System

Abstract

A system is provided.SOLUTION: A system, comprising: means for connecting to an enterprise database to obtain data of proposed cases and associated solutions; means for receiving and preprocessing a problem input in natural language from a user; means for extracting important keywords from the input problem using natural language processing; means for identifying optimal proposed cases and associated solutions using generative artificial intelligence based on the extracted keywords; and means for displaying the identified proposed cases and associated solutions to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Please write according to the format.

[0005] While the company has accumulated numerous proposal examples and individual solutions, the sheer volume of these presents a challenge, making it difficult to quickly arrive at the optimal solution, even for similar cases. This makes it difficult for inexperienced employees to make effective proposals, which can lead to variations in the quality of proposals. Furthermore, a fast and appropriate approach is required for complex problems that cannot be solved with standard solutions alone. [Means for solving the problem]

[0006] The present invention includes a means for connecting to an internal database to acquire data on past proposal examples and related solutions. It also includes a means for receiving issues input in natural language from users and preprocessing them. It also provides a means for extracting important keywords from the received issues using natural language processing, and for generative artificial intelligence to identify optimal proposal examples and related solutions based on these keywords. It also includes a means for displaying the identified proposal examples and related solutions to the user. This system enables even inexperienced employees to quickly and accurately make optimal proposals, improving the quality and efficiency of proposals.

[0007] An "internal database" is a collection of digital information managed within an organization, and is a system that includes data on past proposal cases and related solutions.

[0008] "Proposal examples" refer to information that shows specific solutions and implementation details from proposal activities that have been carried out in the past.

[0009] "Relevant Solutions" are solutions or technological measures implemented to address a specific problem or need.

[0010] "Natural language" refers to the language used by people in their daily lives, expressed in written or spoken form.

[0011] "Preprocessing" refers to the organization and conversion of data that takes place before data analysis or model input.

[0012] "Natural language processing" is a technical field that enables computers to understand, analyze, and generate natural human language.

[0013] "Keywords" are words or phrases that have important meaning in a sentence and play an important role in search and classification.

[0014] "Generative AI" is a type of AI that has the ability to generate new data or suggestions based on given data or input.

[0015] "Identifying" refers to the act of clearly distinguishing and selecting an object.

[0016] "Display" refers to the act or means of visually conveying information to a user. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] This invention relates to a system that enables even inexperienced employees to quickly make optimal proposals. This system connects to an internal database to retrieve past proposal examples and related solutions, and uses generative artificial intelligence to extract and display optimal proposals for the issues entered by the user.

[0039] The main components of this system include a server, a terminal, and a user. The specific roles and operations of each component are explained below.

[0040] 1. Internal database connection and data acquisition

[0041] The server connects to the company's internal database to retrieve data on past proposal cases and related solutions. The retrieved data is cached in the server's memory and used for subsequent processing. This allows for quick access to the required data.

[0042] 2. Accepting User Input

[0043] The terminal provides the user with a form for entering issues and requirements. The user uses this form to enter the problem or requirement they want to solve in natural language. Once they have completed entering the information, they click the "Submit" button, which sends the data to the server.

[0044] 3. Preprocessing User Input

[0045] The server pre-processes the received user input data, which involves using natural language processing (NLP) techniques to extract important keywords and context from the text data. The extracted information is used as the basis for identifying optimal suggestions.

[0046] 4. Data analysis using ChatGPT

[0047] The server then sends a request to ChatGPT, a generative artificial intelligence (AI) system, based on the extracted keywords. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable proposal for the user's input. The algorithms used here are designed to optimally match past data with current requirements.

[0048] 5. Displaying the proposed results

[0049] The server receives the identified proposal cases and related solutions and formats them for display to the user. The formatted data is displayed to the user via their device, allowing the user to quickly confirm the optimal proposal content and take concrete action.

[0050] Specific examples

[0051] For example, if a user inputs a problem such as "I want to protect customer data by adding new security features," the server preprocesses the text and extracts keywords such as "security features," "customer data," and "protection." Based on this information, the server sends a request to ChatGPT to identify relevant case studies. For example, ChatGPT may return suggestions such as "A case study where data breaches were prevented by introducing double authentication" or "A case study where data protection was enhanced by utilizing security add-ons." The server then formats the suggestions and displays them to the user via their device.

[0052] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality and efficiency of proposals.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The server reads the configuration file to obtain the hostname, port, username, password, and database name for the database connection. Then, it connects to the internal database using a database client library. If the connection is successful, the server retrieves the data of the proposed cases and related solutions using an SQL query and caches it in memory.

[0056] Step 2:

[0057] The terminal displays an input form for the user to enter issues and requirements. The user enters the problem or requirement they want to solve in natural language into this form and clicks the "Submit" button. The terminal receives the text data entered by the user and sends it to the server.

[0058] Step 3:

[0059] The server passes the text data received from the device to a natural language processing engine for preprocessing. During preprocessing, important keywords and contextual information are extracted from the input text. For example, if the input is "We would like to add new security features to protect customer data," keywords such as "security features," "customer data," and "protection" are extracted.

[0060] Step 4:

[0061] The server sends the extracted keywords to ChatGPT, a generative artificial intelligence system, and requests it to identify the best proposals and related solutions. ChatGPT then analyzes the proposals and related solutions in its internal database based on the keywords and identifies the proposals that best suit the user's challenges.

[0062] Step 5:

[0063] The server will format the proposed cases and related solutions received from ChatGPT and convert them into a format that is easy for users to understand, including adjusting the text format and adding diagrams and charts as needed.

[0064] Step 6:

[0065] The server sends the formatted proposal cases and related solutions to the terminal, which then displays the received information to the user. The user then checks the displayed proposal content and decides on the next action to take.

[0066] These steps enable even inexperienced employees to quickly and accurately make optimal proposals.

[0067] Example 1

[0068] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0069] The challenge is to provide a system that enables even inexperienced employees to quickly and accurately make optimal proposals. In particular, there is a demand for technology that effectively utilizes past proposal examples and related solutions within the company and utilizes generative artificial intelligence to extract optimal proposals.

[0070] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0071] In this invention, the server includes means for connecting to an internal database to acquire past proposal examples and related solutions, means for receiving and preprocessing issues input in natural language from a user, means for extracting important keywords from the user-input data using natural language processing, means for sending a request to a generative artificial intelligence based on the extracted keywords to identify optimal proposal examples and related solutions, and means for formatting the identified proposal examples and related solutions for display to the user. This enables even inexperienced employees to quickly and accurately make optimal proposals.

[0072] "Proposal examples" refer to specific examples of proposals made in the past and the results of their implementation.

[0073] "Related solutions" refer to solutions or approaches to specific problems or challenges.

[0074] A "database" refers to a collection of data that systematically organizes information and allows it to be accessed and managed efficiently.

[0075] "Natural language" refers to the human language used in everyday communication.

[0076] "Preprocessing" refers to the preparation of data before data analysis.

[0077] "Natural language processing" refers to techniques and methods that allow computers to understand and process human language.

[0078] "Keywords" refer to words or phrases that have significant meaning in text data.

[0079] "Generative AI" refers to AI technology that generates new information or suggestions based on specific input data.

[0080] A "request" refers to an instruction that a computer system is asked to perform.

[0081] "Formatting" refers to the process of converting data or information into an easy-to-read format.

[0082] "Format" refers to the arrangement and structure of information or data.

[0083] "User" refers to a user who operates the system.

[0084] A "server" refers to a computer system that provides data and services to other computers over a network.

[0085] These are the definitions of important words.

[0086] This invention relates to a system that enables even inexperienced employees to quickly and accurately make optimal proposals. This system connects to an internal database to retrieve past proposal examples and related solutions, and uses generative artificial intelligence to extract and display optimal proposals based on the issues entered by the user.

[0087] Hardware and Software Configuration

[0088] This system mainly consists of a server, a terminal, and a user. The detailed hardware and software configuration is shown below.

[0089] server:

[0090] A database server (e.g., MySQL or PostgreSQL)

[0091] Computation server (natural language processing libraries using Python environment: NLTK and spaCy)

[0092] Generative artificial intelligence (ChatGPT API)

[0093] Device:

[0094] A web browser (e.g. Chrome or Firefox)

[0095] Dedicated desktop application

[0096] User:

[0097] User operating the device

[0098] Processing flow

[0099] In-house database connection and data acquisition

[0100] The server connects to the company database and retrieves data on past proposals and related solutions using SQL queries, such as the following:

[0101] sql

[0102] SELECT FROM Proposal Case WHERE Solution='Security'

[0103] The acquired data is cached in the memory of the server and used for subsequent processing.

[0104] Accepting user input

[0105] The terminal provides a form for users to enter their issues and requirements in natural language. The user can enter, for example, "I would like to add new security features to protect customer data" through a web browser or dedicated application. Once the input is complete, the user clicks the "Submit" button, which sends the data to the server as an HTTP POST request.

[0106] Preprocessing User Input

[0107] The server preprocesses the received user input data. For example, it uses spaCy, a Python natural language processing library, to extract important keywords and context from the text data. Specifically, it performs text analysis as follows:

[0108] python

[0109] import spacy

[0110] nlp = spacy.load("en_core_web_sm")

[0111] doc = nlp("We want to add new security features to protect customer data")

[0112] keywords = [token.text for token in doc if token.is_stop != True and token.is_punct != True]

[0113] Data analysis using ChatGPT

[0114] The server sends a request to ChatGPT, a generative AI, based on the extracted keywords. For example, it sends the following prompt to the ChatGPT API:

[0115] A user wants to add new security features to protect customer data. Please suggest the best solution based on past proposal examples.

[0116] ChatGPT analyzes the proposed case and related solutions and returns optimal suggestions, such as "Preventing data breaches by implementing double authentication" and "Enhancing data protection by utilizing security add-ons."

[0117] Displaying the proposed results

[0118] The server receives the proposed cases and related solutions returned by ChatGPT and formats them for display to the user, for example, in HTML using Python's Jinja2 template engine, and sends them to the terminal:

[0119] python

[0120] from flask import render_template

[0121] render_template("result.html", proposals=proposals)

[0122] The formatted results are displayed to the user through the device's web browser or application, allowing the user to quickly and accurately view suggestions.

[0123] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality of proposals and improving business efficiency.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] In-house database connection and data acquisition

[0127] The server connects to the company's internal database to retrieve data on past proposals and related solutions, extracting the necessary information from the database using SQL queries and caching it in memory.

[0128] input

[0129] Database connection information

[0130] SQL Query

[0131] Specific actions

[0132] The server establishes a database connection in the Python environment.

[0133] SQL query example: SELECT FROM Proposal WHERE solution='security'

[0134] The retrieved data is stored in a Python dictionary data structure.

[0135] output

[0136] Proposal cases and related solution data

[0137] Step 2:

[0138] Accepting user input

[0139] The terminal provides a form for users to input issues and requirements in natural language. The user enters text into the input form and presses the "Submit" button to send the data to the server.

[0140] input

[0141] User-entered issue or requirement text

[0142] Specific actions

[0143] Create a form screen using JavaScript on a web browser.

[0144] The form is filled out with the message, "I would like to add new security features to protect customer data."

[0145] When the user clicks the "Submit" button, the data is sent to the server as an HTTP POST request.

[0146] output

[0147] User-entered data sent to the server

[0148] Step 3:

[0149] Preprocessing User Input

[0150] The server preprocesses the received user input data, specifically by using natural language processing (NLP) techniques to extract important keywords and contextual information from the text data.

[0151] input

[0152] User input data (text)

[0153] Specific actions

[0154] Analyze the text using a Python natural language processing library (e.g. spaCy).

[0155] Example code:

[0156] python

[0157] import spacy

[0158] nlp = spacy.load("en_core_web_sm")

[0159] doc = nlp("We want to add new security features to protect customer data")

[0160] keywords = [token.text for token in doc if token.is_stop != True and token.is_punct != True]

[0161] Keyword extraction results: "security features," "customer data," "protection"

[0162] output

[0163] Extracted keywords and context information

[0164] Step 4:

[0165] Data analysis using ChatGPT

[0166] The server then sends a request to ChatGPT, a generative artificial intelligence system, based on the extracted keywords. Specifically, it uses the ChatGPT API to provide prompts and extract the best case studies and related solutions.

[0167] input

[0168] Extracted keywords

[0169] Specific actions

[0170] Send a prompt like this to the ChatGPT API:

[0171] A user wants to add new security features to protect customer data. Please suggest the best solution based on past proposal examples.

[0172] API response examples: "Example of preventing data breaches by implementing double authentication" and "Example of strengthening data protection by utilizing security add-ons"

[0173] output

[0174] Proposal examples and related solutions from ChatGPT

[0175] Step 5:

[0176] Displaying the proposed results

[0177] The server formats the proposed cases and related solutions received from ChatGPT and displays them in a user-friendly format. Specifically, it uses HTML templates to convert the data into a display format and sends it to the terminal.

[0178] input

[0179] Proposal examples and related solutions from ChatGPT

[0180] Specific actions

[0181] The HTML format is created using Python's Jinja2 template engine.

[0182] Example code:

[0183] python

[0184] from flask import render_template

[0185] render_template("result.html", proposals=proposals)

[0186] The formatted HTML is sent to the terminal and displayed on the web browser.

[0187] output

[0188] Proposal examples and related solutions formatted in HTML format

[0189] Through the above processing steps, this system enables even inexperienced employees to quickly and accurately make optimal proposals.

[0190] (Application example 1)

[0191] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0192] The challenge is that inexperienced employees have difficulty making quick and accurate security proposals. In particular, in the field of security services, it is necessary to propose appropriate countermeasures immediately, but employees often fail to make appropriate proposals due to their lack of experience and knowledge. It is necessary to improve this situation and increase the quality and efficiency of proposals.

[0193] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0194] In this invention, the server includes means for connecting to an internal database to acquire data on proposed cases and related solutions, means for receiving and preprocessing a problem input in natural language from a user, means for extracting important keywords from the input problem using natural language processing, means for identifying optimal proposed cases and related solutions using generative artificial intelligence, and means for quickly displaying the proposed cases and related solutions identified using the generative artificial intelligence to the user. This enables even inexperienced employees to make prompt and appropriate security proposals.

[0195] An "internal database" is a database that stores data on past proposal cases and related solutions that are managed within the company.

[0196] A "natural language" is a language used by humans on a daily basis, that is, a language used for human thought and communication, rather than a specific programming language.

[0197] "Preprocessing" refers to the initial data processing process that is performed to analyze natural language text data entered by a user and extract important information.

[0198] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language, and is used to extract important keywords and information from text data.

[0199] "Generative AI" is an AI system that uses machine learning algorithms to automatically generate new information and suggestions, and is particularly involved in natural language generation.

[0200] "Means for promptly displaying" refers to a function that allows a computer system to display processing results to a user in a short period of time.

[0201] "Keywords" are the most important words and phrases extracted from the user's input task.

[0202] "Related solutions" are solutions or countermeasures that are considered effective for solving a particular problem or issue.

[0203] "Proposal examples" are data showing the specific content of proposals made in the past and success stories based on those proposals.

[0204] "Means for displaying to the user" refers to a function for visually showing the information and suggestions generated by the computer system to the user.

[0205] MODE FOR CARRYING OUT THE INVENTION

[0206] The present invention relates to a system that enables even inexperienced employees to quickly and appropriately provide optimal suggestions. In particular, the present invention is applied to a smartphone application for providing instant security suggestions in the field of security services. Specific embodiments of the present invention are described below.

[0207] System Overview

[0208] The system of the present invention comprises the following main components:

[0209] 1. Server: Connects to the internal database and retrieves data on past proposal cases and related solutions.

[0210] 2. Terminal: Installed on the smartphone, it provides an interface for user input.

[0211] 3. User: Field staff enter data using their smartphone.

[0212] Operation of each component

[0213] 1. Internal database connection and data acquisition:

[0214] The server accesses the company's internal database to obtain data on past proposal cases and related solutions.

[0215] The acquired data is cached in the server's memory and used for subsequent processing.

[0216] 2. Accepting user input:

[0217] The terminal provides a form for the user to enter their issues and requirements.

[0218] The user uses the form to enter the task in natural language and presses the "Submit" button to send the data to the server.

[0219] 3. Preprocessing user input:

[0220] The server pre-processes the data received from the user and extracts important keywords using natural language processing (NLP) techniques.

[0221] 4. Data analysis using generative artificial intelligence:

[0222] The server sends a request to a generative artificial intelligence (a model such as ChatGPT) based on the extracted keywords.

[0223] Generative AI analyzes relevant proposal cases and solutions from an internal database to generate optimal proposals.

[0224] 5. Displaying the proposed results:

[0225] The server transmits the generated suggestions to the terminal for quick display to the user.

[0226] Users can check the suggestions on their smartphones and take concrete action.

[0227] Hardware and software used

[0228] Servers: Utilize high-performance database servers, servers for natural language processing, and computing resources to run generative artificial intelligence models.

[0229] Device: A smartphone (iOS or Android) is used.

[0230] Software: We use commercial NLP APIs for natural language processing, and advanced generative AI models such as ChatGPT for generative artificial intelligence.

[0231] Specific examples

[0232] For example, if a user types "I want to prevent unauthorized access" on their smartphone, the server preprocesses this text and extracts keywords such as "unauthorized access" and "prevention." Based on this information, the server sends a request to a generative AI to generate relevant suggestions. For example, a specific suggestion such as "implement two-factor authentication" is displayed.

[0233] Prompt Sentence Examples

[0234] Please create the best security solution to meet your needs. Keywords: Unauthorized access, Prevention

[0235] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0236] Step 1:

[0237] The server connects to the company's internal database to retrieve data on past proposals and related solutions. To do this, the server issues a database query and caches the required information in memory, allowing for quick access in subsequent processes. The database connection information is given as input, and the data on proposals and related solutions is obtained as output.

[0238] Step 2:

[0239] The terminal provides a form for users to enter tasks and requirements. The user enters the task in natural language into this form and presses the "Submit" button. This sends the input data to the server. The input is the user's text input, and the input is sent to the server as the output.

[0240] Step 3:

[0241] The server preprocesses the received user input data. This preprocessing uses natural language processing (NLP) techniques to extract important keywords from the input text. Specifically, it uses text analysis algorithms to select words and interpret context. The input is the user's natural language data, and the output is a list of keywords.

[0242] Step 4:

[0243] The server sends a request to a generative AI system (ChatGPT) based on the extracted keywords. In this process, the keywords and related issues are sent to the generative AI model in the form of a prompt. The generative AI model then generates optimal suggestions based on this prompt. The input is a list of keywords and a prompt, and the output is the generated suggestions.

[0244] Step 5:

[0245] The server sends the generated suggestions to the terminal for quick display to the user. In this process, the generated suggestions are formatted into a format that is easy for humans to understand (for example, bullet points or step format). The input is a suggestion from the generation AI, and the formatted suggestion data is sent to the user's terminal as output.

[0246] Step 6:

[0247] The terminal displays the suggestions sent from the server to the user. This display includes an interface design that allows the user to intuitively understand the suggestions. The input is the formatting suggestions sent from the server, and the output is a visual representation of the suggestions to the user.

[0248] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0249] This invention relates to a system that enables even inexperienced employees to quickly make optimal proposals. This system connects to an internal database to retrieve past proposal examples and related solutions, and uses generative artificial intelligence to extract and display optimal proposals for issues entered by users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the accuracy of proposals and the user experience are improved.

[0250] The main components of this system include a server, a terminal, and a user. The specific roles and operations of each component are explained below.

[0251] 1. Internal database connection and data acquisition

[0252] The server reads the configuration file to obtain the hostname, port, username, password, and database name for the database connection. Then, it connects to the internal database using a database client library. If the connection is successful, the server retrieves the data of the proposed cases and related solutions using an SQL query and caches it in memory.

[0253] 2. Accepting User Input

[0254] The terminal provides the user with an input form for entering issues and requirements. The user enters the problem or requirement they want to solve in natural language into this form and clicks the "Submit" button. The terminal receives the text data entered by the user and sends it to the server.

[0255] 3. Preprocessing User Input

[0256] The server pre-processes the received user input data, which involves using natural language processing (NLP) techniques to extract important keywords and context from the text data. The extracted information is used as the basis for identifying optimal suggestions.

[0257] 4. Emotion Recognition by Emotion Engine

[0258] The server uses an emotion engine to recognize user emotions from pre-processed user input data. The emotion engine analyzes the input text data and identifies the user's emotional state (e.g., joy, sadness, anger, etc.). The emotion data is used as additional context before being sent to the generative artificial intelligence.

[0259] 5. Data analysis using ChatGPT

[0260] The server sends a request to ChatGPT, a generative artificial intelligence system, based on the extracted keywords and user emotional data. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable proposal for the user's input. The algorithms used here are designed to optimally match historical data, current requirements, and the user's emotional state.

[0261] 6. Displaying the proposed results

[0262] The server formats the proposed cases and related solutions received from ChatGPT and converts them into a format that is easy for users to understand. The formatted data is then displayed to the user through their device. The display format and content are dynamically adjusted according to the user's emotions, improving the user experience.

[0263] Specific examples

[0264] For example, if a user inputs a problem such as "I want to protect customer data by adding new security features," the server preprocesses the text and extracts keywords such as "security features," "customer data," and "protection." Furthermore, let's assume that the emotion engine recognizes "anxiety" from the user's input. Based on this information, the server sends a request to ChatGPT to identify relevant case studies. For example, ChatGPT may return suggestions such as "A case study where data breaches were prevented by introducing double authentication" or "A case study where data protection was strengthened by utilizing security add-ons." The server then formats the suggestions and displays them in a way that provides reassurance to the user, reducing their anxiety. The results are displayed to the user via their device, allowing them to quickly and accurately decide on their next course of action.

[0265] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality of proposals and the user experience.

[0266] The processing flow will be explained below.

[0267] Step 1:

[0268] The server reads the configuration file to obtain the hostname, port, username, password, and database name for the database connection. Then, it connects to the internal database using a database client library. If the connection is successful, the server retrieves the data of the proposed cases and related solutions using an SQL query and caches it in memory.

[0269] Step 2:

[0270] The terminal provides the user with an input form for entering issues and requirements. The user enters the problem or requirement they want to solve in natural language into this form and clicks the "Submit" button. The terminal receives the text data entered by the user and sends it to the server.

[0271] Step 3:

[0272] The server passes the text data received from the terminal to a natural language processing engine for preprocessing. Preprocessing involves extracting important keywords and contextual information from the input text. For example, if the input is "We would like to add new security features to protect customer data," keywords such as "security features," "customer data," and "protection" are extracted.

[0273] Step 4:

[0274] The server sends the extracted keywords to an emotion engine to recognize the user's emotions. The emotion engine analyzes the input text data and identifies the user's emotional state (e.g., joy, sadness, anger, etc.). The recognized emotion data is used as additional context before being sent to the generative artificial intelligence.

[0275] Step 5:

[0276] The server sends a request to ChatGPT, a generative artificial intelligence system, based on the extracted keywords and user emotional data. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable proposal for the user's input. The algorithms used here are designed to optimally match historical data, current requirements, and the user's emotional state.

[0277] Step 6:

[0278] The server will format the proposed cases and related solutions received from ChatGPT and convert them into a format that is easy for users to understand, including adjusting the text format and adding diagrams and charts as needed.

[0279] Step 7:

[0280] The server sends the formatted proposals and related solutions to the terminal, which then displays the received information to the user. The display format and content are dynamically adjusted according to the user's emotions, improving the user experience. This allows the user to quickly review the proposals and decide on their next action.

[0281] These steps enable even inexperienced employees to quickly and accurately make optimal proposals.

[0282] Example 2

[0283] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0284] In the past, it was difficult for inexperienced employees to quickly and accurately make optimal suggestions. To improve the quality of suggestions and the user experience, analysis based on a large amount of data and optimal suggestions that take into account the user's emotions are required, but no system that can achieve this has yet existed. The present invention provides technology to solve these problems.

[0285] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for connecting to an in-house database to acquire data on proposed cases and related solutions, a means for receiving and preprocessing a problem input in natural language from a user, a means for extracting important keywords from the input problem using natural language processing, a means for identifying optimal proposed cases and related solutions using generative artificial intelligence based on the extracted keywords, a means for analyzing the user's emotional state using an emotion recognition engine, and a means for displaying the identified proposed cases and related solutions to the user. This enables even inexperienced employees to quickly and accurately make optimal suggestions, thereby improving the quality of proposals and the user experience.

[0286] An "internal database" is a database that stores data on proposed cases and related solutions accumulated within a company or organization.

[0287] A "natural language" is a language that humans use on a daily basis, and in contrast to programming languages, it has the characteristic of being able to be understood and expressed intuitively.

[0288] "Preprocessing" refers to a series of steps that transform raw data into a form that is easier to analyze and process, such as data cleaning, tokenization, and keyword extraction.

[0289] "Natural Language Processing (NLP)" is a field of computer science and artificial intelligence that refers to techniques and methodologies for understanding and processing human language.

[0290] "Generative AI" refers to AI that has the ability to generate new data or information based on input data, such as text generation models.

[0291] An "emotion recognition engine" is software or algorithms that analyze text and voice data and use it to identify a user's emotional state (such as joy, anger, or sadness).

[0292] "Proposal examples" are specific examples of proposals made in the past, and include information about the process and results of those proposals.

[0293] "Related Solutions" are solutions or countermeasures related to the proposed case, which provide optimal solutions to specific problems or issues.

[0294] "Keywords" refer to words or phrases that are particularly important in a given text or data, and are used when analyzing or searching data.

[0295] A "prompt sentence" is an input sentence for generative artificial intelligence, and is used to give specific instructions or questions to the AI.

[0296] "Formatting" refers to the process of converting data or information into a format that is easy for users to understand, and refers to creating a layout or format that is visually easy to read.

[0297] This invention relates to a system that enables even inexperienced employees to make prompt and appropriate proposals. This system connects to an internal database, retrieves data on past proposal cases and related solutions, and combines generative artificial intelligence and an emotion recognition engine to extract and display optimal proposals based on the issues entered by the user. Furthermore, by recognizing the user's emotions, the system improves the accuracy of proposals and the user experience.

[0298] Main components

[0299] The main components of this system are a server, a terminal, and a user.

[0300] In-house database connection and data acquisition

[0301] The server reads the configuration file and obtains the information required to connect to the database (host name, port, user name, password, database name). It then connects to the database using a database client library (e.g., MySQL Connector, PostgreSQL). If the connection is successful, it uses an SQL query to retrieve data on past proposals and related solutions from the internal database and caches the results in memory.

[0302] Accepting user input

[0303] The terminal provides the user with an input form for entering issues and requirements in natural language. The user fills out this form and clicks the "Submit" button. The terminal obtains the user's input text and sends it to the server. The HTTPS protocol is used for transmission to ensure security.

[0304] Preprocessing User Input

[0305] The server preprocesses the received user text data by using a natural language processing (NLP) library (e.g., spaCy, NLTK) to tokenize the text and extract important keywords and phrases, and then determines what types of suggestions are needed based on the extracted keywords.

[0306] Emotion recognition by emotion engine

[0307] The server processes the analyzed user input data with an emotion engine to recognize the user's emotional state. The emotion engine uses, for example, IBM Watson Natural Language Understanding or Microsoft Azure Text Analytics. The emotional state (e.g., joy, sadness, anxiety, etc.) is analyzed and used in subsequent processing.

[0308] Data analysis using ChatGPT

[0309] The server sends a request to a generative AI (e.g., ChatGPT) based on the extracted keywords and user sentiment data. A prompt is generated and sent to the ChatGPT API. ChatGPT then identifies the best case study or solution based on the request.

[0310] Formatting and displaying the proposed results

[0311] The server receives the suggestions from ChatGPT and formats them in a way that is easy for the user to understand. Specifically, it formats them visually using Markdown or HTML templates. The formatted data is sent to the device, which displays it to the user. The display format is dynamically adjusted based on the user's emotional state.

[0312] Specific examples

[0313] For example, if a user inputs a problem such as "I want to protect customer data by adding new security features," the server preprocesses the text and extracts keywords such as "security features," "customer data," and "protection." Suppose the emotion recognition engine recognizes "anxiety" from the user's input. Based on this information, the server sends a request to ChatGPT to identify appropriate case studies. For example, it might suggest "a case study where data breaches were prevented by introducing double authentication" or "a case study where data protection was strengthened by utilizing security add-ons." The server then formats this and displays it on the device to reassure the user.

[0314] Prompt Sentence Examples

[0315] If a user enters the challenge "I want to add new security features to protect customer data," the server might send the following prompt to ChatGPT:

[0316] "Regarding adding security features, please tell me about past examples of ways to protect customer data. Also, since users are feeling uneasy, please give us some suggestions to reassure them."

[0317] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality of proposals and the user experience.

[0318] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0319] Step 1:

[0320] The server reads the configuration file to get the database connection information (hostname, port, username, password, database name). This can be a JSON or YAML file. Then it connects to the internal database using a database client library (e.g. MySQL Connector, PostgreSQL). It connects to the database using the connection information and logs a successful connection message.

[0321] Input: Path to the configuration file

[0322] Output: Database connection object, connection success message

[0323] Step 2:

[0324] The server retrieves data on proposed cases and related solutions from the connected database using SQL queries and caches it in memory for use in future analysis steps.

[0325] Input: Database connection object

[0326] Output: A dataset of proposed cases and related solutions

[0327] Step 3:

[0328] The terminal displays an input form for the user to enter issues and requirements. This form includes a text area and a submit button. The user enters the issues and requirements into the form and clicks the submit button.

[0329] Input: None (initial display when starting the terminal)

[0330] Output: Display of user input form

[0331] Step 4:

[0332] The user enters the challenge in natural language and clicks the submit button, which causes the device to take the input text and send it securely to the server using the HTTPS protocol.

[0333] Input: User input (text)

[0334] Output: The assignment text sent to the server

[0335] Step 5:

[0336] The server receives the user's text data sent from the device and preprocesses it using a natural language processing (NLP) library (e.g., spaCy, NLTK). Specifically, it tokenizes the text and extracts important keywords and context. The extracted keywords are used as the basis for identifying suggestions.

[0337] Input: User assignment text

[0338] Output: Extracted keywords and context information

[0339] Step 6:

[0340] The server runs the preprocessed user input data through an emotion recognition engine (e.g., IBM Watson Natural Language Understanding, Microsoft Azure Text Analytics) to analyze the user's emotional state. The emotion data obtained from the emotion engine is used in the subsequent suggestion identification step.

[0341] Input: Preprocessed user input data

[0342] Output: User's emotional state

[0343] Step 7:

[0344] The server compiles the extracted keywords and user sentiment data and sends a request to a generative AI model (e.g., ChatGPT) based on the collected data. Specifically, it generates a prompt and sends it to the ChatGPT API. ChatGPT then identifies the best proposed case and related solutions based on the request.

[0345] Input: Extracted keywords, user emotion data

[0346] Output: Proposed cases and related solutions from ChatGPT

[0347] Step 8:

[0348] The server retrieves the proposed cases and related solutions returned by ChatGPT and formats them into a user-friendly format, using Markdown or HTML templates for visual presentation. The formatted data is then sent to the device.

[0349] Input: Suggestion data from ChatGPT

[0350] Output: Formatted proposal data

[0351] Step 9:

[0352] The device then displays the formatted suggestion data received from the server to the user. The display format is dynamically adjusted based on the user's emotional state, allowing the user to easily view the most suitable suggestions.

[0353] Input: Formatted proposal data

[0354] Output: Suggestion information displayed to the user

[0355] Through these steps, this system allows users to easily obtain proposals for resolving problems. Each step works in conjunction with the others, allowing even inexperienced employees to quickly and accurately provide optimal proposals.

[0356] (Application example 2)

[0357] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0358] In today's brick-and-mortar stores, it is a difficult task for even inexperienced sales staff to quickly and optimally recommend products. Furthermore, understanding customer emotions and making suggestions based on those emotions is important for improving the accuracy of recommendations and customer experience. Therefore, there is a need to develop a system that utilizes generative artificial intelligence based on past recommendation cases and related solutions to enable sales staff to quickly make recommendations that are optimal for customer needs.

[0359] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for connecting to an in-house database to acquire data on proposed cases and related solutions; means for receiving and preprocessing a problem input in natural language from a user; means for extracting important keywords and contextual information from the input problem using natural language processing; means for identifying optimal proposed cases and related solutions using generative artificial intelligence based on the extracted keywords and emotional data; and means for displaying the identified proposed cases and related solutions to the user in a format that corresponds to the user's emotional state. This enables even inexperienced sales staff to make quick and accurate product suggestions by utilizing past cases and related solutions, and to display suggestions that correspond to the customer's emotions.

[0360] An "internal database" is a database that stores accumulated information within an organization, such as past proposal cases and related solutions, and makes it accessible as needed.

[0361] "Natural language" refers to a language that humans use on a daily basis, and is text data that is converted into a format that is easy for machines to understand.

[0362] "Preprocessing" is an early stage of processing to analyze natural language data entered by the user and extract important information.

[0363] "Natural language processing" is a technology that enables computers to understand and generate human language, and is a technology that analyzes and understands text data.

[0364] "Keywords" are important words or phrases extracted from the user's input data and used for subsequent analysis and suggestion generation.

[0365] "Emotion data" is information about the emotional state analyzed from the user's input, and is data that classifies and recognizes the user's emotions.

[0366] "Generative AI" is an AI technology that learns from large datasets and generates optimal outputs based on input data.

[0367] "Proposal examples" are information about specific proposals made in the past and their results.

[0368] "Related solutions" are appropriate solutions or support information provided for specific issues.

[0369] "Users" are people and organizations that use the system to solve problems and receive suggestions.

[0370] "Display" is the act of providing information to a user in visual or textual form.

[0371] This invention relates to a system for brick-and-mortar stores that enables even inexperienced sales staff to quickly and optimally recommend products. The system acquires past recommendation cases and related solutions, and uses generative artificial intelligence (ChatGPT) to make optimal recommendations based on customer needs. Furthermore, by analyzing customer sentiment, the system improves the accuracy of recommendations and the customer experience.

[0372] Hardware and Software Configuration

[0373] Hardware:

[0374] 1. Server: Provides connectivity to the internal database, data analysis, and an interface with generative artificial intelligence (ChatGPT).

[0375] 2. Terminal: A device such as a smartphone or smart glasses that allows sales staff to operate the system while interacting with customers.

[0376] software:

[0377] 1. SQLite: Used to connect to and retrieve data from the internal database. Stores case studies and related solutions.

[0378] 2. Transformers: Natural Language Processing (NLP) library for preprocessing and analyzing user-supplied text data.

[0379] 3. OpenAI API: Used to connect with generative artificial intelligence (ChatGPT) to send appropriate prompts and generate optimal suggestions.

[0380] Data processing and calculation

[0381] The server performs the following steps:

[0382] 1. Database connection:

[0383] The server connects to an internal database to retrieve data on proposed cases and related solutions, and caches it in memory, allowing for quick access to the data.

[0384] 2. Preprocessing user input:

[0385] The server preprocesses the user input data sent from the device, which involves using natural language processing (NLP) techniques to extract important keywords and contextual information from the input text data.

[0386] 3. Emotion recognition:

[0387] The server uses an emotion engine to recognize emotions from the user's input data, identifying emotional states such as "anxiety," "joy," and "sadness," and sending them as additional context to the generative AI.

[0388] 4. Proposal generation using generative artificial intelligence:

[0389] The server sends a request to the generative AI (ChatGPT) based on the extracted keywords and sentiment data. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable suggestion for the user's input. An example of a prompt is as follows:

[0390] "Provide optimal product suggestions based on customer requirements. Keywords: Gift items Emotion: Anxiety"

[0391] 5. Displaying the proposed results:

[0392] The server formats the proposed cases and related solutions received from ChatGPT and displays them on the terminal in a format that corresponds to the user's emotional state, allowing the user to easily understand and see the proposals that correspond to the customer's emotions.

[0393] Specific examples

[0394] For example, if a customer asks, "I'm looking for a new gift item, but I don't know what to choose," the server preprocesses the text data and extracts keywords such as "gift" and "item." Assume the emotion engine determines the user's emotion as "anxiety." Based on this information, the server sends a request to ChatGPT to retrieve relevant suggestions. For example, "popular gift items" and "recent successful gift suggestion examples" are suggested. The server then displays these in an easy-to-understand format, allowing users to quickly and accurately suggest products.

[0395] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0396] Step 1:

[0397] The server connects to the company's database to retrieve data on proposed cases and related solutions. During this process, the server reads a configuration file to obtain the hostname, port, username, password, and database name for the database connection. It then uses a database client library to connect to the database, retrieves the required data using SQL queries, and caches it in memory, making the data quickly accessible for subsequent searches and proposal generation.

[0398] Input: Database connection information (hostname, port, username, password, database name)

[0399] Output: Data on proposed cases and related solutions cached in memory

[0400] Step 2:

[0401] Users input their issues and requirements in natural language through the terminal. The terminal receives the text data entered by the user and sends it to the server. This input includes specific customer requests, such as "I'm looking for a new gift item, but I don't know what to choose."

[0402] Input: Text data of issues and requirements in the user's natural language

[0403] Output: User's text data sent to the server

[0404] Step 3:

[0405] The server preprocesses the user input data sent from the device. In this step, natural language processing (NLP) techniques are used to extract important keywords and contextual information from the text data. For example, keywords such as "gift" and "item" are extracted from the input text "I'm looking for a new gift item, but I don't know what to choose."

[0406] Input: User's text data

[0407] Output: Extracted keywords and context information

[0408] Step 4:

[0409] The server uses an emotion engine to recognize the user's emotional state based on the extracted keywords and context information. For example, it uses a humorous emotion analysis library to identify the user's emotional state, such as "anxiety," "joy," or "sadness."

[0410] Input: Extracted keywords and context information

[0411] Output: User's emotional state data

[0412] Step 5:

[0413] The server sends a request to the generative AI (ChatGPT) based on the extracted keywords and the user's emotional state. This request includes the previously extracted keywords and the recognized emotional state. ChatGPT generates optimal case studies and related solutions based on this information. An example of the prompt is as follows:

[0414] "Provide optimal product suggestions based on customer requirements. Keywords: Gift items Emotion: Anxiety"

[0415] Input: extracted keywords and user's emotional state

[0416] Output: Best practice case studies and related solutions

[0417] Step 6:

[0418] The server formats the proposed cases and related solutions received from the generative AI (ChatGPT) and displays them on the device in an appropriate format depending on the user's emotional state. For example, if the user is recognized as "anxious," the server formats the proposed text to give a sense of security.

[0419] Input: Best practice case studies and related solutions

[0420] Output: Display of formatting suggestions according to the user's emotional state

[0421] Examples:

[0422] For example, if a customer asks, "I'm looking for a new gift item, but I don't know what to choose," the server preprocesses the text data and extracts keywords such as "gift" and "item." Assume the emotion engine determines the user's emotion as "anxiety." Based on this information, the server sends a request to ChatGPT to retrieve relevant suggestions. For example, "popular gift items" and "recent successful gift suggestion examples" are suggested. The server then displays these in an easy-to-understand format, allowing users to quickly and accurately suggest products.

[0423] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0424] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0425] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0426] [Second embodiment]

[0427] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0428] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0429] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0430] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0431] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0432] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0433] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0434] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0435] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0436] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0437] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0438] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0439] This invention relates to a system that enables even inexperienced employees to quickly make optimal proposals. This system connects to an internal database to retrieve past proposal examples and related solutions, and uses generative artificial intelligence to extract and display optimal proposals for the issues entered by the user.

[0440] The main components of this system include a server, a terminal, and a user. The specific roles and operations of each component are explained below.

[0441] 1. Internal database connection and data acquisition

[0442] The server connects to the company's internal database to retrieve data on past proposal cases and related solutions. The retrieved data is cached in the server's memory and used for subsequent processing. This allows for quick access to the required data.

[0443] 2. Accepting User Input

[0444] The terminal provides the user with a form for entering issues and requirements. The user uses this form to enter the problem or requirement they want to solve in natural language. Once they have completed entering the information, they click the "Submit" button, which sends the data to the server.

[0445] 3. Preprocessing User Input

[0446] The server pre-processes the received user input data, which involves using natural language processing (NLP) techniques to extract important keywords and context from the text data. The extracted information is used as the basis for identifying optimal suggestions.

[0447] 4. Data analysis using ChatGPT

[0448] The server then sends a request to ChatGPT, a generative artificial intelligence (AI) system, based on the extracted keywords. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable proposal for the user's input. The algorithms used here are designed to optimally match past data with current requirements.

[0449] 5. Displaying the proposed results

[0450] The server receives the identified proposal cases and related solutions and formats them for display to the user. The formatted data is displayed to the user via their device, allowing the user to quickly confirm the optimal proposal content and take concrete action.

[0451] Specific examples

[0452] For example, if a user inputs a problem such as "I want to protect customer data by adding new security features," the server preprocesses the text and extracts keywords such as "security features," "customer data," and "protection." Based on this information, the server sends a request to ChatGPT to identify relevant case studies. For example, ChatGPT may return suggestions such as "A case study where data breaches were prevented by introducing double authentication" or "A case study where data protection was enhanced by utilizing security add-ons." The server then formats the suggestions and displays them to the user via their device.

[0453] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality and efficiency of proposals.

[0454] The processing flow will be explained below.

[0455] Step 1:

[0456] The server reads the configuration file to obtain the hostname, port, username, password, and database name for the database connection. Then, it connects to the internal database using a database client library. If the connection is successful, the server retrieves the data of the proposed cases and related solutions using an SQL query and caches it in memory.

[0457] Step 2:

[0458] The terminal displays an input form for the user to enter issues and requirements. The user enters the problem or requirement they want to solve in natural language into this form and clicks the "Submit" button. The terminal receives the text data entered by the user and sends it to the server.

[0459] Step 3:

[0460] The server passes the text data received from the device to a natural language processing engine for preprocessing. During preprocessing, important keywords and contextual information are extracted from the input text. For example, if the input is "We would like to add new security features to protect customer data," keywords such as "security features," "customer data," and "protection" are extracted.

[0461] Step 4:

[0462] The server sends the extracted keywords to ChatGPT, a generative artificial intelligence system, and requests it to identify the best proposals and related solutions. ChatGPT then analyzes the proposals and related solutions in its internal database based on the keywords and identifies the proposals that best suit the user's challenges.

[0463] Step 5:

[0464] The server will format the proposed cases and related solutions received from ChatGPT and convert them into a format that is easy for users to understand, including adjusting the text format and adding diagrams and charts as needed.

[0465] Step 6:

[0466] The server sends the formatted proposal cases and related solutions to the terminal, which then displays the received information to the user. The user then checks the displayed proposal content and decides on the next action to take.

[0467] These steps enable even inexperienced employees to quickly and accurately make optimal proposals.

[0468] Example 1

[0469] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0470] The challenge is to provide a system that enables even inexperienced employees to quickly and accurately make optimal proposals. In particular, there is a demand for technology that effectively utilizes past proposal examples and related solutions within the company and utilizes generative artificial intelligence to extract optimal proposals.

[0471] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0472] In this invention, the server includes means for connecting to an internal database to acquire past proposal examples and related solutions, means for receiving and preprocessing issues input in natural language from a user, means for extracting important keywords from the user-input data using natural language processing, means for sending a request to a generative artificial intelligence based on the extracted keywords to identify optimal proposal examples and related solutions, and means for formatting the identified proposal examples and related solutions for display to the user. This enables even inexperienced employees to quickly and accurately make optimal proposals.

[0473] "Proposal examples" refer to specific examples of proposals made in the past and the results of their implementation.

[0474] "Related solutions" refer to solutions or approaches to specific problems or challenges.

[0475] A "database" refers to a collection of data that systematically organizes information and allows it to be accessed and managed efficiently.

[0476] "Natural language" refers to the human language used in everyday communication.

[0477] "Preprocessing" refers to the preparation of data before data analysis.

[0478] "Natural language processing" refers to techniques and methods that allow computers to understand and process human language.

[0479] "Keywords" refer to words or phrases that have significant meaning in text data.

[0480] "Generative AI" refers to AI technology that generates new information or suggestions based on specific input data.

[0481] A "request" refers to an instruction that a computer system is asked to perform.

[0482] "Formatting" refers to the process of converting data or information into an easy-to-read format.

[0483] "Format" refers to the arrangement and structure of information or data.

[0484] "User" refers to a user who operates the system.

[0485] A "server" refers to a computer system that provides data and services to other computers over a network.

[0486] These are the definitions of important words.

[0487] This invention relates to a system that enables even inexperienced employees to quickly and accurately make optimal proposals. This system connects to an internal database to retrieve past proposal examples and related solutions, and uses generative artificial intelligence to extract and display optimal proposals based on the issues entered by the user.

[0488] Hardware and Software Configuration

[0489] This system mainly consists of a server, a terminal, and a user. The detailed hardware and software configuration is shown below.

[0490] server:

[0491] A database server (e.g., MySQL or PostgreSQL)

[0492] Computation server (natural language processing libraries using Python environment: NLTK and spaCy)

[0493] Generative artificial intelligence (ChatGPT API)

[0494] Device:

[0495] A web browser (e.g. Chrome or Firefox)

[0496] Dedicated desktop application

[0497] User:

[0498] User operating the device

[0499] Processing flow

[0500] In-house database connection and data acquisition

[0501] The server connects to the company database and retrieves data on past proposals and related solutions using SQL queries, such as the following:

[0502] sql

[0503] SELECT FROM Proposal Case WHERE Solution='Security'

[0504] The acquired data is cached in the memory of the server and used for subsequent processing.

[0505] Accepting user input

[0506] The terminal provides a form for users to enter their issues and requirements in natural language. The user can enter, for example, "I would like to add new security features to protect customer data" through a web browser or dedicated application. Once the input is complete, the user clicks the "Submit" button, which sends the data to the server as an HTTP POST request.

[0507] Preprocessing User Input

[0508] The server preprocesses the received user input data. For example, it uses spaCy, a Python natural language processing library, to extract important keywords and context from the text data. Specifically, it performs text analysis as follows:

[0509] python

[0510] import spacy

[0511] nlp = spacy.load("en_core_web_sm")

[0512] doc = nlp("We want to add new security features to protect customer data")

[0513] keywords = [token.text for token in doc if token.is_stop != True and token.is_punct != True]

[0514] Data analysis using ChatGPT

[0515] The server sends a request to ChatGPT, a generative AI, based on the extracted keywords. For example, it sends the following prompt to the ChatGPT API:

[0516] A user wants to add new security features to protect customer data. Please suggest the best solution based on past proposal examples.

[0517] ChatGPT analyzes the proposed case and related solutions and returns optimal suggestions, such as "Preventing data breaches by implementing double authentication" and "Enhancing data protection by utilizing security add-ons."

[0518] Displaying the proposed results

[0519] The server receives the proposed cases and related solutions returned by ChatGPT and formats them for display to the user, for example, in HTML using Python's Jinja2 template engine, and sends them to the terminal:

[0520] python

[0521] from flask import render_template

[0522] render_template("result.html", proposals=proposals)

[0523] The formatted results are displayed to the user through the device's web browser or application, allowing the user to quickly and accurately view suggestions.

[0524] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality of proposals and improving business efficiency.

[0525] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0526] Step 1:

[0527] In-house database connection and data acquisition

[0528] The server connects to the company's internal database to retrieve data on past proposals and related solutions, extracting the necessary information from the database using SQL queries and caching it in memory.

[0529] input

[0530] Database connection information

[0531] SQL Query

[0532] Specific actions

[0533] The server establishes a database connection in the Python environment.

[0534] SQL query example: SELECT FROM Proposal WHERE solution='security'

[0535] The retrieved data is stored in a Python dictionary data structure.

[0536] output

[0537] Proposal cases and related solution data

[0538] Step 2:

[0539] Accepting user input

[0540] The terminal provides a form for users to input issues and requirements in natural language. The user enters text into the input form and presses the "Submit" button to send the data to the server.

[0541] input

[0542] User-entered issue or requirement text

[0543] Specific actions

[0544] Create a form screen using JavaScript on a web browser.

[0545] The form is filled out with the message, "I would like to add new security features to protect customer data."

[0546] When the user clicks the "Submit" button, the data is sent to the server as an HTTP POST request.

[0547] output

[0548] User-entered data sent to the server

[0549] Step 3:

[0550] Preprocessing User Input

[0551] The server preprocesses the received user input data, specifically by using natural language processing (NLP) techniques to extract important keywords and contextual information from the text data.

[0552] input

[0553] User input data (text)

[0554] Specific actions

[0555] Analyze the text using a Python natural language processing library (e.g. spaCy).

[0556] Example code:

[0557] python

[0558] import spacy

[0559] nlp = spacy.load("en_core_web_sm")

[0560] doc = nlp("We want to add new security features to protect customer data")

[0561] keywords = [token.text for token in doc if token.is_stop != True and token.is_punct != True]

[0562] Keyword extraction results: "security features," "customer data," "protection"

[0563] output

[0564] Extracted keywords and context information

[0565] Step 4:

[0566] Data analysis using ChatGPT

[0567] The server then sends a request to ChatGPT, a generative artificial intelligence system, based on the extracted keywords. Specifically, it uses the ChatGPT API to provide prompts and extract the best case studies and related solutions.

[0568] input

[0569] Extracted keywords

[0570] Specific actions

[0571] Send a prompt like this to the ChatGPT API:

[0572] A user wants to add new security features to protect customer data. Please suggest the best solution based on past proposal examples.

[0573] API response examples: "Example of preventing data breaches by implementing double authentication" and "Example of strengthening data protection by utilizing security add-ons"

[0574] output

[0575] Proposal examples and related solutions from ChatGPT

[0576] Step 5:

[0577] Displaying the proposed results

[0578] The server formats the proposed cases and related solutions received from ChatGPT and displays them in a user-friendly format. Specifically, it uses HTML templates to convert the data into a display format and sends it to the terminal.

[0579] input

[0580] Proposal examples and related solutions from ChatGPT

[0581] Specific actions

[0582] The HTML format is created using Python's Jinja2 template engine.

[0583] Example code:

[0584] python

[0585] from flask import render_template

[0586] render_template("result.html", proposals=proposals)

[0587] The formatted HTML is sent to the terminal and displayed on the web browser.

[0588] output

[0589] Proposal examples and related solutions formatted in HTML format

[0590] Through the above processing steps, this system enables even inexperienced employees to quickly and accurately make optimal proposals.

[0591] (Application example 1)

[0592] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0593] The challenge is that inexperienced employees have difficulty making quick and accurate security proposals. In particular, in the field of security services, it is necessary to propose appropriate countermeasures immediately, but employees often fail to make appropriate proposals due to their lack of experience and knowledge. It is necessary to improve this situation and increase the quality and efficiency of proposals.

[0594] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0595] In this invention, the server includes means for connecting to an internal database to acquire data on proposed cases and related solutions, means for receiving and preprocessing a problem input in natural language from a user, means for extracting important keywords from the input problem using natural language processing, means for identifying optimal proposed cases and related solutions using generative artificial intelligence, and means for quickly displaying the proposed cases and related solutions identified using the generative artificial intelligence to the user. This enables even inexperienced employees to make prompt and appropriate security proposals.

[0596] An "internal database" is a database that stores data on past proposal cases and related solutions that are managed within the company.

[0597] A "natural language" is a language used by humans on a daily basis, that is, a language used for human thought and communication, rather than a specific programming language.

[0598] "Preprocessing" refers to the initial data processing process that is performed to analyze natural language text data entered by a user and extract important information.

[0599] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language, and is used to extract important keywords and information from text data.

[0600] "Generative AI" is an AI system that uses machine learning algorithms to automatically generate new information and suggestions, and is particularly involved in natural language generation.

[0601] "Means for promptly displaying" refers to a function that allows a computer system to display processing results to a user in a short period of time.

[0602] "Keywords" are the most important words and phrases extracted from the user's input task.

[0603] "Related solutions" are solutions or countermeasures that are considered effective for solving a particular problem or issue.

[0604] "Proposal examples" are data showing the specific content of proposals made in the past and success stories based on those proposals.

[0605] "Means for displaying to the user" refers to a function for visually showing the information and suggestions generated by the computer system to the user.

[0606] MODE FOR CARRYING OUT THE INVENTION

[0607] The present invention relates to a system that enables even inexperienced employees to quickly and appropriately provide optimal suggestions. In particular, the present invention is applied to a smartphone application for providing instant security suggestions in the field of security services. Specific embodiments of the present invention are described below.

[0608] System Overview

[0609] The system of the present invention comprises the following main components:

[0610] 1. Server: Connects to the internal database and retrieves data on past proposal cases and related solutions.

[0611] 2. Terminal: Installed on the smartphone, it provides an interface for user input.

[0612] 3. User: Field staff enter data using their smartphone.

[0613] Operation of each component

[0614] 1. Internal database connection and data acquisition:

[0615] The server accesses the company's internal database to obtain data on past proposal cases and related solutions.

[0616] The acquired data is cached in the server's memory and used for subsequent processing.

[0617] 2. Accepting user input:

[0618] The terminal provides a form for the user to enter their issues and requirements.

[0619] The user uses the form to enter the task in natural language and presses the "Submit" button to send the data to the server.

[0620] 3. Preprocessing user input:

[0621] The server pre-processes the data received from the user and extracts important keywords using natural language processing (NLP) techniques.

[0622] 4. Data analysis using generative artificial intelligence:

[0623] The server sends a request to a generative artificial intelligence (a model such as ChatGPT) based on the extracted keywords.

[0624] Generative AI analyzes relevant proposal cases and solutions from an internal database to generate optimal proposals.

[0625] 5. Displaying the proposed results:

[0626] The server transmits the generated suggestions to the terminal for quick display to the user.

[0627] Users can check the suggestions on their smartphones and take concrete action.

[0628] Hardware and software used

[0629] Servers: Utilize high-performance database servers, servers for natural language processing, and computing resources to run generative artificial intelligence models.

[0630] Device: A smartphone (iOS or Android) is used.

[0631] Software: We use commercial NLP APIs for natural language processing, and advanced generative AI models such as ChatGPT for generative artificial intelligence.

[0632] Specific examples

[0633] For example, if a user types "I want to prevent unauthorized access" on their smartphone, the server preprocesses this text and extracts keywords such as "unauthorized access" and "prevention." Based on this information, the server sends a request to a generative AI to generate relevant suggestions. For example, a specific suggestion such as "implement two-factor authentication" is displayed.

[0634] Prompt Sentence Examples

[0635] Please create the best security solution to meet your needs. Keywords: Unauthorized access, Prevention

[0636] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0637] Step 1:

[0638] The server connects to the company's internal database to retrieve data on past proposals and related solutions. To do this, the server issues a database query and caches the required information in memory, allowing for quick access in subsequent processes. The database connection information is given as input, and the data on proposals and related solutions is obtained as output.

[0639] Step 2:

[0640] The terminal provides a form for users to enter tasks and requirements. The user enters the task in natural language into this form and presses the "Submit" button. This sends the input data to the server. The input is the user's text input, and the input is sent to the server as the output.

[0641] Step 3:

[0642] The server preprocesses the received user input data. This preprocessing uses natural language processing (NLP) techniques to extract important keywords from the input text. Specifically, it uses text analysis algorithms to select words and interpret context. The input is the user's natural language data, and the output is a list of keywords.

[0643] Step 4:

[0644] The server sends a request to a generative AI system (ChatGPT) based on the extracted keywords. In this process, the keywords and related issues are sent to the generative AI model in the form of a prompt. The generative AI model then generates optimal suggestions based on this prompt. The input is a list of keywords and a prompt, and the output is the generated suggestions.

[0645] Step 5:

[0646] The server sends the generated suggestions to the terminal for quick display to the user. In this process, the generated suggestions are formatted into a format that is easy for humans to understand (for example, bullet points or step format). The input is a suggestion from the generation AI, and the formatted suggestion data is sent to the user's terminal as output.

[0647] Step 6:

[0648] The terminal displays the suggestions sent from the server to the user. This display includes an interface design that allows the user to intuitively understand the suggestions. The input is the formatting suggestions sent from the server, and the output is a visual representation of the suggestions to the user.

[0649] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0650] This invention relates to a system that enables even inexperienced employees to quickly make optimal proposals. This system connects to an internal database to retrieve past proposal examples and related solutions, and uses generative artificial intelligence to extract and display optimal proposals for issues entered by users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the accuracy of proposals and the user experience are improved.

[0651] The main components of this system include a server, a terminal, and a user. The specific roles and operations of each component are explained below.

[0652] 1. Internal database connection and data acquisition

[0653] The server reads the configuration file to obtain the hostname, port, username, password, and database name for the database connection. Then, it connects to the internal database using a database client library. If the connection is successful, the server retrieves the data of the proposed cases and related solutions using an SQL query and caches it in memory.

[0654] 2. Accepting User Input

[0655] The terminal provides the user with an input form for entering issues and requirements. The user enters the problem or requirement they want to solve in natural language into this form and clicks the "Submit" button. The terminal receives the text data entered by the user and sends it to the server.

[0656] 3. Preprocessing User Input

[0657] The server pre-processes the received user input data, which involves using natural language processing (NLP) techniques to extract important keywords and context from the text data. The extracted information is used as the basis for identifying optimal suggestions.

[0658] 4. Emotion Recognition by Emotion Engine

[0659] The server uses an emotion engine to recognize user emotions from pre-processed user input data. The emotion engine analyzes the input text data and identifies the user's emotional state (e.g., joy, sadness, anger, etc.). The emotion data is used as additional context before being sent to the generative artificial intelligence.

[0660] 5. Data analysis using ChatGPT

[0661] The server sends a request to ChatGPT, a generative artificial intelligence system, based on the extracted keywords and user emotional data. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable proposal for the user's input. The algorithms used here are designed to optimally match historical data, current requirements, and the user's emotional state.

[0662] 6. Displaying the proposed results

[0663] The server formats the proposed cases and related solutions received from ChatGPT and converts them into a format that is easy for users to understand. The formatted data is then displayed to the user through their device. The display format and content are dynamically adjusted according to the user's emotions, improving the user experience.

[0664] Specific examples

[0665] For example, if a user inputs a problem such as "I want to protect customer data by adding new security features," the server preprocesses the text and extracts keywords such as "security features," "customer data," and "protection." Furthermore, let's assume that the emotion engine recognizes "anxiety" from the user's input. Based on this information, the server sends a request to ChatGPT to identify relevant case studies. For example, ChatGPT may return suggestions such as "A case study where data breaches were prevented by introducing double authentication" or "A case study where data protection was strengthened by utilizing security add-ons." The server then formats the suggestions and displays them in a way that provides reassurance to the user, reducing their anxiety. The results are displayed to the user via their device, allowing them to quickly and accurately decide on their next course of action.

[0666] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality of proposals and the user experience.

[0667] The processing flow will be explained below.

[0668] Step 1:

[0669] The server reads the configuration file to obtain the hostname, port, username, password, and database name for the database connection. Then, it connects to the internal database using a database client library. If the connection is successful, the server retrieves the data of the proposed cases and related solutions using an SQL query and caches it in memory.

[0670] Step 2:

[0671] The terminal provides the user with an input form for entering issues and requirements. The user enters the problem or requirement they want to solve in natural language into this form and clicks the "Submit" button. The terminal receives the text data entered by the user and sends it to the server.

[0672] Step 3:

[0673] The server passes the text data received from the terminal to a natural language processing engine for preprocessing. Preprocessing involves extracting important keywords and contextual information from the input text. For example, if the input is "We would like to add new security features to protect customer data," keywords such as "security features," "customer data," and "protection" are extracted.

[0674] Step 4:

[0675] The server sends the extracted keywords to an emotion engine to recognize the user's emotions. The emotion engine analyzes the input text data and identifies the user's emotional state (e.g., joy, sadness, anger, etc.). The recognized emotion data is used as additional context before being sent to the generative artificial intelligence.

[0676] Step 5:

[0677] The server sends a request to ChatGPT, a generative artificial intelligence system, based on the extracted keywords and user emotional data. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable proposal for the user's input. The algorithms used here are designed to optimally match historical data, current requirements, and the user's emotional state.

[0678] Step 6:

[0679] The server will format the proposed cases and related solutions received from ChatGPT and convert them into a format that is easy for users to understand, including adjusting the text format and adding diagrams and charts as needed.

[0680] Step 7:

[0681] The server sends the formatted proposals and related solutions to the terminal, which then displays the received information to the user. The display format and content are dynamically adjusted according to the user's emotions, improving the user experience. This allows the user to quickly review the proposals and decide on their next action.

[0682] These steps enable even inexperienced employees to quickly and accurately make optimal proposals.

[0683] Example 2

[0684] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0685] In the past, it was difficult for inexperienced employees to quickly and accurately make optimal suggestions. To improve the quality of suggestions and the user experience, analysis based on a large amount of data and optimal suggestions that take into account the user's emotions are required, but no system that can achieve this has yet existed. The present invention provides technology to solve these problems.

[0686] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for connecting to an in-house database to acquire data on proposed cases and related solutions, a means for receiving and preprocessing a problem input in natural language from a user, a means for extracting important keywords from the input problem using natural language processing, a means for identifying optimal proposed cases and related solutions using generative artificial intelligence based on the extracted keywords, a means for analyzing the user's emotional state using an emotion recognition engine, and a means for displaying the identified proposed cases and related solutions to the user. This enables even inexperienced employees to quickly and accurately make optimal suggestions, thereby improving the quality of proposals and the user experience.

[0687] An "internal database" is a database that stores data on proposed cases and related solutions accumulated within a company or organization.

[0688] A "natural language" is a language that humans use on a daily basis, and in contrast to programming languages, it has the characteristic of being able to be understood and expressed intuitively.

[0689] "Preprocessing" refers to a series of steps that transform raw data into a form that is easier to analyze and process, such as data cleaning, tokenization, and keyword extraction.

[0690] "Natural Language Processing (NLP)" is a field of computer science and artificial intelligence that refers to techniques and methodologies for understanding and processing human language.

[0691] "Generative AI" refers to AI that has the ability to generate new data or information based on input data, such as text generation models.

[0692] An "emotion recognition engine" is software or algorithms that analyze text and voice data and use it to identify a user's emotional state (such as joy, anger, or sadness).

[0693] "Proposal examples" are specific examples of proposals made in the past, and include information about the process and results of those proposals.

[0694] "Related Solutions" are solutions or countermeasures related to the proposed case, which provide optimal solutions to specific problems or issues.

[0695] "Keywords" refer to words or phrases that are particularly important in a given text or data, and are used when analyzing or searching data.

[0696] A "prompt sentence" is an input sentence for generative artificial intelligence, and is used to give specific instructions or questions to the AI.

[0697] "Formatting" refers to the process of converting data or information into a format that is easy for users to understand, and refers to creating a layout or format that is visually easy to read.

[0698] This invention relates to a system that enables even inexperienced employees to make prompt and appropriate proposals. This system connects to an internal database, retrieves data on past proposal cases and related solutions, and combines generative artificial intelligence and an emotion recognition engine to extract and display optimal proposals based on the issues entered by the user. Furthermore, by recognizing the user's emotions, the system improves the accuracy of proposals and the user experience.

[0699] Main components

[0700] The main components of this system are a server, a terminal, and a user.

[0701] In-house database connection and data acquisition

[0702] The server reads the configuration file and obtains the information required to connect to the database (host name, port, user name, password, database name). It then connects to the database using a database client library (e.g., MySQL Connector, PostgreSQL). If the connection is successful, it uses an SQL query to retrieve data on past proposals and related solutions from the internal database and caches the results in memory.

[0703] Accepting user input

[0704] The terminal provides the user with an input form for entering issues and requirements in natural language. The user fills out this form and clicks the "Submit" button. The terminal obtains the user's input text and sends it to the server. The HTTPS protocol is used for transmission to ensure security.

[0705] Preprocessing User Input

[0706] The server preprocesses the received user text data by using a natural language processing (NLP) library (e.g., spaCy, NLTK) to tokenize the text and extract important keywords and phrases, and then determines what types of suggestions are needed based on the extracted keywords.

[0707] Emotion recognition by emotion engine

[0708] The server processes the analyzed user input data with an emotion engine to recognize the user's emotional state. The emotion engine uses, for example, IBM Watson Natural Language Understanding or Microsoft Azure Text Analytics. The emotional state (e.g., joy, sadness, anxiety, etc.) is analyzed and used in subsequent processing.

[0709] Data analysis using ChatGPT

[0710] The server sends a request to a generative AI (e.g., ChatGPT) based on the extracted keywords and user sentiment data. A prompt is generated and sent to the ChatGPT API. ChatGPT then identifies the best case study or solution based on the request.

[0711] Formatting and displaying the proposed results

[0712] The server receives the suggestions from ChatGPT and formats them in a way that is easy for the user to understand. Specifically, it formats them visually using Markdown or HTML templates. The formatted data is sent to the device, which displays it to the user. The display format is dynamically adjusted based on the user's emotional state.

[0713] Specific examples

[0714] For example, if a user inputs a problem such as "I want to protect customer data by adding new security features," the server preprocesses the text and extracts keywords such as "security features," "customer data," and "protection." Suppose the emotion recognition engine recognizes "anxiety" from the user's input. Based on this information, the server sends a request to ChatGPT to identify appropriate case studies. For example, it might suggest "a case study where data breaches were prevented by introducing double authentication" or "a case study where data protection was strengthened by utilizing security add-ons." The server then formats this and displays it on the device to reassure the user.

[0715] Prompt Sentence Examples

[0716] If a user enters the challenge "I want to add new security features to protect customer data," the server might send the following prompt to ChatGPT:

[0717] "Regarding adding security features, please tell me about past examples of ways to protect customer data. Also, since users are feeling uneasy, please give us some suggestions to reassure them."

[0718] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality of proposals and the user experience.

[0719] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0720] Step 1:

[0721] The server reads the configuration file to get the database connection information (hostname, port, username, password, database name). This can be a JSON or YAML file. Then it connects to the internal database using a database client library (e.g. MySQL Connector, PostgreSQL). It connects to the database using the connection information and logs a successful connection message.

[0722] Input: Path to the configuration file

[0723] Output: Database connection object, connection success message

[0724] Step 2:

[0725] The server retrieves data on proposed cases and related solutions from the connected database using SQL queries and caches it in memory for use in future analysis steps.

[0726] Input: Database connection object

[0727] Output: A dataset of proposed cases and related solutions

[0728] Step 3:

[0729] The terminal displays an input form for the user to enter issues and requirements. This form includes a text area and a submit button. The user enters the issues and requirements into the form and clicks the submit button.

[0730] Input: None (initial display when starting the terminal)

[0731] Output: Display of user input form

[0732] Step 4:

[0733] The user enters the challenge in natural language and clicks the submit button, which causes the device to take the input text and send it securely to the server using the HTTPS protocol.

[0734] Input: User input (text)

[0735] Output: The assignment text sent to the server

[0736] Step 5:

[0737] The server receives the user's text data sent from the device and preprocesses it using a natural language processing (NLP) library (e.g., spaCy, NLTK). Specifically, it tokenizes the text and extracts important keywords and context. The extracted keywords are used as the basis for identifying suggestions.

[0738] Input: User assignment text

[0739] Output: Extracted keywords and context information

[0740] Step 6:

[0741] The server runs the preprocessed user input data through an emotion recognition engine (e.g., IBM Watson Natural Language Understanding, Microsoft Azure Text Analytics) to analyze the user's emotional state. The emotion data obtained from the emotion engine is used in the subsequent suggestion identification step.

[0742] Input: Preprocessed user input data

[0743] Output: User's emotional state

[0744] Step 7:

[0745] The server compiles the extracted keywords and user sentiment data and sends a request to a generative AI model (e.g., ChatGPT) based on the collected data. Specifically, it generates a prompt and sends it to the ChatGPT API. ChatGPT then identifies the best proposed case and related solutions based on the request.

[0746] Input: Extracted keywords, user emotion data

[0747] Output: Proposed cases and related solutions from ChatGPT

[0748] Step 8:

[0749] The server retrieves the proposed cases and related solutions returned by ChatGPT and formats them into a user-friendly format, using Markdown or HTML templates for visual presentation. The formatted data is then sent to the device.

[0750] Input: Suggestion data from ChatGPT

[0751] Output: Formatted proposal data

[0752] Step 9:

[0753] The device then displays the formatted suggestion data received from the server to the user. The display format is dynamically adjusted based on the user's emotional state, allowing the user to easily view the most suitable suggestions.

[0754] Input: Formatted proposal data

[0755] Output: Suggestion information displayed to the user

[0756] Through these steps, this system allows users to easily obtain proposals for resolving problems. Each step works in conjunction with the others, allowing even inexperienced employees to quickly and accurately provide optimal proposals.

[0757] (Application example 2)

[0758] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0759] In today's brick-and-mortar stores, it is a difficult task for even inexperienced sales staff to quickly and optimally recommend products. Furthermore, understanding customer emotions and making suggestions based on those emotions is important for improving the accuracy of recommendations and customer experience. Therefore, there is a need to develop a system that utilizes generative artificial intelligence based on past recommendation cases and related solutions to enable sales staff to quickly make recommendations that are optimal for customer needs.

[0760] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for connecting to an in-house database to acquire data on proposed cases and related solutions; means for receiving and preprocessing a problem input in natural language from a user; means for extracting important keywords and contextual information from the input problem using natural language processing; means for identifying optimal proposed cases and related solutions using generative artificial intelligence based on the extracted keywords and emotional data; and means for displaying the identified proposed cases and related solutions to the user in a format that corresponds to the user's emotional state. This enables even inexperienced sales staff to make quick and accurate product suggestions by utilizing past cases and related solutions, and to display suggestions that correspond to the customer's emotions.

[0761] An "internal database" is a database that stores accumulated information within an organization, such as past proposal cases and related solutions, and makes it accessible as needed.

[0762] "Natural language" refers to a language that humans use on a daily basis, and is text data that is converted into a format that is easy for machines to understand.

[0763] "Preprocessing" is an early stage of processing to analyze natural language data entered by the user and extract important information.

[0764] "Natural language processing" is a technology that enables computers to understand and generate human language, and is a technology that analyzes and understands text data.

[0765] "Keywords" are important words or phrases extracted from the user's input data and used for subsequent analysis and suggestion generation.

[0766] "Emotion data" is information about the emotional state analyzed from the user's input, and is data that classifies and recognizes the user's emotions.

[0767] "Generative AI" is an AI technology that learns from large datasets and generates optimal outputs based on input data.

[0768] "Proposal examples" are information about specific proposals made in the past and their results.

[0769] "Related solutions" are appropriate solutions or support information provided for specific issues.

[0770] "Users" are people and organizations that use the system to solve problems and receive suggestions.

[0771] "Display" is the act of providing information to a user in visual or textual form.

[0772] This invention relates to a system for brick-and-mortar stores that enables even inexperienced sales staff to quickly and optimally recommend products. The system acquires past recommendation cases and related solutions, and uses generative artificial intelligence (ChatGPT) to make optimal recommendations based on customer needs. Furthermore, by analyzing customer sentiment, the system improves the accuracy of recommendations and the customer experience.

[0773] Hardware and Software Configuration

[0774] Hardware:

[0775] 1. Server: Provides connectivity to the internal database, data analysis, and an interface with generative artificial intelligence (ChatGPT).

[0776] 2. Terminal: A device such as a smartphone or smart glasses that allows sales staff to operate the system while interacting with customers.

[0777] software:

[0778] 1. SQLite: Used to connect to and retrieve data from the internal database. Stores case studies and related solutions.

[0779] 2. Transformers: Natural Language Processing (NLP) library for preprocessing and analyzing user-supplied text data.

[0780] 3. OpenAI API: Used to connect with generative artificial intelligence (ChatGPT) to send appropriate prompts and generate optimal suggestions.

[0781] Data processing and calculation

[0782] The server performs the following steps:

[0783] 1. Database connection:

[0784] The server connects to an internal database to retrieve data on proposed cases and related solutions, and caches it in memory, allowing for quick access to the data.

[0785] 2. Preprocessing user input:

[0786] The server preprocesses the user input data sent from the device, which involves using natural language processing (NLP) techniques to extract important keywords and contextual information from the input text data.

[0787] 3. Emotion recognition:

[0788] The server uses an emotion engine to recognize emotions from the user's input data, identifying emotional states such as "anxiety," "joy," and "sadness," and sending them as additional context to the generative AI.

[0789] 4. Proposal generation using generative artificial intelligence:

[0790] The server sends a request to the generative AI (ChatGPT) based on the extracted keywords and sentiment data. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable suggestion for the user's input. An example of a prompt is as follows:

[0791] "Provide optimal product suggestions based on customer requirements. Keywords: Gift items Emotion: Anxiety"

[0792] 5. Displaying the proposed results:

[0793] The server formats the proposed cases and related solutions received from ChatGPT and displays them on the terminal in a format that corresponds to the user's emotional state, allowing the user to easily understand and see the proposals that correspond to the customer's emotions.

[0794] Specific examples

[0795] For example, if a customer asks, "I'm looking for a new gift item, but I don't know what to choose," the server preprocesses the text data and extracts keywords such as "gift" and "item." Assume the emotion engine determines the user's emotion as "anxiety." Based on this information, the server sends a request to ChatGPT to retrieve relevant suggestions. For example, "popular gift items" and "recent successful gift suggestion examples" are suggested. The server then displays these in an easy-to-understand format, allowing users to quickly and accurately suggest products.

[0796] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0797] Step 1:

[0798] The server connects to the company's database to retrieve data on proposed cases and related solutions. During this process, the server reads a configuration file to obtain the hostname, port, username, password, and database name for the database connection. It then uses a database client library to connect to the database, retrieves the required data using SQL queries, and caches it in memory, making the data quickly accessible for subsequent searches and proposal generation.

[0799] Input: Database connection information (hostname, port, username, password, database name)

[0800] Output: Data on proposed cases and related solutions cached in memory

[0801] Step 2:

[0802] Users input their issues and requirements in natural language through the terminal. The terminal receives the text data entered by the user and sends it to the server. This input includes specific customer requests, such as "I'm looking for a new gift item, but I don't know what to choose."

[0803] Input: Text data of issues and requirements in the user's natural language

[0804] Output: User's text data sent to the server

[0805] Step 3:

[0806] The server preprocesses the user input data sent from the device. In this step, natural language processing (NLP) techniques are used to extract important keywords and contextual information from the text data. For example, keywords such as "gift" and "item" are extracted from the input text "I'm looking for a new gift item, but I don't know what to choose."

[0807] Input: User's text data

[0808] Output: Extracted keywords and context information

[0809] Step 4:

[0810] The server uses an emotion engine to recognize the user's emotional state based on the extracted keywords and context information. For example, it uses a humorous emotion analysis library to identify the user's emotional state, such as "anxiety," "joy," or "sadness."

[0811] Input: Extracted keywords and context information

[0812] Output: User's emotional state data

[0813] Step 5:

[0814] The server sends a request to the generative AI (ChatGPT) based on the extracted keywords and the user's emotional state. This request includes the previously extracted keywords and the recognized emotional state. ChatGPT generates optimal case studies and related solutions based on this information. An example of the prompt is as follows:

[0815] "Provide optimal product suggestions based on customer requirements. Keywords: Gift items Emotion: Anxiety"

[0816] Input: extracted keywords and user's emotional state

[0817] Output: Best practice case studies and related solutions

[0818] Step 6:

[0819] The server formats the proposed cases and related solutions received from the generative AI (ChatGPT) and displays them on the device in an appropriate format depending on the user's emotional state. For example, if the user is recognized as "anxious," the server formats the proposed text to give a sense of security.

[0820] Input: Best practice case studies and related solutions

[0821] Output: Display of formatting suggestions according to the user's emotional state

[0822] Examples:

[0823] For example, if a customer asks, "I'm looking for a new gift item, but I don't know what to choose," the server preprocesses the text data and extracts keywords such as "gift" and "item." Assume the emotion engine determines the user's emotion as "anxiety." Based on this information, the server sends a request to ChatGPT to retrieve relevant suggestions. For example, "popular gift items" and "recent successful gift suggestion examples" are suggested. The server then displays these in an easy-to-understand format, allowing users to quickly and accurately suggest products.

[0824] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0825] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0826] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0827] [Third embodiment]

[0828] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0829] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0830] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0831] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0832] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0833] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0834] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0835] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0836] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0837] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0838] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0839] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0840] This invention relates to a system that enables even inexperienced employees to quickly make optimal proposals. This system connects to an internal database to retrieve past proposal examples and related solutions, and uses generative artificial intelligence to extract and display optimal proposals for the issues entered by the user.

[0841] The main components of this system include a server, a terminal, and a user. The specific roles and operations of each component are explained below.

[0842] 1. Internal database connection and data acquisition

[0843] The server connects to the company's internal database to retrieve data on past proposal cases and related solutions. The retrieved data is cached in the server's memory and used for subsequent processing. This allows for quick access to the required data.

[0844] 2. Accepting User Input

[0845] The terminal provides the user with a form for entering issues and requirements. The user uses this form to enter the problem or requirement they want to solve in natural language. Once they have completed entering the information, they click the "Submit" button, which sends the data to the server.

[0846] 3. Preprocessing User Input

[0847] The server pre-processes the received user input data, which involves using natural language processing (NLP) techniques to extract important keywords and context from the text data. The extracted information is used as the basis for identifying optimal suggestions.

[0848] 4. Data analysis using ChatGPT

[0849] The server then sends a request to ChatGPT, a generative artificial intelligence (AI) system, based on the extracted keywords. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable proposal for the user's input. The algorithms used here are designed to optimally match past data with current requirements.

[0850] 5. Displaying the proposed results

[0851] The server receives the identified proposal cases and related solutions and formats them for display to the user. The formatted data is displayed to the user via their device, allowing the user to quickly confirm the optimal proposal content and take concrete action.

[0852] Specific examples

[0853] For example, if a user inputs a problem such as "I want to protect customer data by adding new security features," the server preprocesses the text and extracts keywords such as "security features," "customer data," and "protection." Based on this information, the server sends a request to ChatGPT to identify relevant case studies. For example, ChatGPT may return suggestions such as "A case study where data breaches were prevented by introducing double authentication" or "A case study where data protection was enhanced by utilizing security add-ons." The server then formats the suggestions and displays them to the user via their device.

[0854] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality and efficiency of proposals.

[0855] The processing flow will be explained below.

[0856] Step 1:

[0857] The server reads the configuration file to obtain the hostname, port, username, password, and database name for the database connection. Then, it connects to the internal database using a database client library. If the connection is successful, the server retrieves the data of the proposed cases and related solutions using an SQL query and caches it in memory.

[0858] Step 2:

[0859] The terminal displays an input form for the user to enter issues and requirements. The user enters the problem or requirement they want to solve in natural language into this form and clicks the "Submit" button. The terminal receives the text data entered by the user and sends it to the server.

[0860] Step 3:

[0861] The server passes the text data received from the device to a natural language processing engine for preprocessing. During preprocessing, important keywords and contextual information are extracted from the input text. For example, if the input is "We would like to add new security features to protect customer data," keywords such as "security features," "customer data," and "protection" are extracted.

[0862] Step 4:

[0863] The server sends the extracted keywords to ChatGPT, a generative artificial intelligence system, and requests it to identify the best proposals and related solutions. ChatGPT then analyzes the proposals and related solutions in its internal database based on the keywords and identifies the proposals that best suit the user's challenges.

[0864] Step 5:

[0865] The server will format the proposed cases and related solutions received from ChatGPT and convert them into a format that is easy for users to understand, including adjusting the text format and adding diagrams and charts as needed.

[0866] Step 6:

[0867] The server sends the formatted proposal cases and related solutions to the terminal, which then displays the received information to the user. The user then checks the displayed proposal content and decides on the next action to take.

[0868] These steps enable even inexperienced employees to quickly and accurately make optimal proposals.

[0869] Example 1

[0870] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0871] The challenge is to provide a system that enables even inexperienced employees to quickly and accurately make optimal proposals. In particular, there is a demand for technology that effectively utilizes past proposal examples and related solutions within the company and utilizes generative artificial intelligence to extract optimal proposals.

[0872] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0873] In this invention, the server includes means for connecting to an internal database to acquire past proposal examples and related solutions, means for receiving and preprocessing issues input in natural language from a user, means for extracting important keywords from the user-input data using natural language processing, means for sending a request to a generative artificial intelligence based on the extracted keywords to identify optimal proposal examples and related solutions, and means for formatting the identified proposal examples and related solutions for display to the user. This enables even inexperienced employees to quickly and accurately make optimal proposals.

[0874] "Proposal examples" refer to specific examples of proposals made in the past and the results of their implementation.

[0875] "Related solutions" refer to solutions or approaches to specific problems or challenges.

[0876] A "database" refers to a collection of data that systematically organizes information and allows it to be accessed and managed efficiently.

[0877] "Natural language" refers to the human language used in everyday communication.

[0878] "Preprocessing" refers to the preparation of data before data analysis.

[0879] "Natural language processing" refers to techniques and methods that allow computers to understand and process human language.

[0880] "Keywords" refer to words or phrases that have significant meaning in text data.

[0881] "Generative AI" refers to AI technology that generates new information or suggestions based on specific input data.

[0882] A "request" refers to an instruction that a computer system is asked to perform.

[0883] "Formatting" refers to the process of converting data or information into an easy-to-read format.

[0884] "Format" refers to the arrangement and structure of information or data.

[0885] "User" refers to a user who operates the system.

[0886] A "server" refers to a computer system that provides data and services to other computers over a network.

[0887] These are the definitions of important words.

[0888] This invention relates to a system that enables even inexperienced employees to quickly and accurately make optimal proposals. This system connects to an internal database to retrieve past proposal examples and related solutions, and uses generative artificial intelligence to extract and display optimal proposals based on the issues entered by the user.

[0889] Hardware and Software Configuration

[0890] This system mainly consists of a server, a terminal, and a user. The detailed hardware and software configuration is shown below.

[0891] server:

[0892] A database server (e.g., MySQL or PostgreSQL)

[0893] Computation server (natural language processing libraries using Python environment: NLTK and spaCy)

[0894] Generative artificial intelligence (ChatGPT API)

[0895] Device:

[0896] A web browser (e.g. Chrome or Firefox)

[0897] Dedicated desktop application

[0898] User:

[0899] User operating the device

[0900] Processing flow

[0901] In-house database connection and data acquisition

[0902] The server connects to the company database and retrieves data on past proposals and related solutions using SQL queries, such as the following:

[0903] sql

[0904] SELECT FROM Proposal Case WHERE Solution='Security'

[0905] The acquired data is cached in the memory of the server and used for subsequent processing.

[0906] Accepting user input

[0907] The terminal provides a form for users to enter their issues and requirements in natural language. The user can enter, for example, "I would like to add new security features to protect customer data" through a web browser or dedicated application. Once the input is complete, the user clicks the "Submit" button, which sends the data to the server as an HTTP POST request.

[0908] Preprocessing User Input

[0909] The server preprocesses the received user input data. For example, it uses spaCy, a Python natural language processing library, to extract important keywords and context from the text data. Specifically, it performs text analysis as follows:

[0910] python

[0911] import spacy

[0912] nlp = spacy.load("en_core_web_sm")

[0913] doc = nlp("We want to add new security features to protect customer data")

[0914] keywords = [token.text for token in doc if token.is_stop != True and token.is_punct != True]

[0915] Data analysis using ChatGPT

[0916] The server sends a request to ChatGPT, a generative AI, based on the extracted keywords. For example, it sends the following prompt to the ChatGPT API:

[0917] A user wants to add new security features to protect customer data. Please suggest the best solution based on past proposal examples.

[0918] ChatGPT analyzes the proposed case and related solutions and returns optimal suggestions, such as "Preventing data breaches by implementing double authentication" and "Enhancing data protection by utilizing security add-ons."

[0919] Displaying the proposed results

[0920] The server receives the proposed cases and related solutions returned by ChatGPT and formats them for display to the user, for example, in HTML using Python's Jinja2 template engine, and sends them to the terminal:

[0921] python

[0922] from flask import render_template

[0923] render_template("result.html", proposals=proposals)

[0924] The formatted results are displayed to the user through the device's web browser or application, allowing the user to quickly and accurately view suggestions.

[0925] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality of proposals and improving business efficiency.

[0926] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0927] Step 1:

[0928] In-house database connection and data acquisition

[0929] The server connects to the company's internal database to retrieve data on past proposals and related solutions, extracting the necessary information from the database using SQL queries and caching it in memory.

[0930] input

[0931] Database connection information

[0932] SQL Query

[0933] Specific actions

[0934] The server establishes a database connection in the Python environment.

[0935] SQL query example: SELECT FROM Proposal WHERE solution='security'

[0936] The retrieved data is stored in a Python dictionary data structure.

[0937] output

[0938] Proposal cases and related solution data

[0939] Step 2:

[0940] Accepting user input

[0941] The terminal provides a form for users to input issues and requirements in natural language. The user enters text into the input form and presses the "Submit" button to send the data to the server.

[0942] input

[0943] User-entered issue or requirement text

[0944] Specific actions

[0945] Create a form screen using JavaScript on a web browser.

[0946] The form is filled out with the message, "I would like to add new security features to protect customer data."

[0947] When the user clicks the "Submit" button, the data is sent to the server as an HTTP POST request.

[0948] output

[0949] User-entered data sent to the server

[0950] Step 3:

[0951] Preprocessing User Input

[0952] The server preprocesses the received user input data, specifically by using natural language processing (NLP) techniques to extract important keywords and contextual information from the text data.

[0953] input

[0954] User input data (text)

[0955] Specific actions

[0956] Analyze the text using a Python natural language processing library (e.g. spaCy).

[0957] Example code:

[0958] python

[0959] import spacy

[0960] nlp = spacy.load("en_core_web_sm")

[0961] doc = nlp("We want to add new security features to protect customer data")

[0962] keywords = [token.text for token in doc if token.is_stop != True and token.is_punct != True]

[0963] Keyword extraction results: "security features," "customer data," "protection"

[0964] output

[0965] Extracted keywords and context information

[0966] Step 4:

[0967] Data analysis using ChatGPT

[0968] The server then sends a request to ChatGPT, a generative artificial intelligence system, based on the extracted keywords. Specifically, it uses the ChatGPT API to provide prompts and extract the best case studies and related solutions.

[0969] input

[0970] Extracted keywords

[0971] Specific actions

[0972] Send a prompt like this to the ChatGPT API:

[0973] A user wants to add new security features to protect customer data. Please suggest the best solution based on past proposal examples.

[0974] API response examples: "Example of preventing data breaches by implementing double authentication" and "Example of strengthening data protection by utilizing security add-ons"

[0975] output

[0976] Proposal examples and related solutions from ChatGPT

[0977] Step 5:

[0978] Displaying the proposed results

[0979] The server formats the proposed cases and related solutions received from ChatGPT and displays them in a user-friendly format. Specifically, it uses HTML templates to convert the data into a display format and sends it to the terminal.

[0980] input

[0981] Proposal examples and related solutions from ChatGPT

[0982] Specific actions

[0983] The HTML format is created using Python's Jinja2 template engine.

[0984] Example code:

[0985] python

[0986] from flask import render_template

[0987] render_template("result.html", proposals=proposals)

[0988] The formatted HTML is sent to the terminal and displayed on the web browser.

[0989] output

[0990] Proposal examples and related solutions formatted in HTML format

[0991] Through the above processing steps, this system enables even inexperienced employees to quickly and accurately make optimal proposals.

[0992] (Application example 1)

[0993] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0994] The challenge is that inexperienced employees have difficulty making quick and accurate security proposals. In particular, in the field of security services, it is necessary to propose appropriate countermeasures immediately, but employees often fail to make appropriate proposals due to their lack of experience and knowledge. It is necessary to improve this situation and increase the quality and efficiency of proposals.

[0995] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0996] In this invention, the server includes means for connecting to an internal database to acquire data on proposed cases and related solutions, means for receiving and preprocessing a problem input in natural language from a user, means for extracting important keywords from the input problem using natural language processing, means for identifying optimal proposed cases and related solutions using generative artificial intelligence, and means for quickly displaying the proposed cases and related solutions identified using the generative artificial intelligence to the user. This enables even inexperienced employees to make prompt and appropriate security proposals.

[0997] An "internal database" is a database that stores data on past proposal cases and related solutions that are managed within the company.

[0998] A "natural language" is a language used by humans on a daily basis, that is, a language used for human thought and communication, rather than a specific programming language.

[0999] "Preprocessing" refers to the initial data processing process that is performed to analyze natural language text data entered by a user and extract important information.

[1000] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language, and is used to extract important keywords and information from text data.

[1001] "Generative AI" is an AI system that uses machine learning algorithms to automatically generate new information and suggestions, and is particularly involved in natural language generation.

[1002] "Means for promptly displaying" refers to a function that allows a computer system to display processing results to a user in a short period of time.

[1003] "Keywords" are the most important words and phrases extracted from the user's input task.

[1004] "Related solutions" are solutions or countermeasures that are considered effective for solving a particular problem or issue.

[1005] "Proposal examples" are data showing the specific content of proposals made in the past and success stories based on those proposals.

[1006] "Means for displaying to the user" refers to a function for visually showing the information and suggestions generated by the computer system to the user.

[1007] MODE FOR CARRYING OUT THE INVENTION

[1008] The present invention relates to a system that enables even inexperienced employees to quickly and appropriately provide optimal suggestions. In particular, the present invention is applied to a smartphone application for providing instant security suggestions in the field of security services. Specific embodiments of the present invention are described below.

[1009] System Overview

[1010] The system of the present invention comprises the following main components:

[1011] 1. Server: Connects to the internal database and retrieves data on past proposal cases and related solutions.

[1012] 2. Terminal: Installed on the smartphone, it provides an interface for user input.

[1013] 3. User: Field staff enter data using their smartphone.

[1014] Operation of each component

[1015] 1. Internal database connection and data acquisition:

[1016] The server accesses the company's internal database to obtain data on past proposal cases and related solutions.

[1017] The acquired data is cached in the server's memory and used for subsequent processing.

[1018] 2. Accepting user input:

[1019] The terminal provides a form for the user to enter their issues and requirements.

[1020] The user uses the form to enter the task in natural language and presses the "Submit" button to send the data to the server.

[1021] 3. Preprocessing user input:

[1022] The server pre-processes the data received from the user and extracts important keywords using natural language processing (NLP) techniques.

[1023] 4. Data analysis using generative artificial intelligence:

[1024] The server sends a request to a generative artificial intelligence (a model such as ChatGPT) based on the extracted keywords.

[1025] Generative AI analyzes relevant proposal cases and solutions from an internal database to generate optimal proposals.

[1026] 5. Displaying the proposed results:

[1027] The server transmits the generated suggestions to the terminal for quick display to the user.

[1028] Users can check the suggestions on their smartphones and take concrete action.

[1029] Hardware and software used

[1030] Servers: Utilize high-performance database servers, servers for natural language processing, and computing resources to run generative artificial intelligence models.

[1031] Device: A smartphone (iOS or Android) is used.

[1032] Software: We use commercial NLP APIs for natural language processing, and advanced generative AI models such as ChatGPT for generative artificial intelligence.

[1033] Specific examples

[1034] For example, if a user types "I want to prevent unauthorized access" on their smartphone, the server preprocesses this text and extracts keywords such as "unauthorized access" and "prevention." Based on this information, the server sends a request to a generative AI to generate relevant suggestions. For example, a specific suggestion such as "implement two-factor authentication" is displayed.

[1035] Prompt Sentence Examples

[1036] Please create the best security solution to meet your needs. Keywords: Unauthorized access, Prevention

[1037] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1038] Step 1:

[1039] The server connects to the company's internal database to retrieve data on past proposals and related solutions. To do this, the server issues a database query and caches the required information in memory, allowing for quick access in subsequent processes. The database connection information is given as input, and the data on proposals and related solutions is obtained as output.

[1040] Step 2:

[1041] The terminal provides a form for users to enter tasks and requirements. The user enters the task in natural language into this form and presses the "Submit" button. This sends the input data to the server. The input is the user's text input, and the input is sent to the server as the output.

[1042] Step 3:

[1043] The server preprocesses the received user input data. This preprocessing uses natural language processing (NLP) techniques to extract important keywords from the input text. Specifically, it uses text analysis algorithms to select words and interpret context. The input is the user's natural language data, and the output is a list of keywords.

[1044] Step 4:

[1045] The server sends a request to a generative AI system (ChatGPT) based on the extracted keywords. In this process, the keywords and related issues are sent to the generative AI model in the form of a prompt. The generative AI model then generates optimal suggestions based on this prompt. The input is a list of keywords and a prompt, and the output is the generated suggestions.

[1046] Step 5:

[1047] The server sends the generated suggestions to the terminal for quick display to the user. In this process, the generated suggestions are formatted into a format that is easy for humans to understand (for example, bullet points or step format). The input is a suggestion from the generation AI, and the formatted suggestion data is sent to the user's terminal as output.

[1048] Step 6:

[1049] The terminal displays the suggestions sent from the server to the user. This display includes an interface design that allows the user to intuitively understand the suggestions. The input is the formatting suggestions sent from the server, and the output is a visual representation of the suggestions to the user.

[1050] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1051] This invention relates to a system that enables even inexperienced employees to quickly make optimal proposals. This system connects to an internal database to retrieve past proposal examples and related solutions, and uses generative artificial intelligence to extract and display optimal proposals for issues entered by users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the accuracy of proposals and the user experience are improved.

[1052] The main components of this system include a server, a terminal, and a user. The specific roles and operations of each component are explained below.

[1053] 1. Internal database connection and data acquisition

[1054] The server reads the configuration file to obtain the hostname, port, username, password, and database name for the database connection. Then, it connects to the internal database using a database client library. If the connection is successful, the server retrieves the data of the proposed cases and related solutions using an SQL query and caches it in memory.

[1055] 2. Accepting User Input

[1056] The terminal provides the user with an input form for entering issues and requirements. The user enters the problem or requirement they want to solve in natural language into this form and clicks the "Submit" button. The terminal receives the text data entered by the user and sends it to the server.

[1057] 3. Preprocessing User Input

[1058] The server pre-processes the received user input data, which involves using natural language processing (NLP) techniques to extract important keywords and context from the text data. The extracted information is used as the basis for identifying optimal suggestions.

[1059] 4. Emotion Recognition by Emotion Engine

[1060] The server uses an emotion engine to recognize user emotions from pre-processed user input data. The emotion engine analyzes the input text data and identifies the user's emotional state (e.g., joy, sadness, anger, etc.). The emotion data is used as additional context before being sent to the generative artificial intelligence.

[1061] 5. Data analysis using ChatGPT

[1062] The server sends a request to ChatGPT, a generative artificial intelligence system, based on the extracted keywords and user emotional data. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable proposal for the user's input. The algorithms used here are designed to optimally match historical data, current requirements, and the user's emotional state.

[1063] 6. Displaying the proposed results

[1064] The server formats the proposed cases and related solutions received from ChatGPT and converts them into a format that is easy for users to understand. The formatted data is then displayed to the user through their device. The display format and content are dynamically adjusted according to the user's emotions, improving the user experience.

[1065] Specific examples

[1066] For example, if a user inputs a problem such as "I want to protect customer data by adding new security features," the server preprocesses the text and extracts keywords such as "security features," "customer data," and "protection." Furthermore, let's assume that the emotion engine recognizes "anxiety" from the user's input. Based on this information, the server sends a request to ChatGPT to identify relevant case studies. For example, ChatGPT may return suggestions such as "A case study where data breaches were prevented by introducing double authentication" or "A case study where data protection was strengthened by utilizing security add-ons." The server then formats the suggestions and displays them in a way that provides reassurance to the user, reducing their anxiety. The results are displayed to the user via their device, allowing them to quickly and accurately decide on their next course of action.

[1067] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality of proposals and the user experience.

[1068] The processing flow will be explained below.

[1069] Step 1:

[1070] The server reads the configuration file to obtain the hostname, port, username, password, and database name for the database connection. Then, it connects to the internal database using a database client library. If the connection is successful, the server retrieves the data of the proposed cases and related solutions using an SQL query and caches it in memory.

[1071] Step 2:

[1072] The terminal provides the user with an input form for entering issues and requirements. The user enters the problem or requirement they want to solve in natural language into this form and clicks the "Submit" button. The terminal receives the text data entered by the user and sends it to the server.

[1073] Step 3:

[1074] The server passes the text data received from the terminal to a natural language processing engine for preprocessing. Preprocessing involves extracting important keywords and contextual information from the input text. For example, if the input is "We would like to add new security features to protect customer data," keywords such as "security features," "customer data," and "protection" are extracted.

[1075] Step 4:

[1076] The server sends the extracted keywords to an emotion engine to recognize the user's emotions. The emotion engine analyzes the input text data and identifies the user's emotional state (e.g., joy, sadness, anger, etc.). The recognized emotion data is used as additional context before being sent to the generative artificial intelligence.

[1077] Step 5:

[1078] The server sends a request to ChatGPT, a generative artificial intelligence system, based on the extracted keywords and user emotional data. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable proposal for the user's input. The algorithms used here are designed to optimally match historical data, current requirements, and the user's emotional state.

[1079] Step 6:

[1080] The server will format the proposed cases and related solutions received from ChatGPT and convert them into a format that is easy for users to understand, including adjusting the text format and adding diagrams and charts as needed.

[1081] Step 7:

[1082] The server sends the formatted proposals and related solutions to the terminal, which then displays the received information to the user. The display format and content are dynamically adjusted according to the user's emotions, improving the user experience. This allows the user to quickly review the proposals and decide on their next action.

[1083] These steps enable even inexperienced employees to quickly and accurately make optimal proposals.

[1084] Example 2

[1085] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1086] In the past, it was difficult for inexperienced employees to quickly and accurately make optimal suggestions. To improve the quality of suggestions and the user experience, analysis based on a large amount of data and optimal suggestions that take into account the user's emotions are required, but no system that can achieve this has yet existed. The present invention provides technology to solve these problems.

[1087] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for connecting to an in-house database to acquire data on proposed cases and related solutions, a means for receiving and preprocessing a problem input in natural language from a user, a means for extracting important keywords from the input problem using natural language processing, a means for identifying optimal proposed cases and related solutions using generative artificial intelligence based on the extracted keywords, a means for analyzing the user's emotional state using an emotion recognition engine, and a means for displaying the identified proposed cases and related solutions to the user. This enables even inexperienced employees to quickly and accurately make optimal suggestions, thereby improving the quality of proposals and the user experience.

[1088] An "internal database" is a database that stores data on proposed cases and related solutions accumulated within a company or organization.

[1089] A "natural language" is a language that humans use on a daily basis, and in contrast to programming languages, it has the characteristic of being able to be understood and expressed intuitively.

[1090] "Preprocessing" refers to a series of steps that transform raw data into a form that is easier to analyze and process, such as data cleaning, tokenization, and keyword extraction.

[1091] "Natural Language Processing (NLP)" is a field of computer science and artificial intelligence that refers to techniques and methodologies for understanding and processing human language.

[1092] "Generative AI" refers to AI that has the ability to generate new data or information based on input data, such as text generation models.

[1093] An "emotion recognition engine" is software or algorithms that analyze text and voice data and use it to identify a user's emotional state (such as joy, anger, or sadness).

[1094] "Proposal examples" are specific examples of proposals made in the past, and include information about the process and results of those proposals.

[1095] "Related Solutions" are solutions or countermeasures related to the proposed case, which provide optimal solutions to specific problems or issues.

[1096] "Keywords" refer to words or phrases that are particularly important in a given text or data, and are used when analyzing or searching data.

[1097] A "prompt sentence" is an input sentence for generative artificial intelligence, and is used to give specific instructions or questions to the AI.

[1098] "Formatting" refers to the process of converting data or information into a format that is easy for users to understand, and refers to creating a layout or format that is visually easy to read.

[1099] This invention relates to a system that enables even inexperienced employees to make prompt and appropriate proposals. This system connects to an internal database, retrieves data on past proposal cases and related solutions, and combines generative artificial intelligence and an emotion recognition engine to extract and display optimal proposals based on the issues entered by the user. Furthermore, by recognizing the user's emotions, the system improves the accuracy of proposals and the user experience.

[1100] Main components

[1101] The main components of this system are a server, a terminal, and a user.

[1102] In-house database connection and data acquisition

[1103] The server reads the configuration file and obtains the information required to connect to the database (host name, port, user name, password, database name). It then connects to the database using a database client library (e.g., MySQL Connector, PostgreSQL). If the connection is successful, it uses an SQL query to retrieve data on past proposals and related solutions from the internal database and caches the results in memory.

[1104] Accepting user input

[1105] The terminal provides the user with an input form for entering issues and requirements in natural language. The user fills out this form and clicks the "Submit" button. The terminal obtains the user's input text and sends it to the server. The HTTPS protocol is used for transmission to ensure security.

[1106] Preprocessing User Input

[1107] The server preprocesses the received user text data by using a natural language processing (NLP) library (e.g., spaCy, NLTK) to tokenize the text and extract important keywords and phrases, and then determines what types of suggestions are needed based on the extracted keywords.

[1108] Emotion recognition by emotion engine

[1109] The server processes the analyzed user input data with an emotion engine to recognize the user's emotional state. The emotion engine uses, for example, IBM Watson Natural Language Understanding or Microsoft Azure Text Analytics. The emotional state (e.g., joy, sadness, anxiety, etc.) is analyzed and used in subsequent processing.

[1110] Data analysis using ChatGPT

[1111] The server sends a request to a generative AI (e.g., ChatGPT) based on the extracted keywords and user sentiment data. A prompt is generated and sent to the ChatGPT API. ChatGPT then identifies the best case study or solution based on the request.

[1112] Formatting and displaying the proposed results

[1113] The server receives the suggestions from ChatGPT and formats them in a way that is easy for the user to understand. Specifically, it formats them visually using Markdown or HTML templates. The formatted data is sent to the device, which displays it to the user. The display format is dynamically adjusted based on the user's emotional state.

[1114] Specific examples

[1115] For example, if a user inputs a problem such as "I want to protect customer data by adding new security features," the server preprocesses the text and extracts keywords such as "security features," "customer data," and "protection." Suppose the emotion recognition engine recognizes "anxiety" from the user's input. Based on this information, the server sends a request to ChatGPT to identify appropriate case studies. For example, it might suggest "a case study where data breaches were prevented by introducing double authentication" or "a case study where data protection was strengthened by utilizing security add-ons." The server then formats this and displays it on the device to reassure the user.

[1116] Prompt Sentence Examples

[1117] If a user enters the challenge "I want to add new security features to protect customer data," the server might send the following prompt to ChatGPT:

[1118] "Regarding adding security features, please tell me about past examples of ways to protect customer data. Also, since users are feeling uneasy, please give us some suggestions to reassure them."

[1119] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality of proposals and the user experience.

[1120] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1121] Step 1:

[1122] The server reads the configuration file to get the database connection information (hostname, port, username, password, database name). This can be a JSON or YAML file. Then it connects to the internal database using a database client library (e.g. MySQL Connector, PostgreSQL). It connects to the database using the connection information and logs a successful connection message.

[1123] Input: Path to the configuration file

[1124] Output: Database connection object, connection success message

[1125] Step 2:

[1126] The server retrieves data on proposed cases and related solutions from the connected database using SQL queries and caches it in memory for use in future analysis steps.

[1127] Input: Database connection object

[1128] Output: A dataset of proposed cases and related solutions

[1129] Step 3:

[1130] The terminal displays an input form for the user to enter issues and requirements. This form includes a text area and a submit button. The user enters the issues and requirements into the form and clicks the submit button.

[1131] Input: None (initial display when starting the terminal)

[1132] Output: Display of user input form

[1133] Step 4:

[1134] The user enters the challenge in natural language and clicks the submit button, which causes the device to take the input text and send it securely to the server using the HTTPS protocol.

[1135] Input: User input (text)

[1136] Output: The assignment text sent to the server

[1137] Step 5:

[1138] The server receives the user's text data sent from the device and preprocesses it using a natural language processing (NLP) library (e.g., spaCy, NLTK). Specifically, it tokenizes the text and extracts important keywords and context. The extracted keywords are used as the basis for identifying suggestions.

[1139] Input: User assignment text

[1140] Output: Extracted keywords and context information

[1141] Step 6:

[1142] The server runs the preprocessed user input data through an emotion recognition engine (e.g., IBM Watson Natural Language Understanding, Microsoft Azure Text Analytics) to analyze the user's emotional state. The emotion data obtained from the emotion engine is used in the subsequent suggestion identification step.

[1143] Input: Preprocessed user input data

[1144] Output: User's emotional state

[1145] Step 7:

[1146] The server compiles the extracted keywords and user sentiment data and sends a request to a generative AI model (e.g., ChatGPT) based on the collected data. Specifically, it generates a prompt and sends it to the ChatGPT API. ChatGPT then identifies the best proposed case and related solutions based on the request.

[1147] Input: Extracted keywords, user emotion data

[1148] Output: Proposed cases and related solutions from ChatGPT

[1149] Step 8:

[1150] The server retrieves the proposed cases and related solutions returned by ChatGPT and formats them into a user-friendly format, using Markdown or HTML templates for visual presentation. The formatted data is then sent to the device.

[1151] Input: Suggestion data from ChatGPT

[1152] Output: Formatted proposal data

[1153] Step 9:

[1154] The device then displays the formatted suggestion data received from the server to the user. The display format is dynamically adjusted based on the user's emotional state, allowing the user to easily view the most suitable suggestions.

[1155] Input: Formatted proposal data

[1156] Output: Suggestion information displayed to the user

[1157] Through these steps, this system allows users to easily obtain proposals for resolving problems. Each step works in conjunction with the others, allowing even inexperienced employees to quickly and accurately provide optimal proposals.

[1158] (Application example 2)

[1159] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1160] In today's brick-and-mortar stores, it is a difficult task for even inexperienced sales staff to quickly and optimally recommend products. Furthermore, understanding customer emotions and making suggestions based on those emotions is important for improving the accuracy of recommendations and customer experience. Therefore, there is a need to develop a system that utilizes generative artificial intelligence based on past recommendation cases and related solutions to enable sales staff to quickly make recommendations that are optimal for customer needs.

[1161] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for connecting to an in-house database to acquire data on proposed cases and related solutions; means for receiving and preprocessing a problem input in natural language from a user; means for extracting important keywords and contextual information from the input problem using natural language processing; means for identifying optimal proposed cases and related solutions using generative artificial intelligence based on the extracted keywords and emotional data; and means for displaying the identified proposed cases and related solutions to the user in a format that corresponds to the user's emotional state. This enables even inexperienced sales staff to make quick and accurate product suggestions by utilizing past cases and related solutions, and to display suggestions that correspond to the customer's emotions.

[1162] An "internal database" is a database that stores accumulated information within an organization, such as past proposal cases and related solutions, and makes it accessible as needed.

[1163] "Natural language" refers to a language that humans use on a daily basis, and is text data that is converted into a format that is easy for machines to understand.

[1164] "Preprocessing" is an early stage of processing to analyze natural language data entered by the user and extract important information.

[1165] "Natural language processing" is a technology that enables computers to understand and generate human language, and is a technology that analyzes and understands text data.

[1166] "Keywords" are important words or phrases extracted from the user's input data and used for subsequent analysis and suggestion generation.

[1167] "Emotion data" is information about the emotional state analyzed from the user's input, and is data that classifies and recognizes the user's emotions.

[1168] "Generative AI" is an AI technology that learns from large datasets and generates optimal outputs based on input data.

[1169] "Proposal examples" are information about specific proposals made in the past and their results.

[1170] "Related solutions" are appropriate solutions or support information provided for specific issues.

[1171] "Users" are people and organizations that use the system to solve problems and receive suggestions.

[1172] "Display" is the act of providing information to a user in visual or textual form.

[1173] This invention relates to a system for brick-and-mortar stores that enables even inexperienced sales staff to quickly and optimally recommend products. The system acquires past recommendation cases and related solutions, and uses generative artificial intelligence (ChatGPT) to make optimal recommendations based on customer needs. Furthermore, by analyzing customer sentiment, the system improves the accuracy of recommendations and the customer experience.

[1174] Hardware and Software Configuration

[1175] Hardware:

[1176] 1. Server: Provides connectivity to the internal database, data analysis, and an interface with generative artificial intelligence (ChatGPT).

[1177] 2. Terminal: A device such as a smartphone or smart glasses that allows sales staff to operate the system while interacting with customers.

[1178] software:

[1179] 1. SQLite: Used to connect to and retrieve data from the internal database. Stores case studies and related solutions.

[1180] 2. Transformers: Natural Language Processing (NLP) library for preprocessing and analyzing user-supplied text data.

[1181] 3. OpenAI API: Used to connect with generative artificial intelligence (ChatGPT) to send appropriate prompts and generate optimal suggestions.

[1182] Data processing and calculation

[1183] The server performs the following steps:

[1184] 1. Database connection:

[1185] The server connects to an internal database to retrieve data on proposed cases and related solutions, and caches it in memory, allowing for quick access to the data.

[1186] 2. Preprocessing user input:

[1187] The server preprocesses the user input data sent from the device, which involves using natural language processing (NLP) techniques to extract important keywords and contextual information from the input text data.

[1188] 3. Emotion recognition:

[1189] The server uses an emotion engine to recognize emotions from the user's input data, identifying emotional states such as "anxiety," "joy," and "sadness," and sending them as additional context to the generative AI.

[1190] 4. Proposal generation using generative artificial intelligence:

[1191] The server sends a request to the generative AI (ChatGPT) based on the extracted keywords and sentiment data. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable suggestion for the user's input. An example of a prompt is as follows:

[1192] "Provide optimal product suggestions based on customer requirements. Keywords: Gift items Emotion: Anxiety"

[1193] 5. Displaying the proposed results:

[1194] The server formats the proposed cases and related solutions received from ChatGPT and displays them on the terminal in a format that corresponds to the user's emotional state, allowing the user to easily understand and see the proposals that correspond to the customer's emotions.

[1195] Specific examples

[1196] For example, if a customer asks, "I'm looking for a new gift item, but I don't know what to choose," the server preprocesses the text data and extracts keywords such as "gift" and "item." Assume the emotion engine determines the user's emotion as "anxiety." Based on this information, the server sends a request to ChatGPT to retrieve relevant suggestions. For example, "popular gift items" and "recent successful gift suggestion examples" are suggested. The server then displays these in an easy-to-understand format, allowing users to quickly and accurately suggest products.

[1197] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1198] Step 1:

[1199] The server connects to the company's database to retrieve data on proposed cases and related solutions. During this process, the server reads a configuration file to obtain the hostname, port, username, password, and database name for the database connection. It then uses a database client library to connect to the database, retrieves the required data using SQL queries, and caches it in memory, making the data quickly accessible for subsequent searches and proposal generation.

[1200] Input: Database connection information (hostname, port, username, password, database name)

[1201] Output: Data on proposed cases and related solutions cached in memory

[1202] Step 2:

[1203] Users input their issues and requirements in natural language through the terminal. The terminal receives the text data entered by the user and sends it to the server. This input includes specific customer requests, such as "I'm looking for a new gift item, but I don't know what to choose."

[1204] Input: Text data of issues and requirements in the user's natural language

[1205] Output: User's text data sent to the server

[1206] Step 3:

[1207] The server preprocesses the user input data sent from the device. In this step, natural language processing (NLP) techniques are used to extract important keywords and contextual information from the text data. For example, keywords such as "gift" and "item" are extracted from the input text "I'm looking for a new gift item, but I don't know what to choose."

[1208] Input: User's text data

[1209] Output: Extracted keywords and context information

[1210] Step 4:

[1211] The server uses an emotion engine to recognize the user's emotional state based on the extracted keywords and context information. For example, it uses a humorous emotion analysis library to identify the user's emotional state, such as "anxiety," "joy," or "sadness."

[1212] Input: Extracted keywords and context information

[1213] Output: User's emotional state data

[1214] Step 5:

[1215] The server sends a request to the generative AI (ChatGPT) based on the extracted keywords and the user's emotional state. This request includes the previously extracted keywords and the recognized emotional state. ChatGPT generates optimal case studies and related solutions based on this information. An example of the prompt is as follows:

[1216] "Provide optimal product suggestions based on customer requirements. Keywords: Gift items Emotion: Anxiety"

[1217] Input: extracted keywords and user's emotional state

[1218] Output: Best practice case studies and related solutions

[1219] Step 6:

[1220] The server formats the proposed cases and related solutions received from the generative AI (ChatGPT) and displays them on the device in an appropriate format depending on the user's emotional state. For example, if the user is recognized as "anxious," the server formats the proposed text to give a sense of security.

[1221] Input: Best practice case studies and related solutions

[1222] Output: Display of formatting suggestions according to the user's emotional state

[1223] Examples:

[1224] For example, if a customer asks, "I'm looking for a new gift item, but I don't know what to choose," the server preprocesses the text data and extracts keywords such as "gift" and "item." Assume the emotion engine determines the user's emotion as "anxiety." Based on this information, the server sends a request to ChatGPT to retrieve relevant suggestions. For example, "popular gift items" and "recent successful gift suggestion examples" are suggested. The server then displays these in an easy-to-understand format, allowing users to quickly and accurately suggest products.

[1225] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1226] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1227] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1228] [Fourth embodiment]

[1229] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1230] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1231] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1232] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1233] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1234] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1235] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1236] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1237] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1238] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1239] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1240] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1241] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1242] This invention relates to a system that enables even inexperienced employees to quickly make optimal proposals. This system connects to an internal database to retrieve past proposal examples and related solutions, and uses generative artificial intelligence to extract and display optimal proposals for the issues entered by the user.

[1243] The main components of this system include a server, a terminal, and a user. The specific roles and operations of each component are explained below.

[1244] 1. Internal database connection and data acquisition

[1245] The server connects to the company's internal database to retrieve data on past proposal cases and related solutions. The retrieved data is cached in the server's memory and used for subsequent processing. This allows for quick access to the required data.

[1246] 2. Accepting User Input

[1247] The terminal provides the user with a form for entering issues and requirements. The user uses this form to enter the problem or requirement they want to solve in natural language. Once they have completed entering the information, they click the "Submit" button, which sends the data to the server.

[1248] 3. Preprocessing User Input

[1249] The server pre-processes the received user input data, which involves using natural language processing (NLP) techniques to extract important keywords and context from the text data. The extracted information is used as the basis for identifying optimal suggestions.

[1250] 4. Data analysis using ChatGPT

[1251] The server then sends a request to ChatGPT, a generative artificial intelligence (AI) system, based on the extracted keywords. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable proposal for the user's input. The algorithms used here are designed to optimally match past data with current requirements.

[1252] 5. Displaying the proposed results

[1253] The server receives the identified proposal cases and related solutions and formats them for display to the user. The formatted data is displayed to the user via their device, allowing the user to quickly confirm the optimal proposal content and take concrete action.

[1254] Specific examples

[1255] For example, if a user inputs a problem such as "I want to protect customer data by adding new security features," the server preprocesses the text and extracts keywords such as "security features," "customer data," and "protection." Based on this information, the server sends a request to ChatGPT to identify relevant case studies. For example, ChatGPT may return suggestions such as "A case study where data breaches were prevented by introducing double authentication" or "A case study where data protection was enhanced by utilizing security add-ons." The server then formats the suggestions and displays them to the user via their device.

[1256] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality and efficiency of proposals.

[1257] The processing flow will be explained below.

[1258] Step 1:

[1259] The server reads the configuration file to obtain the hostname, port, username, password, and database name for the database connection. Then, it connects to the internal database using a database client library. If the connection is successful, the server retrieves the data of the proposed cases and related solutions using an SQL query and caches it in memory.

[1260] Step 2:

[1261] The terminal displays an input form for the user to enter issues and requirements. The user enters the problem or requirement they want to solve in natural language into this form and clicks the "Submit" button. The terminal receives the text data entered by the user and sends it to the server.

[1262] Step 3:

[1263] The server passes the text data received from the device to a natural language processing engine for preprocessing. During preprocessing, important keywords and contextual information are extracted from the input text. For example, if the input is "We would like to add new security features to protect customer data," keywords such as "security features," "customer data," and "protection" are extracted.

[1264] Step 4:

[1265] The server sends the extracted keywords to ChatGPT, a generative artificial intelligence system, and requests it to identify the best proposals and related solutions. ChatGPT then analyzes the proposals and related solutions in its internal database based on the keywords and identifies the proposals that best suit the user's challenges.

[1266] Step 5:

[1267] The server will format the proposed cases and related solutions received from ChatGPT and convert them into a format that is easy for users to understand, including adjusting the text format and adding diagrams and charts as needed.

[1268] Step 6:

[1269] The server sends the formatted proposal cases and related solutions to the terminal, which then displays the received information to the user. The user then checks the displayed proposal content and decides on the next action to take.

[1270] These steps enable even inexperienced employees to quickly and accurately make optimal proposals.

[1271] Example 1

[1272] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1273] The challenge is to provide a system that enables even inexperienced employees to quickly and accurately make optimal proposals. In particular, there is a demand for technology that effectively utilizes past proposal examples and related solutions within the company and utilizes generative artificial intelligence to extract optimal proposals.

[1274] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1275] In this invention, the server includes means for connecting to an internal database to acquire past proposal examples and related solutions, means for receiving and preprocessing issues input in natural language from a user, means for extracting important keywords from the user-input data using natural language processing, means for sending a request to a generative artificial intelligence based on the extracted keywords to identify optimal proposal examples and related solutions, and means for formatting the identified proposal examples and related solutions for display to the user. This enables even inexperienced employees to quickly and accurately make optimal proposals.

[1276] "Proposal examples" refer to specific examples of proposals made in the past and the results of their implementation.

[1277] "Related solutions" refer to solutions or approaches to specific problems or challenges.

[1278] A "database" refers to a collection of data that systematically organizes information and allows it to be accessed and managed efficiently.

[1279] "Natural language" refers to the human language used in everyday communication.

[1280] "Preprocessing" refers to the preparation of data before data analysis.

[1281] "Natural language processing" refers to techniques and methods that allow computers to understand and process human language.

[1282] "Keywords" refer to words or phrases that have significant meaning in text data.

[1283] "Generative AI" refers to AI technology that generates new information or suggestions based on specific input data.

[1284] A "request" refers to an instruction that a computer system is asked to perform.

[1285] "Formatting" refers to the process of converting data or information into an easy-to-read format.

[1286] "Format" refers to the arrangement and structure of information or data.

[1287] "User" refers to a user who operates the system.

[1288] A "server" refers to a computer system that provides data and services to other computers over a network.

[1289] These are the definitions of important words.

[1290] This invention relates to a system that enables even inexperienced employees to quickly and accurately make optimal proposals. This system connects to an internal database to retrieve past proposal examples and related solutions, and uses generative artificial intelligence to extract and display optimal proposals based on the issues entered by the user.

[1291] Hardware and Software Configuration

[1292] This system mainly consists of a server, a terminal, and a user. The detailed hardware and software configuration is shown below.

[1293] server:

[1294] A database server (e.g., MySQL or PostgreSQL)

[1295] Computation server (natural language processing libraries using Python environment: NLTK and spaCy)

[1296] Generative artificial intelligence (ChatGPT API)

[1297] Device:

[1298] A web browser (e.g. Chrome or Firefox)

[1299] Dedicated desktop application

[1300] User:

[1301] User operating the device

[1302] Processing flow

[1303] In-house database connection and data acquisition

[1304] The server connects to the company database and retrieves data on past proposals and related solutions using SQL queries, such as the following:

[1305] sql

[1306] SELECT FROM Proposal Case WHERE Solution='Security'

[1307] The acquired data is cached in the memory of the server and used for subsequent processing.

[1308] Accepting user input

[1309] The terminal provides a form for users to enter their issues and requirements in natural language. The user can enter, for example, "I would like to add new security features to protect customer data" through a web browser or dedicated application. Once the input is complete, the user clicks the "Submit" button, which sends the data to the server as an HTTP POST request.

[1310] Preprocessing User Input

[1311] The server preprocesses the received user input data. For example, it uses spaCy, a Python natural language processing library, to extract important keywords and context from the text data. Specifically, it performs text analysis as follows:

[1312] python

[1313] import spacy

[1314] nlp = spacy.load("en_core_web_sm")

[1315] doc = nlp("We want to add new security features to protect customer data")

[1316] keywords = [token.text for token in doc if token.is_stop != True and token.is_punct != True]

[1317] Data analysis using ChatGPT

[1318] The server sends a request to ChatGPT, a generative AI, based on the extracted keywords. For example, it sends the following prompt to the ChatGPT API:

[1319] A user wants to add new security features to protect customer data. Please suggest the best solution based on past proposal examples.

[1320] ChatGPT analyzes the proposed case and related solutions and returns optimal suggestions, such as "Preventing data breaches by implementing double authentication" and "Enhancing data protection by utilizing security add-ons."

[1321] Displaying the proposed results

[1322] The server receives the proposed cases and related solutions returned by ChatGPT and formats them for display to the user, for example, in HTML using Python's Jinja2 template engine, and sends them to the terminal:

[1323] python

[1324] from flask import render_template

[1325] render_template("result.html", proposals=proposals)

[1326] The formatted results are displayed to the user through the device's web browser or application, allowing the user to quickly and accurately view suggestions.

[1327] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality of proposals and improving business efficiency.

[1328] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1329] Step 1:

[1330] In-house database connection and data acquisition

[1331] The server connects to the company's internal database to retrieve data on past proposals and related solutions, extracting the necessary information from the database using SQL queries and caching it in memory.

[1332] input

[1333] Database connection information

[1334] SQL Query

[1335] Specific actions

[1336] The server establishes a database connection in the Python environment.

[1337] SQL query example: SELECT FROM Proposal WHERE solution='security'

[1338] The retrieved data is stored in a Python dictionary data structure.

[1339] output

[1340] Proposal cases and related solution data

[1341] Step 2:

[1342] Accepting user input

[1343] The terminal provides a form for users to input issues and requirements in natural language. The user enters text into the input form and presses the "Submit" button to send the data to the server.

[1344] input

[1345] User-entered issue or requirement text

[1346] Specific actions

[1347] Create a form screen using JavaScript on a web browser.

[1348] The form is filled out with the message, "I would like to add new security features to protect customer data."

[1349] When the user clicks the "Submit" button, the data is sent to the server as an HTTP POST request.

[1350] output

[1351] User-entered data sent to the server

[1352] Step 3:

[1353] Preprocessing User Input

[1354] The server preprocesses the received user input data, specifically by using natural language processing (NLP) techniques to extract important keywords and contextual information from the text data.

[1355] input

[1356] User input data (text)

[1357] Specific actions

[1358] Analyze the text using a Python natural language processing library (e.g. spaCy).

[1359] Example code:

[1360] python

[1361] import spacy

[1362] nlp = spacy.load("en_core_web_sm")

[1363] doc = nlp("We want to add new security features to protect customer data")

[1364] keywords = [token.text for token in doc if token.is_stop != True and token.is_punct != True]

[1365] Keyword extraction results: "security features," "customer data," "protection"

[1366] output

[1367] Extracted keywords and context information

[1368] Step 4:

[1369] Data analysis using ChatGPT

[1370] The server then sends a request to ChatGPT, a generative artificial intelligence system, based on the extracted keywords. Specifically, it uses the ChatGPT API to provide prompts and extract the best case studies and related solutions.

[1371] input

[1372] Extracted keywords

[1373] Specific actions

[1374] Send a prompt like this to the ChatGPT API:

[1375] A user wants to add new security features to protect customer data. Please suggest the best solution based on past proposal examples.

[1376] API response examples: "Example of preventing data breaches by implementing double authentication" and "Example of strengthening data protection by utilizing security add-ons"

[1377] output

[1378] Proposal examples and related solutions from ChatGPT

[1379] Step 5:

[1380] Displaying the proposed results

[1381] The server formats the proposed cases and related solutions received from ChatGPT and displays them in a user-friendly format. Specifically, it uses HTML templates to convert the data into a display format and sends it to the terminal.

[1382] input

[1383] Proposal examples and related solutions from ChatGPT

[1384] Specific actions

[1385] The HTML format is created using Python's Jinja2 template engine.

[1386] Example code:

[1387] python

[1388] from flask import render_template

[1389] render_template("result.html", proposals=proposals)

[1390] The formatted HTML is sent to the terminal and displayed on the web browser.

[1391] output

[1392] Proposal examples and related solutions formatted in HTML format

[1393] Through the above processing steps, this system enables even inexperienced employees to quickly and accurately make optimal proposals.

[1394] (Application example 1)

[1395] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1396] The challenge is that inexperienced employees have difficulty making quick and accurate security proposals. In particular, in the field of security services, it is necessary to propose appropriate countermeasures immediately, but employees often fail to make appropriate proposals due to their lack of experience and knowledge. It is necessary to improve this situation and increase the quality and efficiency of proposals.

[1397] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1398] In this invention, the server includes means for connecting to an internal database to acquire data on proposed cases and related solutions, means for receiving and preprocessing a problem input in natural language from a user, means for extracting important keywords from the input problem using natural language processing, means for identifying optimal proposed cases and related solutions using generative artificial intelligence, and means for quickly displaying the proposed cases and related solutions identified using the generative artificial intelligence to the user. This enables even inexperienced employees to make prompt and appropriate security proposals.

[1399] An "internal database" is a database that stores data on past proposal cases and related solutions that are managed within the company.

[1400] A "natural language" is a language used by humans on a daily basis, that is, a language used for human thought and communication, rather than a specific programming language.

[1401] "Preprocessing" refers to the initial data processing process that is performed to analyze natural language text data entered by a user and extract important information.

[1402] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language, and is used to extract important keywords and information from text data.

[1403] "Generative AI" is an AI system that uses machine learning algorithms to automatically generate new information and suggestions, and is particularly involved in natural language generation.

[1404] "Means for promptly displaying" refers to a function that allows a computer system to display processing results to a user in a short period of time.

[1405] "Keywords" are the most important words and phrases extracted from the user's input task.

[1406] "Related solutions" are solutions or countermeasures that are considered effective for solving a particular problem or issue.

[1407] "Proposal examples" are data showing the specific content of proposals made in the past and success stories based on those proposals.

[1408] "Means for displaying to the user" refers to a function for visually showing the information and suggestions generated by the computer system to the user.

[1409] MODE FOR CARRYING OUT THE INVENTION

[1410] The present invention relates to a system that enables even inexperienced employees to quickly and appropriately provide optimal suggestions. In particular, the present invention is applied to a smartphone application for providing instant security suggestions in the field of security services. Specific embodiments of the present invention are described below.

[1411] System Overview

[1412] The system of the present invention comprises the following main components:

[1413] 1. Server: Connects to the internal database and retrieves data on past proposal cases and related solutions.

[1414] 2. Terminal: Installed on the smartphone, it provides an interface for user input.

[1415] 3. User: Field staff enter data using their smartphone.

[1416] Operation of each component

[1417] 1. Internal database connection and data acquisition:

[1418] The server accesses the company's internal database to obtain data on past proposal cases and related solutions.

[1419] The acquired data is cached in the server's memory and used for subsequent processing.

[1420] 2. Accepting user input:

[1421] The terminal provides a form for the user to enter their issues and requirements.

[1422] The user uses the form to enter the task in natural language and presses the "Submit" button to send the data to the server.

[1423] 3. Preprocessing user input:

[1424] The server pre-processes the data received from the user and extracts important keywords using natural language processing (NLP) techniques.

[1425] 4. Data analysis using generative artificial intelligence:

[1426] The server sends a request to a generative artificial intelligence (a model such as ChatGPT) based on the extracted keywords.

[1427] Generative AI analyzes relevant proposal cases and solutions from an internal database to generate optimal proposals.

[1428] 5. Displaying the proposed results:

[1429] The server transmits the generated suggestions to the terminal for quick display to the user.

[1430] Users can check the suggestions on their smartphones and take concrete action.

[1431] Hardware and software used

[1432] Servers: Utilize high-performance database servers, servers for natural language processing, and computing resources to run generative artificial intelligence models.

[1433] Device: A smartphone (iOS or Android) is used.

[1434] Software: We use commercial NLP APIs for natural language processing, and advanced generative AI models such as ChatGPT for generative artificial intelligence.

[1435] Specific examples

[1436] For example, if a user types "I want to prevent unauthorized access" on their smartphone, the server preprocesses this text and extracts keywords such as "unauthorized access" and "prevention." Based on this information, the server sends a request to a generative AI to generate relevant suggestions. For example, a specific suggestion such as "implement two-factor authentication" is displayed.

[1437] Prompt Sentence Examples

[1438] Please create the best security solution to meet your needs. Keywords: Unauthorized access, Prevention

[1439] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1440] Step 1:

[1441] The server connects to the company's internal database to retrieve data on past proposals and related solutions. To do this, the server issues a database query and caches the required information in memory, allowing for quick access in subsequent processes. The database connection information is given as input, and the data on proposals and related solutions is obtained as output.

[1442] Step 2:

[1443] The terminal provides a form for users to enter tasks and requirements. The user enters the task in natural language into this form and presses the "Submit" button. This sends the input data to the server. The input is the user's text input, and the input is sent to the server as the output.

[1444] Step 3:

[1445] The server preprocesses the received user input data. This preprocessing uses natural language processing (NLP) techniques to extract important keywords from the input text. Specifically, it uses text analysis algorithms to select words and interpret context. The input is the user's natural language data, and the output is a list of keywords.

[1446] Step 4:

[1447] The server sends a request to a generative AI system (ChatGPT) based on the extracted keywords. In this process, the keywords and related issues are sent to the generative AI model in the form of a prompt. The generative AI model then generates optimal suggestions based on this prompt. The input is a list of keywords and a prompt, and the output is the generated suggestions.

[1448] Step 5:

[1449] The server sends the generated suggestions to the terminal for quick display to the user. In this process, the generated suggestions are formatted into a format that is easy for humans to understand (for example, bullet points or step format). The input is a suggestion from the generation AI, and the formatted suggestion data is sent to the user's terminal as output.

[1450] Step 6:

[1451] The terminal displays the suggestions sent from the server to the user. This display includes an interface design that allows the user to intuitively understand the suggestions. The input is the formatting suggestions sent from the server, and the output is a visual representation of the suggestions to the user.

[1452] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1453] This invention relates to a system that enables even inexperienced employees to quickly make optimal proposals. This system connects to an internal database to retrieve past proposal examples and related solutions, and uses generative artificial intelligence to extract and display optimal proposals for issues entered by users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the accuracy of proposals and the user experience are improved.

[1454] The main components of this system include a server, a terminal, and a user. The specific roles and operations of each component are explained below.

[1455] 1. Internal database connection and data acquisition

[1456] The server reads the configuration file to obtain the hostname, port, username, password, and database name for the database connection. Then, it connects to the internal database using a database client library. If the connection is successful, the server retrieves the data of the proposed cases and related solutions using an SQL query and caches it in memory.

[1457] 2. Accepting User Input

[1458] The terminal provides the user with an input form for entering issues and requirements. The user enters the problem or requirement they want to solve in natural language into this form and clicks the "Submit" button. The terminal receives the text data entered by the user and sends it to the server.

[1459] 3. Preprocessing User Input

[1460] The server pre-processes the received user input data, which involves using natural language processing (NLP) techniques to extract important keywords and context from the text data. The extracted information is used as the basis for identifying optimal suggestions.

[1461] 4. Emotion Recognition by Emotion Engine

[1462] The server uses an emotion engine to recognize user emotions from pre-processed user input data. The emotion engine analyzes the input text data and identifies the user's emotional state (e.g., joy, sadness, anger, etc.). The emotion data is used as additional context before being sent to the generative artificial intelligence.

[1463] 5. Data analysis using ChatGPT

[1464] The server sends a request to ChatGPT, a generative artificial intelligence system, based on the extracted keywords and user emotional data. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable proposal for the user's input. The algorithms used here are designed to optimally match historical data, current requirements, and the user's emotional state.

[1465] 6. Displaying the proposed results

[1466] The server formats the proposed cases and related solutions received from ChatGPT and converts them into a format that is easy for users to understand. The formatted data is then displayed to the user through their device. The display format and content are dynamically adjusted according to the user's emotions, improving the user experience.

[1467] Specific examples

[1468] For example, if a user inputs a problem such as "I want to protect customer data by adding new security features," the server preprocesses the text and extracts keywords such as "security features," "customer data," and "protection." Furthermore, let's assume that the emotion engine recognizes "anxiety" from the user's input. Based on this information, the server sends a request to ChatGPT to identify relevant case studies. For example, ChatGPT may return suggestions such as "A case study where data breaches were prevented by introducing double authentication" or "A case study where data protection was strengthened by utilizing security add-ons." The server then formats the suggestions and displays them in a way that provides reassurance to the user, reducing their anxiety. The results are displayed to the user via their device, allowing them to quickly and accurately decide on their next course of action.

[1469] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality of proposals and the user experience.

[1470] The processing flow will be explained below.

[1471] Step 1:

[1472] The server reads the configuration file to obtain the hostname, port, username, password, and database name for the database connection. Then, it connects to the internal database using a database client library. If the connection is successful, the server retrieves the data of the proposed cases and related solutions using an SQL query and caches it in memory.

[1473] Step 2:

[1474] The terminal provides the user with an input form for entering issues and requirements. The user enters the problem or requirement they want to solve in natural language into this form and clicks the "Submit" button. The terminal receives the text data entered by the user and sends it to the server.

[1475] Step 3:

[1476] The server passes the text data received from the terminal to a natural language processing engine for preprocessing. Preprocessing involves extracting important keywords and contextual information from the input text. For example, if the input is "We would like to add new security features to protect customer data," keywords such as "security features," "customer data," and "protection" are extracted.

[1477] Step 4:

[1478] The server sends the extracted keywords to an emotion engine to recognize the user's emotions. The emotion engine analyzes the input text data and identifies the user's emotional state (e.g., joy, sadness, anger, etc.). The recognized emotion data is used as additional context before being sent to the generative artificial intelligence.

[1479] Step 5:

[1480] The server sends a request to ChatGPT, a generative artificial intelligence system, based on the extracted keywords and user emotional data. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable proposal for the user's input. The algorithms used here are designed to optimally match historical data, current requirements, and the user's emotional state.

[1481] Step 6:

[1482] The server will format the proposed cases and related solutions received from ChatGPT and convert them into a format that is easy for users to understand, including adjusting the text format and adding diagrams and charts as needed.

[1483] Step 7:

[1484] The server sends the formatted proposals and related solutions to the terminal, which then displays the received information to the user. The display format and content are dynamically adjusted according to the user's emotions, improving the user experience. This allows the user to quickly review the proposals and decide on their next action.

[1485] These steps enable even inexperienced employees to quickly and accurately make optimal proposals.

[1486] Example 2

[1487] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1488] In the past, it was difficult for inexperienced employees to quickly and accurately make optimal suggestions. To improve the quality of suggestions and the user experience, analysis based on a large amount of data and optimal suggestions that take into account the user's emotions are required, but no system that can achieve this has yet existed. The present invention provides technology to solve these problems.

[1489] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for connecting to an in-house database to acquire data on proposed cases and related solutions, a means for receiving and preprocessing a problem input in natural language from a user, a means for extracting important keywords from the input problem using natural language processing, a means for identifying optimal proposed cases and related solutions using generative artificial intelligence based on the extracted keywords, a means for analyzing the user's emotional state using an emotion recognition engine, and a means for displaying the identified proposed cases and related solutions to the user. This enables even inexperienced employees to quickly and accurately make optimal suggestions, thereby improving the quality of proposals and the user experience.

[1490] An "internal database" is a database that stores data on proposed cases and related solutions accumulated within a company or organization.

[1491] A "natural language" is a language that humans use on a daily basis, and in contrast to programming languages, it has the characteristic of being able to be understood and expressed intuitively.

[1492] "Preprocessing" refers to a series of steps that transform raw data into a form that is easier to analyze and process, such as data cleaning, tokenization, and keyword extraction.

[1493] "Natural Language Processing (NLP)" is a field of computer science and artificial intelligence that refers to techniques and methodologies for understanding and processing human language.

[1494] "Generative AI" refers to AI that has the ability to generate new data or information based on input data, such as text generation models.

[1495] An "emotion recognition engine" is software or algorithms that analyze text and voice data and use it to identify a user's emotional state (such as joy, anger, or sadness).

[1496] "Proposal examples" are specific examples of proposals made in the past, and include information about the process and results of those proposals.

[1497] "Related Solutions" are solutions or countermeasures related to the proposed case, which provide optimal solutions to specific problems or issues.

[1498] "Keywords" refer to words or phrases that are particularly important in a given text or data, and are used when analyzing or searching data.

[1499] A "prompt sentence" is an input sentence for generative artificial intelligence, and is used to give specific instructions or questions to the AI.

[1500] "Formatting" refers to the process of converting data or information into a format that is easy for users to understand, and refers to creating a layout or format that is visually easy to read.

[1501] This invention relates to a system that enables even inexperienced employees to make prompt and appropriate proposals. This system connects to an internal database, retrieves data on past proposal cases and related solutions, and combines generative artificial intelligence and an emotion recognition engine to extract and display optimal proposals based on the issues entered by the user. Furthermore, by recognizing the user's emotions, the system improves the accuracy of proposals and the user experience.

[1502] Main components

[1503] The main components of this system are a server, a terminal, and a user.

[1504] In-house database connection and data acquisition

[1505] The server reads the configuration file and obtains the information required to connect to the database (host name, port, user name, password, database name). It then connects to the database using a database client library (e.g., MySQL Connector, PostgreSQL). If the connection is successful, it uses an SQL query to retrieve data on past proposals and related solutions from the internal database and caches the results in memory.

[1506] Accepting user input

[1507] The terminal provides the user with an input form for entering issues and requirements in natural language. The user fills out this form and clicks the "Submit" button. The terminal obtains the user's input text and sends it to the server. The HTTPS protocol is used for transmission to ensure security.

[1508] Preprocessing User Input

[1509] The server preprocesses the received user text data by using a natural language processing (NLP) library (e.g., spaCy, NLTK) to tokenize the text and extract important keywords and phrases, and then determines what types of suggestions are needed based on the extracted keywords.

[1510] Emotion recognition by emotion engine

[1511] The server processes the analyzed user input data with an emotion engine to recognize the user's emotional state. The emotion engine uses, for example, IBM Watson Natural Language Understanding or Microsoft Azure Text Analytics. The emotional state (e.g., joy, sadness, anxiety, etc.) is analyzed and used in subsequent processing.

[1512] Data analysis using ChatGPT

[1513] The server sends a request to a generative AI (e.g., ChatGPT) based on the extracted keywords and user sentiment data. A prompt is generated and sent to the ChatGPT API. ChatGPT then identifies the best case study or solution based on the request.

[1514] Formatting and displaying the proposed results

[1515] The server receives the suggestions from ChatGPT and formats them in a way that is easy for the user to understand. Specifically, it formats them visually using Markdown or HTML templates. The formatted data is sent to the device, which displays it to the user. The display format is dynamically adjusted based on the user's emotional state.

[1516] Specific examples

[1517] For example, if a user inputs a problem such as "I want to protect customer data by adding new security features," the server preprocesses the text and extracts keywords such as "security features," "customer data," and "protection." Suppose the emotion recognition engine recognizes "anxiety" from the user's input. Based on this information, the server sends a request to ChatGPT to identify appropriate case studies. For example, it might suggest "a case study where data breaches were prevented by introducing double authentication" or "a case study where data protection was strengthened by utilizing security add-ons." The server then formats this and displays it on the device to reassure the user.

[1518] Prompt Sentence Examples

[1519] If a user enters the challenge "I want to add new security features to protect customer data," the server might send the following prompt to ChatGPT:

[1520] "Regarding adding security features, please tell me about past examples of ways to protect customer data. Also, since users are feeling uneasy, please give us some suggestions to reassure them."

[1521] With the above configuration, the system of the present invention enables even inexperienced employees to quickly and accurately make optimal proposals, thereby improving the quality of proposals and the user experience.

[1522] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1523] Step 1:

[1524] The server reads the configuration file to get the database connection information (hostname, port, username, password, database name). This can be a JSON or YAML file. Then it connects to the internal database using a database client library (e.g. MySQL Connector, PostgreSQL). It connects to the database using the connection information and logs a successful connection message.

[1525] Input: Path to the configuration file

[1526] Output: Database connection object, connection success message

[1527] Step 2:

[1528] The server retrieves data on proposed cases and related solutions from the connected database using SQL queries and caches it in memory for use in future analysis steps.

[1529] Input: Database connection object

[1530] Output: A dataset of proposed cases and related solutions

[1531] Step 3:

[1532] The terminal displays an input form for the user to enter issues and requirements. This form includes a text area and a submit button. The user enters the issues and requirements into the form and clicks the submit button.

[1533] Input: None (initial display when starting the terminal)

[1534] Output: Display of user input form

[1535] Step 4:

[1536] The user enters the challenge in natural language and clicks the submit button, which causes the device to take the input text and send it securely to the server using the HTTPS protocol.

[1537] Input: User input (text)

[1538] Output: The assignment text sent to the server

[1539] Step 5:

[1540] The server receives the user's text data sent from the device and preprocesses it using a natural language processing (NLP) library (e.g., spaCy, NLTK). Specifically, it tokenizes the text and extracts important keywords and context. The extracted keywords are used as the basis for identifying suggestions.

[1541] Input: User assignment text

[1542] Output: Extracted keywords and context information

[1543] Step 6:

[1544] The server runs the preprocessed user input data through an emotion recognition engine (e.g., IBM Watson Natural Language Understanding, Microsoft Azure Text Analytics) to analyze the user's emotional state. The emotion data obtained from the emotion engine is used in the subsequent suggestion identification step.

[1545] Input: Preprocessed user input data

[1546] Output: User's emotional state

[1547] Step 7:

[1548] The server compiles the extracted keywords and user sentiment data and sends a request to a generative AI model (e.g., ChatGPT) based on the collected data. Specifically, it generates a prompt and sends it to the ChatGPT API. ChatGPT then identifies the best proposed case and related solutions based on the request.

[1549] Input: Extracted keywords, user emotion data

[1550] Output: Proposed cases and related solutions from ChatGPT

[1551] Step 8:

[1552] The server retrieves the proposed cases and related solutions returned by ChatGPT and formats them into a user-friendly format, using Markdown or HTML templates for visual presentation. The formatted data is then sent to the device.

[1553] Input: Suggestion data from ChatGPT

[1554] Output: Formatted proposal data

[1555] Step 9:

[1556] The device then displays the formatted suggestion data received from the server to the user. The display format is dynamically adjusted based on the user's emotional state, allowing the user to easily view the most suitable suggestions.

[1557] Input: Formatted proposal data

[1558] Output: Suggestion information displayed to the user

[1559] Through these steps, this system allows users to easily obtain proposals for resolving problems. Each step works in conjunction with the others, allowing even inexperienced employees to quickly and accurately provide optimal proposals.

[1560] (Application example 2)

[1561] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1562] In today's brick-and-mortar stores, it is a difficult task for even inexperienced sales staff to quickly and optimally recommend products. Furthermore, understanding customer emotions and making suggestions based on those emotions is important for improving the accuracy of recommendations and customer experience. Therefore, there is a need to develop a system that utilizes generative artificial intelligence based on past recommendation cases and related solutions to enable sales staff to quickly make recommendations that are optimal for customer needs.

[1563] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for connecting to an in-house database to acquire data on proposed cases and related solutions; means for receiving and preprocessing a problem input in natural language from a user; means for extracting important keywords and contextual information from the input problem using natural language processing; means for identifying optimal proposed cases and related solutions using generative artificial intelligence based on the extracted keywords and emotional data; and means for displaying the identified proposed cases and related solutions to the user in a format that corresponds to the user's emotional state. This enables even inexperienced sales staff to make quick and accurate product suggestions by utilizing past cases and related solutions, and to display suggestions that correspond to the customer's emotions.

[1564] An "internal database" is a database that stores accumulated information within an organization, such as past proposal cases and related solutions, and makes it accessible as needed.

[1565] "Natural language" refers to a language that humans use on a daily basis, and is text data that is converted into a format that is easy for machines to understand.

[1566] "Preprocessing" is an early stage of processing to analyze natural language data entered by the user and extract important information.

[1567] "Natural language processing" is a technology that enables computers to understand and generate human language, and is a technology that analyzes and understands text data.

[1568] "Keywords" are important words or phrases extracted from the user's input data and used for subsequent analysis and suggestion generation.

[1569] "Emotion data" is information about the emotional state analyzed from the user's input, and is data that classifies and recognizes the user's emotions.

[1570] "Generative AI" is an AI technology that learns from large datasets and generates optimal outputs based on input data.

[1571] "Proposal examples" are information about specific proposals made in the past and their results.

[1572] "Related solutions" are appropriate solutions or support information provided for specific issues.

[1573] "Users" are people and organizations that use the system to solve problems and receive suggestions.

[1574] "Display" is the act of providing information to a user in visual or textual form.

[1575] This invention relates to a system for brick-and-mortar stores that enables even inexperienced sales staff to quickly and optimally recommend products. The system acquires past recommendation cases and related solutions, and uses generative artificial intelligence (ChatGPT) to make optimal recommendations based on customer needs. Furthermore, by analyzing customer sentiment, the system improves the accuracy of recommendations and the customer experience.

[1576] Hardware and Software Configuration

[1577] Hardware:

[1578] 1. Server: Provides connectivity to the internal database, data analysis, and an interface with generative artificial intelligence (ChatGPT).

[1579] 2. Terminal: A device such as a smartphone or smart glasses that allows sales staff to operate the system while interacting with customers.

[1580] software:

[1581] 1. SQLite: Used to connect to and retrieve data from the internal database. Stores case studies and related solutions.

[1582] 2. Transformers: Natural Language Processing (NLP) library for preprocessing and analyzing user-supplied text data.

[1583] 3. OpenAI API: Used to connect with generative artificial intelligence (ChatGPT) to send appropriate prompts and generate optimal suggestions.

[1584] Data processing and calculation

[1585] The server performs the following steps:

[1586] 1. Database connection:

[1587] The server connects to an internal database to retrieve data on proposed cases and related solutions, and caches it in memory, allowing for quick access to the data.

[1588] 2. Preprocessing user input:

[1589] The server preprocesses the user input data sent from the device, which involves using natural language processing (NLP) techniques to extract important keywords and contextual information from the input text data.

[1590] 3. Emotion recognition:

[1591] The server uses an emotion engine to recognize emotions from the user's input data, identifying emotional states such as "anxiety," "joy," and "sadness," and sending them as additional context to the generative AI.

[1592] 4. Proposal generation using generative artificial intelligence:

[1593] The server sends a request to the generative AI (ChatGPT) based on the extracted keywords and sentiment data. ChatGPT analyzes the proposed cases and related solutions in its internal database to identify the most suitable suggestion for the user's input. An example of a prompt is as follows:

[1594] "Provide optimal product suggestions based on customer requirements. Keywords: Gift items Emotion: Anxiety"

[1595] 5. Displaying the proposed results:

[1596] The server formats the proposed cases and related solutions received from ChatGPT and displays them on the terminal in a format that corresponds to the user's emotional state, allowing the user to easily understand and see the proposals that correspond to the customer's emotions.

[1597] Specific examples

[1598] For example, if a customer asks, "I'm looking for a new gift item, but I don't know what to choose," the server preprocesses the text data and extracts keywords such as "gift" and "item." Assume the emotion engine determines the user's emotion as "anxiety." Based on this information, the server sends a request to ChatGPT to retrieve relevant suggestions. For example, "popular gift items" and "recent successful gift suggestion examples" are suggested. The server then displays these in an easy-to-understand format, allowing users to quickly and accurately suggest products.

[1599] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1600] Step 1:

[1601] The server connects to the company's database to retrieve data on proposed cases and related solutions. During this process, the server reads a configuration file to obtain the hostname, port, username, password, and database name for the database connection. It then uses a database client library to connect to the database, retrieves the required data using SQL queries, and caches it in memory, making the data quickly accessible for subsequent searches and proposal generation.

[1602] Input: Database connection information (hostname, port, username, password, database name)

[1603] Output: Data on proposed cases and related solutions cached in memory

[1604] Step 2:

[1605] Users input their issues and requirements in natural language through the terminal. The terminal receives the text data entered by the user and sends it to the server. This input includes specific customer requests, such as "I'm looking for a new gift item, but I don't know what to choose."

[1606] Input: Text data of issues and requirements in the user's natural language

[1607] Output: User's text data sent to the server

[1608] Step 3:

[1609] The server preprocesses the user input data sent from the device. In this step, natural language processing (NLP) techniques are used to extract important keywords and contextual information from the text data. For example, keywords such as "gift" and "item" are extracted from the input text "I'm looking for a new gift item, but I don't know what to choose."

[1610] Input: User's text data

[1611] Output: Extracted keywords and context information

[1612] Step 4:

[1613] The server uses an emotion engine to recognize the user's emotional state based on the extracted keywords and context information. For example, it uses a humorous emotion analysis library to identify the user's emotional state, such as "anxiety," "joy," or "sadness."

[1614] Input: Extracted keywords and context information

[1615] Output: User's emotional state data

[1616] Step 5:

[1617] The server sends a request to the generative AI (ChatGPT) based on the extracted keywords and the user's emotional state. This request includes the previously extracted keywords and the recognized emotional state. ChatGPT generates optimal case studies and related solutions based on this information. An example of the prompt is as follows:

[1618] "Provide optimal product suggestions based on customer requirements. Keywords: Gift items Emotion: Anxiety"

[1619] Input: extracted keywords and user's emotional state

[1620] Output: Best practice case studies and related solutions

[1621] Step 6:

[1622] The server formats the proposed cases and related solutions received from the generative AI (ChatGPT) and displays them on the device in an appropriate format depending on the user's emotional state. For example, if the user is recognized as "anxious," the server formats the proposed text to give a sense of security.

[1623] Input: Best practice case studies and related solutions

[1624] Output: Display of formatting suggestions according to the user's emotional state

[1625] Examples:

[1626] For example, if a customer asks, "I'm looking for a new gift item, but I don't know what to choose," the server preprocesses the text data and extracts keywords such as "gift" and "item." Assume the emotion engine determines the user's emotion as "anxiety." Based on this information, the server sends a request to ChatGPT to retrieve relevant suggestions. For example, "popular gift items" and "recent successful gift suggestion examples" are suggested. The server then displays these in an easy-to-understand format, allowing users to quickly and accurately suggest products.

[1627] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1628] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1629] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1630] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1631] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1632] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1633] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1634] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1635] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1636] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1637] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1638] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1639] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1640] 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.

[1641] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1642] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1643] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1644] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1645] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1646] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1647] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1648] The following is further disclosed regarding the above embodiment.

[1649] (Claim 1)

[1650] A means of connecting to the company's internal database to obtain data on proposed cases and related solutions;

[1651] means for receiving and preprocessing a task input in natural language from a user;

[1652] A means for extracting important keywords from input issues using natural language processing;

[1653] A means for identifying optimal proposal cases and related solutions using generative artificial intelligence based on the extracted keywords;

[1654] a means for displaying the identified proposal cases and related solutions to a user;

[1655] A system including:

[1656] (Claim 2)

[1657] 10. The system of claim 1, further comprising means for extracting keywords and contextual information from the preprocessed user input data.

[1658] (Claim 3)

[1659] The system of claim 1, further comprising means for formatting the proposed cases and related solutions identified by the generative artificial intelligence into a format that is easy for humans to understand and display them to the user.

[1660] "Example 1"

[1661] (Claim 1)

[1662] A means to connect to the company's internal database to retrieve past proposal cases and related solutions;

[1663] means for receiving and preprocessing a task input in natural language from a user;

[1664] means for extracting important keywords from user-entered data using natural language processing;

[1665] A means for sending a request to a generative artificial intelligence to identify optimal proposal cases and related solutions based on the extracted keywords;

[1666] means for formatting the identified proposal cases and related solutions for display to a user;

[1667] A system including:

[1668] (Claim 2)

[1669] 10. The system of claim 1, further comprising means for extracting keywords and contextual information from the preprocessed user input data.

[1670] (Claim 3)

[1671] The system of claim 1, further comprising means for formatting the proposed cases and related solutions identified by the generative artificial intelligence into a format that is easy for humans to understand and display them to the user.

[1672] "Application Example 1"

[1673] (Claim 1)

[1674] A means of connecting to the company's internal database to obtain data on proposed cases and related solutions;

[1675] means for receiving and preprocessing a task input in natural language from a user;

[1676] A means for extracting important keywords from input issues using natural language processing;

[1677] A means for identifying optimal proposal cases and related solutions using generative artificial intelligence based on the extracted keywords;

[1678] A means for quickly displaying to a user the proposed cases and related solutions identified using generative artificial intelligence;

[1679] A system including:

[1680] (Claim 2)

[1681] 10. The system of claim 1, further comprising means for extracting keywords and contextual information from the preprocessed user input data and analyzing past cases and related solutions using generative artificial intelligence.

[1682] (Claim 3)

[1683] The system of claim 1, further comprising means for formatting the proposed cases and related solutions identified by the generative artificial intelligence into a format that is easy for humans to understand and display them to the user.

[1684] "Example 2: Combining Emotion Engines"

[1685] (Claim 1)

[1686] A means of connecting to the company's internal database to obtain data on proposed cases and related solutions;

[1687] means for receiving and preprocessing a task input in natural language from a user;

[1688] A means for extracting important keywords from input issues using natural language processing;

[1689] A means for identifying optimal proposal cases and related solutions using generative artificial intelligence based on the extracted keywords;

[1690] means for analyzing the emotional state of a user using an emotion recognition engine;

[1691] a means for displaying the identified proposal cases and related solutions to a user;

[1692] A system including:

[1693] (Claim 2)

[1694] 10. The system of claim 1, further comprising means for extracting keywords and contextual information from the preprocessed user input data.

[1695] (Claim 3)

[1696] 2. The system of claim 1, further comprising means for generating prompt sentences for the generative artificial intelligence based on the user's emotional state analyzed by the emotion recognition engine, and for identifying suggested cases and related solutions.

[1697] (Claim 4)

[1698] The system of claim 1, further comprising means for formatting the proposed cases and related solutions identified by the generative artificial intelligence into a format that is easy for humans to understand and display them to the user.

[1699] "Application example 2 when combining emotion engines"

[1700] (Claim 1)

[1701] A means of connecting to the company's internal database to obtain data on proposed cases and related solutions;

[1702] means for receiving and preprocessing a task input in natural language from a user;

[1703] A means for extracting important keywords from input issues using natural language processing;

[1704] A means for identifying optimal proposal cases and related solutions using generative artificial intelligence based on the extracted keywords and sentiment data; and

[1705] a means for displaying the identified proposed cases and related solutions to the user in a format that corresponds to the emotional state of the user;

[1706] A system including:

[1707] (Claim 2)

[1708] 10. The system of claim 1, further comprising means for extracting keywords and contextual information from the preprocessed user input data.

[1709] (Claim 3)

[1710] The system of claim 1, further comprising means for formatting the proposed cases and related solutions identified by the generative artificial intelligence into a format that is easy for humans to understand and display them to the user. [Explanation of symbols]

[1711] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of connecting to the company's internal database to obtain data on proposed cases and related solutions; means for receiving and preprocessing a task input in natural language from a user; A means for extracting important keywords from input issues using natural language processing; A means for identifying optimal proposal cases and related solutions using generative artificial intelligence based on the extracted keywords; a means for displaying the identified proposal cases and related solutions to a user; A system including:

2. 10. The system of claim 1, further comprising means for extracting keywords and contextual information from the preprocessed user input data.

3. The system according to claim 1 , further comprising means for formatting the proposed cases and related solutions identified by the generative artificial intelligence into a format that is easy for humans to understand and display them to the user.

Images