System

Abstract

To provide a system.SOLUTION: A system includes: means for receiving a problem of a user input in a natural language; means for analyzing the problem using a generative AI to specify necessary information; means for acquiring the specified information from a database; means for generating, using the generative AI, solutions based on the necessary information acquired from the database; and means for feeding back the generated 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] Data analysis has become essential for solving problems in any profession, but it has the problem of requiring a lot of unproductive time and specialized knowledge. [Means for solving the problem]

[0005] To solve this problem, we provide a system that links databases and generative AI to enable tasks from uncovering issues to analyzing data and devising solutions through natural language interaction. Furthermore, not only can you give instructions to AI to make work more efficient, but by collaborating with AI you can devise new solutions and carry out creative work more quickly. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] One form of the present invention is a system that links a database with generative AI. In this system, the user communicates a problem to the AI ​​in natural language. The AI ​​analyzes the problem and retrieves the necessary information from the database. The AI ​​then generates a solution based on the retrieved information and provides feedback to the user.

[0029] "Example 2"

[0030] As a specific example, consider the application of this system to solving marketing problems. When a user tells the AI ​​that they want to analyze customer purchasing trends, the AI ​​retrieves customer purchasing data from a database. The AI ​​then analyzes the purchasing data and generates a solution that clarifies customer purchasing trends. This solution is fed back to the user, who can then use it to create a marketing strategy.

[0031] "Example 3"

[0032] Furthermore, collaboration between AI and users makes it possible to devise new solutions and carry out creative work at high speed. For example, by repeating the process of users providing feedback on solutions generated by AI and then the AI ​​improving the solutions based on that feedback, more effective solutions can be derived quickly.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The user communicates the problem to the AI ​​in natural language.

[0036] Step 2: The AI ​​analyzes the problem and retrieves the necessary information from the database.

[0037] Step 3: The AI ​​generates a solution based on the acquired information and provides feedback to the user.

[0038] "Example 2"

[0039] Step 1: The user communicates to the AI ​​the problem of "analyzing customer purchasing trends."

[0040] Step 2: The AI ​​retrieves customer purchasing data from the database.

[0041] Step 3: AI analyzes purchasing data and generates solutions that reveal customer purchasing trends.

[0042] Step 4: This solution is fed back to the user, who can then use it to develop their marketing strategy.

[0043] "Example 3"

[0044] Step 1: The user provides feedback on the AI-generated solution.

[0045] Step 2: The AI ​​uses that feedback to improve the solution.

[0046] Step 3: By repeating this process, you can arrive at a more effective solution faster.

[0047] Example 1

[0048] Next, a description will be given of Example 1 of Form 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."

[0049] In conventional systems, users needed multiple tools and manual operations to solve problems, which was inefficient and time-consuming. Furthermore, data acquisition, analysis, and solution generation were disconnected, resulting in a lack of a consistent process. This made it difficult for users to solve problems quickly and effectively.

[0050] 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.

[0051] In this invention, the server includes: a means for a user to input a problem in natural language; a means for the server to send the problem to the generative AI model as a prompt; a means for the generative AI model to analyze the problem; a means for the server to acquire necessary information from a database; a means for the server to send the acquired information to the generative AI model; a means for the generative AI model to generate a solution; and a means for the server to feed back the solution to the user. This allows the user to simply input the problem in natural language, thereby enabling a consistent process from data acquisition to analysis and solution generation.

[0052] A "user" is an entity that uses the system to input problems and obtain solutions.

[0053] The "server" is a computer system whose role is to receive tasks from users, send them as prompts to the generative AI model, retrieve the necessary information from a database, generate solutions, and provide feedback to the user.

[0054] A "generative AI model" is an artificial intelligence model that analyzes prompts received from users and generates solutions based on the necessary information.

[0055] A "prompt" is a text-based instruction that allows a generative AI model to understand the task entered by the user.

[0056] A "database" is a data repository that a server connects to to get the information it needs.

[0057] A "solution" is a specific answer or proposal to a user's problem that is generated based on the information analyzed by the generative AI model.

[0058] "Feedback" is the process by which the server returns the solution obtained from the generative AI model to the user.

[0059] This invention is a system in which a user inputs a problem in natural language, a server analyzes the problem using a generative AI model, retrieves necessary information from a database, generates a solution, and provides feedback to the user. A specific embodiment of this system is described below.

[0060] Hardware and software used

[0061] Hardware

[0062] Terminal: The device through which the user enters the assignment. Examples include a PC or smartphone.

[0063] Server: A computer system for analyzing problems, acquiring data, generating solutions, and providing feedback.

[0064] software

[0065] Generative AI model: An artificial intelligence model for analyzing problems and generating solutions. An example is OpenAI's GPT-4.

[0066] Database: A data storage system for storing required information. Examples include MySQL (registered trademark) and PostgreSQL.

[0067] System Operation

[0068] User operations

[0069] Users use a terminal to access the system's interface and input their problem in natural language, for example, "Please tell me the sales forecast for the next quarter based on the sales data."

[0070] Server Processing

[0071] The server sends the task received from the user to the generative AI model as a prompt. The generative AI model analyzes the prompt and understands the content of the task. The server then connects to the database and obtains the necessary information identified by the generative AI model. The obtained information is then sent back to the generative AI model, instructing it to generate a solution. The generative AI model generates a solution and returns it to the server.

[0072] feedback

[0073] The server then feeds back the generated solution to the user. The solution is then displayed on the user's device. For example, it might say, "Sales forecast for the next quarter is XX yen."

[0074] Specific examples

[0075] Prompt Sentence Examples

[0076] The user types into the system, "Based on the sales data, what is your sales forecast for the next quarter?"

[0077] In this way, users can obtain specific solutions to their problems through the system. This system allows users to consistently perform everything from data acquisition to analysis and the generation of solutions simply by inputting their problem in natural language.

[0078] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0079] Step 1:

[0080] The user enters an assignment.

[0081] Users access the system interface using a terminal and input tasks in natural language. For example, they might input, "Please tell me the sales forecast for the next quarter based on the sales data." The input task is sent to the server as text data.

[0082] Step 2:

[0083] The server sends the task to the generative AI model as a prompt.

[0084] The server receives the task from the user and sends it to the generative AI model as a prompt. Specifically, the server connects to the generative AI model via an API and sends the user's task in text format. The input is the user's task text, and the output is the prompt sent to the generative AI model.

[0085] Step 3:

[0086] A generative AI model analyzes the problem.

[0087] The generative AI model analyzes the received prompt and understands the content of the problem. For example, it extracts keywords such as "sales data" and "sales forecast for the next quarter" and identifies the necessary data based on these. The input is the prompt, and the output is the identification of the necessary data as the analysis result.

[0088] Step 4:

[0089] The server retrieves the necessary information from the database.

[0090] The server connects to the database and retrieves the required information identified by the generative AI model. Specifically, it executes an SQL query to retrieve sales data. For example, it executes the query SELECT FROM sales_data WHERE date >= '2023-01-01' AND date <= '2023-03-31'. The input is the required data identified as the analysis result, and the output is the sales data retrieved from the database.

[0091] Step 5:

[0092] The server sends the acquired information to the generative AI model.

[0093] The server sends the sales data obtained from the database to the generative AI model. Again, via the API, the obtained data is input to the generative AI model in text format. The input is the sales data obtained from the database, and the output is the data sent to the generative AI model.

[0094] Step 6:

[0095] A generative AI model generates a solution.

[0096] The generative AI model generates a sales forecast for the next quarter based on the acquired sales data. The model analyzes the data and generates the forecast results in text format. The input is sales data, and the output is a sales forecast as a solution.

[0097] Step 7:

[0098] The server feeds back the solution to the user.

[0099] The server feeds back the solution received from the generative AI model to the user. Specifically, the solution is displayed on the user's device. For example, it is displayed in the form of "Sales forecast for the next quarter is XX yen." The input is the solution from the generative AI model, and the output is feedback to the user.

[0100] (Application example 1)

[0101] Next, a description will be given of Application Example 1 of Embodiment 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."

[0102] There is a need to improve operational efficiency at logistics centers and optimize inventory management and delivery schedules. However, with conventional systems, it takes a great deal of time and effort to acquire and analyze data and generate solutions, making efficient operation difficult. In addition, because natural language communication is not possible, users need specialized knowledge to master the system.

[0103] 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.

[0104] In this invention, the server includes a means for enabling interactions in natural language from identifying issues to analyzing data and devising solutions, a means for linking the database with generative AI, a means for users to input issues in natural language and for the AI ​​to analyze the issues and obtain necessary information from the database in order to improve the efficiency of logistics center operations, and a means for generating optimal solutions based on the obtained information and providing feedback to the user. This improves the efficiency of logistics center operations and enables optimization of inventory management and delivery schedules.

[0105] "Identifying issues" is the process of finding out the problems users are facing and areas for improvement.

[0106] "Data analysis" is the process of analyzing collected data and extracting meaningful information.

[0107] "Solution development" is the process of proposing an appropriate solution to an identified problem.

[0108] "Natural language interaction" means that users communicate with the system in the language they use on a daily basis.

[0109] A database is a system that systematically organizes and stores information, allowing it to be searched and retrieved as needed.

[0110] "Generative AI" is artificial intelligence that generates new information and solutions based on given data and instructions.

[0111] A "logistics center" is a facility that stores, manages, and delivers goods.

[0112] "Efficient operations" refers to optimizing business processes and reducing time and costs.

[0113] "Analyzing the problem" is the process of understanding the problem entered by the user and clarifying its essence.

[0114] "Obtaining the necessary information" refers to searching and extracting the data necessary to solve the problem from a database.

[0115] "Generating optimal solutions" is the process of proposing the most effective solution based on the information obtained.

[0116] "Providing feedback to the user" refers to communicating the generated solution to the user.

[0117] A system for carrying out this invention is configured as follows: The server includes a means for enabling interactions in natural language from identifying issues to analyzing data and devising solutions, a means for linking the database with generative AI, a means for users to input issues in natural language and for the AI ​​to analyze the issues and obtain necessary information from the database in order to streamline the operation of the logistics center, and a means for generating optimal solutions based on the obtained information and providing feedback to the user.

[0118] Hardware and software used

[0119] Hardware: Smartphone

[0120] Software: Python, OpenAI API, SQLite (database)

[0121] Data processing and calculation

[0122] 1. Database connection: The server connects to the distribution center database using SQLite, which stores information such as inventory, delivery schedules, and staff shifts.

[0123] 2. Issue analysis: The user inputs the issue in natural language using a smartphone. The server analyzes this input and identifies the type of issue (inventory management, delivery schedule, staff shift, etc.).

[0124] 3. Data Acquisition: The server acquires the necessary information from the database based on the analysis results. For example, if the issue is about inventory management, it acquires inventory information.

[0125] 4. Prompt generation: Based on the acquired data, a prompt is created for the generative AI model (OpenAI).

[0126] 5. Solution generation: The server uses the OpenAI API to generate the optimal solution based on the generated prompt.

[0127] 6. Feedback: The server provides the generated solution to the user, who can then check it on their smartphone.

[0128] Specific examples

[0129] If a user types, "I want to optimize inventory reallocation," the server retrieves inventory data and sends a prompt like this to the generative AI model:

[0130] Prompt Sentence Examples

[0131] Based on the data below, propose a solution to optimize inventory reallocation.

[0132] Data: [(product ID, product name, quantity in stock, location), (product ID, product name, quantity in stock, location), ...]

[0133] In this way, a system can be realized that provides specific solutions for improving the efficiency of logistics center operations.

[0134] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0135] Step 1:

[0136] The user inputs the problem in natural language using a smartphone. For example, the input problem might be "I want to optimize the reallocation of inventory." This input is then sent to the server.

[0137] Step 2:

[0138] The server analyzes the natural language assignments received from the user. Specifically, it understands the content of the assignment and identifies which category (inventory management, delivery schedule, staff shift, etc.) it belongs to. For example, if the keyword "inventory" is included, it is determined to be an assignment related to inventory management.

[0139] Step 3:

[0140] The server retrieves the necessary information from the database based on the analysis results. For example, if the issue is inventory management, it executes the SQL query "SELECT FROM inventory" to retrieve inventory information. The retrieved data includes information such as product ID, product name, stock quantity, and location.

[0141] Step 4:

[0142] The server creates a prompt for the generative AI model based on the acquired data. Specifically, it generates the following prompt:

[0143] Based on the data below, propose a solution to optimize inventory reallocation.

[0144] Data: [(product ID, product name, quantity in stock, location), (product ID, product name, quantity in stock, location), ...]

[0145] This prompt is sent to the generative AI model.

[0146] Step 5:

[0147] The server uses a generative AI model (OpenAI API) to generate an optimal solution based on the prompt. The generative AI model analyzes the input data and generates specific suggestions for optimizing inventory reallocation. For example, a solution such as "move product A from position X to position Y" is generated.

[0148] Step 6:

[0149] The server then provides the generated solution to the user as feedback. Specifically, the solution is displayed on the smartphone screen, allowing the user to check the solution and put it into practice.

[0150] In this way, a system can be realized that provides specific solutions for improving the efficiency of logistics center operations.

[0151] Example 2

[0152] Next, a description will be given of Example 2 of Form 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."

[0153] Conventional methods for solving marketing problems have the problem that collecting data, analyzing it, and devising solutions requires a great deal of time and effort. Furthermore, it is difficult for users without specialized knowledge to analyze data, making it difficult to develop efficient marketing strategies. This has created a need for rapid and effective marketing strategy development.

[0154] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0155] In this invention, the server includes means for a user to input a problem in natural language, means for a terminal to transmit the input problem to the server as a prompt sentence, means for the server to analyze the prompt sentence and identify necessary data, means for the server to acquire data from a database, means for the server to process and analyze the acquired data, means for the server to generate a solution based on the analysis results, means for transmitting the solution generated by the server to the terminal, and means for the user to receive the solution. This enables users, even without specialized knowledge, to receive data analysis and proposed solutions to quickly and effectively solve their marketing problems.

[0156] A "user" is an individual or organization that utilizes the system to input problems and receive solutions.

[0157] A "terminal" is a device that a user uses to input tasks and communicate with the server. For example, a PC or smartphone is an example.

[0158] "Server" is a computer system that parses prompts, acquires data, processes and analyzes it, and generates and transmits solutions.

[0159] A "prompt" is text that converts the user-entered task into a format that the server can understand.

[0160] A "generative AI model" is an artificial intelligence model that performs natural language processing, analyzes prompts, and generates solutions.

[0161] A "database" is an information management system that stores information such as customer purchase data and allows the server to obtain the necessary data.

[0162] "Data processing and analysis" is the process of cleaning, aggregating, filtering, and other processes on acquired data to extract the necessary information.

[0163] A "solution" is a specific proposal or answer to a user's problem that the server generates based on the results of data analysis.

[0164] The "Python Pandas library" is a programming library for efficiently processing and analyzing data.

[0165] This invention is a system for users to solve marketing problems, and includes a process in which the user inputs the problem in natural language, and a server analyzes the problem and generates a solution. Specific embodiments of this system are described below.

[0166] The user uses the device to input a marketing problem in natural language. For example, they might input, "I want to know which product category has sold the most in the last three months." The device then sends this input to the server as a prompt sentence. The prompt sentence is in a format that the generative AI model can understand.

[0167] The server analyzes the prompt using a generative AI model (e.g., an artificial intelligence model that processes natural language). From the analysis results, it identifies the necessary data and analysis method. Next, the server connects to a database (e.g., an information management system that stores customer purchase data) and retrieves the necessary data. For example, it retrieves purchase data from the past three months.

[0168] The acquired data is processed and analyzed on the server. Specifically, the data is cleaned, aggregated, and filtered using Python's Pandas library, and sales for each product category are calculated. This allows the information desired by the user to be extracted.

[0169] The server generates a solution based on the analysis results. Using a generative AI model, it generates a solution in natural language, such as "The most popular product category over the last three months is ____." This solution is then sent to the user via their device.

[0170] Users can check the solutions displayed on the device screen and use them as a reference for formulating marketing strategies. For example, they can formulate a strategy to "further promote products in the XX category."

[0171] This system allows users to receive data analysis and proposed solutions to quickly and effectively solve marketing problems, even if they do not have specialized knowledge.

[0172] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0173] Step 1:

[0174] User enters assignment

[0175] The user enters in the input field of the terminal, "I want to know the most popular product category for the last three months." The input task is saved on the terminal as a prompt sentence.

[0176] Input: Issues entered by the user in natural language

[0177] Output: prompt statement

[0178] Step 2:

[0179] The terminal sends a prompt to the server

[0180] The device sends the saved prompt as an HTTP request to the server, which includes the user's challenge.

[0181] Input: prompt statement

[0182] Output: HTTP request sent to the server

[0183] Step 3:

[0184] The server parses the prompt.

[0185] The server inputs the received prompt into the generative AI model and obtains the analysis results, which include the type of data required and the analysis method.

[0186] Input: Prompt text received as an HTTP request

[0187] Output: Analysis results (type of data required and analysis method)

[0188] Step 4:

[0189] The server retrieves data from the database

[0190] The server sends an SQL query to the database to retrieve purchase data for the past three months, for example, "SELECT FROM purchases WHERE date >= '3 months ago'".

[0191] Input: SQL query based on the parsed results

[0192] Output: Purchase data for the past three months

[0193] Step 5:

[0194] The server processes and analyzes the data

[0195] The server processes the acquired data using the Python Pandas library, specifically cleaning the data and aggregating sales figures for each product category.

[0196] Input: Purchase data for the past three months

[0197] Output: Sales data for each product category

[0198] Step 6:

[0199] The server generates a solution

[0200] Based on the analysis results, the server uses a generative AI model to generate a solution such as "The best-selling product category over the last three months is XX."

[0201] Input: Sales data for each product category

[0202] Output: A generated solution in natural language

[0203] Step 7:

[0204] The server sends the solution to the device

[0205] The server sends the generated solution as an HTTP response to the terminal, which receives the response and displays it to the user.

[0206] Input: Natural language generated solution

[0207] Output: HTTP response sent to the device

[0208] Step 8:

[0209] The user receives the solution

[0210] The user checks the solutions displayed on the device screen and uses them as a reference for formulating a marketing strategy. For example, they may formulate a strategy such as "further promoting products in the XX category."

[0211] Input: Solution displayed in terminal

[0212] Output: Marketing strategies developed by users

[0213] (Application example 2)

[0214] Next, a description will be given of Application Example 2 of Form 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."

[0215] With conventional marketing methods, it was difficult to grasp customer purchasing trends in real time and immediately make optimal marketing proposals. Furthermore, it required a great deal of time and effort to efficiently analyze customer purchasing data and develop individual marketing strategies. This has led to a demand for more efficient marketing activities and more effective customer responses in brick-and-mortar stores.

[0216] The specific processing by the specific 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 a means for enabling the process from identifying issues to analyzing data and devising solutions through natural language interactions, a means for linking the database with generative AI, a means for identifying customers, a means for analyzing purchasing data in real time, a means for generating marketing proposals based on the analysis results, and a means for displaying the proposals. This makes it possible to grasp customer purchasing trends in real time and instantly make optimal marketing proposals.

[0217] "Identifying the problem" is the process of clarifying the problems the user wants to solve or the goals they want to achieve.

[0218] "Data analysis" is the process of analyzing collected data using statistical methods and machine learning algorithms to extract useful information and patterns.

[0219] "Solution development" is the process of designing specific methods and strategies for solving problems based on the results of analysis.

[0220] "Interaction in natural language" refers to communication between the system and the user using language that humans use on a daily basis.

[0221] A "database" is a system for efficiently storing, managing, and retrieving data.

[0222] "Generative AI" refers to artificial intelligence that generates new information and solutions based on given data and instructions.

[0223] "Customer identification" is the process of recognizing a specific customer using facial recognition technology or other means of identification.

[0224] "Purchase Data" refers to information about products and services that a customer has previously purchased.

[0225] "Real-time analysis" refers to analyzing data as it is generated.

[0226] "Marketing proposal" refers to proposing the most suitable products and services based on the customer's purchasing trends and preferences.

[0227] "Display Proposal" refers to visually presenting the generated marketing proposal to the user.

[0228] A system for carrying out this invention is configured as follows: The server includes a means for enabling a process from identifying issues to analyzing data and devising solutions through natural language interaction, a means for linking a database with generative AI, a means for identifying customers, a means for analyzing purchasing data in real time, a means for generating marketing proposals based on the analysis results, and a means for displaying the proposals.

[0229] First, the server analyzes the user's input in natural language and retrieves the appropriate data from the database. The retrieved data is then passed to a generative AI system, which analyzes purchasing trends. Based on the analysis results, the generative AI system generates optimal marketing proposals. These proposals are displayed on devices such as smart glasses.

[0230] Specifically, the server uses OpenCV to recognize customer faces from images captured by a camera and uses TENSORFLOW (registered trademark) to analyze purchasing trends. Customer purchasing data is stored in a database, and data preprocessing and clustering are performed using Pandas and Scikit-learn. This makes it possible to grasp customer purchasing trends in real time and generate optimal marketing proposals.

[0231] For example, when a customer enters a store, the smart glasses can recognize them and display a message saying, "New product promotions offered" based on their past purchase data. If another customer enters the store, the glasses can also display a message saying, "Discount coupons offered."

[0232] Examples of prompts to input to a generative AI model include:

[0233] "Based on customer purchasing data, analyze purchasing trends and generate optimal marketing proposals. For example, if a customer is interested in new products, suggest new product promotions; if a customer prefers discounts, suggest discount coupons."

[0234] In this way, the server can analyze customer purchasing trends in real time, generate optimal marketing proposals, and display them on the terminal, thereby improving the efficiency of marketing activities and effectively responding to customers in physical stores.

[0235] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0236] Step 1:

[0237] The server receives a task entered by the user in natural language. For example, the task entered might be, "I want to analyze customer purchasing trends." The server analyzes this task and retrieves the appropriate data from the database. Specifically, the server analyzes the natural language text entered by the user and extracts related keywords. This generates a query to retrieve the necessary purchasing data from the database.

[0238] Input: Issues entered by the user in natural language

[0239] Output: Query to retrieve from the database

[0240] Step 2:

[0241] The server uses the generated query to retrieve customer purchase data from a database, which stores the customer's past purchase history and related information. The retrieved data is used for analysis in the next step.

[0242] Input: Query to retrieve from the database

[0243] Output: Customer purchase data

[0244] Step 3:

[0245] The server passes the acquired purchasing data to a generative AI system to analyze purchasing trends. Specifically, it uses TensorFlow to run a machine learning model and analyze customer purchasing trends. The data is preprocessed using Pandas and Scikit-learn, and standardized and clustered.

[0246] Input: Customer purchase data

[0247] Output: Analysis of purchasing trends

[0248] Step 4:

[0249] The server generates optimal marketing proposals based on the analysis results. The generative AI then generates specific proposals based on the analysis results, such as "proposing new product promotions" or "proposing discount coupons." These proposals provide useful information to users.

[0250] Input: Analysis results of purchasing trends

[0251] Output: Marketing proposal

[0252] Step 5:

[0253] The server transmits the generated marketing proposals to a terminal, which is a device such as smart glasses that visually displays the proposals, allowing the user to view the optimal marketing proposals in real time.

[0254] Input: Marketing Proposal

[0255] Output: Proposal displayed in terminal

[0256] Step 6:

[0257] Based on the suggestions displayed on the terminal, users can respond appropriately to customers. For example, they can introduce new product promotions to customers or provide discount coupons. This will improve the efficiency of marketing activities in physical stores and enable effective customer service.

[0258] Input: Suggestion displayed on terminal

[0259] Output: Appropriate response to the customer

[0260] Through the above steps, a system is realized in which the server, terminals, and users work together to analyze customer purchasing trends in real time and make optimal marketing proposals.

[0261] Example 3

[0262] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0263] In conventional systems, the process from identifying issues to analyzing data and devising solutions was fragmented, making efficient problem solving difficult. Furthermore, the process of improving solutions based on user feedback was often done manually, which was time-consuming and labor-intensive. Furthermore, there was a lack of concrete methods for effectively utilizing generative AI models.

[0264] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0265] In this invention, the server includes a means for enabling a process from identifying a problem to analyzing data and devising a solution through natural language interaction, a means for linking a database with a generative AI, a means for a user to input information about a problem they wish to solve, a means for generating an initial solution using a generative AI model, a means for collecting feedback from the user, a means for improving the solution based on the feedback, and a means for presenting a final solution to the user, thereby enabling efficient and rapid problem solving.

[0266] "Identifying issues" is the process of finding problems that need to be solved or areas for improvement.

[0267] "Data analysis" is the process of organizing collected data and extracting meaningful information.

[0268] "Solution development" is the process of proposing appropriate measures or methods for solving problems that have been discovered.

[0269] "Communicating in natural language" refers to exchanging information using a language that humans use on a daily basis.

[0270] A "database" is a system that systematically stores data and enables it to be searched and used efficiently.

[0271] "Generative AI" is an artificial intelligence technology that generates new data and solutions based on given information.

[0272] "User" refers to an individual or organization that uses the system to solve a problem.

[0273] A "generative AI model" is an artificial intelligence model that is trained to generate new data and solutions for a specific task.

[0274] An "initial solution" is the solution that the generative AI model first proposes.

[0275] "Feedback" refers to information about evaluations and areas for improvement provided by users.

[0276] "Improvement" is the process of making modifications or additions to an existing solution to make it more effective.

[0277] The "final solution" is the final solution that has been refined based on user feedback.

[0278] This invention is a system that allows a user to input information about a problem they want to solve, generates a solution using a generative AI model, and improves the solution based on user feedback. A specific embodiment of this system is described below.

[0279] The server generates a program using a generative AI model. For example, GPT-4 can be used as this generative AI model. The server receives information entered by the user through the terminal and generates an initial solution. The generated solution is presented to the user through the terminal.

[0280] A user uses the terminal to input information about the problem they want to solve—for example, if they are devising a marketing strategy, they input information about the current market situation and their target customers—and the terminal transmits this information to the server.

[0281] The server uses a generative AI model to generate an initial solution based on the received information. The generative AI model analyzes the input information and creates a prompt to generate an appropriate solution. For example, it generates a prompt such as, "Please propose a new marketing strategy based on the current market situation and target customers." The server then sends the generated solution to the device.

[0282] The user checks the initial solution displayed on the device and provides feedback. For example, the user can input specific feedback such as, "The target customer age range is too broad, so please narrow it down a bit more." The device then sends the user's feedback to the server.

[0283] The server receives feedback from the user and again uses the generative AI model to improve the solution. The generative AI model takes the feedback into account to create a new prompt and generate an improved solution. For example, it generates a prompt such as, "Please propose a marketing strategy that narrows the target customer age range to between 25 and 35 years old." The server then sends the improved solution to the device.

[0284] The user reviews the improved solution and provides further feedback if necessary. This process is repeated until a solution that satisfies the user is obtained. The final solution is presented to the user via the terminal.

[0285] Examples:

[0286] Suppose a user wants to devise a new marketing strategy. The user inputs information about the current market situation (e.g., "The market is becoming increasingly competitive") and target customers (e.g., "Our target customers are young people between the ages of 20 and 40") through a terminal. The terminal then sends this information to a server.

[0287] The server uses a generative AI model (GPT-4) to generate a prompt such as "Please propose a new marketing strategy based on the current market situation and target customers," and generates an initial solution. The generated solution might be, for example, "Launch an advertising campaign using social media."

[0288] The user provides feedback on this solution, saying, "The target customer age range is too broad, so I'd like it to be narrowed down a bit more." The terminal sends this feedback to the server.

[0289] Based on the feedback, the server uses the generative AI model again to generate a prompt such as "Please propose a marketing strategy that narrows the target customer age range to 25 to 35 years old," and generates an improved solution. For example, the improved solution might be "Develop influencer marketing targeting young people aged 25 to 35."

[0290] The user checks the improved solution and provides further feedback as necessary. By repeating this process, the user can quickly obtain an optimal marketing strategy. The flow of the identification process in Example 3 will be described with reference to FIG. 15.

[0291] Step 1:

[0292] Data Entry

[0293] A user inputs information about a problem to be solved through a terminal. For example, when devising a marketing strategy, the user inputs information about the current market situation and target customers.

[0294] Input: Market situation, target customer information

[0295] Output: The entered information is sent from the device to the server.

[0296] Step 2:

[0297] Generate an initial solution

[0298] The server generates an initial solution based on the received information using a generative AI model, which analyzes the input information and creates prompts to generate an appropriate solution.

[0299] Input: Market situation and target customer information entered by the user

[0300] Data processing: A generative AI model analyzes the information and generates prompts

[0301] Output: An initial solution is generated and sent to the terminal.

[0302] Step 3:

[0303] Collecting feedback

[0304] The user checks the initial solution displayed on the terminal and provides feedback, for example, by inputting specific feedback such as, "The target customer age range is too broad, so please narrow it down a bit more."

[0305] Input: User feedback on the initial solution

[0306] Output: Feedback is sent from the device to the server

[0307] Step 4:

[0308] Improved solution

[0309] The server receives feedback from the user and refines the solution using the generative AI model again, which takes the feedback into account to create a new prompt and generate an improved solution.

[0310] Input: User feedback

[0311] Data processing: A generative AI model analyzes feedback and generates new prompts

[0312] Output: An improved solution is generated and sent to the terminal

[0313] Step 5:

[0314] Presentation of the final solution

[0315] The user reviews the improved solution and provides further feedback if necessary. This process is repeated until a solution that satisfies the user is obtained. The final solution is presented to the user via the terminal.

[0316] Input: User feedback for an improved solution (if needed)

[0317] Output: The final solution is displayed in the terminal.

[0318] In this way, users, terminals, and servers can work together to solve problems efficiently and quickly.

[0319] (Application example 3)

[0320] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0321] Conventional factory robot operation optimization involves collecting feedback to improve the robot's operation and then making improvements based on that feedback, which is a time-consuming and labor-intensive process. Furthermore, there was a lack of effective means for users and AI to collaborate to quickly derive solutions. This resulted in reduced factory production efficiency and increased costs.

[0322] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0323] In this invention, the server includes a means for enabling interactions in natural language from identifying issues to analyzing data and devising solutions, a means for linking the database with the generative AI, a means for the generative AI to improve solutions based on feedback from users, a means for collecting feedback in real time via a smart device, and a means for the generative AI to re-propose the improved solutions. This enables users and AI to work together to quickly and effectively optimize the operation of factory robots.

[0324] "Identifying issues" means identifying problems and areas for improvement in systems and processes.

[0325] "Data analysis" refers to the analysis of collected data using statistical methods and machine learning algorithms to extract meaningful information.

[0326] "Developing a solution" means designing and proposing effective measures and methods for addressing identified issues.

[0327] "Interaction in natural language" means that the system and the user communicate using language that humans use on a daily basis.

[0328] A "database" is a system for efficiently storing, managing, and retrieving data.

[0329] "Generative AI" is artificial intelligence that generates new information and solutions based on user input and feedback.

[0330] "User feedback" refers to the opinions and evaluations provided by users regarding the solutions proposed by the system.

[0331] "Smart devices" are electronic devices with advanced functions, such as mobile terminals and wearable devices that can connect to the Internet.

[0332] "Collecting feedback in real time" means obtaining opinions and ratings from users immediately.

[0333] An "improved solution" is a new solution that the generative AI has improved based on user feedback.

[0334] A system for implementing the present invention includes a server, a smart device, and a generative AI model. Specific embodiments are described below.

[0335] System Configuration

[0336] 1. Server

[0337] The server provides a means to identify issues, analyze data, and devise solutions through natural language interaction. The server is connected to a database and has a generative AI model installed.

[0338] 2. Smart Devices

[0339] Smart devices, such as smartphones and tablets, are used to collect real-time user feedback.

[0340] 3. Generative AI Models

[0341] Generative AI models provide a way to improve solutions based on user feedback, using APIs such as those from OpenAI.

[0342] Data processing and calculation

[0343] 1. Identifying issues and analyzing data

[0344] The server analyzes the issues entered by the user in natural language and extracts related data stored in the database, thereby identifying issues and analyzing the data.

[0345] 2. Solution Generation

[0346] The generative AI model generates an initial solution based on the analyzed data, which is then presented to the user via their smart device.

[0347] 3. Gather feedback and improve

[0348] Users input feedback on the solution via their smart devices. The server collects this feedback and sends it to the generative AI model, which then refines the solution based on the feedback and presents it to the user again.

[0349] Specific examples

[0350] For example, when a factory robot proposes a solution to streamline parts assembly work, the following prompt sentence is used:

[0351] Initial Prompt

[0352] "Please propose a solution to help factory robots improve the efficiency of parts assembly."

[0353] Feedback-based prompts

[0354] "Please improve the following solution:

[0355] Solution: Increase the robot arm speed by 20%.

[0356] Feedback: Increasing arm speed may result in decreased accuracy.

[0357] Improved solution:

[0358] In this way, users and AI can work together to quickly and effectively optimize the operation of factory robots.

[0359] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0360] Step 1:

[0361] The server receives a challenge input from a user in natural language.

[0362] Input: A problem entered by a user through a smart device (e.g., "I want to improve the efficiency of assembly work by factory robots").

[0363] Data processing: Using natural language processing (NLP) technology, the input task is analyzed and keywords and important information are extracted.

[0364] Output: Extracted keywords and key information (e.g., "factory robot," "assembly work," "efficiency").

[0365] Step 2:

[0366] The server accesses the database and searches for and retrieves data related to the extracted keywords.

[0367] Input: Extracted keywords and important information.

[0368] Data manipulation: Performing database queries to retrieve relevant data.

[0369] Output: Relevant data obtained (e.g. data from past assembly operations, existing methods for improving efficiency).

[0370] Step 3:

[0371] The server inputs relevant data into a generative AI model to generate an initial solution.

[0372] Input: The relevant data retrieved.

[0373] Data Computing: Use generative AI models (e.g., OpenAI APIs) to generate solutions based on relevant data.

[0374] Output: An initial solution (e.g., "Increase the robot's arm speed by 20%").

[0375] Step 4:

[0376] The server presents the generated solution to the user via a smart device.

[0377] Input: Initial solution.

[0378] Data manipulation: Converting the solution into a format that is easy for users to understand.

[0379] Output: A solution presented to the user (e.g., "Increase the robot's arm speed by 20%").

[0380] Step 5:

[0381] The user provides feedback on the proposed solution.

[0382] Input: User feedback (e.g., "Increasing arm speed may decrease accuracy").

[0383] Data processing: Feedback is analyzed using natural language processing techniques to extract key information.

[0384] Output: Extracted feedback key information (e.g. "Potential for accuracy degradation").

[0385] Step 6:

[0386] The server inputs the extracted feedback into a generative AI model to refine the solution.

[0387] Input: Extracted feedback key information.

[0388] Data computation: Using generative AI models to improve solutions based on feedback.

[0389] Output: Improved solution (e.g., "Increase arm speed by 15% and add a compensation algorithm to maintain accuracy").

[0390] Step 7:

[0391] The server presents the improved solution to the user again via the smart device.

[0392] Input: Improved solution.

[0393] Data processing: Converting the improved solution into a format that is easy for users to understand.

[0394] Output: An improved solution presented to the user (e.g., "Increase arm speed by 15% and add a compensation algorithm to maintain accuracy").

[0395] In this way, users and AI can work together to quickly and effectively optimize the operation of factory robots.

[0396] 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.

[0397] "Example 1"

[0398] One embodiment of the present invention is a system that includes an emotion engine that uses AI to recognize user emotions. The system understands the user's emotions through natural language interactions with the user and provides solutions based on those emotions. Specifically, if the user is feeling frustrated, the AI ​​can recognize that emotion and provide a more polite response, thereby improving user satisfaction.

[0399] "Example 2"

[0400] Another embodiment of the present invention is a system in which an emotion engine adjusts the AI's response based on the user's emotions. In this system, if the user is feeling joy, the AI ​​will recognize that emotion and provide a more energetic response, thereby maximizing the user's joy and providing a better user experience.

[0401] "Example 3"

[0402] Furthermore, a system in which an emotion engine generates solutions based on a user's emotions is also one embodiment of the present invention. In this system, if a user is feeling anxious, the AI ​​recognizes that emotion and provides a solution to alleviate the anxiety. For example, if a user is feeling anxious about a new project, the AI ​​recognizes the anxiety and provides project management best practices and past success stories to alleviate the user's anxiety.

[0403] The processing flow of each embodiment will be described below.

[0404] "Example 1"

[0405] Step 1: Understand user sentiment through natural language interactions with users.

[0406] Step 2: The emotion engine recognizes the user's emotion.

[0407] Step 3: Based on the recognized emotion, the AI ​​provides a solution.

[0408] "Example 2"

[0409] Step 1: Understand user sentiment through natural language interactions with users.

[0410] Step 2: The emotion engine recognizes the user's emotion.

[0411] Step 3: The AI ​​tailors its response based on the perceived emotion.

[0412] "Example 3"

[0413] Step 1: Understand user sentiment through natural language interactions with users.

[0414] Step 2: The emotion engine recognizes the user's emotion.

[0415] Step 3: The AI ​​generates a solution based on the recognized emotion.

[0416] Example 1

[0417] Next, a description will be given of Example 1 of Form 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."

[0418] Conventional systems have made it difficult for users to efficiently obtain the information they need to solve problems and find appropriate solutions. Furthermore, they are unable to provide responses that reflect the user's emotions, making it difficult to improve user satisfaction. Furthermore, there is a need for efficient work progression and the rapid execution of creative tasks using generative AI models.

[0419] 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.

[0420] In this invention, the server includes a means for a user to input a problem in natural language, a means for analyzing the problem using a generative AI model, a means for acquiring necessary information from a database, a means for generating a solution based on the acquired information, a means for recognizing the user's emotions and adjusting the response, and a means for feeding back the generated solution to the user. This allows the user to not only solve the problem efficiently, but also receive appropriate support according to their emotions.

[0421] A "user" is an individual or organization that uses the system to input problems and obtain solutions.

[0422] "Natural language" refers to the language used by humans on a daily basis, and refers to normal speech and writing forms, rather than specific programming languages ​​or commands.

[0423] A "generative AI model" is an artificial intelligence algorithm or system that analyzes input natural language and generates appropriate solutions or information.

[0424] "Analyzing the problem" is the process of understanding the problem entered in natural language by the user and identifying the necessary information and solutions based on that content.

[0425] A "database" is a digital storage system that stores information systematically and allows it to be searched and retrieved as needed.

[0426] "Retrieving information" is the process of searching and retrieving the required data from a database.

[0427] "Generating solutions" is the process of creating specific solutions or proposals for the user's problems based on the information obtained.

[0428] "Emotion recognition" is the process of identifying and understanding a user's emotional state from their input and behavior.

[0429] "Response tailoring" is the process of changing the content and tone of the solutions and feedback you generate based on perceived user emotions.

[0430] "Feedback" is the process of providing generated solutions or information to the user so that they can review it.

[0431] This invention is a system that links a database with a generative AI model, where a user inputs a problem in natural language, and the AI ​​analyzes the problem and provides a solution. A specific embodiment of this system is shown below.

[0432] Hardware and software used

[0433] Hardware: Servers, terminals

[0434] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), emotion engines (e.g., Affectiva)

[0435] System configuration

[0436] 1. User issue input

[0437] The user uses the device to input the issue in natural language. For example, the user types "How do I manage the progress of a new project?" into the device's input field.

[0438] 2. Problem Analysis

[0439] The server analyzes the user's problem using a generative AI model, which understands the input natural language and identifies the subject of the problem and the required information.

[0440] 3. Retrieving information from the database

[0441] The server uses a database management system to retrieve necessary information from the database based on the analysis results, for example, the server searches the database for information related to "project management."

[0442] 4. Solution Generation

[0443] The server uses a generative AI model to generate solutions based on the acquired information. For example, based on project management information acquired from the database, the server generates a solution such as, "Task prioritization and progress visualization are important for project management. Specifically, we recommend using a Gantt chart."

[0444] 5. Emotion recognition and response regulation

[0445] The server uses an emotion engine to recognize the user's emotions. For example, the server analyzes the user's input and past interactions to recognize that the user is frustrated. The emotion engine analyzes the user's text and voice data to identify their emotional state. The generative AI model then adjusts its response accordingly.

[0446] 6. User Feedback

[0447] The server sends the generated solution to the device and provides feedback to the user. For example, the server might send a solution such as, "In project management, prioritizing tasks and visualizing progress are important. Specifically, we recommend using a Gantt chart." The device then displays the solution received from the server to the user.

[0448] Specific examples

[0449] Prompt Sentence Examples

[0450] "How do I manage the progress of a new project?"

[0451] "Can you give me some advice on prioritizing tasks?"

[0452] "What are some common project management problems and how can you solve them?"

[0453] This system not only enables users to solve problems efficiently, but also allows them to receive appropriate support according to their emotions.

[0454] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0455] Step 1:

[0456] User issue input

[0457] Input: A user enters an issue in natural language using a terminal.

[0458] What happens: The user types "How do I manage progress on a new project?" into the device's input field.

[0459] Output: The terminal receives user input and sends it to the server.

[0460] Step 2:

[0461] Analysis of the problem

[0462] Input: User challenge submitted from the device (natural language text).

[0463] How it works: The server analyzes the user's problem using a generative AI model. The generative AI model understands the input natural language and identifies the subject of the problem and the required information.

[0464] Output: Identification of the subject and required information.

[0465] Step 3:

[0466] Retrieving information from a database

[0467] Input: Identification of the subject and required information.

[0468] Specific operations: The server uses the database management system to retrieve the necessary information from the database based on the analysis results. The server searches the database for information related to "project management."

[0469] Output: Information retrieved from the database.

[0470] Step 4:

[0471] Solution Generation

[0472] Input: Information retrieved from the database.

[0473] Specific operation: The server uses the generative AI model to generate a solution based on the acquired information. Based on the information about project management acquired from the database, the server generates the solution, "In project management, prioritizing tasks and visualizing progress are important. Specifically, we recommend using a Gantt chart."

[0474] Output: The generated solution.

[0475] Step 5:

[0476] Emotion recognition and response regulation

[0477] Input: User input, past interactions, and generated solutions.

[0478] How it works: The server uses an emotion engine to recognize the user's emotions. The server analyzes the user's input and past interactions and recognizes that the user is frustrated. The emotion engine analyzes the user's text and voice data to identify their emotional state. The generative AI model adjusts its response based on that emotional state.

[0479] Output: The adjusted response.

[0480] Step 6:

[0481] User feedback

[0482] Input: The adjusted response.

[0483] Specific operations: The server sends the generated solution to the device and provides feedback to the user. The server sends the solution "Task prioritization and progress visualization are important for project management. Specifically, we recommend using a Gantt chart." to the device. The device displays the solution received from the server to the user.

[0484] Output: The solution displayed to the user.

[0485] (Application example 1)

[0486] Next, a description will be given of Application Example 1 of Embodiment 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."

[0487] On conventional online shopping sites, it is difficult for users to quickly obtain appropriate product information when searching for a product, and they are unable to respond to the user's emotions, which leads to a decrease in user satisfaction. In particular, when a user feels frustrated, they are unable to respond appropriately, which leads to a worsening user experience.

[0488] 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.

[0489] In this invention, the server includes a means for enabling a process from identifying issues to analyzing data and devising solutions through natural language interaction, a means for linking the database with generative AI, a means for recognizing user emotions and providing solutions based on those emotions, and a means for suggesting optimal product information based on user input. As a result, when a user communicates a problem in natural language, the AI ​​analyzes the problem, retrieves the necessary information from the database, generates a solution, and responds in accordance with the user's emotions.

[0490] "Identifying the problem" is the process of clarifying the problems and needs of users in natural language.

[0491] "Data analysis" is the process of analyzing collected data and extracting meaningful information.

[0492] "Solution creation" is the process of generating an appropriate solution to an identified problem.

[0493] "Natural language interaction" means that users communicate with the system using the language they use on a daily basis.

[0494] A database is a system that systematically organizes and stores information, allowing it to be searched and retrieved as needed.

[0495] "Generative AI" is artificial intelligence that generates new information and solutions based on given data and instructions.

[0496] "Recognizing user emotions" is the process of analyzing and understanding a user's emotional state from their input and behavior.

[0497] "Providing solutions" refers to making appropriate responses or suggestions based on identified issues and emotions.

[0498] "Proposing optimal product information" is the process of selecting and presenting the product that best suits the user's requests and needs.

[0499] To implement this invention, the following system configuration is required: The system consists of a terminal where users can input tasks in natural language, a database, a generative AI, and a server that includes an emotion recognition engine.

[0500] When a user uses a device to input a challenge in natural language, the input is sent to the server, which first analyzes the user's emotions using an emotion recognition engine, which uses a natural language processing library such as TextBlob to classify the emotion of the user's input text as positive, negative, or neutral.

[0501] The server then uses generative AI to analyze the user's problem and retrieves the necessary information from a database. This generative AI uses OpenAI's API to generate optimal product information based on the user's questions and requests. The database stores product information and the user's past purchase history.

[0502] The server then suggests optimal product information to the user based on the acquired information and the results of emotion recognition. For example, if a user types, "The weather has been bad lately, so I don't feel like going out. Please tell me about some useful items I can use at home," the server responds, "We are searching for the best products to resolve your complaint. Please wait a moment," and then suggests, "Recommended products: automatic vacuum cleaner, smart speaker, home exercise kit."

[0503] This system allows users to simply communicate their issues in natural language, and quickly receive appropriate responses based on their emotions and the most appropriate product information.

[0504] An example of a prompt is as follows:

[0505] A user asked the following question: The weather has been so bad lately that I don't feel like going out. What are some handy items I can use around the house?

[0506] Please suggest the best product.

[0507] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0508] Step 1:

[0509] The user enters the issue in natural language using a terminal.

[0510] Input: The user's natural language challenge or question.

[0511] Output: The user's input text data.

[0512] Specific operation: The user enters "The weather has been bad lately, so I don't feel like going out. Please tell me some useful items I can use at home" into the input field on the device and presses the send button.

[0513] Step 2:

[0514] The server receives the user's input text data and analyzes the emotions using an emotion recognition engine.

[0515] Input: User-entered text data.

[0516] Output: Emotion recognition result (positive, negative, neutral).

[0517] Specific behavior: The server uses the TextBlob library to analyze the sentiment of the user's input text and determines it to be "negative."

[0518] Step 3:

[0519] The server uses generative AI to analyze the user's issues and retrieve the necessary information from the database.

[0520] Input: User input text data, emotion recognition results.

[0521] Output: A solution (product information) created by generative AI.

[0522] How it works: The server uses the OpenAI API to generate product information such as "automatic vacuum cleaner, smart speaker, home exercise kit" based on the user's question.

[0523] Step 4:

[0524] The server proposes optimal product information to users based on emotion recognition results and solutions provided by generative AI.

[0525] Input: Generative AI solution, emotion recognition results.

[0526] Output: A response message to the user.

[0527] Specific behavior: The server responds, "We are looking for the best products to resolve your complaint. Please wait a moment." and then suggests, "Recommended products: Automatic vacuum cleaner, smart speaker, home exercise kit."

[0528] Step 5:

[0529] The user receives and displays the response message from the server on the terminal.

[0530] Input: The response message from the server.

[0531] Output: The response message that is displayed on the user's terminal.

[0532] What it does: The user's device will display the message "We're looking for the best products to resolve your complaint. Please wait a moment.", followed by the suggestion "Recommended products: Automatic vacuum cleaner, smart speaker, home exercise kit."

[0533] Example 2

[0534] Next, a description will be given of Example 2 of Form 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."

[0535] In conventional marketing systems, the process of users entering their issues, acquiring data, preprocessing, analyzing, generating results, and providing feedback is often done manually, which takes time and effort. It is also difficult to provide responses that reflect the user's emotions, resulting in a lack of improvement in the user experience. To solve these issues, a system is needed that automates the entire process, from data acquisition to analysis and feedback of results, and that also provides responses that reflect the user's emotions.

[0536] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0537] In this invention, the server includes means for a user to input a task, means for the server to acquire data from a database, means for the server to preprocess the data, means for the server to analyze the data, means for the server to generate analysis results, means for the server to feed back the results to the user, and means for an emotion engine to recognize the user's emotions and adjust responses. This makes it possible to automate the entire process from data acquisition to analysis and feedback of the results, and to provide responses that correspond to the user's emotions.

[0538] The "means for users to input problems" is an interface that allows users to input problems or questions they want to solve to the system in natural language.

[0539] The "means by which the server obtains data from the database" is a function that enables the server to connect to the database and obtain the required data using a query.

[0540] "Means for the server to preprocess data" refers to a function for preprocessing acquired data, such as cleaning, filtering, and aggregation.

[0541] The "means by which the server analyzes data" refers to a function that applies machine learning algorithms and statistical methods to preprocessed data to analyze the data.

[0542] The "means for the server to generate analysis results" refers to a function for generating reports and graphs based on the analysis results and providing them to the user visually.

[0543] The "means for the server to feed back the results to the user" is a function for sending the generated reports and graphs to the user's terminal and notifying the user of the results.

[0544] "Means for the emotion engine to recognize the user's emotions and adjust the response" refers to a function that analyzes the user's input and reactions, recognizes the user's emotions, and provides an appropriate response accordingly.

[0545] This invention is a system that automates a series of processes: a user inputs a task, a server retrieves data from a database, preprocesses it, analyzes it, generates results, and provides feedback. It also uses an emotion engine to provide responses according to the user's emotions.

[0546] Hardware and software used

[0547] Hardware:

[0548] Server: A computer system that connects to a database, processes data, analyzes data, and generates results.

[0549] Terminal: The device (e.g., PC, smartphone) through which users enter tasks and receive results.

[0550] software:

[0551] Database: A relational database management system such as MySQL or PostgreSQL

[0552] Data analysis tools: Python, R, pandas, scikit-learn, TensorFlow, etc.

[0553] Emotion engine: software for recognizing user emotions and adjusting responses

[0554] Program processing

[0555] Users enter their assignments by:

[0556] Users access the system using a terminal and input their problem in natural language. For example, they might enter, "I want to analyze the purchasing trends of women in their 20s."

[0557] The server retrieves data from the database by:

[0558] The server receives the user's request, connects to the database, executes an SQL query, and retrieves the purchasing data for women in their 20s.

[0559] The server preprocesses the data by:

[0560] The server preprocesses the acquired data using Python's pandas library, specifically cleaning the data (removing missing values ​​and outliers), filtering (extracting necessary columns), and aggregating (counting purchase counts and amounts).

[0561] The server analyzes the data by:

[0562] The server then uses the preprocessed data to perform analysis using machine learning libraries such as scikit-learn and TensorFlow, for example, to classify customers into groups and identify their purchasing trends using clustering algorithms.

[0563] The server generates the analysis results by:

[0564] The server generates reports and graphs based on the analysis results, such as heat maps showing purchasing trends and visualizations of clustering results, for users to view.

[0565] The server's means of feeding results back to the user:

[0566] The server sends the generated reports and graphs to the user's device and provides feedback to the user, who can then use this information to develop a marketing strategy.

[0567] How the Emotion Engine recognizes user emotions and adjusts responses:

[0568] The emotion engine analyzes user input and responses to recognize the user's emotions. For example, if a user says, "I'm happy about the success of my recent campaign," the emotion engine will recognize that joy and provide a more energetic response.

[0569] Examples of concrete examples and prompts

[0570] Examples:

[0571] The user types, "I want to know the purchasing trends of women in their 20s."

[0572] User: "I want to know the purchasing trends of women in their 20s."

[0573] Server: "Retrieve purchasing data for women in their 20s from the database."

[0574] The server connects to the database and executes SQL queries to retrieve the data.

[0575] Server: "We've got the data. Now we'll preprocess it."

[0576] The server uses pandas to clean the data and extract the necessary information.

[0577] Server: "Data preprocessing is complete. Now it's time to analyze it."

[0578] The server uses scikit-learn to perform clustering analysis to identify purchasing trends.

[0579] Server: "Analysis complete. Generating results."

[0580] The server generates reports and graphs based on the analysis results and provides feedback to the user.

[0581] Server: "We will provide you with the analysis results."

[0582] The emotion engine recognizes the user's emotions and adjusts the response.

[0583] User: "I'm happy with the success of my recent campaign."

[0584] Emotion Engine: "That's great! Let's make your next campaign a success!"

[0585] In this way, the system solves the user's problems and provides appropriate responses depending on their emotions.

[0586] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0587] Step 1:

[0588] User enters assignment

[0589] Users access the system using a terminal and input their problem in natural language. For example, they might input, "I want to analyze the purchasing trends of women in their 20s." The input problem is sent to the server.

[0590] Input: User's problem (e.g., "I want to analyze the purchasing trends of women in their 20s.")

[0591] Output: Assignments sent to the server

[0592] Step 2:

[0593] The server retrieves data from the database

[0594] The server receives the user's request, connects to the database, executes an SQL query, and retrieves the purchasing data for women in their 20s.

[0595] Input: User's assignment

[0596] Output: Purchase data obtained

[0597] Step 3:

[0598] The server preprocesses the data

[0599] The server preprocesses the acquired data using Python's pandas library, specifically cleaning the data (removing missing values ​​and outliers), filtering (extracting necessary columns), and aggregating (counting purchase counts and amounts).

[0600] Input: Acquired purchasing data

[0601] Output: Preprocessed data

[0602] Step 4:

[0603] The server analyzes the data

[0604] The server then uses the preprocessed data to perform analysis using machine learning libraries such as scikit-learn and TensorFlow, for example, to classify customers into groups and identify their purchasing trends using clustering algorithms.

[0605] Input: Preprocessed data

[0606] Output: Analysis results (e.g., clustering results)

[0607] Step 5:

[0608] The server generates the analysis results.

[0609] The server generates reports and graphs based on the analysis results, such as heat maps showing purchasing trends and visualizations of clustering results, for users to view.

[0610] Input: Analysis results

[0611] Output: Generated reports and graphs

[0612] Step 6:

[0613] The server feeds the results back to the user

[0614] The server sends the generated reports and graphs to the user's device and provides feedback to the user, who can then use this information to develop a marketing strategy.

[0615] Input: Generated reports and graphs

[0616] Output: Results fed back to the user

[0617] Step 7:

[0618] Emotion engine recognizes user emotions and adjusts responses

[0619] The emotion engine analyzes user input and responses to recognize the user's emotions. For example, if a user says, "I'm happy about the success of my recent campaign," the emotion engine will recognize that joy and provide a more energetic response.

[0620] Input: User's emotional input

[0621] Output: Adjusted response

[0622] In this way, the system solves the user's problems and provides appropriate responses depending on their emotions.

[0623] (Application example 2)

[0624] Next, a description will be given of Application Example 2 of Form 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."

[0625] With conventional marketing systems, analyzing customer purchasing trends and formulating appropriate marketing strategies required a great deal of time and effort. Furthermore, there was a lack of systems that provided responses that reflected the user's emotions, making improving the user experience a challenge.

[0626] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0627] In this invention, the server includes a means for enabling a process from identifying issues to analyzing data and devising solutions through natural language interaction, a means for linking a database with generative AI, a means for adjusting responses based on user emotions using an emotion engine, and a means for acquiring purchasing data and analyzing it using a clustering algorithm. This allows users to efficiently analyze customer purchasing trends and receive appropriate responses according to their emotions.

[0628] "Problem discovery" is the process of identifying the problems and needs that users face.

[0629] "Data analysis" is the process of analyzing collected data using statistical methods and algorithms to extract useful information.

[0630] "Solution development" is the process of designing appropriate countermeasures and strategies for an identified problem.

[0631] "Natural language interaction" means that users communicate with the system using the language they use on a daily basis.

[0632] A "database" is a system for efficiently storing, managing, and retrieving data.

[0633] "Generative AI" is artificial intelligence that generates new information and solutions based on given data and instructions.

[0634] An "emotion engine" is a system that analyzes the user's emotional state and generates a response accordingly.

[0635] "Adjusting responses based on user emotion" refers to providing responses with appropriate tone and content that take into account the user's emotional state.

[0636] "Purchase Data" is data that includes information regarding purchases made by a customer.

[0637] A "clustering algorithm" is a computational method for grouping data based on similarity.

[0638] The following system configuration is used as an embodiment of the present invention.

[0639] The server provides a means to uncover issues, analyze data, and devise solutions through natural language interaction. When a user enters a prompt such as "I would like to analyze customer purchasing trends," the server retrieves purchasing data from the database and analyzes the data using generative AI. Specifically, it uses a clustering algorithm to classify customer purchasing trends and generate analysis results.

[0640] Additionally, the server provides a means to tailor responses based on the user's emotions using an emotion engine, which analyzes the user's input and generates responses with appropriate tone and content depending on the user's emotional state, thereby improving the user experience.

[0641] The hardware used includes a database server, an AI processing server, and a sentiment analysis server, while the software used includes a database management system (DBMS), a generative AI model, a sentiment analysis engine, and a clustering algorithm (e.g., KMeans).

[0642] For example, if a user enters "I want to analyze customer purchasing trends," the server will process the following steps:

[0643] 1. Retrieve customer purchase data from the database.

[0644] 2. Analyze the acquired data using a clustering algorithm (KMeans).

[0645] 3. Generate analysis results and provide feedback to users.

[0646] 4. The emotion engine analyzes the user's input and generates a response based on the emotion.

[0647] Example prompt sentence:

[0648] "I want to analyze customer purchasing trends."

[0649] This system allows users to efficiently analyze customer purchasing trends and receive appropriate responses based on their emotions.

[0650] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0651] Step 1:

[0652] The user inputs a prompt sentence "I would like to analyze customer purchasing trends" into the terminal. The terminal sends this input to the server. The input data is text in natural language format.

[0653] Step 2:

[0654] The server analyzes the received prompt and understands the user's intent. Specifically, it uses natural language processing (NLP) technology to analyze the text and identify the task of "analyzing purchasing trends." The input data is the prompt, and the output data is the analysis results.

[0655] Step 3:

[0656] The server retrieves customer purchasing data from the database. Using a database management system (DBMS), it extracts a data set containing purchasing history and customer information. The input data is the analysis results, and the output data is the purchasing data.

[0657] Step 4:

[0658] The server analyzes the acquired purchase data using a clustering algorithm (KMeans). Specifically, it classifies customers into clusters based on features such as purchase amount and purchase frequency. The input data is the purchase data, and the output data is the clustering results.

[0659] Step 5:

[0660] The server uses a generative AI model to generate solutions based on the clustering results. Specifically, it proposes marketing strategies and recommended actions for each cluster. The input data is the clustering results, and the output data is the solutions.

[0661] Step 6:

[0662] The server analyzes the user's input with an emotion engine to identify the user's emotional state. Specifically, it calculates an emotion score using text analysis technology. The input data is the prompt text, and the output data is the emotion score.

[0663] Step 7:

[0664] The server adjusts the response based on the emotion score and provides feedback to the user. Specifically, it presents a solution with a tone and content that corresponds to the emotion. The input data are the solution and the emotion score, and the output data is the adjusted response.

[0665] Step 8:

[0666] The terminal displays the adjusted response received from the server to the user, who can then formulate a marketing strategy based on the adjusted response. The input data is the adjusted response, and the output data is the display to the user.

[0667] Example 3

[0668] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0669] With conventional systems, it was difficult to efficiently identify issues, analyze data, and devise solutions, and it was particularly difficult to generate solutions that took user emotions into account. Furthermore, the process of improving solutions based on user feedback was time-consuming and laborious, making them impractical in situations where a rapid response was required.

[0670] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0671] In this invention, the server includes a means for enabling the process from identifying issues to analyzing data and devising solutions through natural language interaction, a means for linking the database with generative AI, a means for generating solutions using an emotion engine that analyzes user emotions, and a means for collecting feedback from users and improving the solutions using a generative AI model. This enables the rapid and effective generation and improvement of solutions that take user emotions into consideration.

[0672] "Issue discovery" is the process of identifying problems users are facing and areas for improvement.

[0673] "Data analysis" is the process of analyzing collected data using statistical methods and machine learning to extract useful information.

[0674] "Solution development" is the process of proposing appropriate measures or methods for an identified problem.

[0675] "Natural language interaction" is the process by which users and systems communicate using human language.

[0676] A "database" is a system for efficiently storing, managing, and retrieving data.

[0677] "Generative AI" is artificial intelligence that generates new information or content based on given input.

[0678] An "emotion engine" is a system that analyzes emotions from user input and provides information based on those emotions.

[0679] "Feedback gathering" is the process of gathering opinions and ratings from users.

[0680] "Solution refinement" is the process of improving an existing solution based on collected feedback.

[0681] This invention is a system in which users and AI collaborate to devise new solutions and rapidly carry out creative tasks. In particular, it has the function of generating solutions based on the user's emotions using an emotion engine.

[0682] Hardware and software used

[0683] Hardware: Servers, user devices (PCs, smartphones, etc.)

[0684] Software: generative AI models (e.g., GPT-4), emotion engines, project management tools (e.g., Trello, Asana)

[0685] Data processing and calculation flow

[0686] 1. User input: The user uses a device (PC or smartphone) to input their concerns about the new project and their request for a solution. For example, the user might type "I'm feeling anxious about the new project. What should I do?" into an input form on their device.

[0687] 2. Emotion Recognition: The server receives the user's input and analyzes the user's emotions using the emotion engine. The server activates the emotion engine and recognizes the emotion "anxiety" from the user's input text.

[0688] 3. Solution generation: The server generates a solution using a generative AI model (e.g., GPT-4) based on the analysis results of the emotion engine. The server inputs a prompt statement to the generative AI model: "The user is anxious about a new project. Please provide project management best practices and past success stories." and obtains the generated solution.

[0689] 4. Feedback collection: The server presents the generated solution to the user and collects feedback from the user. The user reviews the solution and enters feedback such as, "Breaking the task down into smaller parts is a good idea, but I'd like to know how to use specific tools."

[0690] 5. Solution refinement: The server receives the user's feedback and refines the solution using the generative AI model again. The server inputs a prompt to the generative AI model: "The user wants to know how to use a specific tool. Please explain how to use Trello." to obtain an improved solution.

[0691] 6. Iterative process: The server presents the improved solution to the user again, and the feedback and refinement process is repeated as needed. The user reviews the improved solution and provides further detailed feedback, which allows the server to refine the solution again.

[0692] Specific examples

[0693] User Type: "I'm feeling anxious about a new project. What should I do?"

[0694] Emotion engine analysis: "Users experience high levels of anxiety"

[0695] The generative AI model's solution: "As a best practice for project management, we recommend breaking down tasks into smaller pieces and visualizing progress. We also recommend learning from past examples of successful project management methods used by other companies."

[0696] User feedback: "Breaking down tasks into smaller pieces is a good idea, but I'd like to see specific tools to help me use them."

[0697] Improved solution: "I recommend using Trello as a specific tool. Here's how to use it."

[0698] Prompt Sentence Examples

[0699] "Generate solutions that provide project management best practices and past success stories for users who are nervous about new projects."

[0700] In this way, by taking the user's feelings into consideration and allowing the AI ​​and the user to work together to generate and improve solutions, it is possible to quickly derive more effective solutions. The flow of the identification process in Example 3 will be described with reference to Figure 21.

[0701] Step 1:

[0702] User Input

[0703] Users use a device (PC or smartphone) to input their concerns about a new project and requests for solutions.

[0704] Input: A user types into a form on their device, "I'm feeling anxious about a new project. What should I do?"

[0705] Output: The user's input text is sent to the server.

[0706] Step 2:

[0707] emotion recognition

[0708] The server receives the user's input and analyzes the user's emotions using an emotion engine.

[0709] Input: The text entered by the user.

[0710] Data processing: The server runs the emotion engine and performs text analysis.

[0711] Output: The user's emotion (e.g., anxiety) is recognized.

[0712] Step 3:

[0713] Solution Generation

[0714] The server generates a solution using a generative AI model (e.g., GPT-4) based on the analysis results of the emotion engine.

[0715] Input: Analysis result of emotion engine (user emotion).

[0716] Data calculation: The server inputs a prompt statement into the generative AI model to generate a solution.

[0717] Output: Generated solutions (e.g. project management best practices and past success stories).

[0718] Step 4:

[0719] Collecting feedback

[0720] The server presents the generated solutions to the user and collects feedback from the user.

[0721] Input: The generated solution.

[0722] Specific operation: The server sends the solution to the user's device, and the user enters feedback.

[0723] Output: User feedback (e.g., "Breaking up the tasks into smaller pieces is a good idea, but I'd like to know how to use specific tools as well.").

[0724] Step 5:

[0725] Improved solution

[0726] The server receives user feedback and refines the solution, again using the generative AI model.

[0727] Input: User feedback.

[0728] Data calculation: The server inputs prompt sentences for improvement into the generative AI model and generates an improved solution.

[0729] Output: An improved solution (e.g., instructions on how to use Trello).

[0730] Step 6:

[0731] Iterative Process

[0732] The server presents the improved solution to the user again, repeating the feedback and refinement process as needed.

[0733] Input: Improved solution.

[0734] What it does: The server sends an improved solution to the user's device, and the user provides more detailed feedback.

[0735] Output: An iterative process until a final solution is determined.

[0736] In this way, AI and users can work together to generate and improve solutions while taking into account the user's emotions, resulting in more effective solutions being found more quickly.

[0737] (Application example 3)

[0738] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0739] Conventional systems provide solutions without considering the user's feelings, making it difficult to alleviate user anxiety and stress. Furthermore, they lacked a mechanism for effectively utilizing user feedback to improve solutions, making it difficult to provide quick and effective solutions. This made it difficult to increase users' sense of security, especially in security services.

[0740] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0741] In this invention, the server includes a means for enabling a process from identifying issues to analyzing data and devising solutions through natural language interaction, a means for linking the database with generative AI, a means for recognizing user emotions in real time and generating solutions based on those emotions, and a means for collecting feedback from users and improving the solutions based on that feedback. This makes it possible to provide solutions that take user emotions into consideration, reducing user anxiety and stress and enabling the provision of quick and effective solutions.

[0742] "Problem discovery" is the process of identifying the problems and needs that users face.

[0743] "Data analysis" is the process of analyzing collected data using statistical methods and machine learning algorithms to extract meaningful information.

[0744] "Solution creation" is the process of designing and proposing appropriate measures and methods to address identified issues.

[0745] "Natural language interaction" refers to communication between the user and the system using human language.

[0746] A database is a system that systematically organizes and stores information so that it can be searched and used efficiently.

[0747] "Generative AI" is a type of artificial intelligence that generates new information and solutions based on given data and conditions.

[0748] "Recognizing user emotions in real time" is a technology that instantly determines the user's current emotional state from facial expressions, tone of voice, etc.

[0749] "Gathering feedback" is the process of gathering opinions and ratings from users.

[0750] "Solution refinement" is the process of improving and optimizing an existing solution based on collected feedback.

[0751] A system for carrying out this invention has the following configuration: The server includes a means for enabling interactions in natural language from identifying issues to analyzing data and devising solutions, a means for linking a database with a generative AI, a means for recognizing user emotions in real time and generating solutions based on those emotions, and a means for collecting feedback from users and improving the solutions based on that feedback.

[0752] Hardware and software used

[0753] Hardware: Smartphone

[0754] Software: OpenAI API, Emotion Recognition API, Feedback System

[0755] Data processing and calculation

[0756] 1. Emotion recognition:

[0757] The server uses the Emotion Recognition API to recognize the user's emotions in real time, allowing it to identify the emotion the user is currently feeling (e.g., anxiety, relief, excitement, etc.).

[0758] 2. Solution generation:

[0759] The server uses a generative AI (e.g., OpenAI's GPT-3 (registered trademark)) to generate a solution based on the user's feelings. Specifically, the server obtains a solution by inputting the following prompt sentence into the generative AI:

[0760] My users are worried. Can you suggest a solution to alleviate their security concerns?

[0761] 3. Feedback Collection:

[0762] The server collects feedback from users, who enter their opinions and ratings on the solutions presented, and this information is sent to the server.

[0763] 4. Solution Improvement:

[0764] The server then re-engages the generative AI based on the collected feedback to refine the solution, thereby providing a solution that better meets the user's needs.

[0765] Specific examples

[0766] For example, if a user is concerned about security, the server will recognize the concern using the Emotion Recognition API. Then, by inputting the following prompt into the generative AI, it will generate a solution.

[0767] My users are worried. Can you suggest a solution to alleviate their security concerns?

[0768] The generated solutions are, for example, "how to set up two-factor authentication" or "past security success stories." When the user provides feedback on these solutions, the server uses that feedback to improve the solutions and propose more effective countermeasures.

[0769] In this way, it becomes possible to provide a solution that takes the user's feelings into consideration, reducing the user's anxiety and stress and providing a quick and effective solution.

[0770] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0771] Step 1:

[0772] A user accesses the system using a smartphone. The user inputs security concerns and problems in natural language. The input data is text data that includes the user's emotions.

[0773] Step 2:

[0774] The server uses the Emotion Recognition API to recognize emotions from user input text in real time. The input is the user's text data, and the output is the user's emotional state (e.g., anxious, relieved, excited, etc.). The server runs text analysis and emotion recognition algorithms to identify the user's emotions.

[0775] Step 3:

[0776] The server uses a generative AI (e.g., OpenAI's GPT-3) to generate a solution based on the user's emotions. The input is the user's emotional state and a prompt, and the output is the generated solution. Specifically, the following prompt is input to the generative AI:

[0777] My users are worried. Can you suggest a solution to alleviate their security concerns?

[0778] The generative AI generates an appropriate solution based on this prompt.

[0779] Step 4:

[0780] The server presents the generated solution to the user, who then reviews the presented solution and inputs feedback. The input is the user's feedback, and the output is the feedback data.

[0781] Step 5:

[0782] The server collects feedback from users and improves the solution using a feedback system. The input is feedback data, and the output is an improved solution. The server analyzes the feedback data and re-enters prompt statements into the generative AI to generate an improved solution.

[0783] Step 6:

[0784] The server presents the improved solution back to the user, who can review the improved solution and provide further feedback as needed, resulting in a solution that better suits the user's needs.

[0785] In this way, it is possible to provide a solution that takes the user's feelings into consideration, thereby reducing the user's anxiety and stress and providing a quick and effective solution.

[0786] 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.

[0787] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0788] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0789] 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.

[0790] [Second embodiment]

[0791] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0792] 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.

[0793] 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).

[0794] 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.

[0795] 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.

[0796] 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).

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0803] "Example 1"

[0804] One form of the present invention is a system that links a database with generative AI. In this system, the user communicates a problem to the AI ​​in natural language. The AI ​​analyzes the problem and retrieves the necessary information from the database. The AI ​​then generates a solution based on the retrieved information and provides feedback to the user.

[0805] "Example 2"

[0806] As a specific example, consider the application of this system to solving marketing problems. When a user tells the AI ​​that they want to analyze customer purchasing trends, the AI ​​retrieves customer purchasing data from a database. The AI ​​then analyzes the purchasing data and generates a solution that clarifies customer purchasing trends. This solution is fed back to the user, who can then use it to create a marketing strategy.

[0807] "Example 3"

[0808] Furthermore, collaboration between AI and users makes it possible to devise new solutions and carry out creative work at high speed. For example, by repeating the process of users providing feedback on solutions generated by AI and then the AI ​​improving the solutions based on that feedback, more effective solutions can be derived quickly.

[0809] The processing flow of each embodiment will be described below.

[0810] "Example 1"

[0811] Step 1: The user communicates the problem to the AI ​​in natural language.

[0812] Step 2: The AI ​​analyzes the problem and retrieves the necessary information from the database.

[0813] Step 3: The AI ​​generates a solution based on the acquired information and provides feedback to the user.

[0814] "Example 2"

[0815] Step 1: The user communicates to the AI ​​the problem of "analyzing customer purchasing trends."

[0816] Step 2: The AI ​​retrieves customer purchasing data from the database.

[0817] Step 3: AI analyzes purchasing data and generates solutions that reveal customer purchasing trends.

[0818] Step 4: This solution is fed back to the user, who can then use it to develop their marketing strategy.

[0819] "Example 3"

[0820] Step 1: The user provides feedback on the AI-generated solution.

[0821] Step 2: The AI ​​uses that feedback to improve the solution.

[0822] Step 3: By repeating this process, you can arrive at a more effective solution faster.

[0823] Example 1

[0824] Next, a description will be given of Example 1 of Form 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."

[0825] In conventional systems, users needed multiple tools and manual operations to solve problems, which was inefficient and time-consuming. Furthermore, data acquisition, analysis, and solution generation were disconnected, resulting in a lack of a consistent process. This made it difficult for users to solve problems quickly and effectively.

[0826] 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.

[0827] In this invention, the server includes: a means for a user to input a problem in natural language; a means for the server to send the problem to the generative AI model as a prompt; a means for the generative AI model to analyze the problem; a means for the server to acquire necessary information from a database; a means for the server to send the acquired information to the generative AI model; a means for the generative AI model to generate a solution; and a means for the server to feed back the solution to the user. This allows the user to simply input the problem in natural language, thereby enabling a consistent process from data acquisition to analysis and solution generation.

[0828] A "user" is an entity that uses the system to input problems and obtain solutions.

[0829] The "server" is a computer system whose role is to receive tasks from users, send them as prompts to the generative AI model, retrieve the necessary information from a database, generate solutions, and provide feedback to the user.

[0830] A "generative AI model" is an artificial intelligence model that analyzes prompts received from users and generates solutions based on the necessary information.

[0831] A "prompt" is a text-based instruction that allows a generative AI model to understand the task entered by the user.

[0832] A "database" is a data repository that a server connects to to get the information it needs.

[0833] A "solution" is a specific answer or proposal to a user's problem that is generated based on the information analyzed by the generative AI model.

[0834] "Feedback" is the process by which the server returns the solution obtained from the generative AI model to the user.

[0835] This invention is a system in which a user inputs a problem in natural language, a server analyzes the problem using a generative AI model, retrieves necessary information from a database, generates a solution, and provides feedback to the user. A specific embodiment of this system is described below.

[0836] Hardware and software used

[0837] Hardware

[0838] Terminal: The device through which the user enters the assignment. Examples include a PC or smartphone.

[0839] Server: A computer system for analyzing problems, acquiring data, generating solutions, and providing feedback.

[0840] software

[0841] Generative AI model: An artificial intelligence model that analyzes problems and generates solutions. An example is OpenAI's GPT-4.

[0842] Database: A data storage system used to store the required information. Examples include MySQL and PostgreSQL.

[0843] System Operation

[0844] User operations

[0845] Users use a terminal to access the system's interface and input their problem in natural language, for example, "Please tell me the sales forecast for the next quarter based on the sales data."

[0846] Server Processing

[0847] The server sends the task received from the user to the generative AI model as a prompt. The generative AI model analyzes the prompt and understands the content of the task. The server then connects to the database and obtains the necessary information identified by the generative AI model. The obtained information is then sent back to the generative AI model, instructing it to generate a solution. The generative AI model generates a solution and returns it to the server.

[0848] feedback

[0849] The server then feeds back the generated solution to the user. The solution is then displayed on the user's device. For example, it might say, "Sales forecast for the next quarter is XX yen."

[0850] Specific examples

[0851] Prompt Sentence Examples

[0852] The user types into the system, "Based on the sales data, what is your sales forecast for the next quarter?"

[0853] In this way, users can obtain specific solutions to their problems through the system. This system allows users to consistently perform everything from data acquisition to analysis and the generation of solutions simply by inputting their problem in natural language.

[0854] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0855] Step 1:

[0856] The user enters an assignment.

[0857] Users access the system interface using a terminal and input tasks in natural language. For example, they might input, "Please tell me the sales forecast for the next quarter based on the sales data." The input task is sent to the server as text data.

[0858] Step 2:

[0859] The server sends the task to the generative AI model as a prompt.

[0860] The server receives the task from the user and sends it to the generative AI model as a prompt. Specifically, the server connects to the generative AI model via an API and sends the user's task in text format. The input is the user's task text, and the output is the prompt sent to the generative AI model.

[0861] Step 3:

[0862] A generative AI model analyzes the problem.

[0863] The generative AI model analyzes the received prompt and understands the content of the problem. For example, it extracts keywords such as "sales data" and "sales forecast for the next quarter" and identifies the necessary data based on these. The input is the prompt, and the output is the identification of the necessary data as the analysis result.

[0864] Step 4:

[0865] The server retrieves the necessary information from the database.

[0866] The server connects to the database and retrieves the required information identified by the generative AI model. Specifically, it executes an SQL query to retrieve sales data. For example, it executes the query SELECT FROM sales_data WHERE date >= '2023-01-01' AND date <= '2023-03-31'. The input is the required data identified as the analysis result, and the output is the sales data retrieved from the database.

[0867] Step 5:

[0868] The server sends the acquired information to the generative AI model.

[0869] The server sends the sales data obtained from the database to the generative AI model. Again, via the API, the obtained data is input to the generative AI model in text format. The input is the sales data obtained from the database, and the output is the data sent to the generative AI model.

[0870] Step 6:

[0871] A generative AI model generates a solution.

[0872] The generative AI model generates a sales forecast for the next quarter based on the acquired sales data. The model analyzes the data and generates the forecast results in text format. The input is sales data, and the output is a sales forecast as a solution.

[0873] Step 7:

[0874] The server feeds back the solution to the user.

[0875] The server feeds back the solution received from the generative AI model to the user. Specifically, the solution is displayed on the user's device. For example, it is displayed in the form of "Sales forecast for the next quarter is XX yen." The input is the solution from the generative AI model, and the output is feedback to the user.

[0876] (Application example 1)

[0877] Next, a description will be given of Application Example 1 of Form 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."

[0878] There is a need to improve operational efficiency at logistics centers and optimize inventory management and delivery schedules. However, with conventional systems, it takes a great deal of time and effort to acquire and analyze data and generate solutions, making efficient operation difficult. In addition, because natural language communication is not possible, users need specialized knowledge to master the system.

[0879] 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.

[0880] In this invention, the server includes a means for enabling interactions in natural language from identifying issues to analyzing data and devising solutions, a means for linking the database with generative AI, a means for users to input issues in natural language and for the AI ​​to analyze the issues and obtain necessary information from the database in order to improve the efficiency of logistics center operations, and a means for generating optimal solutions based on the obtained information and providing feedback to the user. This improves the efficiency of logistics center operations and enables optimization of inventory management and delivery schedules.

[0881] "Identifying issues" is the process of finding out the problems users are facing and areas for improvement.

[0882] "Data analysis" is the process of analyzing collected data and extracting meaningful information.

[0883] "Solution development" is the process of proposing an appropriate solution to an identified problem.

[0884] "Natural language interaction" means that users communicate with the system in the language they use on a daily basis.

[0885] A database is a system that systematically organizes and stores information, allowing it to be searched and retrieved as needed.

[0886] "Generative AI" is artificial intelligence that generates new information and solutions based on given data and instructions.

[0887] A "logistics center" is a facility that stores, manages, and delivers goods.

[0888] "Efficient operations" refers to optimizing business processes and reducing time and costs.

[0889] "Analyzing the problem" is the process of understanding the problem entered by the user and clarifying its essence.

[0890] "Obtaining the necessary information" refers to searching and extracting the data necessary to solve the problem from a database.

[0891] "Generating optimal solutions" is the process of proposing the most effective solution based on the information obtained.

[0892] "Providing feedback to the user" refers to communicating the generated solution to the user.

[0893] A system for carrying out this invention is configured as follows: The server includes a means for enabling interactions in natural language from identifying issues to analyzing data and devising solutions, a means for linking the database with generative AI, a means for users to input issues in natural language and for the AI ​​to analyze the issues and obtain necessary information from the database in order to streamline the operation of the logistics center, and a means for generating optimal solutions based on the obtained information and providing feedback to the user.

[0894] Hardware and software used

[0895] Hardware: Smartphone

[0896] Software: Python, OpenAI API, SQLite (database)

[0897] Data processing and calculation

[0898] 1. Database connection: The server connects to the distribution center database using SQLite, which stores information such as inventory, delivery schedules, and staff shifts.

[0899] 2. Issue analysis: The user inputs the issue in natural language using a smartphone. The server analyzes this input and identifies the type of issue (inventory management, delivery schedule, staff shift, etc.).

[0900] 3. Data Acquisition: The server acquires the necessary information from the database based on the analysis results. For example, if the issue is about inventory management, it acquires inventory information.

[0901] 4. Prompt generation: Based on the acquired data, a prompt is created for the generative AI model (OpenAI).

[0902] 5. Solution generation: The server uses the OpenAI API to generate the optimal solution based on the generated prompt.

[0903] 6. Feedback: The server provides the generated solution to the user, who can then check it on their smartphone.

[0904] Specific examples

[0905] If a user types, "I want to optimize inventory reallocation," the server retrieves inventory data and sends a prompt like this to the generative AI model:

[0906] Prompt Sentence Examples

[0907] Based on the data below, propose a solution to optimize inventory reallocation.

[0908] Data: [(product ID, product name, quantity in stock, location), (product ID, product name, quantity in stock, location), ...]

[0909] In this way, a system can be realized that provides specific solutions for improving the efficiency of logistics center operations.

[0910] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0911] Step 1:

[0912] The user inputs the problem in natural language using a smartphone. For example, the input problem might be "I want to optimize the reallocation of inventory." This input is then sent to the server.

[0913] Step 2:

[0914] The server analyzes the natural language assignments received from the user. Specifically, it understands the content of the assignment and identifies which category (inventory management, delivery schedule, staff shift, etc.) it belongs to. For example, if the keyword "inventory" is included, it is determined to be an assignment related to inventory management.

[0915] Step 3:

[0916] The server retrieves the necessary information from the database based on the analysis results. For example, if the issue is inventory management, it executes the SQL query "SELECT FROM inventory" to retrieve inventory information. The retrieved data includes information such as product ID, product name, stock quantity, and location.

[0917] Step 4:

[0918] The server creates a prompt for the generative AI model based on the acquired data. Specifically, it generates the following prompt:

[0919] Based on the data below, propose a solution to optimize inventory reallocation.

[0920] Data: [(product ID, product name, quantity in stock, location), (product ID, product name, quantity in stock, location), ...]

[0921] This prompt is sent to the generative AI model.

[0922] Step 5:

[0923] The server uses a generative AI model (OpenAI API) to generate an optimal solution based on the prompt. The generative AI model analyzes the input data and generates specific suggestions for optimizing inventory reallocation. For example, a solution such as "move product A from position X to position Y" is generated.

[0924] Step 6:

[0925] The server then provides the generated solution to the user as feedback. Specifically, the solution is displayed on the smartphone screen, allowing the user to check the solution and put it into practice.

[0926] In this way, a system can be realized that provides specific solutions for improving the efficiency of logistics center operations.

[0927] Example 2

[0928] Next, a description will be given of Example 2 of Form 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."

[0929] Conventional methods for solving marketing problems have the problem that collecting data, analyzing it, and devising solutions requires a great deal of time and effort. Furthermore, it is difficult for users without specialized knowledge to analyze data, making it difficult to develop efficient marketing strategies. This has created a need for rapid and effective marketing strategy development.

[0930] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0931] In this invention, the server includes means for a user to input a problem in natural language, means for a terminal to transmit the input problem to the server as a prompt sentence, means for the server to analyze the prompt sentence and identify necessary data, means for the server to acquire data from a database, means for the server to process and analyze the acquired data, means for the server to generate a solution based on the analysis results, means for transmitting the solution generated by the server to the terminal, and means for the user to receive the solution. This enables users, even without specialized knowledge, to receive data analysis and proposed solutions to quickly and effectively solve their marketing problems.

[0932] A "user" is an individual or organization that utilizes the system to input problems and receive solutions.

[0933] A "terminal" is a device that a user uses to input tasks and communicate with the server. For example, a PC or smartphone is an example.

[0934] "Server" is a computer system that parses prompts, acquires data, processes and analyzes it, and generates and transmits solutions.

[0935] A "prompt" is text that converts the user-entered task into a format that the server can understand.

[0936] A "generative AI model" is an artificial intelligence model that performs natural language processing, analyzes prompts, and generates solutions.

[0937] A "database" is an information management system that stores information such as customer purchase data and allows the server to obtain the necessary data.

[0938] "Data processing and analysis" is the process of cleaning, aggregating, filtering, and other processes on acquired data to extract the necessary information.

[0939] A "solution" is a specific proposal or answer to a user's problem that the server generates based on the results of data analysis.

[0940] The "Python Pandas library" is a programming library for efficiently processing and analyzing data.

[0941] This invention is a system for users to solve marketing problems, and includes a process in which the user inputs the problem in natural language, and a server analyzes the problem and generates a solution. Specific embodiments of this system are described below.

[0942] The user uses the device to input a marketing problem in natural language. For example, they might input, "I want to know which product category has sold the most in the last three months." The device then sends this input to the server as a prompt sentence. The prompt sentence is in a format that the generative AI model can understand.

[0943] The server analyzes the prompt using a generative AI model (e.g., an artificial intelligence model that processes natural language). From the analysis results, it identifies the necessary data and analysis method. Next, the server connects to a database (e.g., an information management system that stores customer purchase data) and retrieves the necessary data. For example, it retrieves purchase data from the past three months.

[0944] The acquired data is processed and analyzed on the server. Specifically, the data is cleaned, aggregated, and filtered using Python's Pandas library, and sales for each product category are calculated. This allows the information desired by the user to be extracted.

[0945] The server generates a solution based on the analysis results. Using a generative AI model, it generates a solution in natural language, such as "The most popular product category over the last three months is ____." This solution is then sent to the user via their device.

[0946] Users can check the solutions displayed on the device screen and use them as a reference for formulating marketing strategies. For example, they can formulate a strategy to "further promote products in the XX category."

[0947] This system allows users to receive data analysis and proposed solutions to quickly and effectively solve marketing problems, even if they do not have specialized knowledge.

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

[0949] Step 1:

[0950] User enters assignment

[0951] The user enters in the input field of the terminal, "I want to know the most popular product category for the last three months." The input task is saved on the terminal as a prompt sentence.

[0952] Input: Issues entered by the user in natural language

[0953] Output: prompt statement

[0954] Step 2:

[0955] The terminal sends a prompt to the server

[0956] The device sends the saved prompt as an HTTP request to the server, which includes the user's challenge.

[0957] Input: prompt statement

[0958] Output: HTTP request sent to the server

[0959] Step 3:

[0960] The server parses the prompt.

[0961] The server inputs the received prompt into the generative AI model and obtains the analysis results, which include the type of data required and the analysis method.

[0962] Input: Prompt text received as an HTTP request

[0963] Output: Analysis results (type of data required and analysis method)

[0964] Step 4:

[0965] The server retrieves data from the database

[0966] The server sends an SQL query to the database to retrieve purchase data for the past three months, for example, "SELECT FROM purchases WHERE date >= '3 months ago'".

[0967] Input: SQL query based on the parsed results

[0968] Output: Purchase data for the past three months

[0969] Step 5:

[0970] The server processes and analyzes the data

[0971] The server processes the acquired data using the Python Pandas library, specifically cleaning the data and aggregating sales figures for each product category.

[0972] Input: Purchase data for the past three months

[0973] Output: Sales data for each product category

[0974] Step 6:

[0975] The server generates a solution

[0976] Based on the analysis results, the server uses a generative AI model to generate a solution such as "The best-selling product category over the last three months is XX."

[0977] Input: Sales data for each product category

[0978] Output: A generated solution in natural language

[0979] Step 7:

[0980] The server sends the solution to the device

[0981] The server sends the generated solution as an HTTP response to the terminal, which receives the response and displays it to the user.

[0982] Input: Natural language generated solution

[0983] Output: HTTP response sent to the device

[0984] Step 8:

[0985] The user receives the solution

[0986] The user checks the solutions displayed on the device screen and uses them as a reference for formulating a marketing strategy. For example, they may formulate a strategy such as "further promoting products in the XX category."

[0987] Input: Solution displayed in terminal

[0988] Output: Marketing strategies developed by users

[0989] (Application example 2)

[0990] Next, a description will be given of Application Example 2 of Form 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."

[0991] With conventional marketing methods, it was difficult to grasp customer purchasing trends in real time and immediately make optimal marketing proposals. Furthermore, it required a great deal of time and effort to efficiently analyze customer purchasing data and develop individual marketing strategies. This has led to a demand for more efficient marketing activities and more effective customer responses in brick-and-mortar stores.

[0992] The specific processing by the specific 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 a means for enabling the process from identifying issues to analyzing data and devising solutions through natural language interactions, a means for linking the database with generative AI, a means for identifying customers, a means for analyzing purchasing data in real time, a means for generating marketing proposals based on the analysis results, and a means for displaying the proposals. This makes it possible to grasp customer purchasing trends in real time and instantly make optimal marketing proposals.

[0993] "Identifying the problem" is the process of clarifying the problems the user wants to solve or the goals they want to achieve.

[0994] "Data analysis" is the process of analyzing collected data using statistical methods and machine learning algorithms to extract useful information and patterns.

[0995] "Solution development" is the process of designing specific methods and strategies for solving problems based on the results of analysis.

[0996] "Interaction in natural language" refers to communication between the system and the user using language that humans use on a daily basis.

[0997] A "database" is a system for efficiently storing, managing, and retrieving data.

[0998] "Generative AI" refers to artificial intelligence that generates new information and solutions based on given data and instructions.

[0999] "Customer identification" is the process of recognizing a specific customer using facial recognition technology or other means of identification.

[1000] "Purchase Data" refers to information about products and services that a customer has previously purchased.

[1001] "Real-time analysis" refers to analyzing data as it is generated.

[1002] "Marketing proposal" refers to proposing the most suitable products and services based on the customer's purchasing trends and preferences.

[1003] "Display Proposal" refers to visually presenting the generated marketing proposal to the user.

[1004] A system for carrying out this invention is configured as follows: The server includes a means for enabling a process from identifying issues to analyzing data and devising solutions through natural language interaction, a means for linking a database with generative AI, a means for identifying customers, a means for analyzing purchasing data in real time, a means for generating marketing proposals based on the analysis results, and a means for displaying the proposals.

[1005] First, the server analyzes the user's input in natural language and retrieves the appropriate data from the database. The retrieved data is then passed to a generative AI system, which analyzes purchasing trends. Based on the analysis results, the generative AI system generates optimal marketing proposals. These proposals are displayed on devices such as smart glasses.

[1006] Specifically, the server uses OpenCV to recognize customer faces from video captured by the camera and TensorFlow to analyze purchasing trends. Customer purchasing data is stored in a database, and Pandas and Scikit-learn are used to preprocess and cluster the data. This makes it possible to understand customer purchasing trends in real time and generate optimal marketing proposals.

[1007] For example, when a customer enters a store, the smart glasses can recognize them and display a message saying, "New product promotions offered" based on their past purchase data. If another customer enters the store, the glasses can also display a message saying, "Discount coupons offered."

[1008] Examples of prompts to input to a generative AI model include:

[1009] "Based on customer purchasing data, analyze purchasing trends and generate optimal marketing proposals. For example, if a customer is interested in new products, suggest new product promotions; if a customer prefers discounts, suggest discount coupons."

[1010] In this way, the server can analyze customer purchasing trends in real time, generate optimal marketing proposals, and display them on the terminal, thereby improving the efficiency of marketing activities and effectively responding to customers in physical stores.

[1011] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1012] Step 1:

[1013] The server receives a task entered by the user in natural language. For example, the task entered might be, "I want to analyze customer purchasing trends." The server analyzes this task and retrieves the appropriate data from the database. Specifically, the server analyzes the natural language text entered by the user and extracts related keywords. This generates a query to retrieve the necessary purchasing data from the database.

[1014] Input: Issues entered by the user in natural language

[1015] Output: Query to retrieve from the database

[1016] Step 2:

[1017] The server uses the generated query to retrieve customer purchase data from a database, which stores the customer's past purchase history and related information. The retrieved data is used for analysis in the next step.

[1018] Input: Query to retrieve from the database

[1019] Output: Customer purchase data

[1020] Step 3:

[1021] The server passes the acquired purchasing data to a generative AI system to analyze purchasing trends. Specifically, it uses TensorFlow to run a machine learning model and analyze customer purchasing trends. The data is preprocessed using Pandas and Scikit-learn, and standardized and clustered.

[1022] Input: Customer purchase data

[1023] Output: Analysis of purchasing trends

[1024] Step 4:

[1025] The server generates optimal marketing proposals based on the analysis results. The generative AI then generates specific proposals based on the analysis results, such as "proposing new product promotions" or "proposing discount coupons." These proposals provide useful information to users.

[1026] Input: Analysis results of purchasing trends

[1027] Output: Marketing proposal

[1028] Step 5:

[1029] The server transmits the generated marketing proposals to a terminal, which is a device such as smart glasses that visually displays the proposals, allowing the user to view the optimal marketing proposals in real time.

[1030] Input: Marketing Proposal

[1031] Output: Proposal displayed in terminal

[1032] Step 6:

[1033] Based on the suggestions displayed on the terminal, users can respond appropriately to customers. For example, they can introduce new product promotions to customers or provide discount coupons. This will improve the efficiency of marketing activities in physical stores and enable effective customer service.

[1034] Input: Suggestion displayed on terminal

[1035] Output: Appropriate response to the customer

[1036] Through the above steps, a system is realized in which the server, terminals, and users work together to analyze customer purchasing trends in real time and make optimal marketing proposals.

[1037] Example 3

[1038] Next, a description will be given of Example 3 of Form Example 3. 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."

[1039] In conventional systems, the process from identifying issues to analyzing data and devising solutions was fragmented, making efficient problem solving difficult. Furthermore, the process of improving solutions based on user feedback was often done manually, which was time-consuming and labor-intensive. Furthermore, there was a lack of concrete methods for effectively utilizing generative AI models.

[1040] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1041] In this invention, the server includes a means for enabling a process from identifying a problem to analyzing data and devising a solution through natural language interaction, a means for linking a database with a generative AI, a means for a user to input information about a problem they wish to solve, a means for generating an initial solution using a generative AI model, a means for collecting feedback from the user, a means for improving the solution based on the feedback, and a means for presenting a final solution to the user, thereby enabling efficient and rapid problem solving.

[1042] "Identifying issues" is the process of finding problems that need to be solved or areas for improvement.

[1043] "Data analysis" is the process of organizing collected data and extracting meaningful information.

[1044] "Solution development" is the process of proposing appropriate measures or methods for solving problems that have been discovered.

[1045] "Communicating in natural language" refers to exchanging information using a language that humans use on a daily basis.

[1046] A "database" is a system that systematically stores data and enables it to be searched and used efficiently.

[1047] "Generative AI" is an artificial intelligence technology that generates new data and solutions based on given information.

[1048] "User" refers to an individual or organization that uses the system to solve a problem.

[1049] A "generative AI model" is an artificial intelligence model that is trained to generate new data and solutions for a specific task.

[1050] An "initial solution" is the solution that the generative AI model first proposes.

[1051] "Feedback" refers to information about evaluations and areas for improvement provided by users.

[1052] "Improvement" is the process of making modifications or additions to an existing solution to make it more effective.

[1053] The "final solution" is the final solution that has been refined based on user feedback.

[1054] This invention is a system that allows a user to input information about a problem they want to solve, generates a solution using a generative AI model, and improves the solution based on user feedback. A specific embodiment of this system is described below.

[1055] The server generates a program using a generative AI model. For example, GPT-4 can be used as this generative AI model. The server receives information entered by the user through the terminal and generates an initial solution. The generated solution is presented to the user through the terminal.

[1056] A user uses the terminal to input information about the problem they want to solve—for example, if they are devising a marketing strategy, they input information about the current market situation and their target customers—and the terminal transmits this information to the server.

[1057] The server uses a generative AI model to generate an initial solution based on the received information. The generative AI model analyzes the input information and creates a prompt to generate an appropriate solution. For example, it generates a prompt such as, "Please propose a new marketing strategy based on the current market situation and target customers." The server then sends the generated solution to the device.

[1058] The user checks the initial solution displayed on the device and provides feedback. For example, the user can input specific feedback such as, "The target customer age range is too broad, so please narrow it down a bit more." The device then sends the user's feedback to the server.

[1059] The server receives feedback from the user and again uses the generative AI model to improve the solution. The generative AI model takes the feedback into account to create a new prompt and generate an improved solution. For example, it generates a prompt such as, "Please propose a marketing strategy that narrows the target customer age range to between 25 and 35 years old." The server then sends the improved solution to the device.

[1060] The user reviews the improved solution and provides further feedback if necessary. This process is repeated until a solution that satisfies the user is obtained. The final solution is presented to the user via the terminal.

[1061] Examples:

[1062] Suppose a user wants to devise a new marketing strategy. The user inputs information about the current market situation (e.g., "The market is becoming increasingly competitive") and target customers (e.g., "Our target customers are young people between the ages of 20 and 40") through a terminal. The terminal then sends this information to a server.

[1063] The server uses a generative AI model (GPT-4) to generate a prompt such as "Please propose a new marketing strategy based on the current market situation and target customers," and generates an initial solution. The generated solution might be, for example, "Launch an advertising campaign using social media."

[1064] The user provides feedback on this solution, saying, "The target customer age range is too broad, so I'd like it to be narrowed down a bit more." The terminal sends this feedback to the server.

[1065] Based on the feedback, the server uses the generative AI model again to generate a prompt such as "Please propose a marketing strategy that narrows the target customer age range to 25 to 35 years old," and generates an improved solution. For example, the improved solution might be "Develop influencer marketing targeting young people aged 25 to 35."

[1066] The user checks the improved solution and provides further feedback as necessary. By repeating this process, the user can quickly obtain an optimal marketing strategy. The flow of the identification process in Example 3 will be described with reference to FIG. 15.

[1067] Step 1:

[1068] Data Entry

[1069] A user inputs information about a problem to be solved through a terminal. For example, when devising a marketing strategy, the user inputs information about the current market situation and target customers.

[1070] Input: Market situation, target customer information

[1071] Output: The entered information is sent from the device to the server.

[1072] Step 2:

[1073] Generate an initial solution

[1074] The server generates an initial solution based on the received information using a generative AI model, which analyzes the input information and creates prompts to generate an appropriate solution.

[1075] Input: Market situation and target customer information entered by the user

[1076] Data processing: A generative AI model analyzes the information and generates prompts

[1077] Output: An initial solution is generated and sent to the terminal.

[1078] Step 3:

[1079] Collecting feedback

[1080] The user checks the initial solution displayed on the terminal and provides feedback, for example, by inputting specific feedback such as, "The target customer age range is too broad, so please narrow it down a bit more."

[1081] Input: User feedback on the initial solution

[1082] Output: Feedback is sent from the device to the server

[1083] Step 4:

[1084] Improved solution

[1085] The server receives feedback from the user and refines the solution using the generative AI model again, which takes the feedback into account to create a new prompt and generate an improved solution.

[1086] Input: User feedback

[1087] Data processing: A generative AI model analyzes feedback and generates new prompts

[1088] Output: An improved solution is generated and sent to the terminal

[1089] Step 5:

[1090] Presentation of the final solution

[1091] The user reviews the improved solution and provides further feedback if necessary. This process is repeated until a solution that satisfies the user is obtained. The final solution is presented to the user via the terminal.

[1092] Input: User feedback for an improved solution (if needed)

[1093] Output: The final solution is displayed in the terminal.

[1094] In this way, users, terminals, and servers can work together to solve problems efficiently and quickly.

[1095] (Application example 3)

[1096] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1097] Conventional factory robot operation optimization involves collecting feedback to improve the robot's operation and then making improvements based on that feedback, which is a time-consuming and labor-intensive process. Furthermore, there was a lack of effective means for users and AI to collaborate to quickly derive solutions. This resulted in reduced factory production efficiency and increased costs.

[1098] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1099] In this invention, the server includes a means for enabling interactions in natural language from identifying issues to analyzing data and devising solutions, a means for linking the database with the generative AI, a means for the generative AI to improve solutions based on feedback from users, a means for collecting feedback in real time via a smart device, and a means for the generative AI to re-propose the improved solutions. This enables users and AI to work together to quickly and effectively optimize the operation of factory robots.

[1100] "Identifying issues" means identifying problems and areas for improvement in systems and processes.

[1101] "Data analysis" refers to the analysis of collected data using statistical methods and machine learning algorithms to extract meaningful information.

[1102] "Developing a solution" means designing and proposing effective measures and methods for addressing identified issues.

[1103] "Natural language interaction" means that the system and the user communicate using the language that humans use on a daily basis.

[1104] A "database" is a system for efficiently storing, managing, and retrieving data.

[1105] "Generative AI" is artificial intelligence that generates new information and solutions based on user input and feedback.

[1106] "User feedback" refers to the opinions and evaluations provided by users regarding the solutions proposed by the system.

[1107] "Smart devices" are electronic devices with advanced functions, such as mobile terminals and wearable devices that can connect to the Internet.

[1108] "Collecting feedback in real time" means obtaining opinions and ratings from users immediately.

[1109] An "improved solution" is a new solution that the generative AI has improved based on user feedback.

[1110] A system for implementing the present invention includes a server, a smart device, and a generative AI model. Specific embodiments are described below.

[1111] System Configuration

[1112] 1. Server

[1113] The server provides a means to identify issues, analyze data, and devise solutions through natural language interaction. The server is connected to a database and has a generative AI model installed.

[1114] 2. Smart Devices

[1115] Smart devices, such as smartphones and tablets, are used to collect real-time user feedback.

[1116] 3. Generative AI Models

[1117] Generative AI models provide a way to improve solutions based on user feedback, using APIs such as those from OpenAI.

[1118] Data processing and calculation

[1119] 1. Identifying issues and analyzing data

[1120] The server analyzes the issues entered by the user in natural language and extracts related data stored in the database, thereby identifying issues and analyzing the data.

[1121] 2. Solution Generation

[1122] The generative AI model generates an initial solution based on the analyzed data, which is then presented to the user via their smart device.

[1123] 3. Gather feedback and improve

[1124] Users input feedback on the solution via their smart devices. The server collects this feedback and sends it to the generative AI model, which then refines the solution based on the feedback and presents it to the user again.

[1125] Specific examples

[1126] For example, when a factory robot proposes a solution to streamline parts assembly work, the following prompt sentence is used:

[1127] Initial Prompt

[1128] "Please propose a solution to help factory robots improve the efficiency of parts assembly."

[1129] Feedback-based prompts

[1130] "Please improve the following solution:

[1131] Solution: Increase the robot arm speed by 20%.

[1132] Feedback: Increasing arm speed may result in decreased accuracy.

[1133] Improved solution:

[1134] In this way, users and AI can work together to quickly and effectively optimize the operation of factory robots.

[1135] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1136] Step 1:

[1137] The server receives a challenge input from a user in natural language.

[1138] Input: A problem entered by a user through a smart device (e.g., "I want to improve the efficiency of assembly work by factory robots").

[1139] Data processing: Using natural language processing (NLP) technology, the input task is analyzed and keywords and important information are extracted.

[1140] Output: Extracted keywords and key information (e.g., "factory robot," "assembly work," "efficiency").

[1141] Step 2:

[1142] The server accesses the database and searches for and retrieves data related to the extracted keywords.

[1143] Input: Extracted keywords and important information.

[1144] Data manipulation: Performing database queries to retrieve relevant data.

[1145] Output: Relevant data obtained (e.g. data from past assembly operations, existing methods for improving efficiency).

[1146] Step 3:

[1147] The server inputs relevant data into a generative AI model to generate an initial solution.

[1148] Input: The relevant data retrieved.

[1149] Data Computing: Use generative AI models (e.g., OpenAI APIs) to generate solutions based on relevant data.

[1150] Output: An initial solution (e.g., "Increase the robot's arm speed by 20%").

[1151] Step 4:

[1152] The server presents the generated solution to the user via a smart device.

[1153] Input: Initial solution.

[1154] Data manipulation: Converting the solution into a format that is easy for users to understand.

[1155] Output: A solution presented to the user (e.g., "Increase the robot's arm speed by 20%").

[1156] Step 5:

[1157] The user provides feedback on the proposed solution.

[1158] Input: User feedback (e.g., "Increasing arm speed may decrease accuracy").

[1159] Data processing: Feedback is analyzed using natural language processing techniques to extract key information.

[1160] Output: Extracted feedback key information (e.g. "Potential for accuracy degradation").

[1161] Step 6:

[1162] The server inputs the extracted feedback into a generative AI model to refine the solution.

[1163] Input: Extracted feedback key information.

[1164] Data computation: Using generative AI models to improve solutions based on feedback.

[1165] Output: Improved solution (e.g., "Increase arm speed by 15% and add a compensation algorithm to maintain accuracy").

[1166] Step 7:

[1167] The server presents the improved solution to the user again via the smart device.

[1168] Input: Improved solution.

[1169] Data processing: Converting the improved solution into a format that is easy for users to understand.

[1170] Output: An improved solution presented to the user (e.g., "Increase arm speed by 15% and add a compensation algorithm to maintain accuracy").

[1171] In this way, users and AI can work together to quickly and effectively optimize the operation of factory robots.

[1172] 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.

[1173] "Example 1"

[1174] One embodiment of the present invention is a system that includes an emotion engine that uses AI to recognize user emotions. The system understands the user's emotions through natural language interactions with the user and provides solutions based on those emotions. Specifically, if the user is feeling frustrated, the AI ​​can recognize that emotion and provide a more polite response, thereby improving user satisfaction.

[1175] "Example 2"

[1176] Another embodiment of the present invention is a system in which an emotion engine adjusts the AI's response based on the user's emotions. In this system, if the user is feeling joy, the AI ​​will recognize that emotion and provide a more energetic response, thereby maximizing the user's joy and providing a better user experience.

[1177] "Example 3"

[1178] Furthermore, a system in which an emotion engine generates solutions based on a user's emotions is also one embodiment of the present invention. In this system, if a user is feeling anxious, the AI ​​recognizes that emotion and provides a solution to alleviate the anxiety. For example, if a user is feeling anxious about a new project, the AI ​​recognizes the anxiety and provides project management best practices and past success stories to alleviate the user's anxiety.

[1179] The processing flow of each embodiment will be described below.

[1180] "Example 1"

[1181] Step 1: Understand user sentiment through natural language interactions with users.

[1182] Step 2: The emotion engine recognizes the user's emotion.

[1183] Step 3: Based on the recognized emotion, the AI ​​provides a solution.

[1184] "Example 2"

[1185] Step 1: Understand user sentiment through natural language interactions with users.

[1186] Step 2: The emotion engine recognizes the user's emotion.

[1187] Step 3: The AI ​​tailors its response based on the perceived emotion.

[1188] "Example 3"

[1189] Step 1: Understand user sentiment through natural language interactions with users.

[1190] Step 2: The emotion engine recognizes the user's emotion.

[1191] Step 3: The AI ​​generates a solution based on the recognized emotion.

[1192] Example 1

[1193] Next, a description will be given of Example 1 of Form 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."

[1194] Conventional systems have made it difficult for users to efficiently obtain the information they need to solve problems and find appropriate solutions. Furthermore, they are unable to provide responses that reflect the user's emotions, making it difficult to improve user satisfaction. Furthermore, there is a need for efficient work progression and the rapid execution of creative tasks using generative AI models.

[1195] 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.

[1196] In this invention, the server includes a means for a user to input a problem in natural language, a means for analyzing the problem using a generative AI model, a means for acquiring necessary information from a database, a means for generating a solution based on the acquired information, a means for recognizing the user's emotions and adjusting the response, and a means for feeding back the generated solution to the user. This allows the user to not only solve the problem efficiently, but also receive appropriate support according to their emotions.

[1197] A "user" is an individual or organization that uses the system to input problems and obtain solutions.

[1198] "Natural language" refers to the language used by humans on a daily basis, and refers to normal speech and writing forms, rather than specific programming languages ​​or commands.

[1199] A "generative AI model" is an artificial intelligence algorithm or system that analyzes input natural language and generates appropriate solutions or information.

[1200] "Analyzing the problem" is the process of understanding the problem entered in natural language by the user and identifying the necessary information and solutions based on that content.

[1201] A "database" is a digital storage system that stores information systematically and allows it to be searched and retrieved as needed.

[1202] "Retrieving information" is the process of searching and retrieving the required data from a database.

[1203] "Generating solutions" is the process of creating specific solutions or proposals for the user's problems based on the information obtained.

[1204] "Emotion recognition" is the process of identifying and understanding a user's emotional state from their input and behavior.

[1205] "Response tailoring" is the process of changing the content and tone of the solutions and feedback you generate based on perceived user emotions.

[1206] "Feedback" is the process of providing generated solutions or information to the user so that they can review it.

[1207] This invention is a system that links a database with a generative AI model, where a user inputs a problem in natural language, and the AI ​​analyzes the problem and provides a solution. A specific embodiment of this system is shown below.

[1208] Hardware and software used

[1209] Hardware: Servers, terminals

[1210] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), emotion engines (e.g., Affectiva)

[1211] System configuration

[1212] 1. User issue input

[1213] The user uses the device to input the issue in natural language. For example, the user types "How do I manage the progress of a new project?" into the device's input field.

[1214] 2. Problem Analysis

[1215] The server analyzes the user's problem using a generative AI model, which understands the input natural language and identifies the subject of the problem and the required information.

[1216] 3. Retrieving information from the database

[1217] The server uses a database management system to retrieve necessary information from the database based on the analysis results, for example, the server searches the database for information related to "project management."

[1218] 4. Solution Generation

[1219] The server uses a generative AI model to generate solutions based on the acquired information. For example, based on project management information acquired from the database, the server generates a solution such as, "Task prioritization and progress visualization are important for project management. Specifically, we recommend using a Gantt chart."

[1220] 5. Emotion recognition and response regulation

[1221] The server uses an emotion engine to recognize the user's emotions. For example, the server analyzes the user's input and past interactions to recognize that the user is frustrated. The emotion engine analyzes the user's text and voice data to identify their emotional state. The generative AI model then adjusts its response accordingly.

[1222] 6. User Feedback

[1223] The server sends the generated solution to the device and provides feedback to the user. For example, the server might send a solution such as, "In project management, prioritizing tasks and visualizing progress are important. Specifically, we recommend using a Gantt chart." The device then displays the solution received from the server to the user.

[1224] Specific examples

[1225] Prompt Sentence Examples

[1226] "How do I manage the progress of a new project?"

[1227] "Can you give me some advice on prioritizing tasks?"

[1228] "What are some common project management problems and how can you solve them?"

[1229] This system not only enables users to solve problems efficiently, but also allows them to receive appropriate support according to their emotions.

[1230] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1231] Step 1:

[1232] User issue input

[1233] Input: A user enters an issue in natural language using a terminal.

[1234] What happens: The user types "How do I manage progress on a new project?" into the device's input field.

[1235] Output: The terminal receives user input and sends it to the server.

[1236] Step 2:

[1237] Analysis of the problem

[1238] Input: User challenge submitted from the device (natural language text).

[1239] How it works: The server analyzes the user's problem using a generative AI model. The generative AI model understands the input natural language and identifies the subject of the problem and the required information.

[1240] Output: Identification of the subject and required information.

[1241] Step 3:

[1242] Retrieving information from a database

[1243] Input: Identification of the subject and required information.

[1244] Specific operations: The server uses the database management system to retrieve the necessary information from the database based on the analysis results. The server searches the database for information related to "project management."

[1245] Output: Information retrieved from the database.

[1246] Step 4:

[1247] Solution Generation

[1248] Input: Information retrieved from the database.

[1249] Specific operation: The server uses the generative AI model to generate a solution based on the acquired information. Based on the information about project management acquired from the database, the server generates the solution, "In project management, prioritizing tasks and visualizing progress are important. Specifically, we recommend using a Gantt chart."

[1250] Output: The generated solution.

[1251] Step 5:

[1252] Emotion recognition and response regulation

[1253] Input: User input, past interactions, and generated solutions.

[1254] How it works: The server uses an emotion engine to recognize the user's emotions. The server analyzes the user's input and past interactions and recognizes that the user is frustrated. The emotion engine analyzes the user's text and voice data to identify their emotional state. The generative AI model adjusts its response based on that emotional state.

[1255] Output: The adjusted response.

[1256] Step 6:

[1257] User feedback

[1258] Input: The adjusted response.

[1259] Specific operations: The server sends the generated solution to the device and provides feedback to the user. The server sends the solution "Task prioritization and progress visualization are important for project management. Specifically, we recommend using a Gantt chart." to the device. The device displays the solution received from the server to the user.

[1260] Output: The solution displayed to the user.

[1261] (Application example 1)

[1262] Next, a description will be given of Application Example 1 of Form 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."

[1263] On conventional online shopping sites, it is difficult for users to quickly obtain appropriate product information when searching for a product, and they are unable to respond to the user's emotions, which leads to a decrease in user satisfaction. In particular, when a user feels frustrated, they are unable to respond appropriately, which leads to a worsening user experience.

[1264] 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.

[1265] In this invention, the server includes a means for enabling a process from identifying issues to analyzing data and devising solutions through natural language interaction, a means for linking the database with generative AI, a means for recognizing user emotions and providing solutions based on those emotions, and a means for suggesting optimal product information based on user input. As a result, when a user communicates a problem in natural language, the AI ​​analyzes the problem, retrieves the necessary information from the database, generates a solution, and responds in accordance with the user's emotions.

[1266] "Identifying the problem" is the process of clarifying the problems and needs of users in natural language.

[1267] "Data analysis" is the process of analyzing collected data and extracting meaningful information.

[1268] "Solution creation" is the process of generating an appropriate solution to an identified problem.

[1269] "Natural language interaction" means that users communicate with the system using the language they use on a daily basis.

[1270] A database is a system that systematically organizes and stores information, allowing it to be searched and retrieved as needed.

[1271] "Generative AI" is artificial intelligence that generates new information and solutions based on given data and instructions.

[1272] "Recognizing user emotions" is the process of analyzing and understanding a user's emotional state from their input and behavior.

[1273] "Providing solutions" refers to making appropriate responses or suggestions based on identified issues and emotions.

[1274] "Proposing optimal product information" is the process of selecting and presenting the product that best suits the user's requests and needs.

[1275] To implement this invention, the following system configuration is required: The system consists of a terminal where users can input tasks in natural language, a database, a generative AI, and a server that includes an emotion recognition engine.

[1276] When a user uses a device to input a challenge in natural language, the input is sent to the server, which first analyzes the user's emotions using an emotion recognition engine, which uses a natural language processing library such as TextBlob to classify the emotion of the user's input text as positive, negative, or neutral.

[1277] The server then uses generative AI to analyze the user's problem and retrieves the necessary information from a database. This generative AI uses OpenAI's API to generate optimal product information based on the user's questions and requests. The database stores product information and the user's past purchase history.

[1278] The server then suggests optimal product information to the user based on the acquired information and the results of emotion recognition. For example, if a user types, "The weather has been bad lately, so I don't feel like going out. Please tell me about some useful items I can use at home," the server responds, "We are searching for the best products to resolve your complaint. Please wait a moment," and then suggests, "Recommended products: automatic vacuum cleaner, smart speaker, home exercise kit."

[1279] This system allows users to simply communicate their issues in natural language, and quickly receive appropriate responses based on their emotions and the most appropriate product information.

[1280] An example of a prompt is as follows:

[1281] A user asked the following question: The weather has been so bad lately that I don't feel like going out. What are some handy items I can use around the house?

[1282] Please suggest the best product.

[1283] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1284] Step 1:

[1285] The user enters the issue in natural language using a terminal.

[1286] Input: The user's natural language challenge or question.

[1287] Output: The user's input text data.

[1288] Specific operation: The user enters "The weather has been bad lately, so I don't feel like going out. Please tell me some useful items I can use at home" into the input field on the device and presses the send button.

[1289] Step 2:

[1290] The server receives the user's input text data and analyzes the emotions using an emotion recognition engine.

[1291] Input: User-entered text data.

[1292] Output: Emotion recognition result (positive, negative, neutral).

[1293] Specific behavior: The server uses the TextBlob library to analyze the sentiment of the user's input text and determines it to be "negative."

[1294] Step 3:

[1295] The server uses generative AI to analyze the user's issues and retrieve the necessary information from the database.

[1296] Input: User input text data, emotion recognition results.

[1297] Output: A solution (product information) created by generative AI.

[1298] How it works: The server uses the OpenAI API to generate product information such as "automatic vacuum cleaner, smart speaker, home exercise kit" based on the user's question.

[1299] Step 4:

[1300] The server proposes optimal product information to users based on emotion recognition results and solutions provided by generative AI.

[1301] Input: Generative AI solution, emotion recognition results.

[1302] Output: A response message to the user.

[1303] Specific behavior: The server responds, "We are looking for the best products to resolve your complaint. Please wait a moment." and then suggests, "Recommended products: Automatic vacuum cleaner, smart speaker, home exercise kit."

[1304] Step 5:

[1305] The user receives and displays the response message from the server on the terminal.

[1306] Input: The response message from the server.

[1307] Output: The response message that is displayed on the user's terminal.

[1308] What it does: The user's device will display the message "We're looking for the best products to resolve your complaint. Please wait a moment.", followed by the suggestion "Recommended products: Automatic vacuum cleaner, smart speaker, home exercise kit."

[1309] Example 2

[1310] Next, a description will be given of Example 2 of Form 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."

[1311] In conventional marketing systems, the process of users entering their issues, acquiring data, preprocessing, analyzing, generating results, and providing feedback is often done manually, which takes time and effort. It is also difficult to provide responses that reflect the user's emotions, resulting in a lack of improvement in the user experience. To solve these issues, a system is needed that automates the entire process, from data acquisition to analysis and feedback of results, and that also provides responses that reflect the user's emotions.

[1312] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1313] In this invention, the server includes means for a user to input a task, means for the server to acquire data from a database, means for the server to preprocess the data, means for the server to analyze the data, means for the server to generate analysis results, means for the server to feed back the results to the user, and means for an emotion engine to recognize the user's emotions and adjust responses. This makes it possible to automate the entire process from data acquisition to analysis and feedback of the results, and to provide responses that correspond to the user's emotions.

[1314] The "means for users to input problems" is an interface that allows users to input problems or questions they want to solve to the system in natural language.

[1315] The "means by which the server obtains data from the database" is a function that enables the server to connect to the database and obtain the required data using a query.

[1316] "Means for the server to preprocess data" refers to a function for preprocessing acquired data, such as cleaning, filtering, and aggregation.

[1317] The "means by which the server analyzes data" refers to a function that applies machine learning algorithms and statistical methods to preprocessed data to analyze the data.

[1318] The "means for the server to generate analysis results" refers to a function for generating reports and graphs based on the analysis results and providing them to the user visually.

[1319] The "means for the server to feed back the results to the user" is a function for sending the generated reports and graphs to the user's terminal and notifying the user of the results.

[1320] "Means for the emotion engine to recognize the user's emotions and adjust the response" refers to a function that analyzes the user's input and reactions, recognizes the user's emotions, and provides an appropriate response accordingly.

[1321] This invention is a system that automates a series of processes: a user inputs a task, a server retrieves data from a database, preprocesses it, analyzes it, generates results, and provides feedback. It also uses an emotion engine to provide responses according to the user's emotions.

[1322] Hardware and software used

[1323] Hardware:

[1324] Server: A computer system that connects to a database, processes data, analyzes data, and generates results.

[1325] Terminal: The device (e.g., PC, smartphone) through which users enter tasks and receive results.

[1326] software:

[1327] Database: A relational database management system such as MySQL or PostgreSQL

[1328] Data analysis tools: Python, R, pandas, scikit-learn, TensorFlow, etc.

[1329] Emotion engine: software for recognizing user emotions and adjusting responses

[1330] Program processing

[1331] Users enter their assignments by:

[1332] Users access the system using a terminal and input their problem in natural language. For example, they might enter, "I want to analyze the purchasing trends of women in their 20s."

[1333] The server retrieves data from the database by:

[1334] The server receives the user's request, connects to the database, executes an SQL query, and retrieves the purchasing data for women in their 20s.

[1335] The server preprocesses the data by:

[1336] The server preprocesses the acquired data using Python's pandas library, specifically cleaning the data (removing missing values ​​and outliers), filtering (extracting necessary columns), and aggregating (counting purchase counts and amounts).

[1337] The server analyzes the data by:

[1338] The server then uses the preprocessed data to perform analysis using machine learning libraries such as scikit-learn and TensorFlow, for example, to classify customers into groups and identify their purchasing trends using clustering algorithms.

[1339] The server generates the analysis results by:

[1340] The server generates reports and graphs based on the analysis results, such as heat maps showing purchasing trends and visualizations of clustering results, for users to view.

[1341] The server's means of feeding results back to the user:

[1342] The server sends the generated reports and graphs to the user's device and provides feedback to the user, who can then use this information to develop a marketing strategy.

[1343] How the Emotion Engine recognizes user emotions and adjusts responses:

[1344] The emotion engine analyzes user input and responses to recognize the user's emotions. For example, if a user says, "I'm happy about the success of my recent campaign," the emotion engine will recognize that joy and provide a more energetic response.

[1345] Examples of concrete examples and prompts

[1346] Examples:

[1347] The user types, "I want to know the purchasing trends of women in their 20s."

[1348] User: "I want to know the purchasing trends of women in their 20s."

[1349] Server: "Retrieve purchasing data for women in their 20s from the database."

[1350] The server connects to the database and executes SQL queries to retrieve the data.

[1351] Server: "We've got the data. Now we'll preprocess it."

[1352] The server uses pandas to clean the data and extract the necessary information.

[1353] Server: "Data preprocessing is complete. Now it's time to analyze it."

[1354] The server uses scikit-learn to perform clustering analysis to identify purchasing trends.

[1355] Server: "Analysis complete. Generating results."

[1356] The server generates reports and graphs based on the analysis results and provides feedback to the user.

[1357] Server: "We will provide you with the analysis results."

[1358] The emotion engine recognizes the user's emotions and adjusts the response.

[1359] User: "I'm happy with the success of my recent campaign."

[1360] Emotion Engine: "That's great! Let's make your next campaign a success!"

[1361] In this way, the system solves the user's problems and provides appropriate responses depending on their emotions.

[1362] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1363] Step 1:

[1364] User enters assignment

[1365] Users access the system using a terminal and input their problem in natural language. For example, they might input, "I want to analyze the purchasing trends of women in their 20s." The input problem is sent to the server.

[1366] Input: User's problem (e.g., "I want to analyze the purchasing trends of women in their 20s.")

[1367] Output: Assignments sent to the server

[1368] Step 2:

[1369] The server retrieves data from the database

[1370] The server receives the user's request, connects to the database, executes an SQL query, and retrieves the purchasing data for women in their 20s.

[1371] Input: User's assignment

[1372] Output: Purchase data obtained

[1373] Step 3:

[1374] The server preprocesses the data

[1375] The server preprocesses the acquired data using Python's pandas library, specifically cleaning the data (removing missing values ​​and outliers), filtering (extracting necessary columns), and aggregating (counting purchase counts and amounts).

[1376] Input: Acquired purchasing data

[1377] Output: Preprocessed data

[1378] Step 4:

[1379] The server analyzes the data

[1380] The server then uses the preprocessed data to perform analysis using machine learning libraries such as scikit-learn and TensorFlow, for example, to classify customers into groups and identify their purchasing trends using clustering algorithms.

[1381] Input: Preprocessed data

[1382] Output: Analysis results (e.g., clustering results)

[1383] Step 5:

[1384] The server generates the analysis results.

[1385] The server generates reports and graphs based on the analysis results, such as heat maps showing purchasing trends and visualizations of clustering results, for users to view.

[1386] Input: Analysis results

[1387] Output: Generated reports and graphs

[1388] Step 6:

[1389] The server feeds the results back to the user

[1390] The server sends the generated reports and graphs to the user's device and provides feedback to the user, who can then use this information to develop a marketing strategy.

[1391] Input: Generated reports and graphs

[1392] Output: Results fed back to the user

[1393] Step 7:

[1394] Emotion engine recognizes user emotions and adjusts responses

[1395] The emotion engine analyzes user input and responses to recognize the user's emotions. For example, if a user says, "I'm happy about the success of my recent campaign," the emotion engine will recognize that joy and provide a more energetic response.

[1396] Input: User's emotional input

[1397] Output: Adjusted response

[1398] In this way, the system solves the user's problems and provides appropriate responses depending on their emotions.

[1399] (Application example 2)

[1400] Next, a description will be given of Application Example 2 of Form 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."

[1401] With conventional marketing systems, analyzing customer purchasing trends and formulating appropriate marketing strategies required a great deal of time and effort. Furthermore, there was a lack of systems that provided responses that reflected the user's emotions, making improving the user experience a challenge.

[1402] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1403] In this invention, the server includes a means for enabling a process from identifying issues to analyzing data and devising solutions through natural language interaction, a means for linking a database with generative AI, a means for adjusting responses based on user emotions using an emotion engine, and a means for acquiring purchasing data and analyzing it using a clustering algorithm. This allows users to efficiently analyze customer purchasing trends and receive appropriate responses according to their emotions.

[1404] "Problem discovery" is the process of identifying the problems and needs that users face.

[1405] "Data analysis" is the process of analyzing collected data using statistical methods and algorithms to extract useful information.

[1406] "Solution development" is the process of designing appropriate countermeasures and strategies for an identified problem.

[1407] "Natural language interaction" means that users communicate with the system using the language they use on a daily basis.

[1408] A "database" is a system for efficiently storing, managing, and retrieving data.

[1409] "Generative AI" is artificial intelligence that generates new information and solutions based on given data and instructions.

[1410] An "emotion engine" is a system that analyzes the user's emotional state and generates a response accordingly.

[1411] "Adjusting responses based on user emotion" refers to providing responses with appropriate tone and content that take into account the user's emotional state.

[1412] "Purchase Data" is data that includes information regarding purchases made by a customer.

[1413] A "clustering algorithm" is a computational method for grouping data based on similarity.

[1414] The following system configuration is used as an embodiment of the present invention.

[1415] The server provides a means to uncover issues, analyze data, and devise solutions through natural language interaction. When a user enters a prompt such as "I would like to analyze customer purchasing trends," the server retrieves purchasing data from the database and analyzes the data using generative AI. Specifically, it uses a clustering algorithm to classify customer purchasing trends and generate analysis results.

[1416] Additionally, the server provides a means to tailor responses based on the user's emotions using an emotion engine, which analyzes the user's input and generates responses with appropriate tone and content depending on the user's emotional state, thereby improving the user experience.

[1417] The hardware used includes a database server, an AI processing server, and a sentiment analysis server, while the software used includes a database management system (DBMS), a generative AI model, a sentiment analysis engine, and a clustering algorithm (e.g., KMeans).

[1418] For example, if a user enters "I want to analyze customer purchasing trends," the server will process the following steps:

[1419] 1. Retrieve customer purchase data from the database.

[1420] 2. Analyze the acquired data using a clustering algorithm (KMeans).

[1421] 3. Generate analysis results and provide feedback to users.

[1422] 4. The emotion engine analyzes the user's input and generates a response based on the emotion.

[1423] Example prompt sentence:

[1424] "I want to analyze customer purchasing trends."

[1425] This system allows users to efficiently analyze customer purchasing trends and receive appropriate responses based on their emotions.

[1426] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1427] Step 1:

[1428] The user inputs a prompt sentence, "I would like to analyze customer purchasing trends," using a terminal. The terminal sends this input to the server. The input data is text in natural language format.

[1429] Step 2:

[1430] The server analyzes the received prompt and understands the user's intent. Specifically, it uses natural language processing (NLP) technology to analyze the text and identify the task of "analyzing purchasing trends." The input data is the prompt, and the output data is the analysis results.

[1431] Step 3:

[1432] The server retrieves customer purchasing data from the database. Using a database management system (DBMS), it extracts a data set containing purchasing history and customer information. The input data is the analysis results, and the output data is the purchasing data.

[1433] Step 4:

[1434] The server analyzes the acquired purchase data using a clustering algorithm (KMeans). Specifically, it classifies customers into clusters based on features such as purchase amount and purchase frequency. The input data is the purchase data, and the output data is the clustering results.

[1435] Step 5:

[1436] The server uses a generative AI model to generate solutions based on the clustering results. Specifically, it proposes marketing strategies and recommended actions for each cluster. The input data is the clustering results, and the output data is the solutions.

[1437] Step 6:

[1438] The server analyzes the user's input with an emotion engine to identify the user's emotional state. Specifically, it calculates an emotion score using text analysis technology. The input data is the prompt text, and the output data is the emotion score.

[1439] Step 7:

[1440] The server adjusts the response based on the emotion score and provides feedback to the user. Specifically, it presents a solution with a tone and content that corresponds to the emotion. The input data are the solution and the emotion score, and the output data is the adjusted response.

[1441] Step 8:

[1442] The terminal displays the adjusted response received from the server to the user, who can then formulate a marketing strategy based on the adjusted response. The input data is the adjusted response, and the output data is the display to the user.

[1443] Example 3

[1444] Next, a description will be given of Example 3 of Form Example 3. 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."

[1445] With conventional systems, it was difficult to efficiently identify issues, analyze data, and devise solutions, and it was particularly difficult to generate solutions that took user emotions into account. Furthermore, the process of improving solutions based on user feedback was time-consuming and laborious, making them impractical in situations where a rapid response was required.

[1446] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1447] In this invention, the server includes a means for enabling the process from identifying issues to analyzing data and devising solutions through natural language interaction, a means for linking the database with generative AI, a means for generating solutions using an emotion engine that analyzes user emotions, and a means for collecting feedback from users and improving the solutions using a generative AI model. This enables the rapid and effective generation and improvement of solutions that take user emotions into consideration.

[1448] "Issue discovery" is the process of identifying problems users are facing and areas for improvement.

[1449] "Data analysis" is the process of analyzing collected data using statistical methods and machine learning to extract useful information.

[1450] "Solution development" is the process of proposing appropriate measures or methods for an identified problem.

[1451] "Natural language interaction" is the process by which users and systems communicate using human language.

[1452] A "database" is a system for efficiently storing, managing, and retrieving data.

[1453] "Generative AI" is artificial intelligence that generates new information or content based on given input.

[1454] An "emotion engine" is a system that analyzes emotions from user input and provides information based on those emotions.

[1455] "Feedback gathering" is the process of gathering opinions and ratings from users.

[1456] "Solution refinement" is the process of improving an existing solution based on collected feedback.

[1457] This invention is a system in which users and AI collaborate to devise new solutions and rapidly carry out creative tasks. In particular, it has the function of generating solutions based on the user's emotions using an emotion engine.

[1458] Hardware and software used

[1459] Hardware: Servers, user devices (PCs, smartphones, etc.)

[1460] Software: generative AI models (e.g., GPT-4), emotion engines, project management tools (e.g., Trello, Asana)

[1461] Data processing and calculation flow

[1462] 1. User input: The user uses a device (PC or smartphone) to input their concerns about the new project and their request for a solution. For example, the user might type "I'm feeling anxious about the new project. What should I do?" into an input form on their device.

[1463] 2. Emotion Recognition: The server receives the user's input and analyzes the user's emotions using the emotion engine. The server activates the emotion engine and recognizes the emotion "anxiety" from the user's input text.

[1464] 3. Solution generation: The server generates a solution using a generative AI model (e.g., GPT-4) based on the analysis results of the emotion engine. The server inputs a prompt statement to the generative AI model: "The user is anxious about a new project. Please provide project management best practices and past success stories." and obtains the generated solution.

[1465] 4. Feedback collection: The server presents the generated solution to the user and collects feedback from the user. The user reviews the solution and enters feedback such as, "Breaking the task down into smaller parts is a good idea, but I'd like to know how to use specific tools."

[1466] 5. Solution refinement: The server receives the user's feedback and refines the solution using the generative AI model again. The server inputs a prompt to the generative AI model: "The user wants to know how to use a specific tool. Please explain how to use Trello." to obtain an improved solution.

[1467] 6. Iterative process: The server presents the improved solution to the user again, and the feedback and refinement process is repeated as needed. The user reviews the improved solution and provides further detailed feedback, which allows the server to refine the solution again.

[1468] Specific examples

[1469] User Type: "I'm feeling anxious about a new project. What should I do?"

[1470] Emotion engine analysis: "Users experience high levels of anxiety"

[1471] The generative AI model's solution: "As a best practice for project management, we recommend breaking down tasks into smaller pieces and visualizing progress. We also recommend learning from past examples of successful project management methods used by other companies."

[1472] User feedback: "Breaking down tasks into smaller pieces is a good idea, but I'd like to see specific tools to help me use them."

[1473] Improved solution: "I recommend using Trello as a specific tool. Here's how to use it."

[1474] Prompt Sentence Examples

[1475] "Generate solutions that provide project management best practices and past success stories for users who are nervous about new projects."

[1476] In this way, by taking the user's feelings into consideration and allowing the AI ​​and the user to work together to generate and improve solutions, it is possible to quickly derive more effective solutions. The flow of the identification process in Example 3 will be described with reference to Figure 21.

[1477] Step 1:

[1478] User Input

[1479] Users use a device (PC or smartphone) to input their concerns about a new project and requests for solutions.

[1480] Input: A user types into a form on their device, "I'm feeling anxious about a new project. What should I do?"

[1481] Output: The user's input text is sent to the server.

[1482] Step 2:

[1483] emotion recognition

[1484] The server receives the user's input and analyzes the user's emotions using an emotion engine.

[1485] Input: The text entered by the user.

[1486] Data processing: The server runs the emotion engine and performs text analysis.

[1487] Output: The user's emotion (e.g., anxiety) is recognized.

[1488] Step 3:

[1489] Solution Generation

[1490] The server generates a solution using a generative AI model (e.g., GPT-4) based on the analysis results of the emotion engine.

[1491] Input: Analysis result of emotion engine (user emotion).

[1492] Data calculation: The server inputs a prompt statement into the generative AI model to generate a solution.

[1493] Output: Generated solutions (e.g. project management best practices and past success stories).

[1494] Step 4:

[1495] Collecting feedback

[1496] The server presents the generated solutions to the user and collects feedback from the user.

[1497] Input: The generated solution.

[1498] Specific operation: The server sends the solution to the user's device, and the user enters feedback.

[1499] Output: User feedback (e.g., "Breaking up the tasks into smaller pieces is a good idea, but I'd like to know how to use specific tools as well.").

[1500] Step 5:

[1501] Improved solution

[1502] The server receives user feedback and refines the solution, again using the generative AI model.

[1503] Input: User feedback.

[1504] Data calculation: The server inputs prompt sentences for improvement into the generative AI model and generates an improved solution.

[1505] Output: An improved solution (e.g., instructions on how to use Trello).

[1506] Step 6:

[1507] Iterative Process

[1508] The server presents the improved solution to the user again, repeating the feedback and refinement process as needed.

[1509] Input: Improved solution.

[1510] What it does: The server sends an improved solution to the user's device, and the user provides more detailed feedback.

[1511] Output: An iterative process until a final solution is determined.

[1512] In this way, AI and users can work together to generate and improve solutions while taking into account the user's emotions, resulting in more effective solutions being found more quickly.

[1513] (Application example 3)

[1514] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1515] Conventional systems provide solutions without considering the user's feelings, making it difficult to alleviate user anxiety and stress. Furthermore, they lacked a mechanism for effectively utilizing user feedback to improve solutions, making it difficult to provide quick and effective solutions. This made it difficult to increase users' sense of security, especially in security services.

[1516] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1517] In this invention, the server includes a means for enabling a process from identifying issues to analyzing data and devising solutions through natural language interaction, a means for linking the database with generative AI, a means for recognizing user emotions in real time and generating solutions based on those emotions, and a means for collecting feedback from users and improving the solutions based on that feedback. This makes it possible to provide solutions that take user emotions into consideration, reducing user anxiety and stress and enabling the provision of quick and effective solutions.

[1518] "Problem discovery" is the process of identifying the problems and needs that users face.

[1519] "Data analysis" is the process of analyzing collected data using statistical methods and machine learning algorithms to extract meaningful information.

[1520] "Solution creation" is the process of designing and proposing appropriate measures and methods to address identified issues.

[1521] "Natural language interaction" refers to communication between the user and the system using human language.

[1522] A database is a system that systematically organizes and stores information so that it can be searched and used efficiently.

[1523] "Generative AI" is a type of artificial intelligence that generates new information and solutions based on given data and conditions.

[1524] "Recognizing user emotions in real time" is a technology that instantly determines the user's current emotional state from facial expressions, tone of voice, etc.

[1525] "Gathering feedback" is the process of gathering opinions and ratings from users.

[1526] "Solution refinement" is the process of improving and optimizing an existing solution based on collected feedback.

[1527] A system for carrying out this invention has the following configuration: The server includes a means for enabling interactions in natural language from identifying issues to analyzing data and devising solutions, a means for linking a database with a generative AI, a means for recognizing user emotions in real time and generating solutions based on those emotions, and a means for collecting feedback from users and improving the solutions based on that feedback.

[1528] Hardware and software used

[1529] Hardware: Smartphone

[1530] Software: OpenAI API, Emotion Recognition API, Feedback System

[1531] Data processing and calculation

[1532] 1. Emotion recognition:

[1533] The server uses the Emotion Recognition API to recognize the user's emotions in real time, allowing it to identify the emotion the user is currently feeling (e.g., anxiety, relief, excitement, etc.).

[1534] 2. Solution generation:

[1535] The server uses a generative AI (e.g., OpenAI's GPT-3) to generate a solution based on the user's feelings. Specifically, the server obtains a solution by inputting the following prompt sentence into the generative AI:

[1536] My users are worried. Can you suggest a solution to alleviate their security concerns?

[1537] 3. Feedback Collection:

[1538] The server collects feedback from users, who enter their opinions and ratings on the solutions presented, and this information is sent to the server.

[1539] 4. Solution Improvement:

[1540] The server then re-engages the generative AI based on the collected feedback to refine the solution, thereby providing a solution that better meets the user's needs.

[1541] Specific examples

[1542] For example, if a user is concerned about security, the server will recognize the concern using the Emotion Recognition API. Then, by inputting the following prompt into the generative AI, it will generate a solution.

[1543] My users are worried. Can you suggest a solution to alleviate their security concerns?

[1544] The generated solutions are, for example, "how to set up two-factor authentication" or "past security success stories." When the user provides feedback on these solutions, the server uses that feedback to improve the solutions and propose more effective countermeasures.

[1545] In this way, it becomes possible to provide a solution that takes the user's feelings into consideration, reducing the user's anxiety and stress and providing a quick and effective solution.

[1546] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1547] Step 1:

[1548] A user accesses the system using a smartphone. The user inputs security concerns and problems in natural language. The input data is text data that includes the user's emotions.

[1549] Step 2:

[1550] The server uses the Emotion Recognition API to recognize emotions from user input text in real time. The input is the user's text data, and the output is the user's emotional state (e.g., anxious, relieved, excited, etc.). The server runs text analysis and emotion recognition algorithms to identify the user's emotions.

[1551] Step 3:

[1552] The server uses a generative AI (e.g., OpenAI's GPT-3) to generate a solution based on the user's emotions. The input is the user's emotional state and a prompt, and the output is the generated solution. Specifically, the following prompt is input to the generative AI:

[1553] My users are worried. Can you suggest a solution to alleviate their security concerns?

[1554] The generative AI generates an appropriate solution based on this prompt.

[1555] Step 4:

[1556] The server presents the generated solution to the user, who then reviews the presented solution and inputs feedback. The input is the user's feedback, and the output is the feedback data.

[1557] Step 5:

[1558] The server collects feedback from users and improves the solution using a feedback system. The input is feedback data, and the output is an improved solution. The server analyzes the feedback data and re-enters prompt statements into the generative AI to generate an improved solution.

[1559] Step 6:

[1560] The server presents the improved solution back to the user, who can review the improved solution and provide further feedback as needed, resulting in a solution that better suits the user's needs.

[1561] In this way, it is possible to provide a solution that takes the user's feelings into consideration, thereby reducing the user's anxiety and stress and providing a quick and effective solution.

[1562] 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.

[1563] 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> ) 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.

[1564] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1565] 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.

[1566] [Third embodiment]

[1567] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1568] 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.

[1569] 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).

[1570] 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.

[1571] 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.

[1572] 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).

[1573] 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.

[1574] 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.

[1575] 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.

[1576] 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.

[1577] 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.

[1578] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1579] "Example 1"

[1580] One form of the present invention is a system that links a database with generative AI. In this system, the user communicates a problem to the AI ​​in natural language. The AI ​​analyzes the problem and retrieves the necessary information from the database. The AI ​​then generates a solution based on the retrieved information and provides feedback to the user.

[1581] "Example 2"

[1582] As a specific example, consider the application of this system to solving marketing problems. When a user tells the AI ​​that they want to analyze customer purchasing trends, the AI ​​retrieves customer purchasing data from a database. The AI ​​then analyzes the purchasing data and generates a solution that clarifies customer purchasing trends. This solution is fed back to the user, who can then use it to create a marketing strategy.

[1583] "Example 3"

[1584] Furthermore, collaboration between AI and users makes it possible to devise new solutions and carry out creative work at high speed. For example, by repeating the process of users providing feedback on solutions generated by AI and then the AI ​​improving the solutions based on that feedback, more effective solutions can be derived quickly.

[1585] The processing flow of each embodiment will be described below.

[1586] "Example 1"

[1587] Step 1: The user communicates the problem to the AI ​​in natural language.

[1588] Step 2: The AI ​​analyzes the problem and retrieves the necessary information from the database.

[1589] Step 3: The AI ​​generates a solution based on the acquired information and provides feedback to the user.

[1590] "Example 2"

[1591] Step 1: The user communicates to the AI ​​the problem of "analyzing customer purchasing trends."

[1592] Step 2: The AI ​​retrieves customer purchasing data from the database.

[1593] Step 3: AI analyzes purchasing data and generates solutions that reveal customer purchasing trends.

[1594] Step 4: This solution is fed back to the user, who can then use it to develop their marketing strategy.

[1595] "Example 3"

[1596] Step 1: The user provides feedback on the AI-generated solution.

[1597] Step 2: The AI ​​uses that feedback to improve the solution.

[1598] Step 3: By repeating this process, you can arrive at a more effective solution faster.

[1599] Example 1

[1600] Next, a description will be given of Example 1 of Form 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."

[1601] In conventional systems, users needed multiple tools and manual operations to solve problems, which was inefficient and time-consuming. Furthermore, data acquisition, analysis, and solution generation were disconnected, resulting in a lack of a consistent process. This made it difficult for users to solve problems quickly and effectively.

[1602] 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.

[1603] In this invention, the server includes: a means for a user to input a problem in natural language; a means for the server to send the problem to the generative AI model as a prompt; a means for the generative AI model to analyze the problem; a means for the server to acquire necessary information from a database; a means for the server to send the acquired information to the generative AI model; a means for the generative AI model to generate a solution; and a means for the server to feed back the solution to the user. This allows the user to simply input the problem in natural language, thereby enabling a consistent process from data acquisition to analysis and solution generation.

[1604] A "user" is an entity that uses the system to input problems and obtain solutions.

[1605] The "server" is a computer system whose role is to receive tasks from users, send them as prompts to the generative AI model, retrieve the necessary information from a database, generate solutions, and provide feedback to the user.

[1606] A "generative AI model" is an artificial intelligence model that analyzes prompts received from users and generates solutions based on the necessary information.

[1607] A "prompt" is a text-based instruction that allows a generative AI model to understand the task entered by the user.

[1608] A "database" is a data repository that a server connects to to get the information it needs.

[1609] A "solution" is a specific answer or proposal to a user's problem that is generated based on the information analyzed by the generative AI model.

[1610] "Feedback" is the process by which the server returns the solution obtained from the generative AI model to the user.

[1611] This invention is a system in which a user inputs a problem in natural language, a server analyzes the problem using a generative AI model, retrieves necessary information from a database, generates a solution, and provides feedback to the user. A specific embodiment of this system is described below.

[1612] Hardware and software used

[1613] Hardware

[1614] Terminal: The device through which the user enters the assignment. Examples include a PC or smartphone.

[1615] Server: A computer system for analyzing problems, acquiring data, generating solutions, and providing feedback.

[1616] software

[1617] Generative AI model: An artificial intelligence model that analyzes problems and generates solutions. An example is OpenAI's GPT-4.

[1618] Database: A data storage system used to store the required information. Examples include MySQL and PostgreSQL.

[1619] System Operation

[1620] User operations

[1621] Users use a terminal to access the system's interface and input their problem in natural language, for example, "Please tell me the sales forecast for the next quarter based on the sales data."

[1622] Server Processing

[1623] The server sends the task received from the user to the generative AI model as a prompt. The generative AI model analyzes the prompt and understands the content of the task. The server then connects to the database and obtains the necessary information identified by the generative AI model. The obtained information is then sent back to the generative AI model, instructing it to generate a solution. The generative AI model generates a solution and returns it to the server.

[1624] feedback

[1625] The server then feeds back the generated solution to the user. The solution is then displayed on the user's device. For example, it might say, "Sales forecast for the next quarter is XX yen."

[1626] Specific examples

[1627] Prompt Sentence Examples

[1628] The user types into the system, "Based on the sales data, what is your sales forecast for the next quarter?"

[1629] In this way, users can obtain specific solutions to their problems through the system. This system allows users to consistently perform everything from data acquisition to analysis and the generation of solutions simply by inputting their problem in natural language.

[1630] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1631] Step 1:

[1632] The user enters an assignment.

[1633] Users access the system interface using a terminal and input tasks in natural language. For example, they might input, "Please tell me the sales forecast for the next quarter based on the sales data." The input task is sent to the server as text data.

[1634] Step 2:

[1635] The server sends the task to the generative AI model as a prompt.

[1636] The server receives the task from the user and sends it to the generative AI model as a prompt. Specifically, the server connects to the generative AI model via an API and sends the user's task in text format. The input is the user's task text, and the output is the prompt sent to the generative AI model.

[1637] Step 3:

[1638] A generative AI model analyzes the problem.

[1639] The generative AI model analyzes the received prompt and understands the content of the problem. For example, it extracts keywords such as "sales data" and "sales forecast for the next quarter" and identifies the necessary data based on these. The input is the prompt, and the output is the identification of the necessary data as the analysis result.

[1640] Step 4:

[1641] The server retrieves the necessary information from the database.

[1642] The server connects to the database and retrieves the required information identified by the generative AI model. Specifically, it executes an SQL query to retrieve sales data. For example, it executes the query SELECT FROM sales_data WHERE date >= '2023-01-01' AND date <= '2023-03-31'. The input is the required data identified as the analysis result, and the output is the sales data retrieved from the database.

[1643] Step 5:

[1644] The server sends the acquired information to the generative AI model.

[1645] The server sends the sales data obtained from the database to the generative AI model. Again, via the API, the obtained data is input to the generative AI model in text format. The input is the sales data obtained from the database, and the output is the data sent to the generative AI model.

[1646] Step 6:

[1647] A generative AI model generates a solution.

[1648] The generative AI model generates a sales forecast for the next quarter based on the acquired sales data. The model analyzes the data and generates the forecast results in text format. The input is sales data, and the output is a sales forecast as a solution.

[1649] Step 7:

[1650] The server feeds back the solution to the user.

[1651] The server feeds back the solution received from the generative AI model to the user. Specifically, the solution is displayed on the user's device. For example, it is displayed in the form of "Sales forecast for the next quarter is XX yen." The input is the solution from the generative AI model, and the output is feedback to the user.

[1652] (Application example 1)

[1653] Next, a description will be given of Application Example 1 of Form 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."

[1654] There is a need to improve operational efficiency at logistics centers and optimize inventory management and delivery schedules. However, with conventional systems, it takes a great deal of time and effort to acquire and analyze data and generate solutions, making efficient operation difficult. In addition, because natural language communication is not possible, users need specialized knowledge to master the system.

[1655] 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.

[1656] In this invention, the server includes a means for enabling interactions in natural language from identifying issues to analyzing data and devising solutions, a means for linking the database with generative AI, a means for users to input issues in natural language and for the AI ​​to analyze the issues and obtain necessary information from the database in order to improve the efficiency of logistics center operations, and a means for generating optimal solutions based on the obtained information and providing feedback to the user. This improves the efficiency of logistics center operations and enables optimization of inventory management and delivery schedules.

[1657] "Identifying issues" is the process of finding out the problems users are facing and areas for improvement.

[1658] "Data analysis" is the process of analyzing collected data and extracting meaningful information.

[1659] "Solution development" is the process of proposing an appropriate solution to an identified problem.

[1660] "Natural language interaction" means that users communicate with the system in the language they use on a daily basis.

[1661] A database is a system that systematically organizes and stores information, allowing it to be searched and retrieved as needed.

[1662] "Generative AI" is artificial intelligence that generates new information and solutions based on given data and instructions.

[1663] A "logistics center" is a facility that stores, manages, and delivers goods.

[1664] "Efficient operations" refers to optimizing business processes and reducing time and costs.

[1665] "Analyzing the problem" is the process of understanding the problem entered by the user and clarifying its essence.

[1666] "Obtaining the necessary information" refers to searching and extracting the data necessary to solve the problem from a database.

[1667] "Generating optimal solutions" is the process of proposing the most effective solution based on the information obtained.

[1668] "Providing feedback to the user" refers to communicating the generated solution to the user.

[1669] A system for carrying out this invention is configured as follows: The server includes a means for enabling interactions in natural language from identifying issues to analyzing data and devising solutions, a means for linking the database with generative AI, a means for users to input issues in natural language and for the AI ​​to analyze the issues and obtain necessary information from the database in order to streamline the operation of the logistics center, and a means for generating optimal solutions based on the obtained information and providing feedback to the user.

[1670] Hardware and software used

[1671] Hardware: Smartphone

[1672] Software: Python, OpenAI API, SQLite (database)

[1673] Data processing and calculation

[1674] 1. Database connection: The server connects to the distribution center database using SQLite, which stores information such as inventory, delivery schedules, and staff shifts.

[1675] 2. Issue analysis: The user inputs the issue in natural language using a smartphone. The server analyzes this input and identifies the type of issue (inventory management, delivery schedule, staff shift, etc.).

[1676] 3. Data Acquisition: The server acquires the necessary information from the database based on the analysis results. For example, if the issue is about inventory management, it acquires inventory information.

[1677] 4. Prompt generation: Based on the acquired data, a prompt is created for the generative AI model (OpenAI).

[1678] 5. Solution generation: The server uses the OpenAI API to generate the optimal solution based on the generated prompt.

[1679] 6. Feedback: The server provides the generated solution to the user, who can then check it on their smartphone.

[1680] Specific examples

[1681] If a user types, "I want to optimize inventory reallocation," the server retrieves inventory data and sends a prompt like this to the generative AI model:

[1682] Prompt Sentence Examples

[1683] Based on the data below, propose a solution to optimize inventory reallocation.

[1684] Data: [(product ID, product name, quantity in stock, location), (product ID, product name, quantity in stock, location), ...]

[1685] In this way, a system can be realized that provides specific solutions for improving the efficiency of logistics center operations.

[1686] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1687] Step 1:

[1688] The user inputs the problem in natural language using a smartphone. For example, the input problem might be "I want to optimize the reallocation of inventory." This input is then sent to the server.

[1689] Step 2:

[1690] The server analyzes the natural language assignments received from the user. Specifically, it understands the content of the assignment and identifies which category (inventory management, delivery schedule, staff shift, etc.) it belongs to. For example, if the keyword "inventory" is included, it is determined to be an assignment related to inventory management.

[1691] Step 3:

[1692] The server retrieves the necessary information from the database based on the analysis results. For example, if the issue is inventory management, it executes the SQL query "SELECT FROM inventory" to retrieve inventory information. The retrieved data includes information such as product ID, product name, stock quantity, and location.

[1693] Step 4:

[1694] The server creates a prompt for the generative AI model based on the acquired data. Specifically, it generates the following prompt:

[1695] Based on the data below, propose a solution to optimize inventory reallocation.

[1696] Data: [(product ID, product name, quantity in stock, location), (product ID, product name, quantity in stock, location), ...]

[1697] This prompt is sent to the generative AI model.

[1698] Step 5:

[1699] The server uses a generative AI model (OpenAI API) to generate an optimal solution based on the prompt. The generative AI model analyzes the input data and generates specific suggestions for optimizing inventory reallocation. For example, a solution such as "move product A from position X to position Y" is generated.

[1700] Step 6:

[1701] The server then provides the generated solution to the user as feedback. Specifically, the solution is displayed on the smartphone screen, allowing the user to check the solution and put it into practice.

[1702] In this way, a system can be realized that provides specific solutions for improving the efficiency of logistics center operations.

[1703] Example 2

[1704] Next, a description will be given of Example 2 of Form 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."

[1705] Conventional methods for solving marketing problems have the problem that collecting data, analyzing it, and devising solutions requires a great deal of time and effort. Furthermore, it is difficult for users without specialized knowledge to analyze data, making it difficult to develop efficient marketing strategies. This has created a need for rapid and effective marketing strategy development.

[1706] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1707] In this invention, the server includes means for a user to input a problem in natural language, means for a terminal to transmit the input problem to the server as a prompt sentence, means for the server to analyze the prompt sentence and identify necessary data, means for the server to acquire data from a database, means for the server to process and analyze the acquired data, means for the server to generate a solution based on the analysis results, means for transmitting the solution generated by the server to the terminal, and means for the user to receive the solution. This enables users, even without specialized knowledge, to receive data analysis and proposed solutions to quickly and effectively solve their marketing problems.

[1708] A "user" is an individual or organization that utilizes the system to input problems and receive solutions.

[1709] A "terminal" is a device that a user uses to input tasks and communicate with the server. For example, a PC or smartphone is an example.

[1710] "Server" is a computer system that parses prompts, acquires data, processes and analyzes it, and generates and transmits solutions.

[1711] A "prompt" is text that converts the user-entered task into a format that the server can understand.

[1712] A "generative AI model" is an artificial intelligence model that performs natural language processing, analyzes prompts, and generates solutions.

[1713] A "database" is an information management system that stores information such as customer purchase data and allows the server to obtain the necessary data.

[1714] "Data processing and analysis" is the process of cleaning, aggregating, filtering, and other processes on acquired data to extract the necessary information.

[1715] A "solution" is a specific proposal or answer to a user's problem that the server generates based on the results of data analysis.

[1716] The "Python Pandas library" is a programming library for efficiently processing and analyzing data.

[1717] This invention is a system for users to solve marketing problems, and includes a process in which the user inputs the problem in natural language, and a server analyzes the problem and generates a solution. Specific embodiments of this system are described below.

[1718] The user uses the device to input a marketing problem in natural language. For example, they might input, "I want to know which product category has sold the most in the last three months." The device then sends this input to the server as a prompt sentence. The prompt sentence is in a format that the generative AI model can understand.

[1719] The server analyzes the prompt using a generative AI model (e.g., an artificial intelligence model that processes natural language). From the analysis results, it identifies the necessary data and analysis method. Next, the server connects to a database (e.g., an information management system that stores customer purchase data) and retrieves the necessary data. For example, it retrieves purchase data from the past three months.

[1720] The acquired data is processed and analyzed on the server. Specifically, the data is cleaned, aggregated, and filtered using Python's Pandas library, and sales for each product category are calculated. This allows the information desired by the user to be extracted.

[1721] The server generates a solution based on the analysis results. Using a generative AI model, it generates a solution in natural language, such as "The most popular product category over the last three months is ____." This solution is then sent to the user via their device.

[1722] Users can check the solutions displayed on their device screen and use them as a reference for formulating marketing strategies. For example, they can formulate a strategy to "further promote products in the XX category."

[1723] This system allows users to receive data analysis and proposed solutions to quickly and effectively solve marketing problems, even if they do not have specialized knowledge.

[1724] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1725] Step 1:

[1726] User enters assignment

[1727] The user enters in the input field of the terminal, "I want to know the most popular product category for the last three months." The input task is saved on the terminal as a prompt sentence.

[1728] Input: Issues entered by the user in natural language

[1729] Output: prompt statement

[1730] Step 2:

[1731] The terminal sends a prompt to the server

[1732] The device sends the saved prompt as an HTTP request to the server, which includes the user's challenge.

[1733] Input: prompt statement

[1734] Output: HTTP request sent to the server

[1735] Step 3:

[1736] The server parses the prompt.

[1737] The server inputs the received prompt into the generative AI model and obtains the analysis results, which include the type of data required and the analysis method.

[1738] Input: Prompt text received as an HTTP request

[1739] Output: Analysis results (type of data required and analysis method)

[1740] Step 4:

[1741] The server retrieves data from the database

[1742] The server sends an SQL query to the database to retrieve purchase data for the past three months, for example, "SELECT FROM purchases WHERE date >= '3 months ago'".

[1743] Input: SQL query based on the parsed results

[1744] Output: Purchase data for the past three months

[1745] Step 5:

[1746] The server processes and analyzes the data

[1747] The server processes the acquired data using the Python Pandas library, specifically cleaning the data and aggregating sales figures for each product category.

[1748] Input: Purchase data for the past three months

[1749] Output: Sales data for each product category

[1750] Step 6:

[1751] The server generates a solution

[1752] Based on the analysis results, the server uses a generative AI model to generate a solution such as "The best-selling product category over the last three months is XX."

[1753] Input: Sales data for each product category

[1754] Output: A generated solution in natural language

[1755] Step 7:

[1756] The server sends the solution to the device

[1757] The server sends the generated solution as an HTTP response to the terminal, which receives the response and displays it to the user.

[1758] Input: Natural language generated solution

[1759] Output: HTTP response sent to the device

[1760] Step 8:

[1761] The user receives the solution

[1762] The user checks the solutions displayed on the device screen and uses them as a reference for formulating a marketing strategy. For example, they may formulate a strategy such as "further promoting products in the XX category."

[1763] Input: Solution displayed in terminal

[1764] Output: Marketing strategies developed by users

[1765] (Application example 2)

[1766] Next, a description will be given of Application Example 2 of Form 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."

[1767] With conventional marketing methods, it was difficult to grasp customer purchasing trends in real time and immediately make optimal marketing proposals. Furthermore, it required a great deal of time and effort to efficiently analyze customer purchasing data and develop individual marketing strategies. This has led to a demand for more efficient marketing activities and more effective customer responses in brick-and-mortar stores.

[1768] The specific processing by the specific 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 a means for enabling the process from identifying issues to analyzing data and devising solutions through natural language interactions, a means for linking the database with generative AI, a means for identifying customers, a means for analyzing purchasing data in real time, a means for generating marketing proposals based on the analysis results, and a means for displaying the proposals. This makes it possible to grasp customer purchasing trends in real time and instantly make optimal marketing proposals.

[1769] "Identifying the problem" is the process of clarifying the problems the user wants to solve or the goals they want to achieve.

[1770] "Data analysis" is the process of analyzing collected data using statistical methods and machine learning algorithms to extract useful information and patterns.

[1771] "Solution development" is the process of designing specific methods and strategies for solving problems based on the results of analysis.

[1772] "Interaction in natural language" refers to communication between the system and the user using language that humans use on a daily basis.

[1773] A "database" is a system for efficiently storing, managing, and retrieving data.

[1774] "Generative AI" refers to artificial intelligence that generates new information and solutions based on given data and instructions.

[1775] "Customer identification" is the process of recognizing a specific customer using facial recognition technology or other means of identification.

[1776] "Purchase Data" refers to information about products and services that a customer has previously purchased.

[1777] "Real-time analysis" refers to analyzing data as it is generated.

[1778] "Marketing proposal" refers to proposing the most suitable products and services based on the customer's purchasing trends and preferences.

[1779] "Display Proposal" refers to visually presenting the generated marketing proposal to the user.

[1780] A system for carrying out this invention is configured as follows: The server includes a means for enabling a process from identifying issues to analyzing data and devising solutions through natural language interaction, a means for linking a database with generative AI, a means for identifying customers, a means for analyzing purchasing data in real time, a means for generating marketing proposals based on the analysis results, and a means for displaying the proposals.

[1781] First, the server analyzes the user's input in natural language and retrieves the appropriate data from the database. The retrieved data is then passed to a generative AI system, which analyzes purchasing trends. Based on the analysis results, the generative AI system generates optimal marketing proposals. These proposals are displayed on devices such as smart glasses.

[1782] Specifically, the server uses OpenCV to recognize customer faces from video captured by the camera and TensorFlow to analyze purchasing trends. Customer purchasing data is stored in a database, and Pandas and Scikit-learn are used to preprocess and cluster the data. This makes it possible to understand customer purchasing trends in real time and generate optimal marketing proposals.

[1783] For example, when a customer enters a store, the smart glasses can recognize them and display a message saying, "New product promotions offered" based on their past purchase data. If another customer enters the store, the glasses can also display a message saying, "Discount coupons offered."

[1784] Examples of prompts to input to a generative AI model include:

[1785] "Based on customer purchasing data, analyze purchasing trends and generate optimal marketing proposals. For example, if a customer is interested in new products, suggest new product promotions; if a customer prefers discounts, suggest discount coupons."

[1786] In this way, the server can analyze customer purchasing trends in real time, generate optimal marketing proposals, and display them on the terminal, thereby improving the efficiency of marketing activities and effectively responding to customers in physical stores.

[1787] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1788] Step 1:

[1789] The server receives a task entered by the user in natural language. For example, the task entered might be, "I want to analyze customer purchasing trends." The server analyzes this task and retrieves the appropriate data from the database. Specifically, the server analyzes the natural language text entered by the user and extracts related keywords. This generates a query to retrieve the necessary purchasing data from the database.

[1790] Input: Issues entered by the user in natural language

[1791] Output: Query to retrieve from the database

[1792] Step 2:

[1793] The server uses the generated query to retrieve customer purchase data from a database, which stores the customer's past purchase history and related information. The retrieved data is used for analysis in the next step.

[1794] Input: Query to retrieve from the database

[1795] Output: Customer purchase data

[1796] Step 3:

[1797] The server passes the acquired purchasing data to a generative AI system to analyze purchasing trends. Specifically, it uses TensorFlow to run a machine learning model and analyze customer purchasing trends. The data is preprocessed using Pandas and Scikit-learn, and standardized and clustered.

[1798] Input: Customer purchase data

[1799] Output: Analysis of purchasing trends

[1800] Step 4:

[1801] The server generates optimal marketing proposals based on the analysis results. The generative AI then generates specific proposals based on the analysis results, such as "proposing new product promotions" or "proposing discount coupons." These proposals provide useful information to users.

[1802] Input: Analysis results of purchasing trends

[1803] Output: Marketing proposal

[1804] Step 5:

[1805] The server transmits the generated marketing proposals to a terminal, which is a device such as smart glasses that visually displays the proposals, allowing the user to view the optimal marketing proposals in real time.

[1806] Input: Marketing Proposal

[1807] Output: Proposal displayed in terminal

[1808] Step 6:

[1809] Based on the suggestions displayed on the terminal, users can respond appropriately to customers. For example, they can introduce new product promotions to customers or provide discount coupons. This will improve the efficiency of marketing activities in physical stores and enable effective customer service.

[1810] Input: Suggestion displayed on terminal

[1811] Output: Appropriate response to the customer

[1812] Through the above steps, a system is realized in which the server, terminals, and users work together to analyze customer purchasing trends in real time and make optimal marketing proposals.

[1813] Example 3

[1814] Next, a third embodiment of the third embodiment will be described. 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."

[1815] In conventional systems, the process from identifying issues to analyzing data and devising solutions was fragmented, making efficient problem solving difficult. Furthermore, the process of improving solutions based on user feedback was often done manually, which was time-consuming and labor-intensive. Furthermore, there was a lack of concrete methods for effectively utilizing generative AI models.

[1816] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1817] In this invention, the server includes a means for enabling a process from identifying a problem to analyzing data and devising a solution through natural language interaction, a means for linking a database with a generative AI, a means for a user to input information about a problem they wish to solve, a means for generating an initial solution using a generative AI model, a means for collecting feedback from the user, a means for improving the solution based on the feedback, and a means for presenting a final solution to the user, thereby enabling efficient and rapid problem solving.

[1818] "Identifying issues" is the process of finding problems that need to be solved or areas for improvement.

[1819] "Data analysis" is the process of organizing collected data and extracting meaningful information.

[1820] "Solution development" is the process of proposing appropriate measures or methods for solving problems that have been discovered.

[1821] "Communicating in natural language" refers to exchanging information using a language that humans use on a daily basis.

[1822] A "database" is a system that systematically stores data and enables it to be searched and used efficiently.

[1823] "Generative AI" is an artificial intelligence technology that generates new data and solutions based on given information.

[1824] "User" refers to an individual or organization that uses the system to solve a problem.

[1825] A "generative AI model" is an artificial intelligence model that is trained to generate new data and solutions for a specific task.

[1826] An "initial solution" is the solution that the generative AI model first proposes.

[1827] "Feedback" refers to information about evaluations and areas for improvement provided by users.

[1828] "Improvement" is the process of making modifications or additions to an existing solution to make it more effective.

[1829] The "final solution" is the final solution that has been refined based on user feedback.

[1830] This invention is a system that allows a user to input information about a problem they want to solve, generates a solution using a generative AI model, and improves the solution based on user feedback. A specific embodiment of this system is described below.

[1831] The server generates a program using a generative AI model. For example, GPT-4 can be used as this generative AI model. The server receives information entered by the user through the terminal and generates an initial solution. The generated solution is presented to the user through the terminal.

[1832] A user uses the terminal to input information about the problem they want to solve—for example, if they are devising a marketing strategy, they input information about the current market situation and their target customers—and the terminal transmits this information to the server.

[1833] The server uses a generative AI model to generate an initial solution based on the received information. The generative AI model analyzes the input information and creates a prompt to generate an appropriate solution. For example, it generates a prompt such as, "Please propose a new marketing strategy based on the current market situation and target customers." The server then sends the generated solution to the device.

[1834] The user checks the initial solution displayed on the device and provides feedback. For example, the user can input specific feedback such as, "The target customer age range is too broad, so please narrow it down a bit more." The device then sends the user's feedback to the server.

[1835] The server receives feedback from the user and again uses the generative AI model to improve the solution. The generative AI model takes the feedback into account to create a new prompt and generate an improved solution. For example, it generates a prompt such as, "Please propose a marketing strategy that narrows the target customer age range to between 25 and 35 years old." The server then sends the improved solution to the device.

[1836] The user reviews the improved solution and provides further feedback if necessary. This process is repeated until a solution that satisfies the user is obtained. The final solution is presented to the user via the terminal.

[1837] Examples:

[1838] Suppose a user wants to devise a new marketing strategy. The user inputs information about the current market situation (e.g., "The market is becoming increasingly competitive") and target customers (e.g., "Our target customers are young people between the ages of 20 and 40") through a terminal. The terminal then sends this information to a server.

[1839] The server uses a generative AI model (GPT-4) to generate a prompt such as "Please propose a new marketing strategy based on the current market situation and target customers," and generates an initial solution. The generated solution might be, for example, "Launch an advertising campaign using social media."

[1840] The user provides feedback on this solution, saying, "The target customer age range is too broad, so I'd like it to be narrowed down a bit more." The terminal sends this feedback to the server.

[1841] Based on the feedback, the server uses the generative AI model again to generate a prompt such as "Please propose a marketing strategy that narrows the target customer age range to 25 to 35 years old," and generates an improved solution. For example, the improved solution might be "Develop influencer marketing targeting young people aged 25 to 35."

[1842] The user checks the improved solution and provides further feedback as necessary. By repeating this process, the user can quickly obtain an optimal marketing strategy. The flow of the identification process in Example 3 will be described with reference to FIG. 15.

[1843] Step 1:

[1844] Data Entry

[1845] A user inputs information about a problem to be solved through a terminal. For example, when devising a marketing strategy, the user inputs information about the current market situation and target customers.

[1846] Input: Market situation, target customer information

[1847] Output: The entered information is sent from the device to the server.

[1848] Step 2:

[1849] Generate an initial solution

[1850] The server generates an initial solution based on the received information using a generative AI model, which analyzes the input information and creates prompts to generate an appropriate solution.

[1851] Input: Market situation and target customer information entered by the user

[1852] Data processing: A generative AI model analyzes the information and generates prompts

[1853] Output: An initial solution is generated and sent to the terminal.

[1854] Step 3:

[1855] Collecting feedback

[1856] The user checks the initial solution displayed on the terminal and provides feedback, for example, by inputting specific feedback such as, "The target customer age range is too broad, so please narrow it down a bit more."

[1857] Input: User feedback on the initial solution

[1858] Output: Feedback is sent from the device to the server

[1859] Step 4:

[1860] Improved solution

[1861] The server receives feedback from the user and refines the solution using the generative AI model again, which takes the feedback into account to create a new prompt and generate an improved solution.

[1862] Input: User feedback

[1863] Data processing: A generative AI model analyzes feedback and generates new prompts

[1864] Output: An improved solution is generated and sent to the terminal

[1865] Step 5:

[1866] Presentation of the final solution

[1867] The user reviews the improved solution and provides further feedback if necessary. This process is repeated until a solution that satisfies the user is obtained. The final solution is presented to the user via the terminal.

[1868] Input: User feedback for an improved solution (if needed)

[1869] Output: The final solution is displayed in the terminal.

[1870] In this way, users, terminals, and servers can work together to solve problems efficiently and quickly.

[1871] (Application example 3)

[1872] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1873] Conventional factory robot operation optimization involves collecting feedback to improve the robot's operation and then making improvements based on that feedback, which is a time-consuming and labor-intensive process. Furthermore, there was a lack of effective means for users and AI to collaborate to quickly derive solutions. This resulted in reduced factory production efficiency and increased costs.

[1874] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1875] In this invention, the server includes a means for enabling interactions in natural language from identifying issues to analyzing data and devising solutions, a means for linking the database with the generative AI, a means for the generative AI to improve solutions based on feedback from users, a means for collecting feedback in real time via a smart device, and a means for the generative AI to re-propose the improved solutions. This enables users and AI to work together to quickly and effectively optimize the operation of factory robots.

[1876] "Identifying issues" means identifying problems and areas for improvement in systems and processes.

[1877] "Data analysis" refers to the analysis of collected data using statistical methods and machine learning algorithms to extract meaningful information.

[1878] "Developing a solution" means designing and proposing effective measures and methods for addressing identified issues.

[1879] "Natural language interaction" means that the system and the user communicate using the language that humans use on a daily basis.

[1880] A "database" is a system for efficiently storing, managing, and retrieving data.

[1881] "Generative AI" is artificial intelligence that generates new information and solutions based on user input and feedback.

[1882] "User feedback" refers to the opinions and evaluations provided by users regarding the solutions proposed by the system.

[1883] "Smart devices" are electronic devices with advanced functions, such as mobile terminals and wearable devices that can connect to the Internet.

[1884] "Collecting feedback in real time" means obtaining opinions and ratings from users immediately.

[1885] An "improved solution" is a new solution that the generative AI has improved based on user feedback.

[1886] A system for implementing the present invention includes a server, a smart device, and a generative AI model. Specific embodiments are described below.

[1887] System Configuration

[1888] 1. Server

[1889] The server provides a means to identify issues, analyze data, and devise solutions through natural language interaction. The server is connected to a database and has a generative AI model installed.

[1890] 2. Smart Devices

[1891] Smart devices, such as smartphones and tablets, are used to collect real-time user feedback.

[1892] 3. Generative AI Models

[1893] Generative AI models provide a way to improve solutions based on user feedback, using APIs such as those from OpenAI.

[1894] Data processing and calculation

[1895] 1. Identifying issues and analyzing data

[1896] The server analyzes the issues entered by the user in natural language and extracts related data stored in the database, thereby identifying issues and analyzing the data.

[1897] 2. Solution Generation

[1898] The generative AI model generates an initial solution based on the analyzed data, which is then presented to the user via their smart device.

[1899] 3. Gather feedback and improve

[1900] Users input feedback on the solution via their smart devices. The server collects this feedback and sends it to the generative AI model, which then refines the solution based on the feedback and presents it to the user again.

[1901] Specific examples

[1902] For example, when a factory robot proposes a solution to streamline parts assembly work, the following prompt sentence is used:

[1903] Initial Prompt

[1904] "Please propose a solution to help factory robots improve the efficiency of parts assembly."

[1905] Feedback-based prompts

[1906] "Please improve the following solution:

[1907] Solution: Increase the robot arm speed by 20%.

[1908] Feedback: Increasing arm speed may result in decreased accuracy.

[1909] Improved solution:

[1910] In this way, users and AI can work together to quickly and effectively optimize the operation of factory robots.

[1911] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1912] Step 1:

[1913] The server receives a challenge input from a user in natural language.

[1914] Input: A problem entered by a user through a smart device (e.g., "I want to improve the efficiency of assembly work by factory robots").

[1915] Data processing: Using natural language processing (NLP) technology, the input task is analyzed and keywords and important information are extracted.

[1916] Output: Extracted keywords and key information (e.g., "factory robot," "assembly work," "efficiency").

[1917] Step 2:

[1918] The server accesses the database and searches for and retrieves data related to the extracted keywords.

[1919] Input: Extracted keywords and important information.

[1920] Data manipulation: Performing database queries to retrieve relevant data.

[1921] Output: Relevant data obtained (e.g. data from past assembly operations, existing methods for improving efficiency).

[1922] Step 3:

[1923] The server inputs relevant data into a generative AI model to generate an initial solution.

[1924] Input: The relevant data retrieved.

[1925] Data Computing: Use generative AI models (e.g., OpenAI APIs) to generate solutions based on relevant data.

[1926] Output: An initial solution (e.g., "Increase the robot's arm speed by 20%").

[1927] Step 4:

[1928] The server presents the generated solution to the user via a smart device.

[1929] Input: Initial solution.

[1930] Data manipulation: Converting the solution into a format that is easy for users to understand.

[1931] Output: A solution presented to the user (e.g., "Increase the robot's arm speed by 20%").

[1932] Step 5:

[1933] The user provides feedback on the proposed solution.

[1934] Input: User feedback (e.g., "Increasing arm speed may decrease accuracy").

[1935] Data processing: Feedback is analyzed using natural language processing techniques to extract key information.

[1936] Output: Extracted feedback key information (e.g. "Potential for accuracy degradation").

[1937] Step 6:

[1938] The server inputs the extracted feedback into a generative AI model to refine the solution.

[1939] Input: Extracted feedback key information.

[1940] Data computation: Using generative AI models to improve solutions based on feedback.

[1941] Output: Improved solution (e.g., "Increase arm speed by 15% and add a compensation algorithm to maintain accuracy").

[1942] Step 7:

[1943] The server presents the improved solution to the user again via the smart device.

[1944] Input: Improved solution.

[1945] Data processing: Converting the improved solution into a format that is easy for users to understand.

[1946] Output: An improved solution presented to the user (e.g., "Increase arm speed by 15% and add a compensation algorithm to maintain accuracy").

[1947] In this way, users and AI can work together to quickly and effectively optimize the operation of factory robots.

[1948] 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.

[1949] "Example 1"

[1950] One embodiment of the present invention is a system that includes an emotion engine that uses AI to recognize user emotions. The system understands the user's emotions through natural language interactions with the user and provides solutions based on those emotions. Specifically, if the user is feeling frustrated, the AI ​​can recognize that emotion and provide a more polite response, thereby improving user satisfaction.

[1951] "Example 2"

[1952] Another embodiment of the present invention is a system in which an emotion engine adjusts the AI's response based on the user's emotions. In this system, if the user is feeling joy, the AI ​​will recognize that emotion and provide a more energetic response, thereby maximizing the user's joy and providing a better user experience.

[1953] "Example 3"

[1954] Furthermore, a system in which an emotion engine generates solutions based on a user's emotions is also one embodiment of the present invention. In this system, if a user is feeling anxious, the AI ​​recognizes that emotion and provides a solution to alleviate the anxiety. For example, if a user is feeling anxious about a new project, the AI ​​recognizes the anxiety and provides project management best practices and past success stories to alleviate the user's anxiety.

[1955] The processing flow of each embodiment will be described below.

[1956] "Example 1"

[1957] Step 1: Understand user sentiment through natural language interactions with users.

[1958] Step 2: The emotion engine recognizes the user's emotion.

[1959] Step 3: Based on the recognized emotion, the AI ​​provides a solution.

[1960] "Example 2"

[1961] Step 1: Understand user sentiment through natural language interactions with users.

[1962] Step 2: The emotion engine recognizes the user's emotion.

[1963] Step 3: The AI ​​tailors its response based on the perceived emotion.

[1964] "Example 3"

[1965] Step 1: Understand user sentiment through natural language interactions with users.

[1966] Step 2: The emotion engine recognizes the user's emotion.

[1967] Step 3: The AI ​​generates a solution based on the recognized emotion.

[1968] Example 1

[1969] Next, a description will be given of Example 1 of Form 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."

[1970] Conventional systems have made it difficult for users to efficiently obtain the information they need to solve problems and find appropriate solutions. Furthermore, they are unable to provide responses that reflect the user's emotions, making it difficult to improve user satisfaction. Furthermore, there is a need for efficient work progression and the rapid execution of creative tasks using generative AI models.

[1971] 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.

[1972] In this invention, the server includes a means for a user to input a problem in natural language, a means for analyzing the problem using a generative AI model, a means for acquiring necessary information from a database, a means for generating a solution based on the acquired information, a means for recognizing the user's emotions and adjusting the response, and a means for feeding back the generated solution to the user. This allows the user to not only solve the problem efficiently, but also receive appropriate support according to their emotions.

[1973] A "user" is an individual or organization that uses the system to input problems and obtain solutions.

[1974] "Natural language" refers to the language used by humans on a daily basis, and refers to normal speech and writing forms, rather than specific programming languages ​​or commands.

[1975] A "generative AI model" is an artificial intelligence algorithm or system that analyzes input natural language and generates appropriate solutions or information.

[1976] "Analyzing the problem" is the process of understanding the problem entered in natural language by the user and identifying the necessary information and solutions based on that content.

[1977] A "database" is a digital storage system that stores information systematically and allows it to be searched and retrieved as needed.

[1978] "Retrieving information" is the process of searching and retrieving the required data from a database.

[1979] "Generating solutions" is the process of creating specific solutions or proposals for the user's problems based on the information obtained.

[1980] "Emotion recognition" is the process of identifying and understanding a user's emotional state from their input and behavior.

[1981] "Response tailoring" is the process of changing the content and tone of the solutions and feedback you generate based on perceived user emotions.

[1982] "Feedback" is the process of providing generated solutions or information to the user so that they can review it.

[1983] This invention is a system that links a database with a generative AI model, where a user inputs a problem in natural language, and the AI ​​analyzes the problem and provides a solution. A specific embodiment of this system is shown below.

[1984] Hardware and software used

[1985] Hardware: Servers, terminals

[1986] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), emotion engines (e.g., Affectiva)

[1987] System configuration

[1988] 1. User issue input

[1989] The user uses the device to input the issue in natural language. For example, the user types "How do I manage the progress of a new project?" into the device's input field.

[1990] 2. Problem Analysis

[1991] The server analyzes the user's problem using a generative AI model, which understands the input natural language and identifies the subject of the problem and the required information.

[1992] 3. Retrieving information from the database

[1993] The server uses a database management system to retrieve necessary information from the database based on the analysis results, for example, the server searches the database for information related to "project management."

[1994] 4. Solution Generation

[1995] The server uses a generative AI model to generate solutions based on the acquired information. For example, based on project management information acquired from the database, the server generates a solution such as, "Task prioritization and progress visualization are important for project management. Specifically, we recommend using a Gantt chart."

[1996] 5. Emotion recognition and response regulation

[1997] The server uses an emotion engine to recognize the user's emotions. For example, the server analyzes the user's input and past interactions to recognize that the user is frustrated. The emotion engine analyzes the user's text and voice data to identify their emotional state. The generative AI model then adjusts its response accordingly.

[1998] 6. User Feedback

[1999] The server sends the generated solution to the device and provides feedback to the user. For example, the server might send a solution such as, "In project management, prioritizing tasks and visualizing progress are important. Specifically, we recommend using a Gantt chart." The device then displays the solution received from the server to the user.

[2000] Specific examples

[2001] Prompt Sentence Examples

[2002] "How do I manage the progress of a new project?"

[2003] "Can you give me some advice on prioritizing tasks?"

[2004] "What are some common project management problems and how can you solve them?"

[2005] This system not only enables users to solve problems efficiently, but also allows them to receive appropriate support according to their emotions.

[2006] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2007] Step 1:

[2008] User issue input

[2009] Input: A user enters an issue in natural language using a terminal.

[2010] What happens: The user types "How do I manage progress on a new project?" into the device's input field.

[2011] Output: The terminal receives user input and sends it to the server.

[2012] Step 2:

[2013] Analysis of the problem

[2014] Input: User challenge submitted from the device (natural language text).

[2015] How it works: The server analyzes the user's problem using a generative AI model. The generative AI model understands the input natural language and identifies the subject of the problem and the required information.

[2016] Output: Identification of the subject and required information.

[2017] Step 3:

[2018] Retrieving information from a database

[2019] Input: Identification of the subject and required information.

[2020] Specific operations: The server uses the database management system to retrieve the necessary information from the database based on the analysis results. The server searches the database for information related to "project management."

[2021] Output: Information retrieved from the database.

[2022] Step 4:

[2023] Solution Generation

[2024] Input: Information retrieved from the database.

[2025] Specific operation: The server uses the generative AI model to generate a solution based on the acquired information. Based on the information about project management acquired from the database, the server generates the solution, "In project management, prioritizing tasks and visualizing progress are important. Specifically, we recommend using a Gantt chart."

[2026] Output: The generated solution.

[2027] Step 5:

[2028] Emotion recognition and response regulation

[2029] Input: User input, past interactions, and generated solutions.

[2030] How it works: The server uses an emotion engine to recognize the user's emotions. The server analyzes the user's input and past interactions and recognizes that the user is frustrated. The emotion engine analyzes the user's text and voice data to identify their emotional state. The generative AI model adjusts its response based on that emotional state.

[2031] Output: The adjusted response.

[2032] Step 6:

[2033] User feedback

[2034] Input: The adjusted response.

[2035] Specific operations: The server sends the generated solution to the device and provides feedback to the user. The server sends the solution "Task prioritization and progress visualization are important for project management. Specifically, we recommend using a Gantt chart." to the device. The device displays the solution received from the server to the user.

[2036] Output: The solution displayed to the user.

[2037] (Application example 1)

[2038] Next, a description will be given of Application Example 1 of Form 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."

[2039] On conventional online shopping sites, it is difficult for users to quickly obtain appropriate product information when searching for a product, and they are unable to respond to the user's emotions, which leads to a decrease in user satisfaction. In particular, when a user feels frustrated, they are unable to respond appropriately, which leads to a worsening user experience.

[2040] 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.

[2041] In this invention, the server includes a means for enabling a process from identifying issues to analyzing data and devising solutions through natural language interaction, a means for linking the database with generative AI, a means for recognizing user emotions and providing solutions based on those emotions, and a means for suggesting optimal product information based on user input. As a result, when a user communicates a problem in natural language, the AI ​​analyzes the problem, retrieves the necessary information from the database, generates a solution, and responds in accordance with the user's emotions.

[2042] "Identifying the problem" is the process of clarifying the problems and needs of users in natural language.

[2043] "Data analysis" is the process of analyzing collected data and extracting meaningful information.

[2044] "Solution creation" is the process of generating an appropriate solution to an identified problem.

[2045] "Natural language interaction" means that users communicate with the system using the language they use on a daily basis.

[2046] A database is a system that systematically organizes and stores information, allowing it to be searched and retrieved as needed.

[2047] "Generative AI" is artificial intelligence that generates new information and solutions based on given data and instructions.

[2048] "Recognizing user emotions" is the process of analyzing and understanding a user's emotional state from their input and behavior.

[2049] "Providing solutions" refers to making appropriate responses or suggestions based on identified issues and emotions.

[2050] "Proposing optimal product information" is the process of selecting and presenting the product that best suits the user's requests and needs.

[2051] To implement this invention, the following system configuration is required: The system consists of a terminal where users can input tasks in natural language, a database, a generative AI, and a server that includes an emotion recognition engine.

[2052] When a user uses a device to input a challenge in natural language, the input is sent to the server, which first analyzes the user's emotions using an emotion recognition engine, which uses a natural language processing library such as TextBlob to classify the emotion of the user's input text as positive, negative, or neutral.

[2053] The server then uses generative AI to analyze the user's problem and retrieves the necessary information from a database. This generative AI uses OpenAI's API to generate optimal product information based on the user's questions and requests. The database stores product information and the user's past purchase history.

[2054] The server then suggests optimal product information to the user based on the acquired information and the results of emotion recognition. For example, if a user types, "The weather has been bad lately, so I don't feel like going out. Please tell me about some useful items I can use at home," the server responds, "We are searching for the best products to resolve your complaint. Please wait a moment," and then suggests, "Recommended products: automatic vacuum cleaner, smart speaker, home exercise kit."

[2055] This system allows users to simply communicate their issues in natural language, and quickly receive appropriate responses based on their emotions and the most appropriate product information.

[2056] An example of a prompt is as follows:

[2057] A user asked the following question: The weather has been so bad lately that I don't feel like going out. What are some handy items I can use around the house?

[2058] Please suggest the best product.

[2059] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2060] Step 1:

[2061] The user enters the issue in natural language using a terminal.

[2062] Input: The user's natural language challenge or question.

[2063] Output: The user's input text data.

[2064] Specific operation: The user enters "The weather has been bad lately, so I don't feel like going out. Please tell me some useful items I can use at home" into the input field on the device and presses the send button.

[2065] Step 2:

[2066] The server receives the user's input text data and analyzes the emotions using an emotion recognition engine.

[2067] Input: User-entered text data.

[2068] Output: Emotion recognition result (positive, negative, neutral).

[2069] Specific behavior: The server uses the TextBlob library to analyze the sentiment of the user's input text and determines it to be "negative."

[2070] Step 3:

[2071] The server uses generative AI to analyze the user's issues and...

Claims

1. means for receiving a user challenge input in natural language; A means for analyzing the problem by a generating AI and identifying necessary information; A means for retrieving the identified information from a database; A means for generating a solution based on the necessary information obtained from the database using the generating AI; A means for providing feedback of the generated solution to the user; and A system including:

2. The system of claim 1 , wherein the means for identifying the required information identifies the required information by sending the received task to the generation AI as a prompt sentence.

3. The system of claim 1 , wherein the means for generating a solution generates the solution by transmitting the necessary information obtained from the database to the generation AI and instructing it to generate the solution.

Images