell check and removing unnecessary characters and symbols.

[0813] Step 4:

[0814] The server applies natural language processing (NLP) to the pre-processed data. This step involves the following specific processes:

[0815] Tokenization: Divides input text into words and phrases.

[0816] Part-of-speech tagging: Assign part-of-speech information to each token (e.g., noun, verb, adjective, etc.).

[0817] Named Entity Recognition (NER): Extracts important keywords (e.g., "project," "progress," "delay").

[0818] Sentiment Analysis: Analyzes the emotional tendencies of the entire text to determine whether it is positive, negative, or neutral.

[0819] Step 5:

[0820] The server uses an emotion engine to determine the user's emotional state based on the sentiment analysis results (e.g., if the text indicates a negative emotion, the state is determined to be "negative").

[0821] Step 6:

[0822] The server adjusts the feedback based on the user's emotional state. Specifically, it modifies the feedback to take the user's emotional state into consideration.

[0823] Step 7:

[0824] The server compares the NLP results and the emotion engine results with an internal database. It searches for relevant past cases and feedback and retrieves relevant information from the database.

[0825] Step 8:

[0826] The server generates feedback and improvement suggestions for users based on information obtained from the database. In particular, it creates empathetic feedback that takes into account the user's emotional state.

[0827] Step 9:

[0828] The server sends the generated feedback to the terminal. The terminal receives this feedback and displays it to the user.

[0829] Step 10:

[0830] We review the feedback received from users and decide on the next course of action based on it. For example, we consider and implement specific improvement measures such as "reallocating resources" or "implementing progress management tools."

[0831] (Example 2)

[0832] Next, we will describe Example 2. 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".

[0833] Traditional feedback systems often fail to consider user emotions and provide only formulaic responses, leading to decreased user satisfaction and inefficient problem-solving. Furthermore, it's difficult to retrieve relevant information from past data and incorporate it into feedback, potentially resulting in inadequate advice.

[0834] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0835] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data to analyze keywords and emotions, means for determining the emotional state based on the analyzed data, database matching means for comparing with past data and retrieving related information, means for generating feedback based on the obtained information and emotional state, and means for providing the generated feedback to the user. This makes it possible to quickly provide appropriate and empathetic feedback that takes the user's emotions into consideration, thereby improving user satisfaction and the efficiency of problem solving.

[0836] A "user" refers to an entity that uses this system to input information and receive feedback.

[0837] "Input data" refers to the text information that a user provides to the system.

[0838] "Preprocessing" refers to the process of performing cleansing operations on received input data, such as spell checking and removing unnecessary characters.

[0839] "Natural language processing" refers to processes performed on text data, such as tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[0840] "Keywords" are important words or phrases extracted from the input data.

[0841] "Emotion" refers to the user's emotional state (e.g., positive, negative, neutral) analyzed from the input data.

[0842] An "emotion engine" refers to a system component that determines the user's emotional state based on input data and adjusts the feedback accordingly.

[0843] A "database" refers to an information storage system for accumulating past issues, feedback, and related data.

[0844] "Database matching means" refers to a function for comparing and searching received input data with information stored in the database.

[0845] "Feedback" refers to information such as advice, suggestions, and answers provided to the user based on input data and analysis results.

[0846] A "generative AI model" refers to a technology model that utilizes artificial intelligence to perform natural language processing based on input data and generate appropriate responses.

[0847] This invention is a system that provides efficient and rapid feedback based on user input, and in particular includes an emotion engine that recognizes the user's emotions and reflects them in the feedback. A specific embodiment for this system is shown below.

[0848] System Configuration

[0849] This system consists of the following main components:

[0850] 1. Terminal

[0851] 2. Server

[0852] 3. Database

[0853] 4. Emotional Engine

[0854] terminal

[0855] A terminal is a device with an interface that receives user input and sends that input to a server. System processing begins when the user inputs and sends work-related tasks or questions in text format to the terminal. Terminals can take the form of personal computers, smartphones, tablets, etc.

[0856] server

[0857] The server receives the input data sent from the terminal and performs the following processing:

[0858] 1. Preprocessing of input data

[0859] The software used is the open-source spell checker library "pyspellchecker".

[0860] 2. Natural Language Processing (NLP)

[0861] The pre-processed data will undergo tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. Specifically, natural language processing libraries such as "SpaCy" and "NLTK" will be used.

[0862] 3. Emotional Engine

[0863] "VADER" and "TextBlob" are used to determine the user's emotional state based on the sentiment analysis results.

[0864] 4. Database matching

[0865] Search existing databases to find similar past cases and related information. For this purpose, use database management systems (DBMS) such as "PostgreSQL" or "MongoDB".

[0866] 5. Generating Feedback

[0867] Using a generative AI model (for example, "GPT-4"), feedback and improvement suggestions are generated for the user based on the available data and the results of the emotion engine.

[0868] 6. Responding to the user

[0869] The generated feedback is sent to the device and displayed to the user.

[0870] database

[0871] The database is used to store past challenges, feedback, related data, and emotional states. The server can refer to this database to retrieve information related to user input.

[0872] Emotional Engine

[0873] The emotion engine performs sentiment analysis as part of natural language processing and has the function of determining the user's emotional state. For example, if the input text indicates a negative emotion, it adjusts the feedback based on that information and provides an empathetic response.

[0874] Specific example

[0875] The following are examples of specific system operations:

[0876] Example: Organizing business issues

[0877] User: "I need you to identify the reason why the new project is behind schedule."

[0878] Terminal: Receives user input and sends it to the server.

[0879] server:

[0880] Input data preprocessing: Perform spell checking using "pyspellchecker".

[0881] Natural language processing: We use "SpaCy" to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[0882] The emotion engine "VADER" is used to determine the emotion of the text as "negative".

[0883] Database matching: Search the "PostgreSQL" database to find similar issues and feedback from the past.

[0884] Feedback generation: Using "GPT-4," feedback that takes user emotions into consideration is generated.

[0885] Response to user: Send feedback to the device, and the device will display it to the user: "Regarding the project's progress delays, resource shortages and scheduling issues are likely the most common causes. Please consider the following improvements: 1. Reallocate resources 2. Implement progress management tools 3. Hold regular progress review meetings"

[0886] Example of a prompt

[0887] Examples of prompt statements used as generative AI models (e.g., GPT-4):

[0888] In response to the user's question, "Please identify the reasons why the progress of the new project is behind schedule," generate emotionally sensitive feedback. The feedback should include concrete, actionable improvement suggestions and reflect the user's emotional state.

[0889] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0890] Step 1:

[0891] The user enters the information.

[0892] Users input work-related issues or questions into the terminal in text format. For example, they might input, "I need help identifying the reason why the new project is behind schedule." The input data is saved to the terminal in text format.

[0893] Step 2:

[0894] The terminal sends the input to the server.

[0895] The terminal sends user input data to the server in real time. The data is sent in JSON format using the HTTP or WebSockets protocol. The input data arrives at the server.

[0896] Step 3:

[0897] The server preprocesses the input data.

[0898] The server preprocesses the input data it receives. This preprocessing includes spell checking and removal of unnecessary characters. For example, it uses the "pyspellchecker" library to perform spell checking and clean the input data. The preprocessed data is obtained in a clean text format.

[0899] Step 4:

[0900] The server processes the input data using natural language processing.

[0901] The server performs natural language processing (NLP) on pre-processed data. Using tools like "SpaCy" and "NLTK," it performs tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. For example, for the text "Reasons why the progress of the new project is behind schedule," it extracts keywords ("project," "progress," "delay," "cause") and obtains a sentiment analysis result (negative). This provides the analyzed text data and sentiment state.

[0902] Step 5:

[0903] The server uses an emotion engine to perform sentiment analysis.

[0904] The server uses an emotion engine to determine the user's emotional state based on the results of natural language processing. It extracts the emotional state from the analyzed data using libraries such as "VADER" and "TextBlob". For example, the text data "Reasons why the new project is behind schedule" might be determined to be negative. The emotional state is then output as either positive, negative, or neutral.

[0905] Step 6:

[0906] The server checks the database.

[0907] The server searches for relevant past information in the database based on the analyzed data and emotional state. It uses databases such as PostgreSQL or MongoDB to search for relevant past issues and feedback. For example, it retrieves data related to "project progress delays" from the past and uses that to obtain useful information. The search extracts the most relevant data.

[0908] Step 7:

[0909] The server generates feedback.

[0910] The server generates feedback for the user, taking into account relevant information and emotional states acquired by the server. A generative AI model (e.g., GPT-4) is used here. For example, it might generate feedback that includes specific suggestions, such as, "Regarding project delays, resource shortages and scheduling problems are likely common causes." The generated feedback is provided in text format.

[0911] Step 8:

[0912] The server sends feedback to the terminal.

[0913] The server sends the generated feedback to the terminal. The data is sent again using the HTTP or WebSockets protocol in JSON format. The feedback arrives at the terminal.

[0914] Step 9:

[0915] The device displays feedback to the user.

[0916] The device displays the feedback it has received to the user. For example, it might display a message on the screen saying, "Regarding project delays, resource shortages and scheduling problems are likely the most common causes. Please consider the following improvements: 1. Reallocate resources 2. Implement a progress management tool 3. Hold regular progress review meetings." The user is then able to review the feedback.

[0917] The above is a detailed explanation of the processing steps of this system.

[0918] (Application Example 2)

[0919] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0920] In physical stores, it is essential to efficiently collect customer feedback and provide appropriate responses based on their emotional state. In particular, prompt and appropriate responses to negative feedback are crucial for improving customer satisfaction. Furthermore, utilizing past feedback data to propose more effective improvement measures is vital. The current system does not adequately consider emotional states when providing feedback, and this needs improvement.

[0921] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0922] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data and analyzing keywords and emotions, means for comparing with past data and retrieving relevant information from a database, means for adjusting feedback based on the user's emotional state, means for generating feedback based on the obtained information, and means for providing the generated feedback to the user and presenting empathetic responses according to their emotional state. This makes it possible to provide efficient and appropriate feedback that takes into account the emotional state of customers in physical stores.

[0923] "Means of receiving user input" refers to devices or interfaces that allow users to input feedback or questions in text format using a terminal and receive that data.

[0924] "Methods for preprocessing received input data" refer to methods of preparing text data received from users for analysis by performing spell checks, removing unnecessary characters, and other similar actions.

[0925] "Means for applying natural language processing to pre-processed data to analyze keywords and sentiment" refers to a technology that analyzes pre-processed text data through tokenization, part-of-speech tagging, named entity recognition, sentiment analysis, etc., to determine important keywords and the user's emotional state.

[0926] A "database matching means for comparing with past data and searching for related information" is a method for comparing user input data with accumulated past data to search for similar cases or relevant information.

[0927] "Means of adjusting feedback based on the user's emotional state" refers to technologies that appropriately modify the content and expression of feedback provided based on the analyzed user's emotional state (e.g., positive, negative, neutral).

[0928] "Means of generating feedback based on acquired information" refers to methods of creating specific feedback and improvement suggestions for users based on relevant information obtained from a database and the results of an analysis of their emotional state.

[0929] "A means of providing generated feedback to the user and offering empathetic responses according to their emotional state" refers to a method of communicating generated feedback to the user and responding using empathetic language, especially to users in negative emotional states.

[0930] System Overview

[0931] This invention constructs a system that collects customer feedback in physical stores and provides appropriate responses based on the customer's emotional state. The system receives user input and performs preprocessing, natural language processing, sentiment analysis, database matching, feedback generation, and presentation.

[0932] Detailed system configuration

[0933] 1. Hardware Configuration

[0934] Terminal:

[0935] A smartphone, smart glasses, or head-mounted display.

[0936] These devices are used by users to input feedback in text format.

[0937] server:

[0938] Responsible for receiving, processing, analyzing, and generating feedback.

[0939] A backend server with the necessary software installed.

[0940] Database:

[0941] A database for storing past feedback, customer information, and past countermeasures.

[0942] 2. Software Configuration

[0943] Natural language processing libraries:

[0944] We use NLP libraries such as SpaCy and NLTK to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[0945] Emotional engine:

[0946] A software module that analyzes the emotional state of user input text and determines its emotional state, such as positive, negative, or neutral.

[0947] Application Server:

[0948] The feedback processing logic is executed, and feedback is generated using a generative AI model. Frameworks such as Django and Flask can be used.

[0949] Database management system:

[0950] We use database management systems such as MySQL and PostgreSQL to manage past feedback and customer information.

[0951] System operation example

[0952] Feedback input process

[0953] Customers use their smartphones or smart glasses to enter feedback such as: "The service was slow. The wait time was too long."

[0954] Server Processing Flow

[0955] 1. Preprocessing of input data:

[0956] The server receives feedback from users and performs spell checking and removes unnecessary characters.

[0957] 2. Natural Language Processing:

[0958] The pre-processed text data is tokenized, tagged with parts of speech, recognized as a named entity, and subjected to sentiment analysis to extract keywords (e.g., "service," "slow," "waiting time") and sentiment states (e.g., negative).

[0959] 3. Database matching:

[0960] Based on the extracted keywords and emotional states, the system searches a past feedback database to retrieve highly relevant information.

[0961] 4. Feedback generation:

[0962] Using a generative AI model, we generate empathetic feedback for customers by comparing it with past feedback and considering their emotional state.

[0963] Example: We will take your feedback into consideration and strive to improve the speed of our service. We will offer you a special discount on your next visit.

[0964] Introduction of specific examples

[0965] Examples of prompt statements include the following:

[0966] "The service was slow. The wait time was too long."

[0967] The server processes this input, uses an emotion engine to determine negative emotions, matches it with relevant information in the database, and then generates empathetic feedback.

[0968] By combining these components, it becomes possible to efficiently process customer feedback in physical stores and respond based on their emotional state.

[0969] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0970] Step 1:

[0971] Users enter feedback using their devices.

[0972] Input: Users enter feedback in text format (e.g., "The service was slow. The wait time was too long.").

[0973] Output: Feedback data input from the terminal.

[0974] Specific operation: The user enters feedback in text format using a device such as a smartphone or smart glasses. The device then sends this input data to the server.

[0975] Step 2:

[0976] The server preprocesses the input data it receives.

[0977] Input: Feedback data sent from the device.

[0978] Output: Pre-processed, clean text data.

[0979] Specific operation: The server preprocesses the received feedback data by performing spell checks and removing unnecessary characters, preparing it for analysis.

[0980] Step 3:

[0981] The server applies natural language processing to the pre-processed data to analyze keywords and sentiment.

[0982] Input: Pre-processed, clean text data.

[0983] Output: Analyzed keywords and emotional states.

[0984] Specific operation: The server uses an NLP library (e.g., SpaCy, NLTK) to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis, and extracts keywords (e.g., "service," "slow," "wait time") and sentiment states (e.g., negative).

[0985] Step 4:

[0986] The server performs database matching based on the analyzed data.

[0987] Input: Analyzed keywords and emotional state.

[0988] Output: Related information in the database.

[0989] Specific operation: The server searches the database management system (e.g., MySQL, PostgreSQL) and retrieves relevant information from past feedback data. This allows it to collect similar cases and relevant information.

[0990] Step 5:

[0991] The server generates feedback based on the information it receives.

[0992] Input: Relevant information retrieved from the database, analyzed emotional state.

[0993] Output: Generated feedback.

[0994] Specific operation: The server utilizes a generative AI model, taking into account emotional states and database information to generate feedback to provide to the user. For example, it might create an empathetic message in response to a negative emotional state.

[0995] Step 6:

[0996] The server sends the generated feedback to the terminal and provides it to the user.

[0997] Input: Generated feedback.

[0998] Output: A feedback message that the user can see on their device.

[0999] Specific operation: The server sends the generated feedback message to the terminal, which then displays it to the user. This allows the user to receive an appropriate response based on their emotional state.

[1000] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1001] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1002] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1003] [Third Embodiment]

[1004] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1005] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1006] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1007] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1008] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1009] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1010] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1011] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1012] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1013] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1014] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1015] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1016] Modes for carrying out the invention

[1017] This invention is a system that provides efficient and rapid feedback based on user input, thereby promoting business improvement. A specific embodiment of this system is described below.

[1018] System Overview

[1019] This system allows users to input work-related issues and questions using a terminal, and the server processes that information to provide appropriate feedback and improvement suggestions. The system consists of the following main components:

[1020] 1. Terminal

[1021] 2. Server

[1022] 3. Database

[1023] This section describes the detailed components and their functions.

[1024] terminal

[1025] The terminal has an interface that receives user input and sends that input to the server. The system starts processing when the user enters tasks or questions in text format into the terminal.

[1026] server

[1027] The server receives the input data sent from the terminal and performs the following processing:

[1028] 1. Preprocessing of input data

[1029] It cleans up text data by performing spell checks and removing unnecessary characters.

[1030] 2. Natural Language Processing

[1031] The pre-processed data is subjected to tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis to analyze the meaning of the input data.

[1032] 3. Database matching

[1033] By cross-referencing with past data and searching for relevant information, it becomes possible to find similar cases and useful information.

[1034] 4. Generating Feedback

[1035] Based on the matching results, feedback and improvement suggestions for the user are generated.

[1036] 5. Responding to the user

[1037] The generated feedback is sent to the device and displayed to the user.

[1038] database

[1039] The database stores past issues, feedback, and related data. The server refers to this database to search for information relevant to user input.

[1040] Specific example

[1041] The following explains how the system works based on specific cases.

[1042] Example 1: Organizing business challenges

[1043] User: "I need you to identify the reason why the new project is behind schedule."

[1044] Terminal: Receives user input and sends it to the server.

[1045] server:

[1046] Preprocessing of input data: Perform a spell check and clean up phrases like "Please identify the reason why the new project is behind schedule."

[1047] Natural language processing: Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("project," "progress," "delay," "cause") and sentiment (negative).

[1048] Database matching: Search the database to find similar past issues and feedback.

[1049] Feedback generation: Generate common causes of delays (e.g., resource shortages, scheduling issues) and suggestions for improvement.

[1050] User response: Feedback is sent to the device, and the device displays it to the user.

[1051] Terminal: "Common causes of project delays include resource shortages and scheduling problems. Specifically, please consider the following improvement suggestions."

[1052] 1. Resource reallocation

[1053] 2. Implementation of progress management tools

[1054] 3. Hold regular progress review meetings.

[1055] In this way, this system analyzes the business challenges entered by users and provides quick and accurate feedback, thereby supporting the efficiency and improvement of business operations.

[1056] The following describes the processing flow.

[1057] Step 1:

[1058] Users type work-related issues or questions into their terminals and send them as text. For example, they might type, "I need help identifying the reason why the new project is behind schedule."

[1059] Step 2:

[1060] The terminal receives input data from the user. The received data is sent to the server in its original form.

[1061] Step 3:

[1062] The server preprocesses the data received from the terminal. Specifically, it cleans up the text by performing a spell check and removing unnecessary characters and symbols.

[1063] Step 4:

[1064] The server applies natural language processing (NLP) to the pre-processed text data. This step involves the following specific processes:

[1065] Tokenization: Dividing text into words or phrases.

[1066] Part-of-speech tagging: Assigns part-of-speech information to each token.

[1067] Named Entity Recognition (NER): Extracts important keywords (e.g., "project," "progress," "delay," etc.).

[1068] Sentiment Analysis: Analyzes the overall sentiment of the text and determines whether it is positive, negative, or neutral.

[1069] Step 5:

[1070] The server uses NLP results to compare them with an internal database. It searches for relevant past cases and feedback and retrieves relevant information from the database. This matching is performed using SQL queries, etc.

[1071] Step 6:

[1072] The server generates feedback and improvement suggestions for the user based on information retrieved from the database. Here, an AI algorithm operates to construct appropriate feedback based on highly relevant information.

[1073] Step 7:

[1074] The server sends the generated feedback to the terminal. The terminal receives this feedback and displays it to the user.

[1075] Step 8:

[1076] We review the feedback received from users and decide on the next course of action based on it. For example, we consider and implement specific improvement measures such as "reallocating resources" or "implementing progress management tools."

[1077] (Example 1)

[1078] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1079] Traditional business improvement systems have faced challenges in providing rapid and efficient feedback to user input. In particular, insufficient pre-processing of text data, natural language processing, and cross-referencing with historical data often result in inadequate feedback. Furthermore, the lack of emotional analysis meant that feedback tailored to user needs could not be provided.

[1080] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1081] In this invention, the server includes means for preprocessing received input data, means for applying natural language processing to the preprocessed data and analyzing keywords and sentiment, means for comparing with past data and retrieving relevant information from a database, means for generating feedback using a generative model based on the obtained information, and means for providing the generated feedback to the user. This makes it possible to provide rapid and accurate feedback to user input.

[1082] A "user" refers to an individual or organization that uses the system to input business-related issues or questions.

[1083] "Means of receiving" refers to the interface and method by which the system takes in data entered by the user.

[1084] "Preprocessing methods" refer to the processes and techniques used to prepare received text data into a format that is easy to analyze, such as by performing spell checks and removing unnecessary characters.

[1085] "Natural language processing" refers to techniques that analyze text data using methods such as tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis to understand its meaning and sentiment.

[1086] "Database matching means" refers to the process and system for a system to compare past data with current input data and retrieve relevant information.

[1087] A "generative model" refers to an algorithm or system that automatically generates appropriate feedback or suggestions from input data, such as a generative AI model.

[1088] "Means of generating feedback" refers to the processes and technologies for creating feedback and suggestions to provide to users, based on database matching results and the output of generative models.

[1089] "Means of providing feedback" refers to the interface and methods for communicating generated feedback and suggestions to users.

[1090] Modes for carrying out the invention

[1091] This invention is a system that provides efficient and rapid feedback based on user input, thereby promoting business improvement. In this system, users input work-related issues and questions using a terminal, and a server processes this information to provide appropriate feedback and improvement suggestions. A specific embodiment of this system is described below.

[1092] System Overview

[1093] This system consists of the following main components:

[1094] 1. Terminal

[1095] 2. Server

[1096] 3. Database

[1097] terminal

[1098] The terminal has an interface that receives user input and sends that input to the server. The system starts processing when the user enters tasks or questions in text format into the terminal. Specifically, a web browser or dedicated application is used as the user interface, and the input data is sent to the server via an HTTP POST request.

[1099] server

[1100] The server receives the input data sent from the terminal and performs the following processing:

[1101] 1. Preprocessing of input data

[1102] Use spell-checking tools (e.g., Hunspell) or regular expressions to remove unnecessary characters and correct spelling mistakes.

[1103] 2. Natural Language Processing

[1104] Preprocessed data is subjected to tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis using natural language processing tools (e.g., NLTK, Spacy). This allows for the analysis of the meaning and sentiment of the input data.

[1105] 3. Database matching

[1106] The server queries its internal database to retrieve historical data and related information. Relational database systems (e.g., MySQL) or NoSQL databases (e.g., MongoDB) are used.

[1107] 4. Generating Feedback

[1108] Based on the acquired information, a generative AI model (e.g., OpenAI's GPT-3) is used to generate feedback and improvement suggestions.

[1109] 5. Responding to the user

[1110] The generated feedback is sent to the device and displayed to the user.

[1111] database

[1112] The database stores past challenges, feedback, and related data. The server references this database and performs appropriate matching to retrieve information relevant to the user's input.

[1113] Specific example

[1114] The following explains how the system works based on specific cases.

[1115] Example 1: Organizing business challenges

[1116] User: "I need you to identify the reason why the new project is behind schedule."

[1117] Terminal: Receives user input and sends it to the server.

[1118] server:

[1119] Preprocessing of input data: Perform a spell check and clean up phrases like "Please identify the reason why the new project is behind schedule."

[1120] Natural language processing: Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("project," "progress," "delay," "cause") and sentiment (negative).

[1121] Database matching: Search the database to find similar past issues and feedback.

[1122] Feedback generation: Generate common causes of delays (e.g., resource shortages, scheduling issues) and suggestions for improvement.

[1123] Responding to the user: Send feedback to the device and display it to the user.

[1124] Terminal:

[1125] Common causes of project delays include resource shortages and scheduling problems. Specifically, please consider the following improvement suggestions.

[1126] 1. Resource reallocation

[1127] 2. Implementation of progress management tools

[1128] 3. Hold regular progress review meetings.

[1129] In this way, this system analyzes the business challenges entered by users and provides quick and accurate feedback, thereby supporting the efficiency and improvement of business operations.

[1130] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1131] Program processing steps

[1132] Step 1:

[1133] The user enters a work-related issue or question into the text input field on the terminal. For example, "I need help identifying the reason why the new project is behind schedule."

[1134] Input: User's text input

[1135] Output: Raw text data

[1136] Step 2:

[1137] The terminal sends the raw text data received from the user to the server. An HTTP POST request is used for this transmission.

[1138] Input: Raw text data

[1139] Output: HTTP POST request to the server

[1140] Step 3:

[1141] The server preprocesses the received raw text data, performing tasks such as spell checking (e.g., using Hunspel) and removing unwanted characters (e.g., using regular expressions).

[1142] Input: Raw text data

[1143] Data processing:

[1144] Spell check: Corrects spelling mistakes

[1145] Removing unwanted characters: Using regular expressions to remove noise.

[1146] Output: Cleaned-up text data

[1147] Step 4:

[1148] The server performs natural language processing on the cleaned text data. First, it uses tokenization to split the text into lists of words (e.g., NLTK). Next, it performs part-of-speech tagging, named entity recognition (e.g., Spacy), and sentiment analysis.

[1149] Input: Cleaned-up text data

[1150] Data processing:

[1151] Tokenization: Dividing into words or phrases

[1152] Part-of-speech tagging: Adding a part of speech to each word.

[1153] Named entity recognition: Identifying important entities.

[1154] Sentiment analysis: Analyzing the sentiment of text

[1155] Output: Analyzed data (keywords, entities, sentiment)

[1156] Step 5:

[1157] The server queries the database based on the analyzed data to retrieve relevant information. It uses a relational database system (e.g., MySQL) or a NoSQL database (e.g., MongoDB). It prioritizes retrieving past similar cases and feedback information.

[1158] Input: Analyzed data (keywords, entities, sentiment)

[1159] Data Calculation: Database Queries

[1160] Keyword matching, filtering

[1161] Extraction of similar information

[1162] Output: Related Information

[1163] Step 6:

[1164] The server generates feedback based on relevant information. It uses a generative AI model (e.g., OpenAI's GPT-3) to generate appropriate improvement suggestions and answers.

[1165] Input: Related Information

[1166] Data calculation:

[1167] Prompt input to the generative model

[1168] Feedback generation based on the model's output

[1169] Output: Generated feedback

[1170] Step 7:

[1171] The server sends the generated feedback to the terminal. It uses an HTTP POST request to send the feedback data.

[1172] Input: Generated feedback

[1173] Output: HTTP POST request to the terminal

[1174] Step 8:

[1175] The terminal displays feedback received from the server on the user interface. Users can review this feedback and use it to improve their work.

[1176] Input: Feedback received from the server

[1177] Output: Display of feedback

[1178] The above details the processing steps in this system. Each step involves specific data processing and calculations, ultimately providing the user with useful feedback.

[1179] (Application Example 1)

[1180] Next, we will explain Application Example 1. In the following explanation, 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."

[1181] In conventional systems, providing rapid and accurate feedback on user input data was a challenge. In particular, in factory settings, real-time analysis and useful feedback are required, but existing systems struggled to meet these demands.

[1182] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1183] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data and analyzing keywords and sentiment, means for comparing with past data and searching for relevant information in a database, means for generating feedback based on the obtained information, means for providing the generated feedback to the user, means for using a generative AI model to generate new feedback based on the analysis results, and means for generating prompt sentences and inputting them into the generative AI model. This enables the provision of quick and accurate feedback to user input, thereby improving the efficiency and effectiveness of operations.

[1184] A "user" is an individual or group that utilizes the system and is responsible for providing input data.

[1185] "Input data" refers to text or other forms of data provided by the user.

[1186] "Preprocessing" refers to the process of cleaning up input data and converting it into a format suitable for natural language processing.

[1187] "Natural language processing" is a technology that analyzes text data to understand its meaning and extract keywords, emotions, and other relevant information.

[1188] "Keywords" refer to particularly important words or phrases from the input data provided by the user.

[1189] "Emotion" refers to the emotional elements and tone contained in the input data, and is the subject of analysis.

[1190] A "database" is a collection of information that stores past data and feedback to facilitate searching.

[1191] "Database matching" refers to the process of comparing input data with existing data in a database and retrieving related information.

[1192] "Feedback" refers to information such as advice and suggestions for improvement that a system provides to the user.

[1193] A "generative AI model" is an algorithm or framework that uses artificial intelligence to automatically generate new feedback and prompts.

[1194] A "prompt statement" is an instruction or initial statement given to a generative AI model, which the model uses to generate a response.

[1195] A "system" is the set of components that receive, process, and provide feedback from a user.

[1196] This invention is implemented as a robotic system within a factory. Specific embodiments are described below.

[1197] System Overview

[1198] This system receives user input and provides quick and appropriate feedback based on it. The system consists of terminals, a server, and a database.

[1199] terminal

[1200] Users use devices such as smartphones, tablets, and smart glasses to input and submit work-related tasks and questions. The device is responsible for sending the input data to the server.

[1201] server

[1202] The server receives the input data and performs the following processing:

[1203] 1. Preprocessing

[1204] The server preprocesses the input data received from the user, removing unnecessary characters and performing spell checks.

[1205] 2. Natural Language Processing

[1206] Natural language processing is applied to the pre-processed data to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. This allows for the analysis of keywords and sentiment.

[1207] 3. Database matching

[1208] The server searches the database and retrieves relevant information from past issues and feedback. It uses TF-IDF and cosine similarity to prioritize and extract the most relevant information.

[1209] 4. Use of Generative AI Models

[1210] Based on the analysis results, prompt sentences are generated and input into a generation AI model (e.g., OpenAI GPT-3). The model then generates new feedback.

[1211] 5. Providing feedback

[1212] The server sends the generated feedback back to the terminal and provides it to the user.

[1213] database

[1214] The database stores past issues, feedback, and related data. The server references this database to search for information relevant to user input.

[1215] Specific example

[1216] The following is an example of how this system works:

[1217] User

[1218] A factory worker enters the message, "Please identify the cause of the production line delay."

[1219] terminal

[1220] Input is received via smartphone or smart glasses and sent to the server.

[1221] server

[1222] Perform a spell check and cleaning to tidy up the phrase "Please identify the cause of the production line delay."

[1223] Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("production line," "delay," "cause") and sentiment (negative).

[1224] The database is searched, and similar cases are found based on past feedback. TF-IDF and cosine similarity are used to prioritize and extract the most relevant information.

[1225] The system provides feedback via a generative AI model, such as, "Possible causes of production line delays include machine malfunctions and labor shortages. Please consider the following improvement measures: strengthen machine inspection and maintenance, reallocate personnel, and revise the production schedule."

[1226] Example of a prompt

[1227] User question: Please identify the cause of the production line delay.

[1228] Please provide suggestions for improvement based on past feedback.

[1229] This allows the system to provide quick and accurate feedback to user input, supporting the streamlining and improvement of operations.

[1230] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1231] Step 1:

[1232] Users input work-related issues and questions using a device (smartphone or smart glasses). The input data is collected by the device. An example of input data is, "Please identify the cause of the delay on the production line."

[1233] Step 2:

[1234] The terminal sends the input data to the server. At this time, the input data is passed to the server in its original text format.

[1235] Step 3:

[1236] The server preprocesses the received input data. Preprocessing includes spell checking and removal of unnecessary characters. For example, it cleans up the sentence "Please identify the cause of the production line delay" by removing spelling mistakes and unnecessary spaces.

[1237] Step 4:

[1238] The server applies natural language processing to the pre-processed data. Specifically, it performs tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. In this step, keywords ("production line," "delay," "cause") and sentiment (negative) are extracted.

[1239] Step 5:

[1240] The server searches the database based on the results of natural language processing. The database contains past issues and feedback information. Using TF-IDF and cosine similarity, the most relevant information is extracted preferentially. This search yields relevant past feedback.

[1241] Step 6:

[1242] The server generates prompt messages based on the analysis results and inputs them into a generating AI model (e.g., OpenAI GPT-3). An example of such a prompt message is: "User question: Please identify the cause of the production line delay. Please provide improvement suggestions based on past feedback."

[1243] Step 7:

[1244] The AI ​​model generates new feedback based on the prompt text. This feedback will include specific improvement suggestions. For example, it might generate: "The delay in the production line may be due to machine failure or labor shortage. Please consider the following improvement suggestions: strengthen machine inspection and maintenance, reallocate personnel, and revise the production schedule."

[1245] Step 8:

[1246] The server sends the generated feedback back to the terminal. The terminal displays the feedback to the user. This allows the user to immediately receive specific suggestions for improvement.

[1247] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1248] Modes for carrying out the invention

[1249] This invention is a system that provides efficient and rapid feedback based on user input, and in particular includes an emotion engine that recognizes the user's emotions and reflects them in the feedback. Specific embodiments of this system are described below.

[1250] System Overview

[1251] This system allows users to input work-related issues and questions using a terminal, and the server processes this information to provide appropriate feedback and improvement suggestions. It also incorporates an emotion engine that recognizes user emotions and utilizes that information in the feedback. This system primarily consists of the following components:

[1252] 1. Terminal

[1253] 2. Server

[1254] 3. Database

[1255] 4. Emotional Engine

[1256] This section describes the detailed components and their functions.

[1257] terminal

[1258] The terminal has an interface that receives user input and sends that input to the server. The system starts processing when the user enters and sends work-related tasks or questions in text format to the terminal.

[1259] server

[1260] The server receives the input data sent from the terminal and performs the following processing:

[1261] 1. Preprocessing of input data

[1262] It cleans up text data by performing spell checks and removing unnecessary characters.

[1263] 2. Natural Language Processing

[1264] The pre-processed data is subjected to tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis to analyze the meaning and emotional state of the input data.

[1265] 3. Emotional Engine

[1266] The system determines the user's emotional state based on the sentiment analysis results of the text. The feedback content is then adjusted based on the determined emotional state (e.g., positive, negative, neutral).

[1267] 4. Database matching

[1268] By cross-referencing with past data and searching for relevant information, it becomes possible to find similar cases and useful information.

[1269] 5. Generating Feedback

[1270] Based on the available data and the results from the emotion engine, it generates feedback and improvement suggestions to provide to the user.

[1271] 6. Responding to the user

[1272] The generated feedback is sent to the device and displayed to the user.

[1273] database

[1274] The database stores past challenges, feedback, related data, and emotional states. The server refers to this database to retrieve information relevant to user input.

[1275] Emotional Engine

[1276] The emotion engine performs sentiment analysis as part of natural language processing to determine the user's emotional state. For example, if the input text indicates a negative emotion, it adjusts the feedback based on that information to provide a more appropriate and empathetic response.

[1277] Specific example

[1278] The following explains how the system works based on specific cases.

[1279] Example 1: Organizing business challenges

[1280] User: "I need you to identify the reason why the new project is behind schedule."

[1281] Terminal: Receives user input and sends it to the server.

[1282] server:

[1283] Preprocessing of input data: Perform a spell check and clean up phrases like "Please identify the reason why the new project is behind schedule."

[1284] Natural language processing: Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("project," "progress," "delay," "cause") and sentiment (negative).

[1285] Emotion Engine: Based on the sentiment analysis results of the text, it determines that the user's emotional state is negative.

[1286] Database matching: Search the database to find similar past issues and feedback.

[1287] Feedback generation: Generate common causes of delays (e.g., resource shortages, scheduling problems) and suggestions for improvement, and provide empathetic feedback considering the results of the emotion engine.

[1288] User response: Feedback is sent to the device, and the device displays it to the user.

[1289] Terminal: "Regarding project delays, resource shortages and scheduling issues are likely the most common causes. Please consider the following improvement suggestions:"

[1290] 1. Resource reallocation

[1291] 2. Implementation of progress management tools

[1292] 3. Hold regular progress review meetings.

[1293] In this way, this system, which incorporates an emotion engine, supports the efficiency and improvement of business operations by providing more appropriate feedback that takes user emotions into consideration.

[1294] The following describes the processing flow.

[1295] Step 1:

[1296] Users type work-related issues or questions into their terminals and send them as text. For example, they might type, "I need help identifying the reason why the new project is behind schedule."

[1297] Step 2:

[1298] The terminal receives input data from the user and sends that data to the server.

[1299] Step 3:

[1300] The server preprocesses the data received from the terminal. Specifically, it cleans up the text by performing a spell check and removing unnecessary characters and symbols.

[1301] Step 4:

[1302] The server applies natural language processing (NLP) to the pre-processed data. This step involves the following specific processes:

[1303] Tokenization: Divides input text into words and phrases.

[1304] Part-of-speech tagging: Assign part-of-speech information to each token (e.g., noun, verb, adjective, etc.).

[1305] Named Entity Recognition (NER): Extracts important keywords (e.g., "project," "progress," "delay").

[1306] Sentiment Analysis: Analyzes the emotional tendencies of the entire text to determine whether it is positive, negative, or neutral.

[1307] Step 5:

[1308] The server uses an emotion engine to determine the user's emotional state based on the sentiment analysis results (e.g., if the text indicates a negative emotion, the state is determined to be "negative").

[1309] Step 6:

[1310] The server adjusts the feedback based on the user's emotional state. Specifically, it modifies the feedback to take the user's emotional state into consideration.

[1311] Step 7:

[1312] The server compares the NLP results and the emotion engine results with an internal database. It searches for relevant past cases and feedback and retrieves relevant information from the database.

[1313] Step 8:

[1314] The server generates feedback and improvement suggestions for users based on information obtained from the database. In particular, it creates empathetic feedback that takes into account the user's emotional state.

[1315] Step 9:

[1316] The server sends the generated feedback to the terminal. The terminal receives this feedback and displays it to the user.

[1317] Step 10:

[1318] We review the feedback received from users and decide on the next course of action based on it. For example, we consider and implement specific improvement measures such as "reallocating resources" or "implementing progress management tools."

[1319] (Example 2)

[1320] Next, we will describe Example 2. 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."

[1321] Traditional feedback systems often fail to consider user emotions and provide only formulaic responses, leading to decreased user satisfaction and inefficient problem-solving. Furthermore, it's difficult to retrieve relevant information from past data and incorporate it into feedback, potentially resulting in inadequate advice.

[1322] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1323] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data to analyze keywords and emotions, means for determining the emotional state based on the analyzed data, database matching means for comparing with past data and retrieving related information, means for generating feedback based on the obtained information and emotional state, and means for providing the generated feedback to the user. This makes it possible to quickly provide appropriate and empathetic feedback that takes the user's emotions into consideration, thereby improving user satisfaction and the efficiency of problem solving.

[1324] A "user" refers to an entity that uses this system to input information and receive feedback.

[1325] "Input data" refers to the text information that a user provides to the system.

[1326] "Preprocessing" refers to the process of performing cleansing operations on received input data, such as spell checking and removing unnecessary characters.

[1327] "Natural language processing" refers to processes performed on text data, such as tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[1328] "Keywords" are important words or phrases extracted from the input data.

[1329] "Emotion" refers to the user's emotional state (e.g., positive, negative, neutral) analyzed from the input data.

[1330] An "emotion engine" refers to a system component that determines the user's emotional state based on input data and adjusts the feedback accordingly.

[1331] A "database" refers to an information storage system for accumulating past issues, feedback, and related data.

[1332] "Database matching means" refers to a function for comparing and searching received input data with information stored in the database.

[1333] "Feedback" refers to information such as advice, suggestions, and answers provided to the user based on input data and analysis results.

[1334] A "generative AI model" refers to a technology model that utilizes artificial intelligence to perform natural language processing based on input data and generate appropriate responses.

[1335] This invention is a system that provides efficient and rapid feedback based on user input, and in particular includes an emotion engine that recognizes the user's emotions and reflects them in the feedback. A specific embodiment for this system is shown below.

[1336] System Configuration

[1337] This system consists of the following main components:

[1338] 1. Terminal

[1339] 2. Server

[1340] 3. Database

[1341] 4. Emotional Engine

[1342] terminal

[1343] A terminal is a device with an interface that receives user input and sends that input to a server. System processing begins when the user inputs and sends work-related tasks or questions in text format to the terminal. Terminals can take the form of personal computers, smartphones, tablets, etc.

[1344] server

[1345] The server receives the input data sent from the terminal and performs the following processing:

[1346] 1. Preprocessing of input data

[1347] The software used is the open-source spell checker library "pyspellchecker".

[1348] 2. Natural Language Processing (NLP)

[1349] The pre-processed data will undergo tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. Specifically, natural language processing libraries such as "SpaCy" and "NLTK" will be used.

[1350] 3. Emotional Engine

[1351] "VADER" and "TextBlob" are used to determine the user's emotional state based on the sentiment analysis results.

[1352] 4. Database matching

[1353] Search existing databases to find similar past cases and related information. For this purpose, use database management systems (DBMS) such as "PostgreSQL" or "MongoDB".

[1354] 5. Generating Feedback

[1355] Using a generative AI model (for example, "GPT-4"), feedback and improvement suggestions are generated for the user based on the available data and the results of the emotion engine.

[1356] 6. Responding to the user

[1357] The generated feedback is sent to the device and displayed to the user.

[1358] database

[1359] The database is used to store past challenges, feedback, related data, and emotional states. The server can refer to this database to retrieve information related to user input.

[1360] Emotional Engine

[1361] The emotion engine performs sentiment analysis as part of natural language processing and has the function of determining the user's emotional state. For example, if the input text indicates a negative emotion, it adjusts the feedback based on that information and provides an empathetic response.

[1362] Specific example

[1363] The following are examples of specific system operations:

[1364] Example: Organizing business issues

[1365] User: "I need you to identify the reason why the new project is behind schedule."

[1366] Terminal: Receives user input and sends it to the server.

[1367] server:

[1368] Input data preprocessing: Perform spell checking using "pyspellchecker".

[1369] Natural language processing: We use "SpaCy" to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[1370] The emotion engine "VADER" is used to determine the emotion of the text as "negative".

[1371] Database matching: Search the "PostgreSQL" database to find similar issues and feedback from the past.

[1372] Feedback generation: Using "GPT-4," feedback that takes user emotions into consideration is generated.

[1373] Response to user: Send feedback to the device, and the device will display it to the user: "Regarding the project's progress delays, resource shortages and scheduling issues are likely the most common causes. Please consider the following improvements: 1. Reallocate resources 2. Implement progress management tools 3. Hold regular progress review meetings"

[1374] Example of a prompt

[1375] Examples of prompt statements used as generative AI models (e.g., GPT-4):

[1376] In response to the user's question, "Please identify the reasons why the progress of the new project is behind schedule," generate emotionally sensitive feedback. The feedback should include concrete, actionable improvement suggestions and reflect the user's emotional state.

[1377] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1378] Step 1:

[1379] The user enters the information.

[1380] Users input work-related issues or questions into the terminal in text format. For example, they might input, "I need help identifying the reason why the new project is behind schedule." The input data is saved to the terminal in text format.

[1381] Step 2:

[1382] The terminal sends the input to the server.

[1383] The terminal sends user input data to the server in real time. The data is sent in JSON format using the HTTP or WebSockets protocol. The input data arrives at the server.

[1384] Step 3:

[1385] The server preprocesses the input data.

[1386] The server preprocesses the input data it receives. This preprocessing includes spell checking and removal of unnecessary characters. For example, it uses the "pyspellchecker" library to perform spell checking and clean the input data. The preprocessed data is obtained in a clean text format.

[1387] Step 4:

[1388] The server processes the input data using natural language processing.

[1389] The server performs natural language processing (NLP) on pre-processed data. Using tools like "SpaCy" and "NLTK," it performs tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. For example, for the text "Reasons why the progress of the new project is behind schedule," it extracts keywords ("project," "progress," "delay," "cause") and obtains a sentiment analysis result (negative). This provides the analyzed text data and sentiment state.

[1390] Step 5:

[1391] The server uses an emotion engine to perform sentiment analysis.

[1392] The server uses an emotion engine to determine the user's emotional state based on the results of natural language processing. It extracts the emotional state from the analyzed data using libraries such as "VADER" and "TextBlob". For example, the text data "Reasons why the new project is behind schedule" might be determined to be negative. The emotional state is then output as either positive, negative, or neutral.

[1393] Step 6:

[1394] The server checks the database.

[1395] The server searches for relevant past information in the database based on the analyzed data and emotional state. It uses databases such as PostgreSQL or MongoDB to search for relevant past issues and feedback. For example, it retrieves data related to "project progress delays" from the past and uses that to obtain useful information. The search extracts the most relevant data.

[1396] Step 7:

[1397] The server generates feedback.

[1398] The server generates feedback for the user, taking into account relevant information and emotional states acquired by the server. A generative AI model (e.g., GPT-4) is used here. For example, it might generate feedback that includes specific suggestions, such as, "Regarding project delays, resource shortages and scheduling problems are likely common causes." The generated feedback is provided in text format.

[1399] Step 8:

[1400] The server sends feedback to the terminal.

[1401] The server sends the generated feedback to the terminal. The data is sent again using the HTTP or WebSockets protocol in JSON format. The feedback arrives at the terminal.

[1402] Step 9:

[1403] The device displays feedback to the user.

[1404] The device displays the feedback it has received to the user. For example, it might display a message on the screen saying, "Regarding project delays, resource shortages and scheduling problems are likely the most common causes. Please consider the following improvements: 1. Reallocate resources 2. Implement a progress management tool 3. Hold regular progress review meetings." The user is then able to review the feedback.

[1405] The above is a detailed explanation of the processing steps of this system.

[1406] (Application Example 2)

[1407] Next, we will explain application example 2. In the following explanation, 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."

[1408] In physical stores, it is essential to efficiently collect customer feedback and provide appropriate responses based on their emotional state. In particular, prompt and appropriate responses to negative feedback are crucial for improving customer satisfaction. Furthermore, utilizing past feedback data to propose more effective improvement measures is vital. The current system does not adequately consider emotional states when providing feedback, and this needs improvement.

[1409] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1410] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data and analyzing keywords and emotions, means for comparing with past data and retrieving relevant information from a database, means for adjusting feedback based on the user's emotional state, means for generating feedback based on the obtained information, and means for providing the generated feedback to the user and presenting empathetic responses according to their emotional state. This makes it possible to provide efficient and appropriate feedback that takes into account the emotional state of customers in physical stores.

[1411] "Means of receiving user input" refers to devices or interfaces that allow users to input feedback or questions in text format using a terminal and receive that data.

[1412] "Methods for preprocessing received input data" refer to methods of preparing text data received from users for analysis by performing spell checks, removing unnecessary characters, and other similar actions.

[1413] "Means for applying natural language processing to pre-processed data to analyze keywords and sentiment" refers to a technology that analyzes pre-processed text data through tokenization, part-of-speech tagging, named entity recognition, sentiment analysis, etc., to determine important keywords and the user's emotional state.

[1414] A "database matching means for comparing with past data and searching for related information" is a method for comparing user input data with accumulated past data to search for similar cases or relevant information.

[1415] "Means of adjusting feedback based on the user's emotional state" refers to technologies that appropriately modify the content and expression of feedback provided based on the analyzed user's emotional state (e.g., positive, negative, neutral).

[1416] "Means of generating feedback based on acquired information" refers to methods of creating specific feedback and improvement suggestions for users based on relevant information obtained from a database and the results of an analysis of their emotional state.

[1417] "A means of providing generated feedback to the user and offering empathetic responses according to their emotional state" refers to a method of communicating generated feedback to the user and responding using empathetic language, especially to users in negative emotional states.

[1418] System Overview

[1419] This invention constructs a system that collects customer feedback in physical stores and provides appropriate responses based on the customer's emotional state. The system receives user input and performs preprocessing, natural language processing, sentiment analysis, database matching, feedback generation, and presentation.

[1420] Detailed system configuration

[1421] 1. Hardware Configuration

[1422] Terminal:

[1423] A smartphone, smart glasses, or head-mounted display.

[1424] These devices are used by users to input feedback in text format.

[1425] server:

[1426] Responsible for receiving, processing, analyzing, and generating feedback.

[1427] A backend server with the necessary software installed.

[1428] Database:

[1429] A database for storing past feedback, customer information, and past countermeasures.

[1430] 2. Software Configuration

[1431] Natural language processing libraries:

[1432] We use NLP libraries such as SpaCy and NLTK to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[1433] Emotional engine:

[1434] A software module that analyzes the emotional state of user input text and determines its emotional state, such as positive, negative, or neutral.

[1435] Application Server:

[1436] The feedback processing logic is executed, and feedback is generated using a generative AI model. Frameworks such as Django and Flask can be used.

[1437] Database management system:

[1438] We use database management systems such as MySQL and PostgreSQL to manage past feedback and customer information.

[1439] System operation example

[1440] Feedback input process

[1441] Customers use their smartphones or smart glasses to enter feedback such as: "The service was slow. The wait time was too long."

[1442] Server Processing Flow

[1443] 1. Preprocessing of input data:

[1444] The server receives feedback from users and performs spell checking and removes unnecessary characters.

[1445] 2. Natural Language Processing:

[1446] The pre-processed text data is tokenized, tagged with parts of speech, recognized as a named entity, and subjected to sentiment analysis to extract keywords (e.g., "service," "slow," "waiting time") and sentiment states (e.g., negative).

[1447] 3. Database matching:

[1448] Based on the extracted keywords and emotional states, the system searches a past feedback database to retrieve highly relevant information.

[1449] 4. Feedback generation:

[1450] Using a generative AI model, we generate empathetic feedback for customers by comparing it with past feedback and considering their emotional state.

[1451] Example: We will take your feedback into consideration and strive to improve the speed of our service. We will offer you a special discount on your next visit.

[1452] Introduction of specific examples

[1453] Examples of prompt statements include the following:

[1454] "The service was slow. The wait time was too long."

[1455] The server processes this input, uses an emotion engine to determine negative emotions, matches it with relevant information in the database, and then generates empathetic feedback.

[1456] By combining these components, it becomes possible to efficiently process customer feedback in physical stores and respond based on their emotional state.

[1457] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1458] Step 1:

[1459] Users enter feedback using their devices.

[1460] Input: Users enter feedback in text format (e.g., "The service was slow. The wait time was too long.").

[1461] Output: Feedback data input from the terminal.

[1462] Specific operation: The user enters feedback in text format using a device such as a smartphone or smart glasses. The device then sends this input data to the server.

[1463] Step 2:

[1464] The server preprocesses the input data it receives.

[1465] Input: Feedback data sent from the device.

[1466] Output: Pre-processed, clean text data.

[1467] Specific operation: The server preprocesses the received feedback data by performing spell checks and removing unnecessary characters, preparing it for analysis.

[1468] Step 3:

[1469] The server applies natural language processing to the pre-processed data to analyze keywords and sentiment.

[1470] Input: Pre-processed, clean text data.

[1471] Output: Analyzed keywords and emotional states.

[1472] Specific operation: The server uses an NLP library (e.g., SpaCy, NLTK) to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis, and extracts keywords (e.g., "service," "slow," "wait time") and sentiment states (e.g., negative).

[1473] Step 4:

[1474] The server performs database matching based on the analyzed data.

[1475] Input: Analyzed keywords and emotional state.

[1476] Output: Related information in the database.

[1477] Specific operation: The server searches the database management system (e.g., MySQL, PostgreSQL) and retrieves relevant information from past feedback data. This allows it to collect similar cases and relevant information.

[1478] Step 5:

[1479] The server generates feedback based on the information it receives.

[1480] Input: Relevant information retrieved from the database, analyzed emotional state.

[1481] Output: Generated feedback.

[1482] Specific operation: The server utilizes a generative AI model, taking into account emotional states and database information to generate feedback to provide to the user. For example, it might create an empathetic message in response to a negative emotional state.

[1483] Step 6:

[1484] The server sends the generated feedback to the terminal and provides it to the user.

[1485] Input: Generated feedback.

[1486] Output: A feedback message that the user can see on their device.

[1487] Specific operation: The server sends the generated feedback message to the terminal, which then displays it to the user. This allows the user to receive an appropriate response based on their emotional state.

[1488] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1489] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1490] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1491] [Fourth Embodiment]

[1492] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1493] As shown in Figure 7, the 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.

[1494] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1495] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1496] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1497] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1498] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1499] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1500] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1501] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1502] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1503] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1504] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1505] Modes for carrying out the invention

[1506] This invention is a system that provides efficient and rapid feedback based on user input, thereby promoting business improvement. A specific embodiment of this system is described below.

[1507] System Overview

[1508] This system allows users to input work-related issues and questions using a terminal, and the server processes that information to provide appropriate feedback and improvement suggestions. The system consists of the following main components:

[1509] 1. Terminal

[1510] 2. Server

[1511] 3. Database

[1512] This section describes the detailed components and their functions.

[1513] terminal

[1514] The terminal has an interface that receives user input and sends that input to the server. The system starts processing when the user enters tasks or questions in text format into the terminal.

[1515] server

[1516] The server receives the input data sent from the terminal and performs the following processing:

[1517] 1. Preprocessing of input data

[1518] It cleans up text data by performing spell checks and removing unnecessary characters.

[1519] 2. Natural Language Processing

[1520] The pre-processed data is subjected to tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis to analyze the meaning of the input data.

[1521] 3. Database matching

[1522] By cross-referencing with past data and searching for relevant information, it becomes possible to find similar cases and useful information.

[1523] 4. Generating Feedback

[1524] Based on the matching results, feedback and improvement suggestions for the user are generated.

[1525] 5. Responding to the user

[1526] The generated feedback is sent to the device and displayed to the user.

[1527] database

[1528] The database stores past issues, feedback, and related data. The server refers to this database to search for information relevant to user input.

[1529] Specific example

[1530] The following explains how the system works based on specific cases.

[1531] Example 1: Organizing business challenges

[1532] User: "I need you to identify the reason why the new project is behind schedule."

[1533] Terminal: Receives user input and sends it to the server.

[1534] server:

[1535] Preprocessing of input data: Perform a spell check and clean up phrases like "Please identify the reason why the new project is behind schedule."

[1536] Natural language processing: Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("project," "progress," "delay," "cause") and sentiment (negative).

[1537] Database matching: Search the database to find similar past issues and feedback.

[1538] Feedback generation: Generate common causes of delays (e.g., resource shortages, scheduling issues) and suggestions for improvement.

[1539] User response: Feedback is sent to the device, and the device displays it to the user.

[1540] Terminal: "Common causes of project delays include resource shortages and scheduling problems. Specifically, please consider the following improvement suggestions."

[1541] 1. Resource reallocation

[1542] 2. Implementation of progress management tools

[1543] 3. Hold regular progress review meetings.

[1544] In this way, this system analyzes the business challenges entered by users and provides quick and accurate feedback, thereby supporting the efficiency and improvement of business operations.

[1545] The following describes the processing flow.

[1546] Step 1:

[1547] Users type work-related issues or questions into their terminals and send them as text. For example, they might type, "I need help identifying the reason why the new project is behind schedule."

[1548] Step 2:

[1549] The terminal receives input data from the user. The received data is sent to the server in its original form.

[1550] Step 3:

[1551] The server preprocesses the data received from the terminal. Specifically, it cleans up the text by performing a spell check and removing unnecessary characters and symbols.

[1552] Step 4:

[1553] The server applies natural language processing (NLP) to the pre-processed text data. This step involves the following specific processes:

[1554] Tokenization: Dividing text into words or phrases.

[1555] Part-of-speech tagging: Assigns part-of-speech information to each token.

[1556] Named Entity Recognition (NER): Extracts important keywords (e.g., "project," "progress," "delay," etc.).

[1557] Sentiment Analysis: Analyzes the overall sentiment of the text and determines whether it is positive, negative, or neutral.

[1558] Step 5:

[1559] The server uses NLP results to compare them with an internal database. It searches for relevant past cases and feedback and retrieves relevant information from the database. This matching is performed using SQL queries, etc.

[1560] Step 6:

[1561] The server generates feedback and improvement suggestions for the user based on information retrieved from the database. Here, an AI algorithm operates to construct appropriate feedback based on highly relevant information.

[1562] Step 7:

[1563] The server sends the generated feedback to the terminal. The terminal receives this feedback and displays it to the user.

[1564] Step 8:

[1565] We review the feedback received from users and decide on the next course of action based on it. For example, we consider and implement specific improvement measures such as "reallocating resources" or "implementing progress management tools."

[1566] (Example 1)

[1567] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1568] Traditional business improvement systems have faced challenges in providing rapid and efficient feedback to user input. In particular, insufficient pre-processing of text data, natural language processing, and cross-referencing with historical data often result in inadequate feedback. Furthermore, the lack of emotional analysis meant that feedback tailored to user needs could not be provided.

[1569] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1570] In this invention, the server includes means for preprocessing received input data, means for applying natural language processing to the preprocessed data and analyzing keywords and sentiment, means for comparing with past data and retrieving relevant information from a database, means for generating feedback using a generative model based on the obtained information, and means for providing the generated feedback to the user. This makes it possible to provide rapid and accurate feedback to user input.

[1571] A "user" refers to an individual or organization that uses the system to input business-related issues or questions.

[1572] "Means of receiving" refers to the interface and method by which the system takes in data entered by the user.

[1573] "Preprocessing methods" refer to the processes and techniques used to prepare received text data into a format that is easy to analyze, such as by performing spell checks and removing unnecessary characters.

[1574] "Natural language processing" refers to techniques that analyze text data using methods such as tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis to understand its meaning and sentiment.

[1575] "Database matching means" refers to the process and system for a system to compare past data with current input data and retrieve relevant information.

[1576] A "generative model" refers to an algorithm or system that automatically generates appropriate feedback or suggestions from input data, such as a generative AI model.

[1577] "Means of generating feedback" refers to the processes and technologies for creating feedback and suggestions to provide to users, based on database matching results and the output of generative models.

[1578] "Means of providing feedback" refers to the interface and methods for communicating generated feedback and suggestions to users.

[1579] Modes for carrying out the invention

[1580] This invention is a system that provides efficient and rapid feedback based on user input, thereby promoting business improvement. In this system, users input work-related issues and questions using a terminal, and a server processes this information to provide appropriate feedback and improvement suggestions. A specific embodiment of this system is described below.

[1581] System Overview

[1582] This system consists of the following main components:

[1583] 1. Terminal

[1584] 2. Server

[1585] 3. Database

[1586] terminal

[1587] The terminal has an interface that receives user input and sends that input to the server. The system starts processing when the user enters tasks or questions in text format into the terminal. Specifically, a web browser or dedicated application is used as the user interface, and the input data is sent to the server via an HTTP POST request.

[1588] server

[1589] The server receives the input data sent from the terminal and performs the following processing:

[1590] 1. Preprocessing of input data

[1591] Use spell-checking tools (e.g., Hunspell) or regular expressions to remove unnecessary characters and correct spelling mistakes.

[1592] 2. Natural Language Processing

[1593] Preprocessed data is subjected to tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis using natural language processing tools (e.g., NLTK, Spacy). This allows for the analysis of the meaning and sentiment of the input data.

[1594] 3. Database matching

[1595] The server queries its internal database to retrieve historical data and related information. Relational database systems (e.g., MySQL) or NoSQL databases (e.g., MongoDB) are used.

[1596] 4. Generating Feedback

[1597] Based on the acquired information, a generative AI model (e.g., OpenAI's GPT-3) is used to generate feedback and improvement suggestions.

[1598] 5. Responding to the user

[1599] The generated feedback is sent to the device and displayed to the user.

[1600] database

[1601] The database stores past challenges, feedback, and related data. The server references this database and performs appropriate matching to retrieve information relevant to the user's input.

[1602] Specific example

[1603] The following explains how the system works based on specific cases.

[1604] Example 1: Organizing business challenges

[1605] User: "I need you to identify the reason why the new project is behind schedule."

[1606] Terminal: Receives user input and sends it to the server.

[1607] server:

[1608] Preprocessing of input data: Perform a spell check and clean up phrases like "Please identify the reason why the new project is behind schedule."

[1609] Natural language processing: Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("project," "progress," "delay," "cause") and sentiment (negative).

[1610] Database matching: Search the database to find similar past issues and feedback.

[1611] Feedback generation: Generate common causes of delays (e.g., resource shortages, scheduling issues) and suggestions for improvement.

[1612] Responding to the user: Send feedback to the device and display it to the user.

[1613] Terminal:

[1614] Common causes of project delays include resource shortages and scheduling problems. Specifically, please consider the following improvement suggestions.

[1615] 1. Resource reallocation

[1616] 2. Implementation of progress management tools

[1617] 3. Hold regular progress review meetings.

[1618] In this way, this system analyzes the business challenges entered by users and provides quick and accurate feedback, thereby supporting the efficiency and improvement of business operations.

[1619] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1620] Program processing steps

[1621] Step 1:

[1622] The user enters a work-related issue or question into the text input field on the terminal. For example, "I need help identifying the reason why the new project is behind schedule."

[1623] Input: User's text input

[1624] Output: Raw text data

[1625] Step 2:

[1626] The terminal sends the raw text data received from the user to the server. An HTTP POST request is used for this transmission.

[1627] Input: Raw text data

[1628] Output: HTTP POST request to the server

[1629] Step 3:

[1630] The server preprocesses the received raw text data, performing tasks such as spell checking (e.g., using Hunspel) and removing unwanted characters (e.g., using regular expressions).

[1631] Input: Raw text data

[1632] Data processing:

[1633] Spell check: Corrects spelling mistakes

[1634] Removing unwanted characters: Using regular expressions to remove noise.

[1635] Output: Cleaned-up text data

[1636] Step 4:

[1637] The server performs natural language processing on the cleaned text data. First, it uses tokenization to split the text into lists of words (e.g., NLTK). Next, it performs part-of-speech tagging, named entity recognition (e.g., Spacy), and sentiment analysis.

[1638] Input: Cleaned-up text data

[1639] Data processing:

[1640] Tokenization: Dividing into words or phrases

[1641] Part-of-speech tagging: Adding a part of speech to each word.

[1642] Named entity recognition: Identifying important entities.

[1643] Sentiment analysis: Analyzing the sentiment of text

[1644] Output: Analyzed data (keywords, entities, sentiment)

[1645] Step 5:

[1646] The server queries the database based on the analyzed data to retrieve relevant information. It uses a relational database system (e.g., MySQL) or a NoSQL database (e.g., MongoDB). It prioritizes retrieving past similar cases and feedback information.

[1647] Input: Analyzed data (keywords, entities, sentiment)

[1648] Data Calculation: Database Queries

[1649] Keyword matching, filtering

[1650] Extraction of similar information

[1651] Output: Related Information

[1652] Step 6:

[1653] The server generates feedback based on relevant information. It uses a generative AI model (e.g., OpenAI's GPT-3) to generate appropriate improvement suggestions and answers.

[1654] Input: Related Information

[1655] Data calculation:

[1656] Prompt input to the generative model

[1657] Feedback generation based on the model's output

[1658] Output: Generated feedback

[1659] Step 7:

[1660] The server sends the generated feedback to the terminal. It uses an HTTP POST request to send the feedback data.

[1661] Input: Generated feedback

[1662] Output: HTTP POST request to the terminal

[1663] Step 8:

[1664] The terminal displays feedback received from the server on the user interface. Users can review this feedback and use it to improve their work.

[1665] Input: Feedback received from the server

[1666] Output: Display of feedback

[1667] The above details the processing steps in this system. Each step involves specific data processing and calculations, ultimately providing the user with useful feedback.

[1668] (Application Example 1)

[1669] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1670] In conventional systems, providing rapid and accurate feedback on user input data was a challenge. In particular, in factory settings, real-time analysis and useful feedback are required, but existing systems struggled to meet these demands.

[1671] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1672] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data and analyzing keywords and sentiment, means for comparing with past data and searching for relevant information in a database, means for generating feedback based on the obtained information, means for providing the generated feedback to the user, means for using a generative AI model to generate new feedback based on the analysis results, and means for generating prompt sentences and inputting them into the generative AI model. This enables the provision of quick and accurate feedback to user input, thereby improving the efficiency and effectiveness of operations.

[1673] A "user" is an individual or group that utilizes the system and is responsible for providing input data.

[1674] "Input data" refers to text or other forms of data provided by the user.

[1675] "Preprocessing" refers to the process of cleaning up input data and converting it into a format suitable for natural language processing.

[1676] "Natural language processing" is a technology that analyzes text data to understand its meaning and extract keywords, emotions, and other relevant information.

[1677] "Keywords" refer to particularly important words or phrases from the input data provided by the user.

[1678] "Emotion" refers to the emotional elements and tone contained in the input data, and is the subject of analysis.

[1679] A "database" is a collection of information that stores past data and feedback to facilitate searching.

[1680] "Database matching" refers to the process of comparing input data with existing data in a database and retrieving related information.

[1681] "Feedback" refers to information such as advice and suggestions for improvement that a system provides to the user.

[1682] A "generative AI model" is an algorithm or framework that uses artificial intelligence to automatically generate new feedback and prompts.

[1683] A "prompt statement" is an instruction or initial statement given to a generative AI model, which the model uses to generate a response.

[1684] A "system" is the set of components that receive, process, and provide feedback from a user.

[1685] This invention is implemented as a robotic system within a factory. Specific embodiments are described below.

[1686] System Overview

[1687] This system receives user input and provides quick and appropriate feedback based on it. The system consists of terminals, a server, and a database.

[1688] terminal

[1689] Users use devices such as smartphones, tablets, and smart glasses to input and submit work-related tasks and questions. The device is responsible for sending the input data to the server.

[1690] server

[1691] The server receives the input data and performs the following processing:

[1692] 1. Preprocessing

[1693] The server preprocesses the input data received from the user, removing unnecessary characters and performing spell checks.

[1694] 2. Natural Language Processing

[1695] Natural language processing is applied to the pre-processed data to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. This allows for the analysis of keywords and sentiment.

[1696] 3. Database matching

[1697] The server searches the database and retrieves relevant information from past issues and feedback. It uses TF-IDF and cosine similarity to prioritize and extract the most relevant information.

[1698] 4. Use of Generative AI Models

[1699] Based on the analysis results, prompt sentences are generated and input into a generation AI model (e.g., OpenAI GPT-3). The model then generates new feedback.

[1700] 5. Providing feedback

[1701] The server sends the generated feedback back to the terminal and provides it to the user.

[1702] database

[1703] The database stores past issues, feedback, and related data. The server references this database to search for information relevant to user input.

[1704] Specific example

[1705] The following is an example of how this system works:

[1706] User

[1707] A factory worker enters the message, "Please identify the cause of the production line delay."

[1708] terminal

[1709] Input is received via smartphone or smart glasses and sent to the server.

[1710] server

[1711] Perform a spell check and cleaning to tidy up the phrase "Please identify the cause of the production line delay."

[1712] Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("production line," "delay," "cause") and sentiment (negative).

[1713] The database is searched, and similar cases are found based on past feedback. TF-IDF and cosine similarity are used to prioritize and extract the most relevant information.

[1714] The system provides feedback via a generative AI model, such as, "Possible causes of production line delays include machine malfunctions and labor shortages. Please consider the following improvement measures: strengthen machine inspection and maintenance, reallocate personnel, and revise the production schedule."

[1715] Example of a prompt

[1716] User question: Please identify the cause of the production line delay.

[1717] Please provide suggestions for improvement based on past feedback.

[1718] This allows the system to provide quick and accurate feedback to user input, supporting the streamlining and improvement of operations.

[1719] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1720] Step 1:

[1721] Users input work-related issues and questions using a device (smartphone or smart glasses). The input data is collected by the device. An example of input data is, "Please identify the cause of the delay on the production line."

[1722] Step 2:

[1723] The terminal sends the input data to the server. At this time, the input data is passed to the server in its original text format.

[1724] Step 3:

[1725] The server preprocesses the received input data. Preprocessing includes spell checking and removal of unnecessary characters. For example, it cleans up the sentence "Please identify the cause of the production line delay" by removing spelling mistakes and unnecessary spaces.

[1726] Step 4:

[1727] The server applies natural language processing to the pre-processed data. Specifically, it performs tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. In this step, keywords ("production line," "delay," "cause") and sentiment (negative) are extracted.

[1728] Step 5:

[1729] The server searches the database based on the results of natural language processing. The database contains past issues and feedback information. Using TF-IDF and cosine similarity, the most relevant information is extracted preferentially. This search yields relevant past feedback.

[1730] Step 6:

[1731] The server generates prompt messages based on the analysis results and inputs them into a generating AI model (e.g., OpenAI GPT-3). An example of such a prompt message is: "User question: Please identify the cause of the production line delay. Please provide improvement suggestions based on past feedback."

[1732] Step 7:

[1733] The AI ​​model generates new feedback based on the prompt text. This feedback will include specific improvement suggestions. For example, it might generate: "The delay in the production line may be due to machine failure or labor shortage. Please consider the following improvement suggestions: strengthen machine inspection and maintenance, reallocate personnel, and revise the production schedule."

[1734] Step 8:

[1735] The server sends the generated feedback back to the terminal. The terminal displays the feedback to the user. This allows the user to immediately receive specific suggestions for improvement.

[1736] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1737] Modes for carrying out the invention

[1738] This invention is a system that provides efficient and rapid feedback based on user input, and in particular includes an emotion engine that recognizes the user's emotions and reflects them in the feedback. Specific embodiments of this system are described below.

[1739] System Overview

[1740] This system allows users to input work-related issues and questions using a terminal, and the server processes this information to provide appropriate feedback and improvement suggestions. It also incorporates an emotion engine that recognizes user emotions and utilizes that information in the feedback. This system primarily consists of the following components:

[1741] 1. Terminal

[1742] 2. Server

[1743] 3. Database

[1744] 4. Emotional Engine

[1745] This section describes the detailed components and their functions.

[1746] terminal

[1747] The terminal has an interface that receives user input and sends that input to the server. The system starts processing when the user enters and sends work-related tasks or questions in text format to the terminal.

[1748] server

[1749] The server receives the input data sent from the terminal and performs the following processing:

[1750] 1. Preprocessing of input data

[1751] It cleans up text data by performing spell checks and removing unnecessary characters.

[1752] 2. Natural Language Processing

[1753] The pre-processed data is subjected to tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis to analyze the meaning and emotional state of the input data.

[1754] 3. Emotional Engine

[1755] The system determines the user's emotional state based on the sentiment analysis results of the text. The feedback content is then adjusted based on the determined emotional state (e.g., positive, negative, neutral).

[1756] 4. Database matching

[1757] By cross-referencing with past data and searching for relevant information, it becomes possible to find similar cases and useful information.

[1758] 5. Generating Feedback

[1759] Based on the available data and the results from the emotion engine, it generates feedback and improvement suggestions to provide to the user.

[1760] 6. Responding to the user

[1761] The generated feedback is sent to the device and displayed to the user.

[1762] database

[1763] The database stores past challenges, feedback, related data, and emotional states. The server refers to this database to retrieve information relevant to user input.

[1764] Emotional Engine

[1765] The emotion engine performs sentiment analysis as part of natural language processing to determine the user's emotional state. For example, if the input text indicates a negative emotion, it adjusts the feedback based on that information to provide a more appropriate and empathetic response.

[1766] Specific example

[1767] The following explains how the system works based on specific cases.

[1768] Example 1: Organizing business challenges

[1769] User: "I need you to identify the reason why the new project is behind schedule."

[1770] Terminal: Receives user input and sends it to the server.

[1771] server:

[1772] Preprocessing of input data: Perform a spell check and clean up phrases like "Please identify the reason why the new project is behind schedule."

[1773] Natural language processing: Tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis are performed to extract keywords ("project," "progress," "delay," "cause") and sentiment (negative).

[1774] Emotion Engine: Based on the sentiment analysis results of the text, it determines that the user's emotional state is negative.

[1775] Database matching: Search the database to find similar past issues and feedback.

[1776] Feedback generation: Generate common causes of delays (e.g., resource shortages, scheduling problems) and suggestions for improvement, and provide empathetic feedback considering the results of the emotion engine.

[1777] User response: Feedback is sent to the device, and the device displays it to the user.

[1778] Terminal: "Regarding project delays, resource shortages and scheduling issues are likely the most common causes. Please consider the following improvement suggestions:"

[1779] 1. Resource reallocation

[1780] 2. Implementation of progress management tools

[1781] 3. Hold regular progress review meetings.

[1782] In this way, this system, which incorporates an emotion engine, supports the efficiency and improvement of business operations by providing more appropriate feedback that takes user emotions into consideration.

[1783] The following describes the processing flow.

[1784] Step 1:

[1785] Users type work-related issues or questions into their terminals and send them as text. For example, they might type, "I need help identifying the reason why the new project is behind schedule."

[1786] Step 2:

[1787] The terminal receives input data from the user and sends that data to the server.

[1788] Step 3:

[1789] The server preprocesses the data received from the terminal. Specifically, it cleans up the text by performing a spell check and removing unnecessary characters and symbols.

[1790] Step 4:

[1791] The server applies natural language processing (NLP) to the pre-processed data. This step involves the following specific processes:

[1792] Tokenization: Divides input text into words and phrases.

[1793] Part-of-speech tagging: Assign part-of-speech information to each token (e.g., noun, verb, adjective, etc.).

[1794] Named Entity Recognition (NER): Extracts important keywords (e.g., "project," "progress," "delay").

[1795] Sentiment Analysis: Analyzes the emotional tendencies of the entire text to determine whether it is positive, negative, or neutral.

[1796] Step 5:

[1797] The server uses an emotion engine to determine the user's emotional state based on the sentiment analysis results (e.g., if the text indicates a negative emotion, the state is determined to be "negative").

[1798] Step 6:

[1799] The server adjusts the feedback based on the user's emotional state. Specifically, it modifies the feedback to take the user's emotional state into consideration.

[1800] Step 7:

[1801] The server compares the NLP results and the emotion engine results with an internal database. It searches for relevant past cases and feedback and retrieves relevant information from the database.

[1802] Step 8:

[1803] The server generates feedback and improvement suggestions for users based on information obtained from the database. In particular, it creates empathetic feedback that takes into account the user's emotional state.

[1804] Step 9:

[1805] The server sends the generated feedback to the terminal. The terminal receives this feedback and displays it to the user.

[1806] Step 10:

[1807] We review the feedback received from users and decide on the next course of action based on it. For example, we consider and implement specific improvement measures such as "reallocating resources" or "implementing progress management tools."

[1808] (Example 2)

[1809] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1810] Traditional feedback systems often fail to consider user emotions and provide only formulaic responses, leading to decreased user satisfaction and inefficient problem-solving. Furthermore, it's difficult to retrieve relevant information from past data and incorporate it into feedback, potentially resulting in inadequate advice.

[1811] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1812] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data to analyze keywords and emotions, means for determining the emotional state based on the analyzed data, database matching means for comparing with past data and retrieving related information, means for generating feedback based on the obtained information and emotional state, and means for providing the generated feedback to the user. This makes it possible to quickly provide appropriate and empathetic feedback that takes the user's emotions into consideration, thereby improving user satisfaction and the efficiency of problem solving.

[1813] A "user" refers to an entity that uses this system to input information and receive feedback.

[1814] "Input data" refers to the text information that a user provides to the system.

[1815] "Preprocessing" refers to the process of performing cleansing operations on received input data, such as spell checking and removing unnecessary characters.

[1816] "Natural language processing" refers to processes performed on text data, such as tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[1817] "Keywords" are important words or phrases extracted from the input data.

[1818] "Emotion" refers to the user's emotional state (e.g., positive, negative, neutral) analyzed from the input data.

[1819] An "emotion engine" refers to a system component that determines the user's emotional state based on input data and adjusts the feedback accordingly.

[1820] A "database" refers to an information storage system for accumulating past issues, feedback, and related data.

[1821] "Database matching means" refers to a function for comparing and searching received input data with information stored in the database.

[1822] "Feedback" refers to information such as advice, suggestions, and answers provided to the user based on input data and analysis results.

[1823] A "generative AI model" refers to a technology model that utilizes artificial intelligence to perform natural language processing based on input data and generate appropriate responses.

[1824] This invention is a system that provides efficient and rapid feedback based on user input, and in particular includes an emotion engine that recognizes the user's emotions and reflects them in the feedback. A specific embodiment for this system is shown below.

[1825] System Configuration

[1826] This system consists of the following main components:

[1827] 1. Terminal

[1828] 2. Server

[1829] 3. Database

[1830] 4. Emotional Engine

[1831] terminal

[1832] A terminal is a device with an interface that receives user input and sends that input to a server. System processing begins when the user inputs and sends work-related tasks or questions in text format to the terminal. Terminals can take the form of personal computers, smartphones, tablets, etc.

[1833] server

[1834] The server receives the input data sent from the terminal and performs the following processing:

[1835] 1. Preprocessing of input data

[1836] The software used is the open-source spell checker library "pyspellchecker".

[1837] 2. Natural Language Processing (NLP)

[1838] The pre-processed data will undergo tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. Specifically, natural language processing libraries such as "SpaCy" and "NLTK" will be used.

[1839] 3. Emotional Engine

[1840] "VADER" and "TextBlob" are used to determine the user's emotional state based on the sentiment analysis results.

[1841] 4. Database matching

[1842] Search existing databases to find similar past cases and related information. For this purpose, use database management systems (DBMS) such as "PostgreSQL" or "MongoDB".

[1843] 5. Generating Feedback

[1844] Using a generative AI model (for example, "GPT-4"), feedback and improvement suggestions are generated for the user based on the available data and the results of the emotion engine.

[1845] 6. Responding to the user

[1846] The generated feedback is sent to the device and displayed to the user.

[1847] database

[1848] The database is used to store past challenges, feedback, related data, and emotional states. The server can refer to this database to retrieve information related to user input.

[1849] Emotional Engine

[1850] The emotion engine performs sentiment analysis as part of natural language processing and has the function of determining the user's emotional state. For example, if the input text indicates a negative emotion, it adjusts the feedback based on that information and provides an empathetic response.

[1851] Specific example

[1852] The following are examples of specific system operations:

[1853] Example: Organizing business issues

[1854] User: "I need you to identify the reason why the new project is behind schedule."

[1855] Terminal: Receives user input and sends it to the server.

[1856] server:

[1857] Input data preprocessing: Perform spell checking using "pyspellchecker".

[1858] Natural language processing: We use "SpaCy" to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[1859] The emotion engine "VADER" is used to determine the emotion of the text as "negative".

[1860] Database matching: Search the "PostgreSQL" database to find similar issues and feedback from the past.

[1861] Feedback generation: Using "GPT-4," feedback that takes user emotions into consideration is generated.

[1862] Response to user: Send feedback to the device, and the device will display it to the user: "Regarding the project's progress delays, resource shortages and scheduling issues are likely the most common causes. Please consider the following improvements: 1. Reallocate resources 2. Implement progress management tools 3. Hold regular progress review meetings"

[1863] Example of a prompt

[1864] Examples of prompt statements used as generative AI models (e.g., GPT-4):

[1865] In response to the user's question, "Please identify the reasons why the progress of the new project is behind schedule," generate emotionally sensitive feedback. The feedback should include concrete, actionable improvement suggestions and reflect the user's emotional state.

[1866] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1867] Step 1:

[1868] The user enters the information.

[1869] Users input work-related issues or questions into the terminal in text format. For example, they might input, "I need help identifying the reason why the new project is behind schedule." The input data is saved to the terminal in text format.

[1870] Step 2:

[1871] The terminal sends the input to the server.

[1872] The terminal sends user input data to the server in real time. The data is sent in JSON format using the HTTP or WebSockets protocol. The input data arrives at the server.

[1873] Step 3:

[1874] The server preprocesses the input data.

[1875] The server preprocesses the input data it receives. This preprocessing includes spell checking and removal of unnecessary characters. For example, it uses the "pyspellchecker" library to perform spell checking and clean the input data. The preprocessed data is obtained in a clean text format.

[1876] Step 4:

[1877] The server processes the input data using natural language processing.

[1878] The server performs natural language processing (NLP) on pre-processed data. Using tools like "SpaCy" and "NLTK," it performs tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. For example, for the text "Reasons why the progress of the new project is behind schedule," it extracts keywords ("project," "progress," "delay," "cause") and obtains a sentiment analysis result (negative). This provides the analyzed text data and sentiment state.

[1879] Step 5:

[1880] The server uses an emotion engine to perform sentiment analysis.

[1881] The server uses an emotion engine to determine the user's emotional state based on the results of natural language processing. It extracts the emotional state from the analyzed data using libraries such as "VADER" and "TextBlob". For example, the text data "Reasons why the new project is behind schedule" might be determined to be negative. The emotional state is then output as either positive, negative, or neutral.

[1882] Step 6:

[1883] The server checks the database.

[1884] The server searches for relevant past information in the database based on the analyzed data and emotional state. It uses databases such as PostgreSQL or MongoDB to search for relevant past issues and feedback. For example, it retrieves data related to "project progress delays" from the past and uses that to obtain useful information. The search extracts the most relevant data.

[1885] Step 7:

[1886] The server generates feedback.

[1887] The server generates feedback for the user, taking into account relevant information and emotional states acquired by the server. A generative AI model (e.g., GPT-4) is used here. For example, it might generate feedback that includes specific suggestions, such as, "Regarding project delays, resource shortages and scheduling problems are likely common causes." The generated feedback is provided in text format.

[1888] Step 8:

[1889] The server sends feedback to the terminal.

[1890] The server sends the generated feedback to the terminal. The data is sent again using the HTTP or WebSockets protocol in JSON format. The feedback arrives at the terminal.

[1891] Step 9:

[1892] The device displays feedback to the user.

[1893] The device displays the feedback it has received to the user. For example, it might display a message on the screen saying, "Regarding project delays, resource shortages and scheduling problems are likely the most common causes. Please consider the following improvements: 1. Reallocate resources 2. Implement a progress management tool 3. Hold regular progress review meetings." The user is then able to review the feedback.

[1894] The above is a detailed explanation of the processing steps of this system.

[1895] (Application Example 2)

[1896] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1897] In physical stores, it is essential to efficiently collect customer feedback and provide appropriate responses based on their emotional state. In particular, prompt and appropriate responses to negative feedback are crucial for improving customer satisfaction. Furthermore, utilizing past feedback data to propose more effective improvement measures is vital. The current system does not adequately consider emotional states when providing feedback, and this needs improvement.

[1898] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1899] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input data, means for applying natural language processing to the preprocessed data and analyzing keywords and emotions, means for comparing with past data and retrieving relevant information from a database, means for adjusting feedback based on the user's emotional state, means for generating feedback based on the obtained information, and means for providing the generated feedback to the user and presenting empathetic responses according to their emotional state. This makes it possible to provide efficient and appropriate feedback that takes into account the emotional state of customers in physical stores.

[1900] "Means of receiving user input" refers to devices or interfaces that allow users to input feedback or questions in text format using a terminal and receive that data.

[1901] "Methods for preprocessing received input data" refer to methods of preparing text data received from users for analysis by performing spell checks, removing unnecessary characters, and other similar actions.

[1902] "Means for applying natural language processing to pre-processed data to analyze keywords and sentiment" refers to a technology that analyzes pre-processed text data through tokenization, part-of-speech tagging, named entity recognition, sentiment analysis, etc., to determine important keywords and the user's emotional state.

[1903] A "database matching means for comparing with past data and searching for related information" is a method for comparing user input data with accumulated past data to search for similar cases or relevant information.

[1904] "Means of adjusting feedback based on the user's emotional state" refers to technologies that appropriately modify the content and expression of feedback provided based on the analyzed user's emotional state (e.g., positive, negative, neutral).

[1905] "Means of generating feedback based on acquired information" refers to methods of creating specific feedback and improvement suggestions for users based on relevant information obtained from a database and the results of an analysis of their emotional state.

[1906] "A means of providing generated feedback to the user and offering empathetic responses according to their emotional state" refers to a method of communicating generated feedback to the user and responding using empathetic language, especially to users in negative emotional states.

[1907] System Overview

[1908] This invention constructs a system that collects customer feedback in physical stores and provides appropriate responses based on the customer's emotional state. The system receives user input and performs preprocessing, natural language processing, sentiment analysis, database matching, feedback generation, and presentation.

[1909] Detailed system configuration

[1910] 1. Hardware Configuration

[1911] Terminal:

[1912] A smartphone, smart glasses, or head-mounted display.

[1913] These devices are used by users to input feedback in text format.

[1914] server:

[1915] Responsible for receiving, processing, analyzing, and generating feedback.

[1916] A backend server with the necessary software installed.

[1917] Database:

[1918] A database for storing past feedback, customer information, and past countermeasures.

[1919] 2. Software Configuration

[1920] Natural language processing libraries:

[1921] We use NLP libraries such as SpaCy and NLTK to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[1922] Emotional engine:

[1923] A software module that analyzes the emotional state of user input text and determines its emotional state, such as positive, negative, or neutral.

[1924] Application Server:

[1925] The feedback processing logic is executed, and feedback is generated using a generative AI model. Frameworks such as Django and Flask can be used.

[1926] Database management system:

[1927] We use database management systems such as MySQL and PostgreSQL to manage past feedback and customer information.

[1928] System operation example

[1929] Feedback input process

[1930] Customers use their smartphones or smart glasses to enter feedback such as: "The service was slow. The wait time was too long."

[1931] Server Processing Flow

[1932] 1. Preprocessing of input data:

[1933] The server receives feedback from users and performs spell checking and removes unnecessary characters.

[1934] 2. Natural Language Processing:

[1935] The pre-processed text data is tokenized, tagged with parts of speech, recognized as a named entity, and subjected to sentiment analysis to extract keywords (e.g., "service," "slow," "waiting time") and sentiment states (e.g., negative).

[1936] 3. Database matching:

[1937] Based on the extracted keywords and emotional states, the system searches a past feedback database to retrieve highly relevant information.

[1938] 4. Feedback generation:

[1939] Using a generative AI model, we generate empathetic feedback for customers by comparing it with past feedback and considering their emotional state.

[1940] Example: We will take your feedback into consideration and strive to improve the speed of our service. We will offer you a special discount on your next visit.

[1941] Introduction of specific examples

[1942] Examples of prompt statements include the following:

[1943] "The service was slow. The wait time was too long."

[1944] The server processes this input, uses an emotion engine to determine negative emotions, matches it with relevant information in the database, and then generates empathetic feedback.

[1945] By combining these components, it becomes possible to efficiently process customer feedback in physical stores and respond based on their emotional state.

[1946] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1947] Step 1:

[1948] Users enter feedback using their devices.

[1949] Input: Users enter feedback in text format (e.g., "The service was slow. The wait time was too long.").

[1950] Output: Feedback data input from the terminal.

[1951] Specific operation: The user enters feedback in text format using a device such as a smartphone or smart glasses. The device then sends this input data to the server.

[1952] Step 2:

[1953] The server preprocesses the input data it receives.

[1954] Input: Feedback data sent from the device.

[1955] Output: Pre-processed, clean text data.

[1956] Specific operation: The server preprocesses the received feedback data by performing spell checks and removing unnecessary characters, preparing it for analysis.

[1957] Step 3:

[1958] The server applies natural language processing to the pre-processed data to analyze keywords and sentiment.

[1959] Input: Pre-processed, clean text data.

[1960] Output: Analyzed keywords and emotional states.

[1961] Specific operation: The server uses an NLP library (e.g., SpaCy, NLTK) to perform tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis, and extracts keywords (e.g., "service," "slow," "wait time") and sentiment states (e.g., negative).

[1962] Step 4:

[1963] The server performs database matching based on the analyzed data.

[1964] Input: Analyzed keywords and emotional state.

[1965] Output: Related information in the database.

[1966] Specific operation: The server searches the database management system (e.g., MySQL, PostgreSQL) and retrieves relevant information from past feedback data. This allows it to collect similar cases and relevant information.

[1967] Step 5:

[1968] The server generates feedback based on the information it receives.

[1969] Input: Relevant information retrieved from the database, analyzed emotional state.

[1970] Output: Generated feedback.

[1971] Specific operation: The server utilizes a generative AI model, taking into account emotional states and database information to generate feedback to provide to the user. For example, it might create an empathetic message in response to a negative emotional state.

[1972] Step 6:

[1973] The server sends the generated feedback to the terminal and provides it to the user.

[1974] Input: Generated feedback.

[1975] Output: A feedback message that the user can see on their device.

[1976] Specific operation: The server sends the generated feedback message to the terminal, which then displays it to the user. This allows the user to receive an appropriate response based on their emotional state.

[1977] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1978] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1979] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1980] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1981] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1982] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1983] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1984] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1985] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1986] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1987] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1988] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1989] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1990] 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.

[1991] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1992] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1993] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1994] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1995] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1996] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1997] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1998] The following is further disclosed regarding the embodiments described above.

[1999] (Claim 1)

[2000] A means of receiving input from the user,

[2001] A means for preprocessing the received input data,

[2002] A means for applying natural language processing to preprocessed data to analyze keywords and sentiment,

[2003] A database matching means for comparing with past data and searching for related information,

[2004] A means of generating feedback based on the information obtained,

[2005] A system that includes means for providing generated feedback to the user.

[2006] (Claim 2)

[2007] The system according to claim 1, wherein the natural language processing means includes tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[2008] (Claim 3)

[2009] The system according to claim 1, wherein the database matching means searches for past issues and feedback and prioritizes obtaining information with high relevance.

[2010] "Example 1"

[2011] (Claim 1)

[2012] A means of receiving input from the user,

[2013] A means for preprocessing the received input data,

[2014] A means for applying natural language processing to preprocessed data to analyze keywords and sentiment,

[2015] A database matching means for comparing with past data and searching for related information,

[2016] A means of generating feedback using a generative model based on the information obtained,

[2017] A system that includes means for providing generated feedback to the user.

[2018] (Claim 2)

[2019] The system according to claim 1, wherein the natural language processing means includes tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[2020] (Claim 3)

[2021] The system according to claim 1, wherein the database matching means searches for past issues and feedback and prioritizes obtaining information with high relevance.

[2022] "Application Example 1"

[2023] (Claim 1)

[2024] A means of receiving input from the user,

[2025] A means for preprocessing the received input data,

[2026] A means for applying natural language processing to preprocessed data to analyze keywords and sentiment,

[2027] A database matching means for comparing with past data and searching for related information,

[2028] A means of generating feedback based on the information obtained,

[2029] A means of providing the generated feedback to the user,

[2030] A means of using a generative AI model to generate new feedback based on the analysis results,

[2031] A system that includes means for generating prompt statements and inputting them into a generative AI model.

[2032] (Claim 2)

[2033] The system according to claim 1, wherein the natural language processing means includes tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[2034] (Claim 3)

[2035] The system according to claim 1, wherein the database matching means searches for past issues and feedback and prioritizes obtaining information with high relevance.

[2036] "Example 2 of combining an emotion engine"

[2037] (Claim 1)

[2038] A means of receiving input from the user,

[2039] A means for preprocessing the received input data,

[2040] A means for applying natural language processing to preprocessed data to analyze keywords and sentiment,

[2041] A means for determining emotional state based on analyzed data,

[2042] A database matching means for comparing with past data and searching for related information,

[2043] A means for generating feedback based on the obtained information and emotional state,

[2044] A system that includes means for providing generated feedback to the user.

[2045] (Claim 2)

[2046] The system according to claim 1, wherein the natural language processing means includes tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[2047] (Claim 3)

[2048] The system according to claim 1, wherein the database matching means searches for past issues and feedback and prioritizes obtaining information with high relevance.

[2049] "Application example 2 when combining with an emotional engine"

[2050] (Claim 1)

[2051] A means of receiving input from the user,

[2052] A means for preprocessing the received input data,

[2053] A means for applying natural language processing to preprocessed data to analyze keywords and sentiment,

[2054] A database matching means for comparing with past data and searching for related information,

[2055] A means of adjusting feedback based on the user's emotional state,

[2056] A means of generating feedback based on the information obtained,

[2057] A system that provides generated feedback to the user and includes means for offering empathetic responses according to their emotional state.

[2058] (Claim 2)

[2059] The system according to claim 1, wherein the natural language processing means includes tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

[2060] (Claim 3)

[2061] The system according to claim 1, wherein the database matching means searches for past issues and feedback and prioritizes obtaining information with high relevance. [Explanation of Symbols]

[2062] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving input from the user, A means for preprocessing the received input data, A means for applying natural language processing to preprocessed data to analyze keywords and sentiment, A database matching means for comparing with past data and searching for related information, A means of generating feedback based on the information obtained, A system including means for providing generated feedback to the user.

2. The system according to claim 1, wherein the natural language processing means includes tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis.

3. The system according to claim 1, wherein the database matching means searches for past issues and feedback and preferentially retrieves information with a high degree of relevance.

Images