System

Abstract

To provide a system.SOLUTION: A system includes means for analyzing accumulated data related to business management using a generative AI model, means for providing advice to a user for making decisions related to business management based on the analysis result obtained by the generative AI model, means for recognizing emotions of the user using an emotion engine, and means for adjusting the advice based on the recognized emotions of 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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] When faced with large amounts of information and complex problems, it is difficult to organize and analyze the information and provide appropriate advice and decisions, especially when it comes to providing advice and decisions that take into account the company or industry vision, the management's thinking, and market conditions. [Means for solving the problem]

[0005] This invention provides a means for organizing and analyzing large amounts of information, a means for providing advice based on the results of that organization and analysis, and a means for making decisions that take into account the vision of the company or industry, the thinking of the management, and market conditions. This makes it possible to provide accurate advice and decision-making in situations where individuals or business people are having difficulty organizing information or making decisions in industries such as marketing, consulting, finance, medicine, and manufacturing. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 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. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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 wide area network (WAN) and / or a local area network (LAN).

[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 and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. 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 (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0023] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as 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] The system of the present invention uses a database and AI technology as a means for organizing and analyzing large amounts of information. Specifically, data such as industry information and market conditions is stored in the database, and AI technology is used to organize and analyze this data. In addition, as a means for providing advice, optimal advice is provided to users based on data organized and analyzed using AI technology. Furthermore, as a means for making decisions that take into account the vision of the company or industry, the thinking of the management, and the market conditions, these elements are stored as data in a database, and AI technology is used to make decisions that take these elements into consideration.

[0029] "Example 2"

[0030] As a specific example of use, if a manufacturing businessperson requests advice on market conditions, competitor trends, or the direction of their own company's product development, the system will retrieve this information from the database and use AI technology to organize and analyze it. Based on the results, it will provide optimal advice and support decision-making that takes into account the vision, management thinking, and market conditions.

[0031] The process flow of each embodiment will be described below.

[0032] "Example 1"

[0033] Step 1: The user makes a request to the system for information organization and decision-making. This request may be about information such as the market situation in a particular industry, the trends of competitors, or the direction of the company's product development.

[0034] Step 2: The system retrieves the required information from a database, which contains industry information, market conditions, and other data.

[0035] Step 3: The acquired information is organized and analyzed using AI technology. This analysis uses technologies such as machine learning and deep learning.

[0036] Step 4: Based on the analysis results, provide the user with optimal advice, which will help the user organize information and make decisions.

[0037] "Example 2"

[0038] Step 1: A manufacturing business person asks the system for advice on market conditions, competitor trends, and their company's product development direction.

[0039] Step 2: The system retrieves this information from the database and organizes and analyzes it using AI technology.

[0040] Step 3: Based on the analysis results, provide the businessperson with the best advice possible. This advice will help the businessperson make decisions about the market situation, the trends of competitors, and the direction of their own product development.

[0041] Example 1

[0042] Next, a description will be given of Example 1 of the embodiment 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".

[0043] In today's business environment, it is extremely important to efficiently organize and analyze large amounts of information and provide appropriate advice based on the results. However, in conventional systems, data collection, preprocessing, analysis, advice generation, and decision-making support are carried out separately, and there is no integrated system, making efficient information processing and decision-making difficult. In addition, there is a lack of support for making decisions that comprehensively take into account the company or industry vision, management thinking, and market conditions.

[0044] 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.

[0045] In this invention, the server includes a means for collecting data such as industry information and market conditions and storing the data in a database, a means for preprocessing the stored data, a means for analyzing the preprocessed data using a machine learning model, a means for generating optimal advice for users based on the analysis results, and a means for supporting decision-making that takes into account the vision of the company or industry, the thinking of the management, and the market conditions, thereby enabling efficient information processing and integrated decision-making support.

[0046] "Industry intelligence" refers to data and knowledge related to a particular industry, including market trends, competitor actions, and technological innovations.

[0047] "Market conditions" refers to data that describes the current state or trends in a particular market, including supply and demand, price trends, and consumer behavior.

[0048] A "database" is a system for efficiently storing, managing, and searching data, and includes relational database management systems (RDBMS).

[0049] "Preprocessing" is the process of formatting data before data analysis, filling in missing values, removing outliers, normalizing the data, etc.

[0050] A "machine learning model" refers to an algorithm or mathematical model that learns patterns and rules from data and makes predictions or classifications.

[0051] "Analysis" is the process of using data to find patterns and trends and extract meaningful information.

[0052] "Advice" refers to specific suggestions or instructions provided to the user based on the results of the analysis.

[0053] A "vision" indicates the direction or goals that a company or industry aims for in the future.

[0054] "Management thinking" refers to the strategic thinking and decision-making criteria held by company managers.

[0055] "Decision support" is the process of providing assistance to users to make optimal decisions based on data and analysis results.

[0056] This invention is a system that efficiently organizes and analyzes large amounts of information and provides appropriate advice based on the results. A specific embodiment of this system will be described below.

[0057] Data collection and storage

[0058] The server collects data such as industry information and market conditions from the Internet and from data sources within the company. Specifically, it uses web scraping technology to obtain data from news sites and market research reports. The collected data is stored in a relational database such as MySQL (registered trademark) or PostgreSQL.

[0059] Data Preprocessing

[0060] The server preprocesses the accumulated data. Specifically, it complements missing values, removes outliers, normalizes data, etc. It uses the pandas library of Python (registered trademark) to manipulate data in data frame format and perform preprocessing.

[0061] Analyzing data

[0062] The server uses the preprocessed data to perform analysis. It uses machine learning libraries such as TENSORFLOW® and PyTorch to analyze the data for patterns and trends. For example, it uses time series data to build models that forecast market trends.

[0063] Generating Advice

[0064] The server generates optimal advice for the user based on the analysis results. When the user enters a specific question as a prompt, the server retrieves relevant data and uses the AI ​​model to generate advice.

[0065] Decision support

[0066] The server supports decision-making by taking into account the vision of the company or industry, the thinking of the management, and market conditions. These elements are stored in a database, and AI technology is used to provide information for optimal decision-making.

[0067] Examples and prompts

[0068] Examples

[0069] If a user wants to know when a new product will be released to the market, they can input a prompt like this into the generative AI model:

[0070] Examples of prompt statements

[0071] "What is the best time to bring a new product to market? Please provide an analysis based on current market conditions and historical data."

[0072] Once this prompt is entered, the server will retrieve relevant data from the database, use an AI model to analyze the optimal timing, and provide advice to the user.

[0073] In this way, a system is realized that enables efficient information processing and integrated decision-making support.

[0074] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0075] Step 1:

[0076] Data collection and storage

[0077] The server collects data such as industry information and market conditions from the Internet and internal company data sources. Specifically, it uses web scraping technology to obtain data from news sites and market research reports. Inputs include URLs and API endpoints to be collected. Outputs include the collected data stored in JSON or CSV format. The server periodically runs scheduled jobs to retrieve new data from specified data sources and insert it into the database.

[0078] Step 2:

[0079] Data Preprocessing

[0080] The server preprocesses the accumulated data, i.e., imputing missing values, removing outliers, normalizing data, etc. The input includes raw data read from the database. The output is clean preprocessed data. The server executes the preprocessing script, reads the data from the database, performs the necessary preprocessing, and saves it back to the database.

[0081] Step 3:

[0082] Analyzing data

[0083] The server performs analysis using the preprocessed data. It uses machine learning libraries such as TensorFlow and PyTorch to analyze the data for patterns and trends. The input includes the preprocessed data. The output is an analysis or predictive model. The server trains the machine learning model, evaluates it, and stores the trained model in a database.

[0084] Step 4:

[0085] Generating Advice

[0086] The server generates optimal advice for the user based on the analysis results. When the user inputs a specific question as a prompt, the server retrieves relevant data and generates advice using an AI model. The input includes the prompt from the user. The output is the generated advice provided to the user. In concrete terms, when a user inputs a prompt such as "What is the best timing to launch a new product on the market?", the server retrieves market trend data, calculates the optimal timing using an AI model, and returns the result to the user.

[0087] Step 5:

[0088] Decision support

[0089] The server supports decision-making that takes into account the company and industry vision, the management's thinking, and market conditions. These elements are stored in a database and provide information for optimal decision-making using AI technology. Inputs include data on the company and industry vision, the management's thinking, and market conditions. Outputs generate specific proposals and strategies to support decision-making. In concrete terms, when a manager considers a new business strategy, the server proposes an optimal strategy based on past data and market trends. For example, when a prompt such as "Please tell me the risks and benefits of entering a new market" is entered, the server analyzes the relevant data, evaluates the risks and benefits, and provides the results.

[0090] (Application example 1)

[0091] 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 device 14 will be referred to as a "terminal."

[0092] Inventory management and optimization at logistics centers are important issues for efficient operation. Conventional methods do not adequately monitor inventory status in real time or forecast demand, resulting in inventory shortages and surpluses. In addition, calculations for efficient picking routes are often done manually, which reduces work efficiency. To solve these issues, an advanced system that utilizes databases and AI technology is needed.

[0093] 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. In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions taking into account the vision of the company or industry, the manager's thinking, and the market situation, a means for supporting inventory management and optimization in the logistics center, a means for forecasting demand, a means for proposing the optimal timing and amount of inventory replenishment, and a means for calculating and instructing an efficient picking route. This enables efficient and optimized inventory management in the logistics center.

[0094] "Means of organizing and analyzing large amounts of information" refers to a method of systematically organizing and analyzing large amounts of data, such as industry information and market conditions, using databases and AI technology.

[0095] "Means for providing advice based on the results of the organization and analysis" refers to a method for providing optimal advice to users based on the organized and analyzed data.

[0096] "A means of making decisions that take into account the vision of the company or industry, the thinking of management, and market conditions" is a method for making optimal decisions by taking into account the long-term goals of the company or industry, the thinking of management, and market trends.

[0097] The "means for supporting inventory management and optimization in logistics centers" refers to a method for monitoring inventory status within a logistics center in real time and achieving efficient inventory management and optimization.

[0098] A "demand forecasting means" is a method for predicting future demand based on past data and market conditions.

[0099] The "means for proposing optimal inventory replenishment timing and amount" is a method for proposing optimal inventory replenishment timing and amount based on a demand forecast.

[0100] The "means for calculating and instructing an efficient picking route" is a method for calculating an efficient picking route within a logistics center and instructing the worker on the route.

[0101] This invention is a system that supports inventory management and optimization in a logistics center. The system operates in cooperation with a server, a terminal, and a user.

[0102] Server Roles

[0103] The server includes a means for organizing and analyzing large amounts of information, a means for providing advice based on the results of that organization and analysis, and a means for making decisions that take into account the vision of the company or industry, the thinking of the management, and market conditions. Specifically, it performs the following processes:

[0104] 1. Database management: The server accumulates data on inventory in the distribution center, past sales data, market situation data, etc. in a database. For this purpose, a database management system such as MySQL or PostgreSQL is used.

[0105] 2. Training the AI ​​model: The server trains the demand forecasting model based on the accumulated data, using the Python Scikit-learn library.

[0106] 3. Demand forecasting: Using trained AI models to predict future demand, which helps prevent shortages and overstocks.

[0107] 4. Inventory replenishment proposal: Calculate and propose the optimal timing and amount of inventory replenishment based on the results of demand forecasting.

[0108] 5. Picking route optimization: Calculates efficient picking routes within the distribution center and provides instructions to workers.

[0109] Terminal Roles

[0110] The terminals are smartphones or tablets used by workers in the logistics center. The terminals receive instructions from the server and display them to the workers. Specifically, they perform the following processes:

[0111] 1. View inventory status: View inventory status in real time.

[0112] 2. Displaying the results of the demand forecast: Displaying the results of the demand forecast and providing information to workers.

[0113] 3. Inventory replenishment instructions: Displays the optimal timing and amount of inventory replenishment and gives instructions to workers.

[0114] 4. Picking route instructions: Displays efficient picking routes and instructs workers on them.

[0115] User Roles

[0116] The users are the managers and workers of the logistics center. They receive instructions from the server through their terminals and perform the actual work. Specifically, they perform the following processes:

[0117] 1. Inventory management: Check stock status in real time and replenish stock as needed.

[0118] 2. Check the demand forecast: Check the results of the demand forecast and perform appropriate inventory management.

[0119] 3. Picking: Pick products by following efficient picking routes.

[0120] Examples

[0121] For example, if the inventory of "Product A" is decreasing at a logistics center, the server will predict that demand for "Product A" will increase in the following week based on past sales data and market conditions. As a result, the server will calculate the optimal timing and amount of inventory replenishment and send instructions to the terminal. Workers receive these instructions through their terminals and replenish inventory at the appropriate time. In addition, efficient picking routes are also displayed on the terminals, allowing workers to perform picking work efficiently.

[0122] Examples of prompt statements

[0123] "In order to optimize inventory management at distribution centers, please develop an application that predicts demand based on past sales data and market conditions, and suggests the optimal timing and amount of inventory replenishment."

[0124] By inputting this prompt into a generative AI model, more specific application designs and improvement suggestions can be obtained.

[0125] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0126] Step 1:

[0127] The server accumulates inventory data, past sales data, and market status data from the logistics center in a database. Specifically, it collects data in real time from each sensor and terminal in the logistics center and stores it in a database management system such as MySQL or PostgreSQL. The input is various data (inventory data, sales data, market status data), and the output is the data accumulated in the database.

[0128] Step 2:

[0129] The server trains a demand forecasting model based on the accumulated data. Specifically, it uses Python's Scikit-learn library to build a demand forecasting model using past sales data and market status data as input. The input is the past sales data and market status data accumulated in the database, and the output is the trained demand forecasting model.

[0130] Step 3:

[0131] The server uses the trained demand forecasting model to forecast future demand. Specifically, the server applies the demand forecasting model to future market situation data as input to obtain a demand forecast result. The input is future market situation data, and the output is the demand forecast result.

[0132] Step 4:

[0133] The server calculates and proposes the optimal timing and amount of inventory replenishment based on the results of the demand forecast. Specifically, it generates an optimal inventory replenishment plan using the demand forecast results and current inventory data as input. The inputs are the demand forecast results and current inventory data, and the output is the inventory replenishment plan.

[0134] Step 5:

[0135] The server calculates the most efficient picking route within the distribution center and instructs the workers. Specifically, it inputs the current inventory location data and the picking list, calculates the shortest route, and sends instructions to the terminal. The input is the inventory location data and the picking list, and the output is the optimal picking route.

[0136] Step 6:

[0137] The terminal receives instructions from the server and displays them to the worker. Specifically, it displays the inventory status, demand forecast results, inventory replenishment plans, and picking routes in real time. The input is instruction data from the server, and the output is information to be displayed to the worker.

[0138] Step 7:

[0139] The user receives instructions from the server through the terminal and performs the actual work. Specifically, the user performs inventory management, checking demand forecasts, replenishing stock, and picking work. The input is instruction information from the terminal, and the output is the actual work results.

[0140] Example 2

[0141] Next, a second embodiment of the second embodiment will be described. 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."

[0142] In today's business environment, it is extremely important for companies and individuals to efficiently organize and analyze large amounts of information and make appropriate decisions. However, due to the sheer volume and complexity of information, doing this manually is difficult and requires time and effort. In addition, specialized knowledge and experience are required to obtain appropriate advice, which is also a hurdle for many people. Therefore, there is a demand for a system that can efficiently organize and analyze information and provide appropriate advice.

[0143] 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.

[0144] In this invention, the server includes a means for a user to input a prompt sentence, a means for a terminal to transmit the input prompt sentence to the server, a means for the server to obtain related information from a database, a means for the server to organize and clean the obtained data, a means for the server to analyze the data using a generative AI model, a means for the server to generate advice based on the analysis results, a means for the server to transmit the generated advice to the terminal, a means for the terminal to display advice to the user, and a means for making decisions taking into account the vision of the company or industry, the thinking of the management, and market conditions. This enables the user to efficiently organize and analyze large amounts of information and obtain appropriate advice.

[0145] A "User" is any individual or entity that utilizes the System to input information and receive advice.

[0146] A "prompt sentence" is text that a user enters to ask the system a specific question or for advice.

[0147] A "terminal" is a device through which a user enters prompt statements and receives advice from a server.

[0148] "Server" means a computer system that retrieves information from a database, organizes and analyzes the data, generates advice, and sends it to the terminal.

[0149] A "database" is a collection of information that a server accesses to obtain information.

[0150] A "generative AI model" is an artificial intelligence technique used by the server to analyze data and generate advice.

[0151] "Advice" refers to instructions or suggestions provided to the user based on the results of analysis performed by the server using a generative AI model.

[0152] A "vision" is the direction or goal that a company or industry aims for in the future.

[0153] "Executive thinking" refers to the strategic thinking and decision-making standards held by company executives.

[0154] "Market conditions" refers to the current trends and environment in a particular industry or market.

[0155] A "decision" is a choice or judgment made by a user based on advice provided.

[0156] This invention is a system in which a user inputs a prompt sentence, a server retrieves information from a database, analyzes the data using a generative AI model, generates advice, and provides it to the user. A specific embodiment of this system will be described below.

[0157] First, the user uses a terminal to input a prompt, which is text that the user enters to ask the system a specific question or request advice, such as "Please advise me on the market situation and competitor trends for our new product line."

[0158] The terminal then sends the input prompt to the server, using an HTTP request. The server then queries a database to obtain data related to the prompt, including market conditions, competitor trends, and the server's own product development. The database is typically a database management system such as SQL Server.

[0159] The server organizes the acquired data and cleans unnecessary data. Specifically, it uses Python's Pandas library to format the data and extract the necessary information. The server then inputs the organized data into a generative AI model (e.g., GPT-4 (registered trademark) from OpenAI (registered trademark)) to analyze the data. The generative AI model finds trends and patterns in the data and generates analysis results.

[0160] The server generates advice to provide to the user based on the analysis results of the generative AI model. This advice takes into account the company and industry vision, the management's thinking, and the market situation. The generated advice is sent from the server to the terminal. This communication also uses HTTP requests.

[0161] Finally, the terminal displays the advice received from the server to the user, who can then make a decision based on the advice.

[0162] As a concrete example, consider a manufacturing businessperson considering developing a new product line. The user types into the terminal, "Please provide advice on the market situation and competitor trends for the new product line." The terminal sends this prompt text to the server via an HTTP request, and the server queries SQL Server to obtain relevant market data and competitor information. The server uses Python's Pandas library to clean the data and extract the necessary information. The server inputs the data into a generative AI model (GPT-4) to analyze trends and patterns. Based on the analysis results, the server generates advice to provide to the user and sends it to the terminal via an HTTP response. The terminal displays the advice to the user, and the user makes a decision based on it.

[0163] In this way, the system provides optimal advice to users and supports efficient decision-making.

[0164] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0165] Step 1:

[0166] The user enters a prompt sentence.

[0167] Input: The text that the user has a specific question or request for advice (e.g., "Please provide advice on the market situation and competitor behavior for a new product line")

[0168] Output: The prompt is typed into the terminal.

[0169] Specific actions: The user enters a prompt sentence into the input field of the terminal and presses the send button.

[0170] Step 2:

[0171] The terminal sends the prompt text entered to the server.

[0172] Input: The prompt text entered by the user

[0173] Output: The prompt text is sent to the server as an HTTP request.

[0174] Specific operation: The terminal includes the prompt text in the body of an HTTP request and sends it to the specified endpoint of the server.

[0175] Step 3:

[0176] The server retrieves the relevant information from a database.

[0177] Input: Prompt statement (e.g., "Please advise on the market situation and competitor trends for a new product line.")

[0178] Output: Data from the database on market conditions, competitors' activities, and our own product developments.

[0179] Specific behavior: The server generates an SQL query based on the prompt statement and sends it to the database to retrieve relevant information.

[0180] Step 4:

[0181] Organize and clean the data retrieved by the server.

[0182] Input: Raw data retrieved from the database

[0183] Output: Organized and cleaned data

[0184] What it does: The server uses Python's Pandas library to format the data, remove unnecessary data, and extract the necessary information.

[0185] Step 5:

[0186] The server analyzes the data using a generative AI model.

[0187] Input: Organized and cleaned data

[0188] Output: Analysis results from generative AI models

[0189] What it does: The server feeds the organized data into a generative AI model (e.g. GPT-4) to analyze trends and patterns.

[0190] Step 6:

[0191] The server generates advice based on the analysis results.

[0192] Input: Analysis results from generative AI models

[0193] Output: Advice to give to the user

[0194] Specific operation: Based on the analysis results of the generative AI model, the server generates specific advice to provide to the user.

[0195] Step 7:

[0196] The server transmits the generated advice to the terminal.

[0197] Input: Generated advice

[0198] Output: The advice is sent to the device as an HTTP response.

[0199] Specific operation: The server includes the generated advice in the body of the HTTP response and sends it to the terminal.

[0200] Step 8:

[0201] The terminal displays the advice to the user.

[0202] Input: Advice sent by the server

[0203] Output: Advice displayed to the user

[0204] Specific operation: The device displays the received advice on the user interface so that the user can view it.

[0205] (Application example 2)

[0206] 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."

[0207] In modern manufacturing, there is a need to grasp market conditions, competitor trends, and the direction of one's own product development in real time in order to create optimal manufacturing strategies. However, there are still not enough systems in place that can efficiently collect and analyze this information and provide appropriate advice. As a result, manufacturing business people often have difficulty organizing information and making decisions. To solve this problem, a system that uses AI technology to analyze market data and propose optimal manufacturing strategies is needed.

[0208] 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.

[0209] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organization and analysis, a means for making decisions taking into account the vision of the company or industry, the thinking of the management, and the market situation, a means for collecting and analyzing data on the market situation, the trends of competitors, and the direction of the company's product development, and proposing an optimal manufacturing strategy, a means for inputting a prompt sentence using a generative AI model and generating advice based on the analysis results, and a means for displaying and notifying the advice through an application installed on a factory robot. This enables business people in the manufacturing industry to collect and analyze market data in real time and create optimal manufacturing strategies.

[0210] "Means of organizing and analyzing large amounts of information" refers to a function for collecting huge amounts of data, organizing it into an appropriate format, and analyzing it using statistical methods and machine learning algorithms.

[0211] "A means of providing advice based on the results of organization and analysis" is a function for proposing specific courses of action and strategies based on the results of data analysis.

[0212] "A means of making decisions that take into account the vision of the company and the industry, the thinking of management, and market conditions" is a function that allows optimal decision-making by taking into account the company's long-term goals, the intentions of management, and market trends.

[0213] "A means of collecting and analyzing data on market conditions, competitor trends, and the company's own product development direction, and proposing optimal manufacturing strategies" refers to a function that collects market data, competitor information, and the company's own development status in real time, analyzes them, and creates optimal manufacturing plans.

[0214] "A means for inputting a prompt sentence using a generative AI model and generating advice based on the analysis results" refers to a function for inputting a specific prompt sentence to a generative AI model and generating advice based on the resulting analysis results.

[0215] "Means for displaying and notifying advice through an application installed on a factory robot" means a function for visually or audibly displaying and notifying generated advice through software installed on a factory robot.

[0216] A system for carrying out this invention has the following configuration: The server includes means for organizing and analyzing large amounts of information, means for providing advice based on the results of the organization and analysis, means for making decisions taking into account the vision of the company or industry, the thinking of the management, and the market situation, means for collecting and analyzing data on the market situation, the trends of competitors, and the direction of the company's product development, and proposing an optimal manufacturing strategy, means for inputting prompt sentences using a generative AI model and generating advice based on the analysis results, and means for displaying and notifying advice through an application installed on a factory robot.

[0217] Hardware and Software Used

[0218] Hardware: Factory robots, servers, network connections

[0219] Software: Database management systems (e.g. MySQL), AI models (e.g. GPT-4), data analysis tools (e.g. Pandas, NumPy)

[0220] Data processing and calculation flow

[0221] 1. Data collection: The server obtains data on market conditions, competitors' activities, and the company's own product development from a database via the network.

[0222] 2. Data reduction: The server reduces and preprocesses the acquired data using Pandas and NumPy.

[0223] 3. Data analysis: The server inputs the organized data into the AI ​​model (GPT-4) for analysis.

[0224] 4. Advice generation: The server generates optimal manufacturing strategies and advice based on the analysis results.

[0225] 5. Result display: The factory robot displays and notifies the user of advice through a display and voice output.

[0226] Examples

[0227] For example, the following prompt sentence is input to the generative AI model:

[0228] Example prompt:

[0229] Considering the current market situation, competitor trends, and your company's product development direction, please suggest the optimal manufacturing strategy for the next quarter.

[0230] Examples of advice that can be generated include specific manufacturing strategies such as, "Market demand is increasing, so we recommend that you increase production of product A by 20%. Also, your competitor is planning to release a new product B, so you should speed up improving your product C."

[0231] In this way, market analysis advisors for factory robots can support decision-making in manufacturing industries and achieve efficient production.

[0232] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0233] Step 1:

[0234] The server retrieves data on market conditions, competitors' activities, and the company's own product development from the database via the network. The input is market data, competitor information, and in-house development data, and the output is the retrieved raw data. In concrete terms, the server sends a query to the MySQL database to retrieve the required data.

[0235] Step 2:

[0236] The server organizes and preprocesses the acquired data using Pandas and NumPy. The input is raw data, and the output is preprocessed data. Specifically, the server performs operations such as filling in missing values, normalizing data, and deleting unnecessary data.

[0237] Step 3:

[0238] The server inputs the organized data into the AI ​​model (GPT-4) and performs analysis. The input is the preprocessed data, and the output is the analysis result. Specifically, the server generates a prompt sentence for the GPT-4 model and inputs the data.

[0239] Step 4:

[0240] The server generates optimal manufacturing strategies and advice based on the analysis results. The input is the analysis results, and the output is the generated advice. Specifically, the server analyzes the output of the generative AI model and generates specific advice in text format.

[0241] Step 5:

[0242] The factory robot displays and notifies the user of advice through a display and voice output. The input is the generated advice, and the output is the displayed advice. In terms of specific operations, the factory robot displays text on the display and notifies the user by voice if necessary.

[0243] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0244] "Example 1"

[0245] As one embodiment of the present invention, there is a system that combines an emotion engine. This system includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organization and analysis, and a means for making decisions that take into account the vision of the company or industry, the thoughts of the management, and the market situation. It also includes an emotion engine that recognizes the emotions of the user. This emotion engine recognizes emotions from the tone of the user's voice, facial expression, choice of words, etc., and reflects the recognition results in providing advice and making decisions. For example, if it recognizes that the user is feeling stressed, it provides advice taking that information into account. Also, if it recognizes that the user is feeling happy, it makes decisions taking that information into account.

[0246] "Example 2"

[0247] Another embodiment of the present invention is a system that combines an emotion engine. This system includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organization and analysis, and a means for making decisions that take into account the vision of the company or industry, the thoughts of the management, and the market situation. It also includes an emotion engine that recognizes the emotions of the user. This emotion engine recognizes emotions from the user's behavioral patterns and the contents of posts on SNS, and reflects the recognition results in providing advice and making decisions. For example, if it is recognized that the user is feeling anxious, it provides advice taking that information into account. Also, if it is recognized that the user is excited, it makes decisions taking that information into account.

[0248] The process flow of each embodiment will be described below.

[0249] "Example 1"

[0250] Step 1: The system receives input from the user, including the user's tone of voice, facial expressions, and choice of words.

[0251] Step 2: The emotion engine recognizes the user's emotion from the received input information.

[0252] Step 3: The system organizes and analyzes large amounts of information based on the emotion recognition results from the emotion engine.

[0253] Step 4: The system provides advice based on the results of the analysis and analysis, including the emotion recognition results.

[0254] Step 5: The system makes decisions based on the company and industry vision, management's thinking, and market conditions, including the emotion recognition results.

[0255] "Example 2"

[0256] Step 1: The system receives input information from the user, including the user's behavioral patterns and the content of posts on social media.

[0257] Step 2: The emotion engine recognizes the user's emotion from the received input information.

[0258] Step 3: The system organizes and analyzes large amounts of information based on the emotion recognition results from the emotion engine.

[0259] Step 4: The system provides advice based on the results of the analysis and analysis, including the emotion recognition results.

[0260] Step 5: The system makes decisions based on the company and industry vision, management's thinking, and market conditions, including the emotion recognition results.

[0261] Example 1

[0262] Next, a description will be given of Example 1 of the embodiment 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".

[0263] Conventional information sorting and analysis systems have difficulty efficiently collecting large amounts of information and providing appropriate advice based on the analysis results. They also cannot provide advice or make decisions that take into account the user's emotions, and therefore cannot fully meet the needs of users. Furthermore, there is a lack of means to make decisions that take into account the vision of the company or industry, the thinking of the management, and market conditions.

[0264] 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.

[0265] In this invention, the server includes a means for collecting a large amount of information and storing it in a database, a means for preprocessing the stored data, a means for analyzing the preprocessed data using AI technology, a means for generating advice based on the analysis results, a means for recognizing the user's emotions, a means for adjusting the advice based on the recognized emotions, and a means for making decisions taking into account the vision of the company or industry, the thoughts of the management, and the market situation. This enables efficient information collection and analysis, provision of advice taking into account the user's emotions, and decision-making taking into account the vision of the company or industry.

[0266] "Large amounts of information" refers to a wide range of data, including industry information, market conditions, corporate vision, management thinking, and market trends.

[0267] A "database" refers to a system for efficiently storing, managing, and searching collected information.

[0268] "Preprocessing" refers to the process of cleaning and normalizing collected data to convert it into a form suitable for analysis.

[0269] "AI technology" refers to the use of algorithms such as machine learning and deep learning to analyze data and extract patterns and trends.

[0270] "Advice" refers to specific suggestions or instructions provided to the User based on the results of the Analysis.

[0271] "User emotions" refers to the psychological state that can be perceived from the user's tone of voice, facial expressions, choice of words, etc.

[0272] "Means of recognizing emotions" refers to technologies and systems for analyzing user emotions.

[0273] "Means for tailoring advice" refers to technologies or systems for changing the content of the advice provided based on perceived user emotions.

[0274] "Vision for a company or industry" refers to the direction or goals that a company or industry aims for in the future.

[0275] "Management thinking" refers to the strategies and decision-making criteria held by a company's management.

[0276] "Market conditions" refers to current market movements, trends, competitive environment, etc.

[0277] "Decision-making" refers to specific actions or choices made based on collected information, analysis results, and user feelings.

[0278] This invention is a system that efficiently collects large amounts of information and provides appropriate advice based on the analysis results. Furthermore, it is possible to provide advice and make decisions that take into account the user's emotions. A specific embodiment of this system will be described below.

[0279] Data collection and storage

[0280] The server collects data such as industry information and market conditions, and stores it in a database. This data is collected using web scraping tools and APIs (e.g., Google (registered trademark) News API, APIs of various SNS). A relational database such as MySQL or PostgreSQL is used as the database.

[0281] Data Preprocessing

[0282] The server preprocesses the collected data. Preprocessing includes data cleaning (filling missing values, removing outliers) and normalization (scaling the data). Specifically, it uses libraries such as Pandas and NumPy.

[0283] Analyzing data

[0284] The server analyzes the preprocessed data using AI technology. For the analysis, machine learning models (e.g., random forests, support vector machines) and deep learning models (e.g., neural networks) are used. Specifically, TensorFlow and PyTorch are used.

[0285] Generating Advice

[0286] The server generates advice for the user based on the analysis results. It uses a generative AI model (e.g., GPT-3 (registered trademark), BERT) to create advice in natural language. For example, the following prompt sentence is input to the generative AI model:

[0287] Example prompt:

[0288] "What should I consider when bringing a new product to market? I'd like your advice based on historical market data and industry trends."

[0289] Emotion recognition

[0290] The device recognizes emotions from the user's tone of voice, facial expressions, choice of words, etc. Emotion recognition uses OpenCV and Microsoft (registered trademark) Azure (registered trademark) emotion recognition APIs. If the user is feeling stressed, the device takes that information into account when providing advice.

[0291] Tailoring advice based on emotions

[0292] The server receives the emotion recognition results sent from the device and adjusts the advice. If the user is feeling stressed, it adds advice to help them relax. For example, the following prompt sentences are input to the generative AI model:

[0293] Example prompt:

[0294] "What relaxation techniques should we offer our users if they are feeling stressed?"

[0295] Decision support

[0296] The server makes decisions that take into account the company and industry vision, management's thinking, and market conditions. To achieve this, it uses AI technology to implement decision-making algorithms that take these factors into account. For example, when a user starts a new project, it helps them make decisions based on past success stories and market trends.

[0297] In this way, the invention enables efficient information collection and analysis, provides advice that takes into account user emotions, and makes decisions that take into account the vision of the company or industry.

[0298] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0299] Step 1:

[0300] The server collects data such as industry information and market conditions, and stores it in a database. As input, it uses data obtained from web scraping tools and APIs. In concrete terms, the server uses web scraping tools to extract information from websites, and obtains real-time data through the Google News API and APIs of various SNS. As output, the collected data is stored in the database.

[0301] Step 2:

[0302] The server preprocesses the accumulated data. As input, it uses the raw data stored in the database. Specifically, it creates a data frame using Pandas, imputes missing values, and removes outliers. It also scales and normalizes the data using NumPy. As output, it obtains the preprocessed and clean data.

[0303] Step 3:

[0304] The server analyzes the preprocessed data using AI techniques. It uses the preprocessed data as input. Specifically, the server uses TensorFlow to build a neural network model, inputs data to train it, and uses the trained model to predict new data and generate analysis results. The analysis results are obtained as output.

[0305] Step 4:

[0306] The server generates advice for the user based on the analysis results. It uses the analysis results as input. Specifically, the server inputs the prompt sentence into a generative AI model (e.g., GPT-3, BERT) to generate advice. The generated advice is obtained as output.

[0307] Step 5:

[0308] The device recognizes emotions from the user's tone of voice, facial expressions, choice of words, etc. As input, it uses the user's facial expressions and voice captured using a camera and microphone. Specifically, the device calls OpenCV and Microsoft Azure emotion recognition APIs to analyze the user's emotions. The recognized emotion data is obtained as output.

[0309] Step 6:

[0310] The server receives the emotion recognition results sent by the terminal and adjusts the advice. As input, it uses the emotion recognition results and the generated advice. In concrete terms, the server analyzes the emotion recognition results and determines whether the user is feeling stressed. If necessary, it inputs new prompt sentences into the generative AI model to generate advice based on the emotion. As output, it obtains the adjusted advice.

[0311] Step 7:

[0312] The server makes decisions taking into account the company and industry vision, management thinking, and market conditions. As input, it uses data on the company and industry vision, management thinking, and market conditions stored in a database. In concrete terms, the server uses AI technology to implement a decision-making algorithm that takes these factors into account, and helps users make optimal decisions. The result of the decision is obtained as output.

[0313] (Application example 1)

[0314] 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 device 14 will be referred to as a "terminal."

[0315] Conventional information sorting and analysis systems are required to efficiently process large amounts of data and provide appropriate advice to users. However, these systems cannot take into account the emotions of users, making it difficult to provide personalized advice or make decisions. In addition, in physical stores, there is a need to analyze customer emotions, purchase history, and market trends in real time to provide optimal product suggestions and services, but current systems have difficulty achieving this.

[0316] 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.

[0317] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions taking into account the vision of the company or industry, the thinking of the management, and the market situation, an emotion engine for recognizing the emotions of the user, a means for giving advice and making decisions based on the emotion information recognized by the emotion engine, and a means for analyzing the emotions, purchase history, and market trends of customers in real time using a smart device and providing optimal product proposals and services. This enables personalized advice and decision-making that takes into account the emotions of the user, and makes it possible to provide optimal product proposals and services to customers in real time even in physical stores.

[0318] "Means of organizing and analyzing large amounts of information" refers to technologies that use databases and AI technology to efficiently process, organize, and analyze huge amounts of data such as industry information and market conditions.

[0319] "Means for providing advice" refers to technology for providing optimal advice to users based on organized and analyzed data.

[0320] "A means of making decisions that take into account the vision of a company or industry, the thinking of management, and market conditions" is a technique for making optimal decisions by taking into account the long-term goals of a company or industry, the thinking of management, and market trends.

[0321] The "emotion engine that recognizes the user's emotions" is a technology that recognizes emotions from the user's tone of voice, facial expressions, choice of words, etc.

[0322] The "means for providing advice or making decisions based on emotional information recognized by an emotion engine" is a technology for providing advice or making decisions by taking into account the emotional information of a user recognized by an emotion engine.

[0323] "A means of using smart devices to analyze customer sentiment, purchasing history, and market trends in real time, and to provide optimal product proposals and services" refers to technology that uses smart glasses or other smart devices to analyze customer sentiment, purchasing history, and market trends in real time, and propose optimal products and services.

[0324] A system for carrying out this invention has the following configuration: The server includes means for organizing and analyzing large amounts of information, means for providing advice, means for making decisions taking into account the vision of the company or industry, the thinking of the management, and market conditions, an emotion engine for recognizing the emotions of users, means for giving advice and making decisions based on the emotion information recognized by the emotion engine, and means for analyzing customer emotions, purchase history, and market trends in real time using smart devices to provide optimal product proposals and services.

[0325] Hardware and Software Configuration

[0326] 1. Hardware:

[0327] Smart devices: Smart glasses (e.g. Google Glass (registered trademark))

[0328] Server: A high-performance server to host the database and AI models

[0329] 2. Software:

[0330] Database Management System: A database management system such as MySQL

[0331] AI models: Machine learning frameworks such as TensorFlow

[0332] Emotion Recognition Engine: Emotion Recognition Software

[0333] Data processing and calculation

[0334] The server receives the data sent from the smart device and performs the following processes.

[0335] 1. Data collection:

[0336] The smart glasses use a camera and microphone to capture a customer's facial expressions and tone of voice in real time.

[0337] 2. Data transmission:

[0338] Send the captured data to the server.

[0339] 3. Data Analysis:

[0340] An AI model on the server analyzes customer sentiment and compares it with purchasing history and market trends stored in a database.

[0341] 4. Advice Generation:

[0342] Based on the analysis results, the AI ​​model generates optimal product suggestions and services.

[0343] 5. Results display:

[0344] Advice and suggestions for store clerks are shown on the smart glasses display.

[0345] Examples

[0346] For example, if the emotion engine detects that a customer is feeling stressed, the AI ​​will suggest products that have a relaxing effect (e.g., aromatic candles or relaxation items). Conversely, if a customer is feeling happy, the AI ​​will suggest products that will enhance that emotion (e.g., luxury chocolates or gift sets).

[0347] Examples of prompt statements

[0348] An example of a prompt to be input to the generative AI model is as follows:

[0349] Recognize your customer's emotions and suggest the best products considering their purchase history and market trends. If they're stressed, suggest products that will relax them, if they're happy, suggest products that will enhance that emotion.

[0350] In this way, customer service in physical stores can be made more personalized, improving customer satisfaction.

[0351] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0352] Step 1:

[0353] The smart device (smart glasses) captures the customer's facial expressions and tone of voice in real time. The input is video and audio data obtained from the camera and microphone of the smart glasses. The output is the captured video and audio data.

[0354] Step 2:

[0355] The smart device sends the captured video and audio data to the server. The input is the video and audio data obtained in step 1. The output is the data sent to the server.

[0356] Step 3:

[0357] The server inputs the received video and audio data into an emotion recognition engine to analyze the customer's emotions. The input is the video and audio data sent in step 2. The output is the emotion information analyzed by the emotion recognition engine.

[0358] Step 4:

[0359] The server compares the emotion information obtained from the emotion recognition engine with the purchase history and market trend data stored in the database. The input is the emotion information obtained in step 3 and the purchase history and market trend data in the database. The output is the comparison result.

[0360] Step 5:

[0361] The server uses the AI ​​model to generate optimal product proposals and services based on the matching results. The input is the matching results obtained in step 4. The output is the generated product proposal or service information.

[0362] Step 6:

[0363] The server transmits the generated product proposal or service information to the smart device. The input is the product proposal or service information generated in step 5. The output is the information transmitted to the smart device.

[0364] Step 7:

[0365] The smart device displays the received product proposal or service information to the store clerk. The input is the product proposal or service information sent in step 6. The output is the information displayed on the display of the smart device.

[0366] In this way, customer service in physical stores can be made more personalized, improving customer satisfaction.

[0367] Example 2

[0368] Next, a second embodiment of the second embodiment will be described. 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."

[0369] In the modern business environment, companies and individuals need to quickly and accurately organize and analyze large amounts of information to make appropriate decisions. However, due to the sheer volume and complexity of information, it is difficult to organize information and make decisions efficiently using traditional methods. In addition, there is a demand for advice that takes into account the user's emotions, but there is no effective system to achieve this. Furthermore, there is a lack of means to analyze data using generative AI models or to start processing by inputting prompt sentences, making it difficult to respond flexibly to user needs.

[0370] 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.

[0371] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions taking into account the vision of the company or industry, the manager's thinking, and the market situation, a means for recognizing the user's emotions, a means for adjusting the advice based on the recognition results, a means for analyzing data using a generative AI model, and a means for starting processing using a prompt sentence as input. This enables the user to efficiently organize and analyze a large amount of information and receive appropriate advice that takes emotions into consideration. In addition, advanced data analysis using a generative AI model and flexible responses using a prompt sentence as input are possible.

[0372] "Means of organizing and analyzing large amounts of information" refers to techniques for collecting, classifying, organizing, and analyzing huge amounts of data using databases and data analysis tools.

[0373] "Means for providing advice" refers to technology that generates and provides advice to encourage users to take optimal actions and make optimal decisions based on organized and analyzed data.

[0374] "A means of making decisions that take into account the vision of the company and industry, the thinking of management, and market conditions" is a technique for making optimal decisions by taking into account the company's long-term goals, the strategic thinking of management, and current market trends.

[0375] "Means of recognizing user emotions" refers to technology for analyzing and recognizing emotions from user behavior patterns and the content of social media posts.

[0376] The "means for adjusting advice based on the recognition results" refers to a technology that appropriately changes the content and method of advice provided based on the recognized user's emotions.

[0377] "Means of analyzing data using generative AI models" refers to techniques that use AI technologies such as machine learning and deep learning to analyze data and extract patterns and trends.

[0378] "Means for starting processing using a prompt sentence as input" refers to a technique that enables a system to start appropriate processing based on the text (prompt sentence) entered by the user.

[0379] This invention is a system implemented by combining the elements of a server, a terminal, and a user. Specific hardware and software configurations and the roles of each will be described below.

[0380] Hardware and Software Used

[0381] Server: A high-performance database server (e.g. MySQL, PostgreSQL)

[0382] Device: PC or smartphone used by the user

[0383] Software: AI technology (e.g. TensorFlow, PyTorch), emotion engine (e.g. IBM Watson(R), Microsoft Azure Emotion API)

[0384] Specific operation of the system

[0385] Data Acquisition

[0386] The server retrieves data from the database about the market situation, competitors' trends, and the company's product development direction that the user desires. For example, the server connects to a MySQL database and retrieves the latest data from the "Market Trends" table using a SQL query. Specifically, it executes the query SELECT FROM Market Trends WHERE Date = CURDATE();

[0387] Data organization and analysis

[0388] The server organizes and analyzes the acquired data using AI technology. For example, the server uses TensorFlow to cluster competitor trend data. Specifically, the K-means clustering algorithm is used to classify the data into several clusters. As a code example, run kmeans = KMeans(n_clusters=5).fit(competitor data).

[0389] Advice Generation

[0390] The server generates optimal advice based on the results of the analysis and sends it to the terminal. For example, the server uses PyTorch to build a predictive model for the direction of product development. Specifically, it trains the predictive model using a neural network and provides the results to the user. As a code example, run model = NeuralNetwork().train(product development data).

[0391] emotion recognition

[0392] The server uses an emotion engine to recognize the user's emotions. For example, the server uses IBM Watson to analyze emotions from the user's SNS posts. Specifically, it executes emotion_analysis = watson.analyze(text=user's SNS post).

[0393] Advice adjustment based on emotions

[0394] The server adjusts advice based on the recognized emotions to support decision-making. For example, if the user is feeling anxious, the server takes that information into account and provides advice to reduce risk. Specifically, the server performs a conditional branch as follows: if emotion_analysis['emotion'] == 'fear': advice = 'We recommend that you take measures to reduce risk.'

[0395] Examples

[0396] Examples of prompt statements

[0397] "A manufacturing businessperson is looking for advice on the market situation, competitor trends, and the direction of their own product development. Please obtain the latest market trend data and competitor trend data and analyze them using AI technology. Also, please recognize the emotions of users from their social media posts and adjust your advice based on the results."

[0398] In this way, the server provides optimal advice to support the user's decision making.

[0399] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0400] Step 1:

[0401] Data Acquisition

[0402] The server retrieves data related to the market conditions desired by the user, the trends of competitors, and the direction of the company's product development from the database.

[0403] Input: A prompt statement specified by the user (e.g., "Please provide data on the market situation, competitor trends, and product development direction of your company.")

[0404] What happens: The server connects to the MySQL database and retrieves the latest data from the "Market Trends" table using the SQL query SELECT FROM Market Trends WHERE Date = CURDATE();

[0405] Output: Obtained market trend data

[0406] Step 2:

[0407] Data organization and analysis

[0408] The server organizes and analyzes the acquired data using AI technology.

[0409] Input: Obtained market trend data

[0410] Specific operation: The server uses TensorFlow to cluster the competitor trend data. Specifically, it uses the K-means clustering algorithm to classify the data into several clusters. For example code, run kmeans = KMeans(n_clusters=5).fit(competitor data).

[0411] Output: Clustered competitor behavior data

[0412] Step 3:

[0413] Advice Generation

[0414] The server generates optimal advice based on the results of the organization and analysis and sends it to the terminal.

[0415] Input: Clustered competitor behavior data

[0416] Specific operation: The server uses PyTorch to build a predictive model for the direction of product development. Specifically, it uses a neural network to train the predictive model and provides the results to the user. For example code, run model = NeuralNetwork().train(product development data).

[0417] Output: Generated advice

[0418] Step 4:

[0419] emotion recognition

[0420] The server uses an emotion engine to recognize the user's emotions.

[0421] Input: User's social media posts

[0422] Specific operation: The server uses IBM Watson to analyze emotions from the content of the user's SNS posts. Specifically, it executes emotion_analysis = watson.analyze(text=user's SNS post).

[0423] Output: Recognized user emotion data

[0424] Step 5:

[0425] Advice adjustment based on emotions

[0426] The server then tailors advice based on the emotions it recognizes to support decision-making.

[0427] Input: Recognized user emotion data, generated advice

[0428] Specific behavior: If the user feels anxious, the server takes that information into account and provides advice to reduce the risk. Specifically, it performs the following conditional branch: if emotion_analysis['emotion'] == 'fear': advice = 'We recommend that you take measures to reduce the risk.'

[0429] Output: Adjusted advice

[0430] (Application example 2)

[0431] 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."

[0432] In the modern manufacturing industry, it is extremely important for businesspeople to receive prompt and accurate advice about market conditions, competitor trends, and the direction of their own company's product development. However, it is difficult to organize and analyze vast amounts of information and make decisions that take into account the emotions of users. In particular, there is no system that provides advice that reflects the emotions of factory managers and workers. For this reason, a system that combines information organization and analysis with emotion recognition is needed.

[0433] 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.

[0434] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions that take into account the vision of the company or industry, the thoughts of the management, and the market situation, a means including an emotion engine for recognizing the emotions of the user, a means for acquiring and analyzing market data and information on competitors in real time, and a means for recognizing the emotions of factory managers and workers and reflecting the results in advice and decision-making. This enables business people to receive prompt and accurate advice on the market situation, the trends of competitors, and the direction of their own product development. Furthermore, since decisions can be made taking into account the emotions of the user, more appropriate advice can be provided.

[0435] "Means of organizing and analyzing large amounts of information" refers to a method for collecting huge amounts of data, organizing it systematically, and analyzing it using advanced algorithms.

[0436] The "means for providing advice based on the results of the organization and analysis" refers to a means for generating and providing optimal advice to a user based on the organized and analyzed data.

[0437] "A means of making decisions that take into account the vision of the company and the industry, the thinking of management, and market conditions" is a means for making optimal decisions by taking into account the company's long-term goals, the intentions of management, and the current market conditions.

[0438] "Means including an emotion engine that recognizes user emotions" refers to means for analyzing emotions from users' actions, comments, and social media posts, and reflecting the results in the system.

[0439] "Means of obtaining and analyzing market data and competitor information in real time" refers to means of collecting market information and competitor trends in real time from the Internet and other data sources and analyzing this information.

[0440] "Means of recognizing the emotions of factory managers and workers and reflecting the results in advice and decision-making" refers to a means of analyzing the emotions of managers and workers in a factory and providing advice and decision-making based on the results.

[0441] The system for carrying out the present invention is configured as follows: The server includes a means for organizing and analyzing large amounts of information, a means for providing advice based on the results of the organization and analysis, a means for making decisions taking into account the vision of the company or industry, the thoughts of the management, and the market situation, a means including an emotion engine for recognizing the emotions of users, a means for acquiring and analyzing market data and information on competitors in real time, and a means for recognizing the emotions of factory managers and workers and reflecting the results in advice and decision-making.

[0442] Program processing explanation

[0443] The server first retrieves market data and competitor information in real time from the internet and other data sources. This data is retrieved from an API using the requests library. Then, an AI model is used to organize and analyze the retrieved data. This AI model is implemented, for example, using a pipeline from the transformers library.

[0444] To recognize user emotions, the emotion engine analyzes the content of social media posts and behavioral patterns. This analysis uses emotion analysis models from the transformers library. The emotion engine extracts emotions from user text and reflects the results in the system.

[0445] As a concrete example, consider a factory manager who is anxious about introducing a new product line. In this case, the emotion of "anxiety" is recognized from the manager's social media posts and behavioral patterns. Taking this emotion into account, the server generates advice that suggests measures to minimize risk.

[0446] Examples and prompts

[0447] As a concrete example, the following scenario can be considered.

[0448] Market Data: {"market_share": "20%"}

[0449] Competitor information: {"trends": "Increased introduction of new product lines"}

[0450] User text: "I'm nervous about introducing a new product line."

[0451] An example of a prompt is as follows:

[0452] user_text = "I'm nervous about introducing a new product line."

[0453] emotion = analyze_emotion(user_text)[0]['label']

[0454] In this way, a system can be built in which the server analyzes market conditions and competitors' activities, recognizes the emotions of managers and workers using an emotion engine, and provides optimal advice.

[0455] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0456] Step 1:

[0457] The server retrieves market data and competitor information in real time from the internet and other data sources. Specifically, it retrieves data from APIs using the requests library. The input for this step is the API endpoint and the output is the market data and competitor information.

[0458] Step 2:

[0459] The server organizes and analyzes the acquired market data and competitor information. Specifically, it analyzes the data using an AI model. For this analysis, it uses the pipeline from the transformers library. The input for this step is the market data and competitor information, and the output is the organized and analyzed data.

[0460] Step 3:

[0461] The server uses an emotion engine to recognize the user's emotions. Specifically, it analyzes the user's social media posts and behavioral patterns to extract emotions. For this analysis, it uses a sentiment analysis model from the transformers library. The input for this step is the user's text data, and the output is the recognized emotion.

[0462] Step 4:

[0463] The server generates advice based on the organized and analyzed data and the recognized emotions. Specifically, it uses an AI model to generate optimal advice. The input of this step is the organized and analyzed data and the recognized emotions, and the output is the generated advice.

[0464] Step 5:

[0465] The server provides the generated advice to the user, specifically, by sending the advice to the user's terminal. The input of this step is the generated advice, and the output is the advice provided to the user.

[0466] Step 6:

[0467] The user makes a decision based on the advice provided, such as introducing a new product line. The input of this step is the advice provided, and the output is the user's decision.

[0468] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0469] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0470] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0471] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0472] [Second embodiment]

[0473] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0474] 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.

[0475] 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 wide area network (WAN) and / or a local area network (LAN).

[0476] 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.

[0477] 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 the voice according to instructions from the processor 46.

[0478] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0479] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0480] Fig. 4 shows an example of 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.

[0481] 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.

[0482] 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.

[0483] 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.

[0484] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0485] "Example 1"

[0486] The system of the present invention uses a database and AI technology as a means for organizing and analyzing large amounts of information. Specifically, data such as industry information and market conditions is stored in the database, and AI technology is used to organize and analyze this data. In addition, as a means for providing advice, optimal advice is provided to users based on data organized and analyzed using AI technology. Furthermore, as a means for making decisions that take into account the vision of the company or industry, the thinking of the management, and the market conditions, these elements are stored as data in a database, and AI technology is used to make decisions that take these elements into consideration.

[0487] "Example 2"

[0488] As a specific example of use, if a manufacturing businessperson requests advice on market conditions, competitor trends, or the direction of their own company's product development, the system will retrieve this information from the database and use AI technology to organize and analyze it. Based on the results, it will provide optimal advice and support decision-making that takes into account the vision, management thinking, and market conditions.

[0489] The process flow of each embodiment will be described below.

[0490] "Example 1"

[0491] Step 1: The user makes a request to the system for information organization and decision-making. This request may be about information such as the market situation in a particular industry, the trends of competitors, or the direction of the company's product development.

[0492] Step 2: The system retrieves the required information from a database, which contains industry information, market conditions, and other data.

[0493] Step 3: The acquired information is organized and analyzed using AI technology. This analysis uses technologies such as machine learning and deep learning.

[0494] Step 4: Based on the analysis results, provide the user with optimal advice, which will help the user organize information and make decisions.

[0495] "Example 2"

[0496] Step 1: A manufacturing business person asks the system for advice on market conditions, competitor trends, and their company's product development direction.

[0497] Step 2: The system retrieves this information from the database and organizes and analyzes it using AI technology.

[0498] Step 3: Based on the analysis results, provide the businessperson with the best advice possible. This advice will help the businessperson make decisions about the market situation, the trends of competitors, and the direction of their own product development.

[0499] Example 1

[0500] 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".

[0501] In today's business environment, it is extremely important to efficiently organize and analyze large amounts of information and provide appropriate advice based on the results. However, in conventional systems, data collection, preprocessing, analysis, advice generation, and decision-making support are carried out separately, and there is no integrated system, making efficient information processing and decision-making difficult. In addition, there is a lack of support for making decisions that comprehensively take into account the company or industry vision, management thinking, and market conditions.

[0502] 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.

[0503] In this invention, the server includes a means for collecting data such as industry information and market conditions and storing the data in a database, a means for preprocessing the stored data, a means for analyzing the preprocessed data using a machine learning model, a means for generating optimal advice for users based on the analysis results, and a means for supporting decision-making that takes into account the vision of the company or industry, the thinking of the management, and the market conditions, thereby enabling efficient information processing and integrated decision-making support.

[0504] "Industry intelligence" refers to data and knowledge related to a particular industry, including market trends, competitor actions, and technological innovations.

[0505] "Market conditions" refers to data that describes the current state or trends in a particular market, including supply and demand, price trends, and consumer behavior.

[0506] A "database" is a system for efficiently storing, managing, and searching data, and includes relational database management systems (RDBMS).

[0507] "Preprocessing" is the process of formatting data before data analysis, filling in missing values, removing outliers, normalizing the data, etc.

[0508] A "machine learning model" refers to an algorithm or mathematical model that learns patterns and rules from data and makes predictions or classifications.

[0509] "Analysis" is the process of using data to find patterns and trends and extract meaningful information.

[0510] "Advice" refers to specific suggestions or instructions provided to the user based on the results of the analysis.

[0511] A "vision" indicates the direction or goals that a company or industry aims for in the future.

[0512] "Management thinking" refers to the strategic thinking and decision-making criteria held by company managers.

[0513] "Decision support" is the process of providing assistance to users to make optimal decisions based on data and analysis results.

[0514] This invention is a system that efficiently organizes and analyzes large amounts of information and provides appropriate advice based on the results. A specific embodiment of this system will be described below.

[0515] Data collection and storage

[0516] The server collects data such as industry information and market conditions from the Internet and internal data sources within the company. Specifically, it uses web scraping technology to obtain data from news sites and market research reports. The collected data is stored in a relational database such as MySQL or PostgreSQL.

[0517] Data Preprocessing

[0518] The server preprocesses the accumulated data. Specifically, it complements missing values, removes outliers, normalizes data, etc. It uses Python's pandas library to manipulate the data in data frame format and perform preprocessing.

[0519] Analyzing data

[0520] The server then uses the pre-processed data to perform analytics. It uses machine learning libraries such as TensorFlow and PyTorch to analyze the data for patterns and trends. For example, it uses time-series data to build models that forecast market movements.

[0521] Generating Advice

[0522] The server generates optimal advice for the user based on the analysis results. When the user enters a specific question as a prompt, the server retrieves relevant data and uses the AI ​​model to generate advice.

[0523] Decision support

[0524] The server supports decision-making by taking into account the vision of the company or industry, the thinking of the management, and market conditions. These elements are stored in a database, and AI technology is used to provide information for optimal decision-making.

[0525] Examples and prompts

[0526] Examples

[0527] If a user wants to know when a new product will be released to the market, they can input a prompt like this into the generative AI model:

[0528] Examples of prompt statements

[0529] "What is the best time to bring a new product to market? Please provide an analysis based on current market conditions and historical data."

[0530] Once this prompt is entered, the server will retrieve relevant data from the database, use an AI model to analyze the optimal timing, and provide advice to the user.

[0531] In this way, a system is realized that enables efficient information processing and integrated decision-making support.

[0532] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0533] Step 1:

[0534] Data collection and storage

[0535] The server collects data such as industry information and market conditions from the Internet and internal company data sources. Specifically, it uses web scraping technology to obtain data from news sites and market research reports. Inputs include URLs and API endpoints to be collected. Outputs include the collected data stored in JSON or CSV format. The server periodically runs scheduled jobs to retrieve new data from specified data sources and insert it into the database.

[0536] Step 2:

[0537] Data Preprocessing

[0538] The server preprocesses the accumulated data, i.e., imputing missing values, removing outliers, normalizing data, etc. The input includes raw data read from the database. The output is clean preprocessed data. The server executes the preprocessing script, reads the data from the database, performs the necessary preprocessing, and saves it back to the database.

[0539] Step 3:

[0540] Analyzing data

[0541] The server performs analysis using the preprocessed data. It uses machine learning libraries such as TensorFlow and PyTorch to analyze the data for patterns and trends. The input includes the preprocessed data. The output is an analysis or predictive model. The server trains the machine learning model, evaluates it, and stores the trained model in a database.

[0542] Step 4:

[0543] Generating Advice

[0544] The server generates optimal advice for the user based on the analysis results. When the user inputs a specific question as a prompt, the server retrieves relevant data and generates advice using an AI model. The input includes the prompt from the user. The output is the generated advice provided to the user. In concrete terms, when a user inputs a prompt such as "What is the best timing to launch a new product on the market?", the server retrieves market trend data, calculates the optimal timing using an AI model, and returns the result to the user.

[0545] Step 5:

[0546] Decision support

[0547] The server supports decision-making that takes into account the company and industry vision, the management's thinking, and market conditions. These elements are stored in a database and provide information for optimal decision-making using AI technology. Inputs include data on the company and industry vision, the management's thinking, and market conditions. Outputs generate specific proposals and strategies to support decision-making. In concrete terms, when a manager considers a new business strategy, the server proposes an optimal strategy based on past data and market trends. For example, when a prompt such as "Please tell me the risks and benefits of entering a new market" is entered, the server analyzes the relevant data, evaluates the risks and benefits, and provides the results.

[0548] (Application example 1)

[0549] 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".

[0550] Inventory management and optimization at logistics centers are important issues for efficient operation. Conventional methods do not adequately monitor inventory status in real time or forecast demand, resulting in inventory shortages and surpluses. In addition, calculations for efficient picking routes are often done manually, which reduces work efficiency. To solve these issues, an advanced system that utilizes databases and AI technology is needed.

[0551] 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. In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions taking into account the vision of the company or industry, the manager's thinking, and the market situation, a means for supporting inventory management and optimization in the logistics center, a means for forecasting demand, a means for proposing the optimal timing and amount of inventory replenishment, and a means for calculating and instructing an efficient picking route. This enables efficient and optimized inventory management in the logistics center.

[0552] "Means of organizing and analyzing large amounts of information" refers to a method of systematically organizing and analyzing large amounts of data, such as industry information and market conditions, using databases and AI technology.

[0553] "Means for providing advice based on the results of the organization and analysis" refers to a method for providing optimal advice to users based on the organized and analyzed data.

[0554] "A means of making decisions that take into account the vision of the company or industry, the thinking of management, and market conditions" is a method for making optimal decisions by taking into account the long-term goals of the company or industry, the thinking of management, and market trends.

[0555] The "means for supporting inventory management and optimization in logistics centers" refers to a method for monitoring inventory status within a logistics center in real time and achieving efficient inventory management and optimization.

[0556] A "demand forecasting means" is a method for predicting future demand based on past data and market conditions.

[0557] The "means for proposing optimal inventory replenishment timing and amount" is a method for proposing optimal inventory replenishment timing and amount based on a demand forecast.

[0558] The "means for calculating and instructing an efficient picking route" is a method for calculating an efficient picking route within a logistics center and instructing the worker on the route.

[0559] This invention is a system that supports inventory management and optimization in a logistics center. The system operates in cooperation with a server, a terminal, and a user.

[0560] Server Roles

[0561] The server includes a means for organizing and analyzing large amounts of information, a means for providing advice based on the results of that organization and analysis, and a means for making decisions that take into account the vision of the company or industry, the thinking of the management, and market conditions. Specifically, it performs the following processes:

[0562] 1. Database management: The server accumulates data on inventory in the distribution center, past sales data, market situation data, etc. in a database. For this purpose, a database management system such as MySQL or PostgreSQL is used.

[0563] 2. Training the AI ​​model: The server trains the demand forecasting model based on the accumulated data, using the Python Scikit-learn library.

[0564] 3. Demand forecasting: Using trained AI models to predict future demand, which helps prevent shortages and overstocks.

[0565] 4. Inventory replenishment proposal: Calculate and propose the optimal timing and amount of inventory replenishment based on the results of demand forecasting.

[0566] 5. Picking route optimization: Calculates efficient picking routes within the distribution center and provides instructions to workers.

[0567] Terminal Roles

[0568] The terminals are smartphones or tablets used by workers in the logistics center. The terminals receive instructions from the server and display them to the workers. Specifically, they perform the following processes:

[0569] 1. View inventory status: View inventory status in real time.

[0570] 2. Displaying the results of the demand forecast: Displaying the results of the demand forecast and providing information to workers.

[0571] 3. Inventory replenishment instructions: Displays the optimal timing and amount of inventory replenishment and gives instructions to workers.

[0572] 4. Picking route instructions: Displays efficient picking routes and instructs workers on them.

[0573] User Roles

[0574] The users are the managers and workers of the logistics center. They receive instructions from the server through their terminals and perform the actual work. Specifically, they perform the following processes:

[0575] 1. Inventory management: Check stock status in real time and replenish stock as needed.

[0576] 2. Check the demand forecast: Check the results of the demand forecast and perform appropriate inventory management.

[0577] 3. Picking: Pick products by following efficient picking routes.

[0578] Examples

[0579] For example, if the inventory of "Product A" is decreasing at a logistics center, the server will predict that demand for "Product A" will increase in the following week based on past sales data and market conditions. As a result, the server will calculate the optimal timing and amount of inventory replenishment and send instructions to the terminal. Workers receive these instructions through their terminals and replenish inventory at the appropriate time. In addition, efficient picking routes are also displayed on the terminals, allowing workers to perform picking work efficiently.

[0580] Examples of prompt statements

[0581] "In order to optimize inventory management at distribution centers, please develop an application that predicts demand based on past sales data and market conditions, and suggests the optimal timing and amount of inventory replenishment."

[0582] By inputting this prompt into a generative AI model, more specific application designs and improvement suggestions can be obtained.

[0583] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0584] Step 1:

[0585] The server accumulates inventory data, past sales data, and market status data from the logistics center in a database. Specifically, it collects data in real time from each sensor and terminal in the logistics center and stores it in a database management system such as MySQL or PostgreSQL. The input is various data (inventory data, sales data, market status data), and the output is the data accumulated in the database.

[0586] Step 2:

[0587] The server trains a demand forecasting model based on the accumulated data. Specifically, it uses Python's Scikit-learn library to build a demand forecasting model using past sales data and market status data as input. The input is the past sales data and market status data accumulated in the database, and the output is the trained demand forecasting model.

[0588] Step 3:

[0589] The server uses the trained demand forecasting model to forecast future demand. Specifically, the server applies the demand forecasting model to future market situation data as input to obtain a demand forecast result. The input is future market situation data, and the output is the demand forecast result.

[0590] Step 4:

[0591] The server calculates and proposes the optimal timing and amount of inventory replenishment based on the results of the demand forecast. Specifically, it generates an optimal inventory replenishment plan using the demand forecast results and current inventory data as input. The inputs are the demand forecast results and current inventory data, and the output is the inventory replenishment plan.

[0592] Step 5:

[0593] The server calculates the most efficient picking route within the distribution center and instructs the workers. Specifically, it inputs the current inventory location data and the picking list, calculates the shortest route, and sends instructions to the terminal. The input is the inventory location data and the picking list, and the output is the optimal picking route.

[0594] Step 6:

[0595] The terminal receives instructions from the server and displays them to the worker. Specifically, it displays the inventory status, demand forecast results, inventory replenishment plans, and picking routes in real time. The input is instruction data from the server, and the output is information to be displayed to the worker.

[0596] Step 7:

[0597] The user receives instructions from the server through the terminal and performs the actual work. Specifically, the user performs inventory management, checking demand forecasts, replenishing stock, and picking work. The input is instruction information from the terminal, and the output is the actual work results.

[0598] Example 2

[0599] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0600] In today's business environment, it is extremely important for companies and individuals to efficiently organize and analyze large amounts of information and make appropriate decisions. However, due to the sheer volume and complexity of information, doing this manually is difficult and requires time and effort. In addition, specialized knowledge and experience are required to obtain appropriate advice, which is also a hurdle for many people. Therefore, there is a demand for a system that can efficiently organize and analyze information and provide appropriate advice.

[0601] 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.

[0602] In this invention, the server includes a means for a user to input a prompt sentence, a means for a terminal to transmit the input prompt sentence to the server, a means for the server to obtain related information from a database, a means for the server to organize and clean the obtained data, a means for the server to analyze the data using a generative AI model, a means for the server to generate advice based on the analysis results, a means for the server to transmit the generated advice to the terminal, a means for the terminal to display advice to the user, and a means for making decisions taking into account the vision of the company or industry, the thinking of the management, and market conditions. This enables the user to efficiently organize and analyze large amounts of information and obtain appropriate advice.

[0603] A "User" is any individual or entity that utilizes the System to input information and receive advice.

[0604] A "prompt sentence" is text that a user enters to ask the system a specific question or for advice.

[0605] A "terminal" is a device through which a user enters prompt statements and receives advice from a server.

[0606] "Server" means a computer system that retrieves information from a database, organizes and analyzes the data, generates advice, and sends it to the terminal.

[0607] A "database" is a collection of information that a server accesses to obtain information.

[0608] A "generative AI model" is an artificial intelligence technique used by the server to analyze data and generate advice.

[0609] "Advice" refers to instructions or suggestions provided to the user based on the results of analysis performed by the server using a generative AI model.

[0610] A "vision" is the direction or goal that a company or industry aims for in the future.

[0611] "Executive thinking" refers to the strategic thinking and decision-making standards held by company executives.

[0612] "Market conditions" refers to the current trends and environment in a particular industry or market.

[0613] A "decision" is a choice or judgment made by a user based on advice provided.

[0614] This invention is a system in which a user inputs a prompt sentence, a server retrieves information from a database, analyzes the data using a generative AI model, generates advice, and provides it to the user. A specific embodiment of this system will be described below.

[0615] First, the user uses a terminal to input a prompt, which is text that the user enters to ask the system a specific question or request advice, such as "Please advise me on the market situation and competitor trends for our new product line."

[0616] The terminal then sends the input prompt to the server, using an HTTP request. The server then queries a database to obtain data related to the prompt, including market conditions, competitor trends, and the server's own product development. The database is typically a database management system such as SQL Server.

[0617] The server organizes the acquired data and cleans unnecessary data. Specifically, it uses Python's Pandas library to shape the data and extract the necessary information. The server then inputs the organized data into a generative AI model (for example, OpenAI's GPT-4) to analyze the data. The generative AI model finds trends and patterns in the data and generates analysis results.

[0618] The server generates advice to provide to the user based on the analysis results of the generative AI model. This advice takes into account the company and industry vision, the management's thinking, and the market situation. The generated advice is sent from the server to the terminal. This communication also uses HTTP requests.

[0619] Finally, the terminal displays the advice received from the server to the user, who can then make a decision based on the advice.

[0620] As a concrete example, consider a manufacturing businessperson considering developing a new product line. The user types into the terminal, "Please provide advice on the market situation and competitor trends for the new product line." The terminal sends this prompt text to the server via an HTTP request, and the server queries SQL Server to obtain relevant market data and competitor information. The server uses Python's Pandas library to clean the data and extract the necessary information. The server inputs the data into a generative AI model (GPT-4) to analyze trends and patterns. Based on the analysis results, the server generates advice to provide to the user and sends it to the terminal via an HTTP response. The terminal displays the advice to the user, and the user makes a decision based on it.

[0621] In this way, the system provides optimal advice to users and supports efficient decision-making.

[0622] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0623] Step 1:

[0624] The user enters a prompt sentence.

[0625] Input: The text that the user has a specific question or request for advice (e.g., "Please provide advice on the market situation and competitor behavior for a new product line")

[0626] Output: The prompt is typed into the terminal.

[0627] Specific actions: The user enters a prompt sentence into the input field of the terminal and presses the send button.

[0628] Step 2:

[0629] The terminal sends the prompt text entered to the server.

[0630] Input: The prompt text entered by the user

[0631] Output: The prompt text is sent to the server as an HTTP request.

[0632] Specific operation: The terminal includes the prompt text in the body of an HTTP request and sends it to the specified endpoint of the server.

[0633] Step 3:

[0634] The server retrieves the relevant information from a database.

[0635] Input: Prompt statement (e.g., "Please advise on the market situation and competitor trends for a new product line.")

[0636] Output: Data from the database on market conditions, competitors' activities, and our own product developments.

[0637] Specific behavior: The server generates an SQL query based on the prompt statement and sends it to the database to retrieve relevant information.

[0638] Step 4:

[0639] Organize and clean the data retrieved by the server.

[0640] Input: Raw data retrieved from the database

[0641] Output: Organized and cleaned data

[0642] What it does: The server uses Python's Pandas library to format the data, remove unnecessary data, and extract the necessary information.

[0643] Step 5:

[0644] The server analyzes the data using a generative AI model.

[0645] Input: Organized and cleaned data

[0646] Output: Analysis results from generative AI models

[0647] What it does: The server feeds the organized data into a generative AI model (e.g. GPT-4) to analyze trends and patterns.

[0648] Step 6:

[0649] The server generates advice based on the analysis results.

[0650] Input: Analysis results from generative AI models

[0651] Output: Advice to give to the user

[0652] Specific operation: Based on the analysis results of the generative AI model, the server generates specific advice to provide to the user.

[0653] Step 7:

[0654] The server transmits the generated advice to the terminal.

[0655] Input: Generated advice

[0656] Output: The advice is sent to the device as an HTTP response.

[0657] Specific operation: The server includes the generated advice in the body of the HTTP response and sends it to the terminal.

[0658] Step 8:

[0659] The terminal displays the advice to the user.

[0660] Input: Advice sent by the server

[0661] Output: Advice displayed to the user

[0662] Specific operation: The device displays the received advice on the user interface so that the user can view it.

[0663] (Application example 2)

[0664] 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".

[0665] In modern manufacturing, there is a need to grasp market conditions, competitor trends, and the direction of one's own product development in real time in order to create optimal manufacturing strategies. However, there are still not enough systems in place that can efficiently collect and analyze this information and provide appropriate advice. As a result, manufacturing business people often have difficulty organizing information and making decisions. To solve this problem, a system that uses AI technology to analyze market data and propose optimal manufacturing strategies is needed.

[0666] 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.

[0667] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organization and analysis, a means for making decisions taking into account the vision of the company or industry, the thinking of the management, and the market situation, a means for collecting and analyzing data on the market situation, the trends of competitors, and the direction of the company's product development, and proposing an optimal manufacturing strategy, a means for inputting a prompt sentence using a generative AI model and generating advice based on the analysis results, and a means for displaying and notifying the advice through an application installed on a factory robot. This enables business people in the manufacturing industry to collect and analyze market data in real time and create optimal manufacturing strategies.

[0668] "Means of organizing and analyzing large amounts of information" refers to a function for collecting huge amounts of data, organizing it into an appropriate format, and analyzing it using statistical methods and machine learning algorithms.

[0669] "A means of providing advice based on the results of organization and analysis" is a function for proposing specific courses of action and strategies based on the results of data analysis.

[0670] "A means of making decisions that take into account the vision of the company and the industry, the thinking of management, and market conditions" is a function that allows optimal decision-making by taking into account the company's long-term goals, the intentions of management, and market trends.

[0671] "A means of collecting and analyzing data on market conditions, competitor trends, and the company's own product development direction, and proposing optimal manufacturing strategies" refers to a function that collects market data, competitor information, and the company's own development status in real time, analyzes them, and creates optimal manufacturing plans.

[0672] "A means for inputting a prompt sentence using a generative AI model and generating advice based on the analysis results" refers to a function for inputting a specific prompt sentence to a generative AI model and generating advice based on the resulting analysis results.

[0673] "Means for displaying and notifying advice through an application installed on a factory robot" means a function for visually or audibly displaying and notifying generated advice through software installed on a factory robot.

[0674] A system for carrying out this invention has the following configuration: The server includes means for organizing and analyzing large amounts of information, means for providing advice based on the results of the organization and analysis, means for making decisions taking into account the vision of the company or industry, the thinking of the management, and the market situation, means for collecting and analyzing data on the market situation, the trends of competitors, and the direction of the company's product development, and proposing an optimal manufacturing strategy, means for inputting prompt sentences using a generative AI model and generating advice based on the analysis results, and means for displaying and notifying advice through an application installed on a factory robot.

[0675] Hardware and Software Used

[0676] Hardware: Factory robots, servers, network connections

[0677] Software: Database management systems (e.g. MySQL), AI models (e.g. GPT-4), data analysis tools (e.g. Pandas, NumPy)

[0678] Data processing and calculation flow

[0679] 1. Data collection: The server obtains data on market conditions, competitors' activities, and the company's own product development from a database via the network.

[0680] 2. Data reduction: The server reduces and preprocesses the acquired data using Pandas and NumPy.

[0681] 3. Data analysis: The server inputs the organized data into the AI ​​model (GPT-4) for analysis.

[0682] 4. Advice generation: The server generates optimal manufacturing strategies and advice based on the analysis results.

[0683] 5. Result display: The factory robot displays and notifies the user of advice through a display and voice output.

[0684] Examples

[0685] For example, the following prompt sentence is input to the generative AI model:

[0686] Example prompt:

[0687] Considering the current market situation, competitor trends, and your company's product development direction, please suggest the optimal manufacturing strategy for the next quarter.

[0688] Examples of advice that can be generated include specific manufacturing strategies such as, "Market demand is increasing, so we recommend that you increase production of product A by 20%. Also, your competitor is planning to release a new product B, so you should speed up improving your product C."

[0689] In this way, market analysis advisors for factory robots can support decision-making in manufacturing industries and achieve efficient production.

[0690] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0691] Step 1:

[0692] The server retrieves data on market conditions, competitors' activities, and the company's own product development from the database via the network. The input is market data, competitor information, and in-house development data, and the output is the retrieved raw data. In concrete terms, the server sends a query to the MySQL database to retrieve the required data.

[0693] Step 2:

[0694] The server organizes and preprocesses the acquired data using Pandas and NumPy. The input is raw data, and the output is preprocessed data. Specifically, the server performs operations such as filling in missing values, normalizing data, and deleting unnecessary data.

[0695] Step 3:

[0696] The server inputs the organized data into the AI ​​model (GPT-4) and performs analysis. The input is the preprocessed data, and the output is the analysis result. Specifically, the server generates a prompt sentence for the GPT-4 model and inputs the data.

[0697] Step 4:

[0698] The server generates optimal manufacturing strategies and advice based on the analysis results. The input is the analysis results, and the output is the generated advice. Specifically, the server analyzes the output of the generative AI model and generates specific advice in text format.

[0699] Step 5:

[0700] The factory robot displays and notifies the user of advice through a display and voice output. The input is the generated advice, and the output is the displayed advice. In terms of specific operations, the factory robot displays text on the display and notifies the user by voice if necessary.

[0701] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0702] "Example 1"

[0703] As one embodiment of the present invention, there is a system that combines an emotion engine. This system includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organization and analysis, and a means for making decisions that take into account the vision of the company or industry, the thoughts of the management, and the market situation. It also includes an emotion engine that recognizes the emotions of the user. This emotion engine recognizes emotions from the tone of the user's voice, facial expression, choice of words, etc., and reflects the recognition results in providing advice and making decisions. For example, if it recognizes that the user is feeling stressed, it provides advice taking that information into account. Also, if it recognizes that the user is feeling happy, it makes decisions taking that information into account.

[0704] "Example 2"

[0705] Another embodiment of the present invention is a system that combines an emotion engine. This system includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organization and analysis, and a means for making decisions that take into account the vision of the company or industry, the thoughts of the management, and the market situation. It also includes an emotion engine that recognizes the emotions of the user. This emotion engine recognizes emotions from the user's behavioral patterns and the contents of posts on SNS, and reflects the recognition results in providing advice and making decisions. For example, if it is recognized that the user is feeling anxious, it provides advice taking that information into account. Also, if it is recognized that the user is excited, it makes decisions taking that information into account.

[0706] The process flow of each embodiment will be described below.

[0707] "Example 1"

[0708] Step 1: The system receives input from the user, including the user's tone of voice, facial expressions, and choice of words.

[0709] Step 2: The emotion engine recognizes the user's emotion from the received input information.

[0710] Step 3: The system organizes and analyzes large amounts of information based on the emotion recognition results from the emotion engine.

[0711] Step 4: The system provides advice based on the results of the analysis and analysis, including the emotion recognition results.

[0712] Step 5: The system makes decisions based on the company and industry vision, management's thinking, and market conditions, including the emotion recognition results.

[0713] "Example 2"

[0714] Step 1: The system receives input information from the user, including the user's behavioral patterns and the content of posts on social media.

[0715] Step 2: The emotion engine recognizes the user's emotion from the received input information.

[0716] Step 3: The system organizes and analyzes large amounts of information based on the emotion recognition results from the emotion engine.

[0717] Step 4: The system provides advice based on the results of the analysis and analysis, including the emotion recognition results.

[0718] Step 5: The system makes decisions based on the company and industry vision, management's thinking, and market conditions, including the emotion recognition results.

[0719] Example 1

[0720] 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".

[0721] Conventional information sorting and analysis systems have difficulty efficiently collecting large amounts of information and providing appropriate advice based on the analysis results. They also cannot provide advice or make decisions that take into account the user's emotions, and therefore cannot fully meet the needs of users. Furthermore, there is a lack of means to make decisions that take into account the vision of the company or industry, the thinking of the management, and market conditions.

[0722] 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.

[0723] In this invention, the server includes a means for collecting a large amount of information and storing it in a database, a means for preprocessing the stored data, a means for analyzing the preprocessed data using AI technology, a means for generating advice based on the analysis results, a means for recognizing the user's emotions, a means for adjusting the advice based on the recognized emotions, and a means for making decisions taking into account the vision of the company or industry, the thoughts of the management, and the market situation. This enables efficient information collection and analysis, provision of advice taking into account the user's emotions, and decision-making taking into account the vision of the company or industry.

[0724] "Large amounts of information" refers to a wide range of data, including industry information, market conditions, corporate vision, management thinking, and market trends.

[0725] A "database" refers to a system for efficiently storing, managing, and searching collected information.

[0726] "Preprocessing" refers to the process of cleaning and normalizing collected data to convert it into a form suitable for analysis.

[0727] "AI technology" refers to the use of algorithms such as machine learning and deep learning to analyze data and extract patterns and trends.

[0728] "Advice" refers to specific suggestions or instructions provided to the User based on the results of the Analysis.

[0729] "User emotions" refers to the psychological state that can be perceived from the user's tone of voice, facial expressions, choice of words, etc.

[0730] "Means of recognizing emotions" refers to technologies and systems for analyzing user emotions.

[0731] "Means for tailoring advice" refers to technologies or systems for changing the content of the advice provided based on perceived user emotions.

[0732] "Vision for a company or industry" refers to the direction or goals that a company or industry aims for in the future.

[0733] "Management thinking" refers to the strategies and decision-making criteria held by a company's management.

[0734] "Market conditions" refers to current market movements, trends, competitive environment, etc.

[0735] "Decision-making" refers to specific actions or choices made based on collected information, analysis results, and user feelings.

[0736] This invention is a system that efficiently collects large amounts of information and provides appropriate advice based on the analysis results. Furthermore, it is possible to provide advice and make decisions that take into account the user's emotions. A specific embodiment of this system will be described below.

[0737] Data collection and storage

[0738] The server collects data such as industry information and market conditions, and stores it in a database. This data is collected using web scraping tools and APIs (e.g. Google News API, APIs of various SNS). A relational database such as MySQL or PostgreSQL is used as the database.

[0739] Data Preprocessing

[0740] The server preprocesses the collected data. Preprocessing includes data cleaning (filling missing values, removing outliers) and normalization (scaling the data). Specifically, it uses libraries such as Pandas and NumPy.

[0741] Analyzing data

[0742] The server analyzes the preprocessed data using AI technology. For the analysis, machine learning models (e.g., random forests, support vector machines) and deep learning models (e.g., neural networks) are used. Specifically, TensorFlow and PyTorch are used.

[0743] Generating Advice

[0744] The server generates advice for the user based on the analysis results. It uses a generative AI model (e.g. GPT-3, BERT) to create advice in natural language. For example, the following prompt sentence is input to the generative AI model:

[0745] Example prompt:

[0746] "What should I consider when bringing a new product to market? I'd like your advice based on historical market data and industry trends."

[0747] Emotion recognition

[0748] The device recognizes emotions from the user's tone of voice, facial expressions, choice of words, etc. Emotion recognition uses OpenCV and Microsoft Azure's emotion recognition API. If the user is feeling stressed, the device will provide advice taking that information into account.

[0749] Tailoring advice based on emotions

[0750] The server receives the emotion recognition results sent from the device and adjusts the advice. If the user is feeling stressed, it adds advice to help them relax. For example, the following prompt sentences are input to the generative AI model:

[0751] Example prompt:

[0752] "What relaxation techniques should we offer our users if they are feeling stressed?"

[0753] Decision support

[0754] The server makes decisions that take into account the company and industry vision, management's thinking, and market conditions. To achieve this, it uses AI technology to implement decision-making algorithms that take these factors into account. For example, when a user starts a new project, it helps them make decisions based on past success stories and market trends.

[0755] In this way, the invention enables efficient information collection and analysis, provides advice that takes into account user emotions, and makes decisions that take into account the vision of the company or industry.

[0756] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0757] Step 1:

[0758] The server collects data such as industry information and market conditions, and stores it in a database. As input, it uses data obtained from web scraping tools and APIs. In concrete terms, the server uses web scraping tools to extract information from websites, and obtains real-time data through the Google News API and APIs of various SNS. As output, the collected data is stored in the database.

[0759] Step 2:

[0760] The server preprocesses the accumulated data. As input, it uses the raw data stored in the database. Specifically, it creates a data frame using Pandas, imputes missing values, and removes outliers. It also scales and normalizes the data using NumPy. As output, it obtains the preprocessed and clean data.

[0761] Step 3:

[0762] The server analyzes the preprocessed data using AI techniques. It uses the preprocessed data as input. Specifically, the server uses TensorFlow to build a neural network model, inputs data to train it, and uses the trained model to predict new data and generate analysis results. The analysis results are obtained as output.

[0763] Step 4:

[0764] The server generates advice for the user based on the analysis results. It uses the analysis results as input. Specifically, the server inputs the prompt sentence into a generative AI model (e.g., GPT-3, BERT) to generate advice. The generated advice is obtained as output.

[0765] Step 5:

[0766] The device recognizes emotions from the user's tone of voice, facial expressions, choice of words, etc. As input, it uses the user's facial expressions and voice captured using a camera and microphone. Specifically, the device calls OpenCV and Microsoft Azure emotion recognition APIs to analyze the user's emotions. The recognized emotion data is obtained as output.

[0767] Step 6:

[0768] The server receives the emotion recognition results sent by the terminal and adjusts the advice. As input, it uses the emotion recognition results and the generated advice. In concrete terms, the server analyzes the emotion recognition results and determines whether the user is feeling stressed. If necessary, it inputs new prompt sentences into the generative AI model to generate advice based on the emotion. As output, it obtains the adjusted advice.

[0769] Step 7:

[0770] The server makes decisions taking into account the company and industry vision, management thinking, and market conditions. As input, it uses data on the company and industry vision, management thinking, and market conditions stored in a database. In concrete terms, the server uses AI technology to implement a decision-making algorithm that takes these factors into account, and helps users make optimal decisions. The result of the decision is obtained as output.

[0771] (Application example 1)

[0772] 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".

[0773] Conventional information sorting and analysis systems are required to efficiently process large amounts of data and provide appropriate advice to users. However, these systems cannot take into account the emotions of users, making it difficult to provide personalized advice or make decisions. In addition, in physical stores, there is a need to analyze customer emotions, purchase history, and market trends in real time to provide optimal product suggestions and services, but current systems have difficulty achieving this.

[0774] 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.

[0775] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions taking into account the vision of the company or industry, the thinking of the management, and the market situation, an emotion engine for recognizing the emotions of the user, a means for giving advice and making decisions based on the emotion information recognized by the emotion engine, and a means for analyzing the emotions, purchase history, and market trends of customers in real time using a smart device and providing optimal product proposals and services. This enables personalized advice and decision-making that takes into account the emotions of the user, and makes it possible to provide optimal product proposals and services to customers in real time even in physical stores.

[0776] "Means of organizing and analyzing large amounts of information" refers to technologies that use databases and AI technology to efficiently process, organize, and analyze huge amounts of data such as industry information and market conditions.

[0777] "Means for providing advice" refers to technology for providing optimal advice to users based on organized and analyzed data.

[0778] "A means of making decisions that take into account the vision of a company or industry, the thinking of management, and market conditions" is a technique for making optimal decisions by taking into account the long-term goals of a company or industry, the thinking of management, and market trends.

[0779] The "emotion engine that recognizes the user's emotions" is a technology that recognizes emotions from the user's tone of voice, facial expressions, choice of words, etc.

[0780] The "means for providing advice or making decisions based on emotional information recognized by an emotion engine" is a technology for providing advice or making decisions by taking into account the emotional information of a user recognized by an emotion engine.

[0781] "A means of using smart devices to analyze customer sentiment, purchasing history, and market trends in real time, and to provide optimal product proposals and services" refers to technology that uses smart glasses or other smart devices to analyze customer sentiment, purchasing history, and market trends in real time, and propose optimal products and services.

[0782] A system for carrying out this invention has the following configuration: The server includes means for organizing and analyzing large amounts of information, means for providing advice, means for making decisions taking into account the vision of the company or industry, the thinking of the management, and market conditions, an emotion engine for recognizing the emotions of users, means for giving advice and making decisions based on the emotion information recognized by the emotion engine, and means for analyzing customer emotions, purchase history, and market trends in real time using smart devices to provide optimal product proposals and services.

[0783] Hardware and Software Configuration

[0784] 1. Hardware:

[0785] Smart devices: Smart glasses (e.g. Google Glass)

[0786] Server: A high-performance server to host the database and AI models

[0787] 2. Software:

[0788] Database Management System: A database management system such as MySQL

[0789] AI models: Machine learning frameworks such as TensorFlow

[0790] Emotion Recognition Engine: Emotion Recognition Software

[0791] Data processing and calculation

[0792] The server receives the data sent from the smart device and performs the following processes.

[0793] 1. Data collection:

[0794] The smart glasses use a camera and microphone to capture a customer's facial expressions and tone of voice in real time.

[0795] 2. Data transmission:

[0796] Send the captured data to the server.

[0797] 3. Data Analysis:

[0798] An AI model on the server analyzes customer sentiment and compares it with purchasing history and market trends stored in a database.

[0799] 4. Advice Generation:

[0800] Based on the analysis results, the AI ​​model generates optimal product suggestions and services.

[0801] 5. Results display:

[0802] Advice and suggestions for store clerks are shown on the smart glasses display.

[0803] Examples

[0804] For example, if the emotion engine detects that a customer is feeling stressed, the AI ​​will suggest products that have a relaxing effect (e.g., aromatic candles or relaxation items). Conversely, if a customer is feeling happy, the AI ​​will suggest products that will enhance that emotion (e.g., luxury chocolates or gift sets).

[0805] Examples of prompt statements

[0806] An example of a prompt to be input to the generative AI model is as follows:

[0807] Recognize your customer's emotions and suggest the best products considering their purchase history and market trends. If they're stressed, suggest products that will relax them, if they're happy, suggest products that will enhance that emotion.

[0808] In this way, customer service in physical stores can be made more personalized, improving customer satisfaction.

[0809] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0810] Step 1:

[0811] The smart device (smart glasses) captures the customer's facial expressions and tone of voice in real time. The input is video and audio data obtained from the camera and microphone of the smart glasses. The output is the captured video and audio data.

[0812] Step 2:

[0813] The smart device sends the captured video and audio data to the server. The input is the video and audio data obtained in step 1. The output is the data sent to the server.

[0814] Step 3:

[0815] The server inputs the received video and audio data into an emotion recognition engine to analyze the customer's emotions. The input is the video and audio data sent in step 2. The output is the emotion information analyzed by the emotion recognition engine.

[0816] Step 4:

[0817] The server compares the emotion information obtained from the emotion recognition engine with the purchase history and market trend data stored in the database. The input is the emotion information obtained in step 3 and the purchase history and market trend data in the database. The output is the comparison result.

[0818] Step 5:

[0819] The server uses the AI ​​model to generate optimal product proposals and services based on the matching results. The input is the matching results obtained in step 4. The output is the generated product proposal or service information.

[0820] Step 6:

[0821] The server transmits the generated product proposal or service information to the smart device. The input is the product proposal or service information generated in step 5. The output is the information transmitted to the smart device.

[0822] Step 7:

[0823] The smart device displays the received product proposal or service information to the store clerk. The input is the product proposal or service information sent in step 6. The output is the information displayed on the display of the smart device.

[0824] In this way, customer service in physical stores can be made more personalized, improving customer satisfaction.

[0825] Example 2

[0826] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0827] In the modern business environment, companies and individuals need to quickly and accurately organize and analyze large amounts of information to make appropriate decisions. However, due to the sheer volume and complexity of information, it is difficult to organize information and make decisions efficiently using traditional methods. In addition, there is a demand for advice that takes into account the user's emotions, but there is no effective system to achieve this. Furthermore, there is a lack of means to analyze data using generative AI models or to start processing by inputting prompt sentences, making it difficult to respond flexibly to user needs.

[0828] 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.

[0829] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions taking into account the vision of the company or industry, the manager's thinking, and the market situation, a means for recognizing the user's emotions, a means for adjusting the advice based on the recognition results, a means for analyzing data using a generative AI model, and a means for starting processing using a prompt sentence as input. This enables the user to efficiently organize and analyze a large amount of information and receive appropriate advice that takes emotions into consideration. In addition, advanced data analysis using a generative AI model and flexible responses using a prompt sentence as input are possible.

[0830] "Means of organizing and analyzing large amounts of information" refers to techniques for collecting, classifying, organizing, and analyzing huge amounts of data using databases and data analysis tools.

[0831] "Means for providing advice" refers to technology that generates and provides advice to encourage users to take optimal actions and make optimal decisions based on organized and analyzed data.

[0832] "A means of making decisions that take into account the vision of the company and industry, the thinking of management, and market conditions" is a technique for making optimal decisions by taking into account the company's long-term goals, the strategic thinking of management, and current market trends.

[0833] "Means of recognizing user emotions" refers to technology for analyzing and recognizing emotions from user behavior patterns and the content of social media posts.

[0834] The "means for adjusting advice based on the recognition results" refers to a technology that appropriately changes the content and method of advice provided based on the recognized user's emotions.

[0835] "Means of analyzing data using generative AI models" refers to techniques that use AI technologies such as machine learning and deep learning to analyze data and extract patterns and trends.

[0836] "Means for starting processing using a prompt sentence as input" refers to a technique that enables a system to start appropriate processing based on the text (prompt sentence) entered by the user.

[0837] This invention is a system implemented by combining the elements of a server, a terminal, and a user. Specific hardware and software configurations and the roles of each will be described below.

[0838] Hardware and Software Used

[0839] Server: A high-performance database server (e.g. MySQL, PostgreSQL)

[0840] Device: PC or smartphone used by the user

[0841] Software: AI technology (e.g. TensorFlow, PyTorch), emotion engine (e.g. IBM Watson, Microsoft Azure Emotion API)

[0842] Specific operation of the system

[0843] Data Acquisition

[0844] The server retrieves data from the database about the market situation, competitors' trends, and the company's product development direction that the user desires. For example, the server connects to a MySQL database and retrieves the latest data from the "Market Trends" table using a SQL query. Specifically, it executes the query SELECT FROM Market Trends WHERE Date = CURDATE();

[0845] Data organization and analysis

[0846] The server organizes and analyzes the acquired data using AI technology. For example, the server uses TensorFlow to cluster competitor trend data. Specifically, the K-means clustering algorithm is used to classify the data into several clusters. As a code example, run kmeans = KMeans(n_clusters=5).fit(competitor data).

[0847] Advice Generation

[0848] The server generates optimal advice based on the results of the analysis and sends it to the terminal. For example, the server uses PyTorch to build a predictive model for the direction of product development. Specifically, it trains the predictive model using a neural network and provides the results to the user. As a code example, run model = NeuralNetwork().train(product development data).

[0849] emotion recognition

[0850] The server uses an emotion engine to recognize the user's emotions. For example, the server uses IBM Watson to analyze emotions from the user's SNS posts. Specifically, it executes emotion_analysis = watson.analyze(text=user's SNS post).

[0851] Advice adjustment based on emotions

[0852] The server adjusts advice based on the recognized emotions to support decision-making. For example, if the user is feeling anxious, the server takes that information into account and provides advice to reduce risk. Specifically, the server performs a conditional branch as follows: if emotion_analysis['emotion'] == 'fear': advice = 'We recommend that you take measures to reduce risk.'

[0853] Examples

[0854] Examples of prompt statements

[0855] "A manufacturing businessperson is looking for advice on the market situation, competitor trends, and the direction of their own product development. Please obtain the latest market trend data and competitor trend data and analyze them using AI technology. Also, please recognize the emotions of users from their social media posts and adjust your advice based on the results."

[0856] In this way, the server provides optimal advice to support the user's decision making.

[0857] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0858] Step 1:

[0859] Data Acquisition

[0860] The server retrieves data related to the market conditions desired by the user, the trends of competitors, and the direction of the company's product development from the database.

[0861] Input: A prompt statement specified by the user (e.g., "Please provide data on the market situation, competitor trends, and product development direction of your company.")

[0862] What happens: The server connects to the MySQL database and retrieves the latest data from the "Market Trends" table using the SQL query SELECT FROM Market Trends WHERE Date = CURDATE();

[0863] Output: Obtained market trend data

[0864] Step 2:

[0865] Data organization and analysis

[0866] The server organizes and analyzes the acquired data using AI technology.

[0867] Input: Obtained market trend data

[0868] Specific operation: The server uses TensorFlow to cluster the competitor trend data. Specifically, it uses the K-means clustering algorithm to classify the data into several clusters. For example code, run kmeans = KMeans(n_clusters=5).fit(competitor data).

[0869] Output: Clustered competitor behavior data

[0870] Step 3:

[0871] Advice Generation

[0872] The server generates optimal advice based on the results of the organization and analysis and sends it to the terminal.

[0873] Input: Clustered competitor behavior data

[0874] Specific operation: The server uses PyTorch to build a predictive model for the direction of product development. Specifically, it uses a neural network to train the predictive model and provides the results to the user. For example code, run model = NeuralNetwork().train(product development data).

[0875] Output: Generated advice

[0876] Step 4:

[0877] emotion recognition

[0878] The server uses an emotion engine to recognize the user's emotions.

[0879] Input: User's social media posts

[0880] Specific operation: The server uses IBM Watson to analyze emotions from the content of the user's SNS posts. Specifically, it executes emotion_analysis = watson.analyze(text=user's SNS post).

[0881] Output: Recognized user emotion data

[0882] Step 5:

[0883] Advice adjustment based on emotions

[0884] The server then tailors advice based on the emotions it recognizes to support decision-making.

[0885] Input: Recognized user emotion data, generated advice

[0886] Specific behavior: If the user feels anxious, the server takes that information into account and provides advice to reduce the risk. Specifically, it performs the following conditional branch: if emotion_analysis['emotion'] == 'fear': advice = 'We recommend that you take measures to reduce the risk.'

[0887] Output: Adjusted advice

[0888] (Application example 2)

[0889] 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".

[0890] In the modern manufacturing industry, it is extremely important for businesspeople to receive prompt and accurate advice about market conditions, competitor trends, and the direction of their own company's product development. However, it is difficult to organize and analyze vast amounts of information and make decisions that take into account the emotions of users. In particular, there is no system that provides advice that reflects the emotions of factory managers and workers. For this reason, a system that combines information organization and analysis with emotion recognition is needed.

[0891] 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.

[0892] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions that take into account the vision of the company or industry, the thoughts of the management, and the market situation, a means including an emotion engine for recognizing the emotions of the user, a means for acquiring and analyzing market data and information on competitors in real time, and a means for recognizing the emotions of factory managers and workers and reflecting the results in advice and decision-making. This enables business people to receive prompt and accurate advice on the market situation, the trends of competitors, and the direction of their own product development. Furthermore, since decisions can be made taking into account the emotions of the user, more appropriate advice can be provided.

[0893] "Means of organizing and analyzing large amounts of information" refers to a method for collecting huge amounts of data, organizing it systematically, and analyzing it using advanced algorithms.

[0894] The "means for providing advice based on the results of the organization and analysis" refers to a means for generating and providing optimal advice to a user based on the organized and analyzed data.

[0895] "A means of making decisions that take into account the vision of the company and the industry, the thinking of management, and market conditions" is a means for making optimal decisions by taking into account the company's long-term goals, the intentions of management, and the current market conditions.

[0896] "Means including an emotion engine that recognizes user emotions" refers to means for analyzing emotions from users' actions, comments, and social media posts, and reflecting the results in the system.

[0897] "Means of obtaining and analyzing market data and competitor information in real time" refers to means of collecting market information and competitor trends in real time from the Internet and other data sources and analyzing this information.

[0898] "Means of recognizing the emotions of factory managers and workers and reflecting the results in advice and decision-making" refers to a means of analyzing the emotions of managers and workers in a factory and providing advice and decision-making based on the results.

[0899] The system for carrying out the present invention is configured as follows: The server includes a means for organizing and analyzing large amounts of information, a means for providing advice based on the results of the organization and analysis, a means for making decisions taking into account the vision of the company or industry, the thoughts of the management, and the market situation, a means including an emotion engine for recognizing the emotions of users, a means for acquiring and analyzing market data and information on competitors in real time, and a means for recognizing the emotions of factory managers and workers and reflecting the results in advice and decision-making.

[0900] Program processing explanation

[0901] The server first retrieves market data and competitor information in real time from the internet and other data sources. This data is retrieved from an API using the requests library. Then, an AI model is used to organize and analyze the retrieved data. This AI model is implemented, for example, using a pipeline from the transformers library.

[0902] To recognize user emotions, the emotion engine analyzes the content of social media posts and behavioral patterns. This analysis uses emotion analysis models from the transformers library. The emotion engine extracts emotions from user text and reflects the results in the system.

[0903] As a concrete example, consider a factory manager who is anxious about introducing a new product line. In this case, the emotion of "anxiety" is recognized from the manager's social media posts and behavioral patterns. Taking this emotion into account, the server generates advice that suggests measures to minimize risk.

[0904] Examples and prompts

[0905] As a concrete example, the following scenario can be considered.

[0906] Market Data: {"market_share": "20%"}

[0907] Competitor information: {"trends": "Increased introduction of new product lines"}

[0908] User text: "I'm nervous about introducing a new product line."

[0909] An example of a prompt is as follows:

[0910] user_text = "I'm nervous about introducing a new product line."

[0911] emotion = analyze_emotion(user_text)[0]['label']

[0912] In this way, a system can be built in which the server analyzes market conditions and competitors' activities, recognizes the emotions of managers and workers using an emotion engine, and provides optimal advice.

[0913] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0914] Step 1:

[0915] The server retrieves market data and competitor information in real time from the internet and other data sources. Specifically, it retrieves data from APIs using the requests library. The input for this step is the API endpoint and the output is the market data and competitor information.

[0916] Step 2:

[0917] The server organizes and analyzes the acquired market data and competitor information. Specifically, it analyzes the data using an AI model. For this analysis, it uses the pipeline from the transformers library. The input for this step is the market data and competitor information, and the output is the organized and analyzed data.

[0918] Step 3:

[0919] The server uses an emotion engine to recognize the user's emotions. Specifically, it analyzes the user's social media posts and behavioral patterns to extract emotions. For this analysis, it uses a sentiment analysis model from the transformers library. The input for this step is the user's text data, and the output is the recognized emotion.

[0920] Step 4:

[0921] The server generates advice based on the organized and analyzed data and the recognized emotions. Specifically, it uses an AI model to generate optimal advice. The input of this step is the organized and analyzed data and the recognized emotions, and the output is the generated advice.

[0922] Step 5:

[0923] The server provides the generated advice to the user, specifically, by sending the advice to the user's terminal. The input of this step is the generated advice, and the output is the advice provided to the user.

[0924] Step 6:

[0925] The user makes a decision based on the advice provided, such as introducing a new product line. The input of this step is the advice provided, and the output is the user's decision.

[0926] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0927] 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 making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0928] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0929] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0930] [Third embodiment]

[0931] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0932] 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.

[0933] 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 wide area network (WAN) and / or a local area network (LAN).

[0934] 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.

[0935] 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 the voice according to instructions from the processor 46.

[0936] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0937] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0938] 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.

[0939] 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.

[0940] 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.

[0941] In the headset type terminal 314, 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.

[0942] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0943] "Example 1"

[0944] The system of the present invention uses a database and AI technology as a means for organizing and analyzing large amounts of information. Specifically, data such as industry information and market conditions is stored in the database, and AI technology is used to organize and analyze this data. In addition, as a means for providing advice, optimal advice is provided to users based on data organized and analyzed using AI technology. Furthermore, as a means for making decisions that take into account the vision of the company or industry, the thinking of the management, and the market conditions, these elements are stored as data in a database, and AI technology is used to make decisions that take these elements into consideration.

[0945] "Example 2"

[0946] As a specific example of use, if a manufacturing businessperson requests advice on market conditions, competitor trends, or the direction of their own company's product development, the system will retrieve this information from the database and use AI technology to organize and analyze it. Based on the results, it will provide optimal advice and support decision-making that takes into account the vision, management thinking, and market conditions.

[0947] The process flow of each embodiment will be described below.

[0948] "Example 1"

[0949] Step 1: The user makes a request to the system for information organization and decision-making. This request may be about information such as the market situation in a particular industry, the trends of competitors, or the direction of the company's product development.

[0950] Step 2: The system retrieves the required information from a database, which contains industry information, market conditions, and other data.

[0951] Step 3: The acquired information is organized and analyzed using AI technology. This analysis uses technologies such as machine learning and deep learning.

[0952] Step 4: Based on the analysis results, provide the user with optimal advice, which will help the user organize information and make decisions.

[0953] "Example 2"

[0954] Step 1: A manufacturing business person asks the system for advice on market conditions, competitor trends, and their company's product development direction.

[0955] Step 2: The system retrieves this information from the database and organizes and analyzes it using AI technology.

[0956] Step 3: Based on the analysis results, provide the businessperson with the best advice possible. This advice will help the businessperson make decisions about the market situation, the trends of competitors, and the direction of their own product development.

[0957] Example 1

[0958] Next, a description will be given of Example 1 of the embodiment 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".

[0959] In today's business environment, it is extremely important to efficiently organize and analyze large amounts of information and provide appropriate advice based on the results. However, in conventional systems, data collection, preprocessing, analysis, advice generation, and decision-making support are carried out separately, and there is no integrated system, making efficient information processing and decision-making difficult. In addition, there is a lack of support for making decisions that comprehensively take into account the company or industry vision, management thinking, and market conditions.

[0960] 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.

[0961] In this invention, the server includes a means for collecting data such as industry information and market conditions and storing the data in a database, a means for preprocessing the stored data, a means for analyzing the preprocessed data using a machine learning model, a means for generating optimal advice for users based on the analysis results, and a means for supporting decision-making that takes into account the vision of the company or industry, the thinking of the management, and the market conditions, thereby enabling efficient information processing and integrated decision-making support.

[0962] "Industry intelligence" refers to data and knowledge related to a particular industry, including market trends, competitor actions, and technological innovations.

[0963] "Market conditions" refers to data that describes the current state or trends in a particular market, including supply and demand, price trends, and consumer behavior.

[0964] A "database" is a system for efficiently storing, managing, and searching data, and includes relational database management systems (RDBMS).

[0965] "Preprocessing" is the process of formatting data before data analysis, filling in missing values, removing outliers, normalizing the data, etc.

[0966] A "machine learning model" refers to an algorithm or mathematical model that learns patterns and rules from data and makes predictions or classifications.

[0967] "Analysis" is the process of using data to find patterns and trends and extract meaningful information.

[0968] "Advice" refers to specific suggestions or instructions provided to the user based on the results of the analysis.

[0969] A "vision" indicates the direction or goals that a company or industry aims for in the future.

[0970] "Management thinking" refers to the strategic thinking and decision-making criteria held by company managers.

[0971] "Decision support" is the process of providing assistance to users to make optimal decisions based on data and analysis results.

[0972] This invention is a system that efficiently organizes and analyzes large amounts of information and provides appropriate advice based on the results. A specific embodiment of this system will be described below.

[0973] Data collection and storage

[0974] The server collects data such as industry information and market conditions from the Internet and internal data sources within the company. Specifically, it uses web scraping technology to obtain data from news sites and market research reports. The collected data is stored in a relational database such as MySQL or PostgreSQL.

[0975] Data Preprocessing

[0976] The server preprocesses the accumulated data. Specifically, it complements missing values, removes outliers, normalizes data, etc. It uses Python's pandas library to manipulate the data in data frame format and perform preprocessing.

[0977] Analyzing data

[0978] The server then uses the pre-processed data to perform analytics. It uses machine learning libraries such as TensorFlow and PyTorch to analyze the data for patterns and trends. For example, it uses time-series data to build models that forecast market movements.

[0979] Generating Advice

[0980] The server generates optimal advice for the user based on the analysis results. When the user enters a specific question as a prompt, the server retrieves relevant data and uses the AI ​​model to generate advice.

[0981] Decision support

[0982] The server supports decision-making by taking into account the vision of the company or industry, the thinking of the management, and market conditions. These elements are stored in a database, and AI technology is used to provide information for optimal decision-making.

[0983] Examples and prompts

[0984] Examples

[0985] If a user wants to know when a new product will be released to the market, they can input a prompt like this into the generative AI model:

[0986] Examples of prompt statements

[0987] "What is the best time to bring a new product to market? Please provide an analysis based on current market conditions and historical data."

[0988] Once this prompt is entered, the server will retrieve relevant data from the database, use an AI model to analyze the optimal timing, and provide advice to the user.

[0989] In this way, a system is realized that enables efficient information processing and integrated decision-making support.

[0990] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0991] Step 1:

[0992] Data collection and storage

[0993] The server collects data such as industry information and market conditions from the Internet and internal company data sources. Specifically, it uses web scraping technology to obtain data from news sites and market research reports. Inputs include URLs and API endpoints to be collected. Outputs include the collected data stored in JSON or CSV format. The server periodically runs scheduled jobs to retrieve new data from specified data sources and insert it into the database.

[0994] Step 2:

[0995] Data Preprocessing

[0996] The server preprocesses the accumulated data, i.e., imputing missing values, removing outliers, normalizing data, etc. The input includes raw data read from the database. The output is clean preprocessed data. The server executes the preprocessing script, reads the data from the database, performs the necessary preprocessing, and saves it back to the database.

[0997] Step 3:

[0998] Analyzing data

[0999] The server performs analysis using the preprocessed data. It uses machine learning libraries such as TensorFlow and PyTorch to analyze the data for patterns and trends. The input includes the preprocessed data. The output is an analysis or predictive model. The server trains the machine learning model, evaluates it, and stores the trained model in a database.

[1000] Step 4:

[1001] Generating Advice

[1002] The server generates optimal advice for the user based on the analysis results. When the user inputs a specific question as a prompt, the server retrieves relevant data and generates advice using an AI model. The input includes the prompt from the user. The output is the generated advice provided to the user. In concrete terms, when a user inputs a prompt such as "What is the best timing to launch a new product on the market?", the server retrieves market trend data, calculates the optimal timing using an AI model, and returns the result to the user.

[1003] Step 5:

[1004] Decision support

[1005] The server supports decision-making that takes into account the company and industry vision, the management's thinking, and market conditions. These elements are stored in a database and provide information for optimal decision-making using AI technology. Inputs include data on the company and industry vision, the management's thinking, and market conditions. Outputs generate specific proposals and strategies to support decision-making. In concrete terms, when a manager considers a new business strategy, the server proposes an optimal strategy based on past data and market trends. For example, when a prompt such as "Please tell me the risks and benefits of entering a new market" is entered, the server analyzes the relevant data, evaluates the risks and benefits, and provides the results.

[1006] (Application example 1)

[1007] 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".

[1008] Inventory management and optimization at logistics centers are important issues for efficient operation. Conventional methods do not adequately monitor inventory status in real time or forecast demand, resulting in inventory shortages and surpluses. In addition, calculations for efficient picking routes are often done manually, which reduces work efficiency. To solve these issues, an advanced system that utilizes databases and AI technology is needed.

[1009] 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. In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions taking into account the vision of the company or industry, the manager's thinking, and the market situation, a means for supporting inventory management and optimization in the logistics center, a means for forecasting demand, a means for proposing the optimal timing and amount of inventory replenishment, and a means for calculating and instructing an efficient picking route. This enables efficient and optimized inventory management in the logistics center.

[1010] "Means of organizing and analyzing large amounts of information" refers to a method of systematically organizing and analyzing large amounts of data, such as industry information and market conditions, using databases and AI technology.

[1011] "Means for providing advice based on the results of the organization and analysis" refers to a method for providing optimal advice to users based on the organized and analyzed data.

[1012] "A means of making decisions that take into account the vision of the company or industry, the thinking of management, and market conditions" is a method for making optimal decisions by taking into account the long-term goals of the company or industry, the thinking of management, and market trends.

[1013] The "means for supporting inventory management and optimization in logistics centers" refers to a method for monitoring inventory status within a logistics center in real time and achieving efficient inventory management and optimization.

[1014] A "demand forecasting means" is a method for predicting future demand based on past data and market conditions.

[1015] The "means for proposing optimal inventory replenishment timing and amount" is a method for proposing optimal inventory replenishment timing and amount based on a demand forecast.

[1016] The "means for calculating and instructing an efficient picking route" is a method for calculating an efficient picking route within a logistics center and instructing the worker on the route.

[1017] This invention is a system that supports inventory management and optimization in a logistics center. The system operates in cooperation with a server, a terminal, and a user.

[1018] Server Roles

[1019] The server includes a means for organizing and analyzing large amounts of information, a means for providing advice based on the results of that organization and analysis, and a means for making decisions that take into account the vision of the company or industry, the thinking of the management, and market conditions. Specifically, it performs the following processes:

[1020] 1. Database management: The server accumulates data on inventory in the distribution center, past sales data, market situation data, etc. in a database. For this purpose, a database management system such as MySQL or PostgreSQL is used.

[1021] 2. Training the AI ​​model: The server trains the demand forecasting model based on the accumulated data, using the Python Scikit-learn library.

[1022] 3. Demand forecasting: Using trained AI models to predict future demand, which helps prevent shortages and overstocks.

[1023] 4. Inventory replenishment proposal: Calculate and propose the optimal timing and amount of inventory replenishment based on the results of demand forecasting.

[1024] 5. Picking route optimization: Calculates efficient picking routes within the distribution center and provides instructions to workers.

[1025] Terminal Roles

[1026] The terminals are smartphones or tablets used by workers in the logistics center. The terminals receive instructions from the server and display them to the workers. Specifically, they perform the following processes:

[1027] 1. View inventory status: View inventory status in real time.

[1028] 2. Displaying the results of the demand forecast: Displaying the results of the demand forecast and providing information to workers.

[1029] 3. Inventory replenishment instructions: Displays the optimal timing and amount of inventory replenishment and gives instructions to workers.

[1030] 4. Picking route instructions: Displays efficient picking routes and instructs workers on them.

[1031] User Roles

[1032] The users are the managers and workers of the logistics center. They receive instructions from the server through their terminals and perform the actual work. Specifically, they perform the following processes:

[1033] 1. Inventory management: Check stock status in real time and replenish stock as needed.

[1034] 2. Check the demand forecast: Check the results of the demand forecast and perform appropriate inventory management.

[1035] 3. Picking: Pick products by following efficient picking routes.

[1036] Examples

[1037] For example, if the inventory of "Product A" is decreasing at a logistics center, the server will predict that demand for "Product A" will increase in the following week based on past sales data and market conditions. As a result, the server will calculate the optimal timing and amount of inventory replenishment and send instructions to the terminal. Workers receive these instructions through their terminals and replenish inventory at the appropriate time. In addition, efficient picking routes are also displayed on the terminals, allowing workers to perform picking work efficiently.

[1038] Examples of prompt statements

[1039] "In order to optimize inventory management at distribution centers, please develop an application that predicts demand based on past sales data and market conditions, and suggests the optimal timing and amount of inventory replenishment."

[1040] By inputting this prompt into a generative AI model, more specific application designs and improvement suggestions can be obtained.

[1041] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1042] Step 1:

[1043] The server accumulates inventory data, past sales data, and market status data from the logistics center in a database. Specifically, it collects data in real time from each sensor and terminal in the logistics center and stores it in a database management system such as MySQL or PostgreSQL. The input is various data (inventory data, sales data, market status data), and the output is the data accumulated in the database.

[1044] Step 2:

[1045] The server trains a demand forecasting model based on the accumulated data. Specifically, it uses Python's Scikit-learn library to build a demand forecasting model using past sales data and market status data as input. The input is the past sales data and market status data accumulated in the database, and the output is the trained demand forecasting model.

[1046] Step 3:

[1047] The server uses the trained demand forecasting model to forecast future demand. Specifically, the server applies the demand forecasting model to future market situation data as input to obtain a demand forecast result. The input is future market situation data, and the output is the demand forecast result.

[1048] Step 4:

[1049] The server calculates and proposes the optimal timing and amount of inventory replenishment based on the results of the demand forecast. Specifically, it generates an optimal inventory replenishment plan using the demand forecast results and current inventory data as input. The inputs are the demand forecast results and current inventory data, and the output is the inventory replenishment plan.

[1050] Step 5:

[1051] The server calculates the most efficient picking route within the distribution center and instructs the workers. Specifically, it inputs the current inventory location data and the picking list, calculates the shortest route, and sends instructions to the terminal. The input is the inventory location data and the picking list, and the output is the optimal picking route.

[1052] Step 6:

[1053] The terminal receives instructions from the server and displays them to the worker. Specifically, it displays the inventory status, demand forecast results, inventory replenishment plans, and picking routes in real time. The input is instruction data from the server, and the output is information to be displayed to the worker.

[1054] Step 7:

[1055] The user receives instructions from the server through the terminal and performs the actual work. Specifically, the user performs inventory management, checking demand forecasts, replenishing stock, and picking work. The input is instruction information from the terminal, and the output is the actual work results.

[1056] Example 2

[1057] Next, a second embodiment of the second form 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".

[1058] In today's business environment, it is extremely important for companies and individuals to efficiently organize and analyze large amounts of information and make appropriate decisions. However, due to the sheer volume and complexity of information, doing this manually is difficult and requires time and effort. In addition, specialized knowledge and experience are required to obtain appropriate advice, which is also a hurdle for many people. Therefore, there is a demand for a system that can efficiently organize and analyze information and provide appropriate advice.

[1059] 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.

[1060] In this invention, the server includes a means for a user to input a prompt sentence, a means for a terminal to transmit the input prompt sentence to the server, a means for the server to obtain related information from a database, a means for the server to organize and clean the obtained data, a means for the server to analyze the data using a generative AI model, a means for the server to generate advice based on the analysis results, a means for the server to transmit the generated advice to the terminal, a means for the terminal to display advice to the user, and a means for making decisions taking into account the vision of the company or industry, the thinking of the management, and market conditions. This enables the user to efficiently organize and analyze large amounts of information and obtain appropriate advice.

[1061] A "User" is any individual or entity that utilizes the System to input information and receive advice.

[1062] A "prompt sentence" is text that a user enters to ask the system a specific question or for advice.

[1063] A "terminal" is a device through which a user enters prompt statements and receives advice from a server.

[1064] "Server" means a computer system that retrieves information from a database, organizes and analyzes the data, generates advice, and sends it to the terminal.

[1065] A "database" is a collection of information that a server accesses to obtain information.

[1066] A "generative AI model" is an artificial intelligence technique used by the server to analyze data and generate advice.

[1067] "Advice" refers to instructions or suggestions provided to the user based on the results of analysis performed by the server using a generative AI model.

[1068] A "vision" is the direction or goal that a company or industry aims for in the future.

[1069] "Executive thinking" refers to the strategic thinking and decision-making standards held by company executives.

[1070] "Market conditions" refers to the current trends and environment in a particular industry or market.

[1071] A "decision" is a choice or judgment made by a user based on advice provided.

[1072] This invention is a system in which a user inputs a prompt sentence, a server retrieves information from a database, analyzes the data using a generative AI model, generates advice, and provides it to the user. A specific embodiment of this system will be described below.

[1073] First, the user uses a terminal to input a prompt, which is text that the user enters to ask the system a specific question or request advice, such as "Please advise me on the market situation and competitor trends for our new product line."

[1074] The terminal then sends the input prompt to the server, using an HTTP request. The server then queries a database to obtain data related to the prompt, including market conditions, competitor trends, and the server's own product development. The database is typically a database management system such as SQL Server.

[1075] The server organizes the acquired data and cleans unnecessary data. Specifically, it uses Python's Pandas library to shape the data and extract the necessary information. The server then inputs the organized data into a generative AI model (for example, OpenAI's GPT-4) to analyze the data. The generative AI model finds trends and patterns in the data and generates analysis results.

[1076] The server generates advice to provide to the user based on the analysis results of the generative AI model. This advice takes into account the company and industry vision, the management's thinking, and the market situation. The generated advice is sent from the server to the terminal. This communication also uses HTTP requests.

[1077] Finally, the terminal displays the advice received from the server to the user, who can then make a decision based on the advice.

[1078] As a concrete example, consider a manufacturing businessperson considering developing a new product line. The user types into the terminal, "Please provide advice on the market situation and competitor trends for the new product line." The terminal sends this prompt text to the server via an HTTP request, and the server queries SQL Server to obtain relevant market data and competitor information. The server uses Python's Pandas library to clean the data and extract the necessary information. The server inputs the data into a generative AI model (GPT-4) to analyze trends and patterns. Based on the analysis results, the server generates advice to provide to the user and sends it to the terminal via an HTTP response. The terminal displays the advice to the user, and the user makes a decision based on it.

[1079] In this way, the system provides optimal advice to users and supports efficient decision-making.

[1080] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1081] Step 1:

[1082] The user enters a prompt sentence.

[1083] Input: The text that the user has a specific question or request for advice (e.g., "Please provide advice on the market situation and competitor behavior for a new product line")

[1084] Output: The prompt is typed into the terminal.

[1085] Specific actions: The user enters a prompt sentence into the input field of the terminal and presses the send button.

[1086] Step 2:

[1087] The terminal sends the prompt text entered to the server.

[1088] Input: The prompt text entered by the user

[1089] Output: The prompt text is sent to the server as an HTTP request.

[1090] Specific operation: The terminal includes the prompt text in the body of an HTTP request and sends it to the specified endpoint of the server.

[1091] Step 3:

[1092] The server retrieves the relevant information from a database.

[1093] Input: Prompt statement (e.g., "Please advise on the market situation and competitor trends for a new product line.")

[1094] Output: Data from the database on market conditions, competitors' activities, and our own product developments.

[1095] Specific behavior: The server generates an SQL query based on the prompt statement and sends it to the database to retrieve relevant information.

[1096] Step 4:

[1097] Organize and clean the data retrieved by the server.

[1098] Input: Raw data retrieved from the database

[1099] Output: Organized and cleaned data

[1100] What it does: The server uses Python's Pandas library to format the data, remove unnecessary data, and extract the necessary information.

[1101] Step 5:

[1102] The server analyzes the data using a generative AI model.

[1103] Input: Organized and cleaned data

[1104] Output: Analysis results from generative AI models

[1105] What it does: The server feeds the organized data into a generative AI model (e.g. GPT-4) to analyze trends and patterns.

[1106] Step 6:

[1107] The server generates advice based on the analysis results.

[1108] Input: Analysis results from generative AI models

[1109] Output: Advice to give to the user

[1110] Specific operation: Based on the analysis results of the generative AI model, the server generates specific advice to provide to the user.

[1111] Step 7:

[1112] The server transmits the generated advice to the terminal.

[1113] Input: Generated advice

[1114] Output: The advice is sent to the device as an HTTP response.

[1115] Specific operation: The server includes the generated advice in the body of the HTTP response and sends it to the terminal.

[1116] Step 8:

[1117] The terminal displays the advice to the user.

[1118] Input: Advice sent by the server

[1119] Output: Advice displayed to the user

[1120] Specific operation: The device displays the received advice on the user interface so that the user can view it.

[1121] (Application example 2)

[1122] 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".

[1123] In modern manufacturing, there is a need to grasp market conditions, competitor trends, and the direction of one's own product development in real time in order to create optimal manufacturing strategies. However, there are still not enough systems in place that can efficiently collect and analyze this information and provide appropriate advice. As a result, manufacturing business people often have difficulty organizing information and making decisions. To solve this problem, a system that uses AI technology to analyze market data and propose optimal manufacturing strategies is needed.

[1124] 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.

[1125] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organization and analysis, a means for making decisions taking into account the vision of the company or industry, the thinking of the management, and the market situation, a means for collecting and analyzing data on the market situation, the trends of competitors, and the direction of the company's product development, and proposing an optimal manufacturing strategy, a means for inputting a prompt sentence using a generative AI model and generating advice based on the analysis results, and a means for displaying and notifying the advice through an application installed on a factory robot. This enables business people in the manufacturing industry to collect and analyze market data in real time and create optimal manufacturing strategies.

[1126] "Means of organizing and analyzing large amounts of information" refers to a function for collecting huge amounts of data, organizing it into an appropriate format, and analyzing it using statistical methods and machine learning algorithms.

[1127] "A means of providing advice based on the results of organization and analysis" is a function for proposing specific courses of action and strategies based on the results of data analysis.

[1128] "A means of making decisions that take into account the vision of the company and the industry, the thinking of management, and market conditions" is a function that allows optimal decision-making by taking into account the company's long-term goals, the intentions of management, and market trends.

[1129] "A means of collecting and analyzing data on market conditions, competitor trends, and the company's own product development direction, and proposing optimal manufacturing strategies" refers to a function that collects market data, competitor information, and the company's own development status in real time, analyzes them, and creates optimal manufacturing plans.

[1130] "A means for inputting a prompt sentence using a generative AI model and generating advice based on the analysis results" refers to a function for inputting a specific prompt sentence to a generative AI model and generating advice based on the resulting analysis results.

[1131] "Means for displaying and notifying advice through an application installed on a factory robot" means a function for visually or audibly displaying and notifying generated advice through software installed on a factory robot.

[1132] A system for carrying out this invention has the following configuration: The server includes means for organizing and analyzing large amounts of information, means for providing advice based on the results of the organization and analysis, means for making decisions taking into account the vision of the company or industry, the thinking of the management, and the market situation, means for collecting and analyzing data on the market situation, the trends of competitors, and the direction of the company's product development, and proposing an optimal manufacturing strategy, means for inputting prompt sentences using a generative AI model and generating advice based on the analysis results, and means for displaying and notifying advice through an application installed on a factory robot.

[1133] Hardware and Software Used

[1134] Hardware: Factory robots, servers, network connections

[1135] Software: Database management systems (e.g. MySQL), AI models (e.g. GPT-4), data analysis tools (e.g. Pandas, NumPy)

[1136] Data processing and calculation flow

[1137] 1. Data collection: The server obtains data on market conditions, competitors' activities, and the company's own product development from a database via the network.

[1138] 2. Data reduction: The server reduces and preprocesses the acquired data using Pandas and NumPy.

[1139] 3. Data analysis: The server inputs the organized data into the AI ​​model (GPT-4) for analysis.

[1140] 4. Advice generation: The server generates optimal manufacturing strategies and advice based on the analysis results.

[1141] 5. Result display: The factory robot displays and notifies the user of advice through a display and voice output.

[1142] Examples

[1143] For example, the following prompt sentence is input to the generative AI model:

[1144] Example prompt:

[1145] Considering the current market situation, competitor trends, and your company's product development direction, please suggest the optimal manufacturing strategy for the next quarter.

[1146] Examples of advice that can be generated include specific manufacturing strategies such as, "Market demand is increasing, so we recommend that you increase production of product A by 20%. Also, your competitor is planning to release a new product B, so you should speed up improving your product C."

[1147] In this way, market analysis advisors for factory robots can support decision-making in manufacturing industries and achieve efficient production.

[1148] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1149] Step 1:

[1150] The server retrieves data on market conditions, competitors' activities, and the company's own product development from the database via the network. The input is market data, competitor information, and in-house development data, and the output is the retrieved raw data. In concrete terms, the server sends a query to the MySQL database to retrieve the required data.

[1151] Step 2:

[1152] The server organizes and preprocesses the acquired data using Pandas and NumPy. The input is raw data, and the output is preprocessed data. Specifically, the server performs operations such as filling in missing values, normalizing data, and deleting unnecessary data.

[1153] Step 3:

[1154] The server inputs the organized data into the AI ​​model (GPT-4) and performs analysis. The input is the preprocessed data, and the output is the analysis result. Specifically, the server generates a prompt sentence for the GPT-4 model and inputs the data.

[1155] Step 4:

[1156] The server generates optimal manufacturing strategies and advice based on the analysis results. The input is the analysis results, and the output is the generated advice. Specifically, the server analyzes the output of the generative AI model and generates specific advice in text format.

[1157] Step 5:

[1158] The factory robot displays and notifies the user of advice through a display and voice output. The input is the generated advice, and the output is the displayed advice. In terms of specific operations, the factory robot displays text on the display and notifies the user by voice if necessary.

[1159] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[1160] "Example 1"

[1161] As one embodiment of the present invention, there is a system that combines an emotion engine. This system includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organization and analysis, and a means for making decisions that take into account the vision of the company or industry, the thoughts of the management, and the market situation. It also includes an emotion engine that recognizes the emotions of the user. This emotion engine recognizes emotions from the tone of the user's voice, facial expression, choice of words, etc., and reflects the recognition results in providing advice and making decisions. For example, if it recognizes that the user is feeling stressed, it provides advice taking that information into account. Also, if it recognizes that the user is feeling happy, it makes decisions taking that information into account.

[1162] "Example 2"

[1163] Another embodiment of the present invention is a system that combines an emotion engine. This system includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organization and analysis, and a means for making decisions that take into account the vision of the company or industry, the thoughts of the management, and the market situation. It also includes an emotion engine that recognizes the emotions of the user. This emotion engine recognizes emotions from the user's behavioral patterns and the contents of posts on SNS, and reflects the recognition results in providing advice and making decisions. For example, if it is recognized that the user is feeling anxious, it provides advice taking that information into account. Also, if it is recognized that the user is excited, it makes decisions taking that information into account.

[1164] The process flow of each embodiment will be described below.

[1165] "Example 1"

[1166] Step 1: The system receives input from the user, including the user's tone of voice, facial expressions, and choice of words.

[1167] Step 2: The emotion engine recognizes the user's emotion from the received input information.

[1168] Step 3: The system organizes and analyzes large amounts of information based on the emotion recognition results from the emotion engine.

[1169] Step 4: The system provides advice based on the results of the analysis and analysis, including the emotion recognition results.

[1170] Step 5: The system makes decisions based on the company and industry vision, management's thinking, and market conditions, including the emotion recognition results.

[1171] "Example 2"

[1172] Step 1: The system receives input information from the user, including the user's behavioral patterns and the content of posts on social media.

[1173] Step 2: The emotion engine recognizes the user's emotion from the received input information.

[1174] Step 3: The system organizes and analyzes large amounts of information based on the emotion recognition results from the emotion engine.

[1175] Step 4: The system provides advice based on the results of the analysis and analysis, including the emotion recognition results.

[1176] Step 5: The system makes decisions based on the company and industry vision, management's thinking, and market conditions, including the emotion recognition results.

[1177] Example 1

[1178] Next, a description will be given of Example 1 of the embodiment 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".

[1179] Conventional information sorting and analysis systems have difficulty efficiently collecting large amounts of information and providing appropriate advice based on the analysis results. They also cannot provide advice or make decisions that take into account the user's emotions, and therefore cannot fully meet the needs of users. Furthermore, there is a lack of means to make decisions that take into account the vision of the company or industry, the thinking of the management, and market conditions.

[1180] 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.

[1181] In this invention, the server includes a means for collecting a large amount of information and storing it in a database, a means for preprocessing the stored data, a means for analyzing the preprocessed data using AI technology, a means for generating advice based on the analysis results, a means for recognizing the user's emotions, a means for adjusting the advice based on the recognized emotions, and a means for making decisions taking into account the vision of the company or industry, the thoughts of the management, and the market situation. This enables efficient information collection and analysis, provision of advice taking into account the user's emotions, and decision-making taking into account the vision of the company or industry.

[1182] "Large amounts of information" refers to a wide range of data, including industry information, market conditions, corporate vision, management thinking, and market trends.

[1183] A "database" refers to a system for efficiently storing, managing, and searching collected information.

[1184] "Preprocessing" refers to the process of cleaning and normalizing collected data to convert it into a form suitable for analysis.

[1185] "AI technology" refers to the use of algorithms such as machine learning and deep learning to analyze data and extract patterns and trends.

[1186] "Advice" refers to specific suggestions or instructions provided to the User based on the results of the Analysis.

[1187] "User emotions" refers to the psychological state that can be perceived from the user's tone of voice, facial expressions, choice of words, etc.

[1188] "Means of recognizing emotions" refers to technologies and systems for analyzing user emotions.

[1189] "Means for tailoring advice" refers to technologies or systems for changing the content of the advice provided based on perceived user emotions.

[1190] "Vision for a company or industry" refers to the direction or goals that a company or industry aims for in the future.

[1191] "Management thinking" refers to the strategies and decision-making criteria held by a company's management.

[1192] "Market conditions" refers to current market movements, trends, competitive environment, etc.

[1193] "Decision-making" refers to specific actions or choices made based on collected information, analysis results, and user feelings.

[1194] This invention is a system that efficiently collects large amounts of information and provides appropriate advice based on the analysis results. Furthermore, it is possible to provide advice and make decisions that take into account the user's emotions. A specific embodiment of this system will be described below.

[1195] Data collection and storage

[1196] The server collects data such as industry information and market conditions, and stores it in a database. This data is collected using web scraping tools and APIs (e.g. Google News API, APIs of various SNS). A relational database such as MySQL or PostgreSQL is used as the database.

[1197] Data Preprocessing

[1198] The server preprocesses the collected data. Preprocessing includes data cleaning (filling missing values, removing outliers) and normalization (scaling the data). Specifically, it uses libraries such as Pandas and NumPy.

[1199] Analyzing data

[1200] The server analyzes the preprocessed data using AI technology. For the analysis, machine learning models (e.g., random forests, support vector machines) and deep learning models (e.g., neural networks) are used. Specifically, TensorFlow and PyTorch are used.

[1201] Generating Advice

[1202] The server generates advice for the user based on the analysis results. It uses a generative AI model (e.g. GPT-3, BERT) to create advice in natural language. For example, the following prompt sentence is input to the generative AI model:

[1203] Example prompt:

[1204] "What should I consider when bringing a new product to market? I'd like your advice based on historical market data and industry trends."

[1205] Emotion recognition

[1206] The device recognizes emotions from the user's tone of voice, facial expressions, choice of words, etc. Emotion recognition uses OpenCV and Microsoft Azure's emotion recognition API. If the user is feeling stressed, the device will provide advice taking that information into account.

[1207] Tailoring advice based on emotions

[1208] The server receives the emotion recognition results sent from the device and adjusts the advice. If the user is feeling stressed, it adds advice to help them relax. For example, the following prompt sentences are input to the generative AI model:

[1209] Example prompt:

[1210] "What relaxation techniques should we offer our users if they are feeling stressed?"

[1211] Decision support

[1212] The server makes decisions that take into account the company and industry vision, management's thinking, and market conditions. To achieve this, it uses AI technology to implement decision-making algorithms that take these factors into account. For example, when a user starts a new project, it helps them make decisions based on past success stories and market trends.

[1213] In this way, the invention enables efficient information collection and analysis, provides advice that takes into account user emotions, and makes decisions that take into account the vision of the company or industry.

[1214] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1215] Step 1:

[1216] The server collects data such as industry information and market conditions, and stores it in a database. As input, it uses data obtained from web scraping tools and APIs. In concrete terms, the server uses web scraping tools to extract information from websites, and obtains real-time data through the Google News API and APIs of various SNS. As output, the collected data is stored in the database.

[1217] Step 2:

[1218] The server preprocesses the accumulated data. As input, it uses the raw data stored in the database. Specifically, it creates a data frame using Pandas, imputes missing values, and removes outliers. It also scales and normalizes the data using NumPy. As output, it obtains the preprocessed and clean data.

[1219] Step 3:

[1220] The server analyzes the preprocessed data using AI techniques. It uses the preprocessed data as input. Specifically, the server uses TensorFlow to build a neural network model, inputs data to train it, and uses the trained model to predict new data and generate analysis results. The analysis results are obtained as output.

[1221] Step 4:

[1222] The server generates advice for the user based on the analysis results. It uses the analysis results as input. Specifically, the server inputs the prompt sentence into a generative AI model (e.g., GPT-3, BERT) to generate advice. The generated advice is obtained as output.

[1223] Step 5:

[1224] The device recognizes emotions from the user's tone of voice, facial expressions, choice of words, etc. As input, it uses the user's facial expressions and voice captured using a camera and microphone. Specifically, the device calls OpenCV and Microsoft Azure emotion recognition APIs to analyze the user's emotions. The recognized emotion data is obtained as output.

[1225] Step 6:

[1226] The server receives the emotion recognition results sent by the terminal and adjusts the advice. As input, it uses the emotion recognition results and the generated advice. In concrete terms, the server analyzes the emotion recognition results and determines whether the user is feeling stressed. If necessary, it inputs new prompt sentences into the generative AI model to generate advice based on the emotion. As output, it obtains the adjusted advice.

[1227] Step 7:

[1228] The server makes decisions taking into account the company and industry vision, management thinking, and market conditions. As input, it uses data on the company and industry vision, management thinking, and market conditions stored in a database. In concrete terms, the server uses AI technology to implement a decision-making algorithm that takes these factors into account, and helps users make optimal decisions. The result of the decision is obtained as output.

[1229] (Application example 1)

[1230] 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".

[1231] Conventional information sorting and analysis systems are required to efficiently process large amounts of data and provide appropriate advice to users. However, these systems cannot take into account the emotions of users, making it difficult to provide personalized advice or make decisions. In addition, in physical stores, there is a need to analyze customer emotions, purchase history, and market trends in real time to provide optimal product suggestions and services, but current systems have difficulty achieving this.

[1232] 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.

[1233] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions taking into account the vision of the company or industry, the thinking of the management, and the market situation, an emotion engine for recognizing the emotions of the user, a means for giving advice and making decisions based on the emotion information recognized by the emotion engine, and a means for analyzing the emotions, purchase history, and market trends of customers in real time using a smart device and providing optimal product proposals and services. This enables personalized advice and decision-making that takes into account the emotions of the user, and makes it possible to provide optimal product proposals and services to customers in real time even in physical stores.

[1234] "Means of organizing and analyzing large amounts of information" refers to technologies that use databases and AI technology to efficiently process, organize, and analyze huge amounts of data such as industry information and market conditions.

[1235] "Means for providing advice" refers to technology for providing optimal advice to users based on organized and analyzed data.

[1236] "A means of making decisions that take into account the vision of a company or industry, the thinking of management, and market conditions" is a technique for making optimal decisions by taking into account the long-term goals of a company or industry, the thinking of management, and market trends.

[1237] The "emotion engine that recognizes the user's emotions" is a technology that recognizes emotions from the user's tone of voice, facial expressions, choice of words, etc.

[1238] The "means for providing advice or making decisions based on emotional information recognized by an emotion engine" is a technology for providing advice or making decisions by taking into account the emotional information of a user recognized by an emotion engine.

[1239] "A means of using smart devices to analyze customer sentiment, purchasing history, and market trends in real time, and to provide optimal product proposals and services" refers to technology that uses smart glasses or other smart devices to analyze customer sentiment, purchasing history, and market trends in real time, and propose optimal products and services.

[1240] A system for carrying out this invention has the following configuration: The server includes means for organizing and analyzing large amounts of information, means for providing advice, means for making decisions taking into account the vision of the company or industry, the thinking of the management, and market conditions, an emotion engine for recognizing the emotions of users, means for giving advice and making decisions based on the emotion information recognized by the emotion engine, and means for analyzing customer emotions, purchase history, and market trends in real time using smart devices to provide optimal product proposals and services.

[1241] Hardware and Software Configuration

[1242] 1. Hardware:

[1243] Smart devices: Smart glasses (e.g. Google Glass)

[1244] Server: A high-performance server to host the database and AI models

[1245] 2. Software:

[1246] Database Management System: A database management system such as MySQL

[1247] AI models: Machine learning frameworks such as TensorFlow

[1248] Emotion Recognition Engine: Emotion Recognition Software

[1249] Data processing and calculation

[1250] The server receives the data sent from the smart device and performs the following processes.

[1251] 1. Data collection:

[1252] The smart glasses use a camera and microphone to capture a customer's facial expressions and tone of voice in real time.

[1253] 2. Data transmission:

[1254] Send the captured data to the server.

[1255] 3. Data Analysis:

[1256] An AI model on the server analyzes customer sentiment and compares it with purchasing history and market trends stored in a database.

[1257] 4. Advice Generation:

[1258] Based on the analysis results, the AI ​​model generates optimal product suggestions and services.

[1259] 5. Results display:

[1260] Advice and suggestions for store clerks are shown on the smart glasses display.

[1261] Examples

[1262] For example, if the emotion engine detects that a customer is feeling stressed, the AI ​​will suggest products that have a relaxing effect (e.g., aromatic candles or relaxation items). Conversely, if a customer is feeling happy, the AI ​​will suggest products that will enhance that emotion (e.g., luxury chocolates or gift sets).

[1263] Examples of prompt statements

[1264] An example of a prompt to be input to the generative AI model is as follows:

[1265] Recognize your customer's emotions and suggest the best products considering their purchase history and market trends. If they're stressed, suggest products that will relax them, if they're happy, suggest products that will enhance that emotion.

[1266] In this way, customer service in physical stores can be made more personalized, improving customer satisfaction.

[1267] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1268] Step 1:

[1269] The smart device (smart glasses) captures the customer's facial expressions and tone of voice in real time. The input is video and audio data obtained from the camera and microphone of the smart glasses. The output is the captured video and audio data.

[1270] Step 2:

[1271] The smart device sends the captured video and audio data to the server. The input is the video and audio data obtained in step 1. The output is the data sent to the server.

[1272] Step 3:

[1273] The server inputs the received video and audio data into an emotion recognition engine to analyze the customer's emotions. The input is the video and audio data sent in step 2. The output is the emotion information analyzed by the emotion recognition engine.

[1274] Step 4:

[1275] The server compares the emotion information obtained from the emotion recognition engine with the purchase history and market trend data stored in the database. The input is the emotion information obtained in step 3 and the purchase history and market trend data in the database. The output is the comparison result.

[1276] Step 5:

[1277] The server uses the AI ​​model to generate optimal product proposals and services based on the matching results. The input is the matching results obtained in step 4. The output is the generated product proposal or service information.

[1278] Step 6:

[1279] The server transmits the generated product proposal or service information to the smart device. The input is the product proposal or service information generated in step 5. The output is the information transmitted to the smart device.

[1280] Step 7:

[1281] The smart device displays the received product proposal or service information to the store clerk. The input is the product proposal or service information sent in step 6. The output is the information displayed on the display of the smart device.

[1282] In this way, customer service in physical stores can be made more personalized, improving customer satisfaction.

[1283] Example 2

[1284] Next, a second embodiment of the second form 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".

[1285] In the modern business environment, companies and individuals need to quickly and accurately organize and analyze large amounts of information to make appropriate decisions. However, due to the sheer volume and complexity of information, it is difficult to organize information and make decisions efficiently using traditional methods. In addition, there is a demand for advice that takes into account the user's emotions, but there is no effective system to achieve this. Furthermore, there is a lack of means to analyze data using generative AI models or to start processing by inputting prompt sentences, making it difficult to respond flexibly to user needs.

[1286] 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.

[1287] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions taking into account the vision of the company or industry, the manager's thinking, and the market situation, a means for recognizing the user's emotions, a means for adjusting the advice based on the recognition results, a means for analyzing data using a generative AI model, and a means for starting processing using a prompt sentence as input. This enables the user to efficiently organize and analyze a large amount of information and receive appropriate advice that takes emotions into consideration. In addition, advanced data analysis using a generative AI model and flexible responses using a prompt sentence as input are possible.

[1288] "Means of organizing and analyzing large amounts of information" refers to techniques for collecting, classifying, organizing, and analyzing huge amounts of data using databases and data analysis tools.

[1289] "Means for providing advice" refers to technology that generates and provides advice to encourage users to take optimal actions and make optimal decisions based on organized and analyzed data.

[1290] "A means of making decisions that take into account the vision of the company and industry, the thinking of management, and market conditions" is a technique for making optimal decisions by taking into account the company's long-term goals, the strategic thinking of management, and current market trends.

[1291] "Means of recognizing user emotions" refers to technology for analyzing and recognizing emotions from user behavior patterns and the content of social media posts.

[1292] The "means for adjusting advice based on the recognition results" refers to a technology that appropriately changes the content and method of advice provided based on the recognized user's emotions.

[1293] "Means of analyzing data using generative AI models" refers to techniques that use AI technologies such as machine learning and deep learning to analyze data and extract patterns and trends.

[1294] "Means for starting processing using a prompt sentence as input" refers to a technique that enables a system to start appropriate processing based on the text (prompt sentence) entered by the user.

[1295] This invention is a system implemented by combining the elements of a server, a terminal, and a user. Specific hardware and software configurations and the roles of each will be described below.

[1296] Hardware and Software Used

[1297] Server: A high-performance database server (e.g. MySQL, PostgreSQL)

[1298] Device: PC or smartphone used by the user

[1299] Software: AI technology (e.g. TensorFlow, PyTorch), emotion engine (e.g. IBM Watson, Microsoft Azure Emotion API)

[1300] Specific operation of the system

[1301] Data Acquisition

[1302] The server retrieves data from the database about the market situation, competitors' trends, and the company's product development direction that the user desires. For example, the server connects to a MySQL database and retrieves the latest data from the "Market Trends" table using a SQL query. Specifically, it executes the query SELECT FROM Market Trends WHERE Date = CURDATE();

[1303] Data organization and analysis

[1304] The server organizes and analyzes the acquired data using AI technology. For example, the server uses TensorFlow to cluster competitor trend data. Specifically, the K-means clustering algorithm is used to classify the data into several clusters. As a code example, run kmeans = KMeans(n_clusters=5).fit(competitor data).

[1305] Advice Generation

[1306] The server generates optimal advice based on the results of the analysis and sends it to the terminal. For example, the server uses PyTorch to build a predictive model for the direction of product development. Specifically, it trains the predictive model using a neural network and provides the results to the user. As a code example, run model = NeuralNetwork().train(product development data).

[1307] emotion recognition

[1308] The server uses an emotion engine to recognize the user's emotions. For example, the server uses IBM Watson to analyze emotions from the user's SNS posts. Specifically, it executes emotion_analysis = watson.analyze(text=user's SNS post).

[1309] Advice adjustment based on emotions

[1310] The server adjusts advice based on the recognized emotions to support decision-making. For example, if the user is feeling anxious, the server takes that information into account and provides advice to reduce risk. Specifically, the server performs a conditional branch as follows: if emotion_analysis['emotion'] == 'fear': advice = 'We recommend that you take measures to reduce risk.'

[1311] Examples

[1312] Examples of prompt statements

[1313] "A manufacturing businessperson is looking for advice on the market situation, competitor trends, and the direction of their own product development. Please obtain the latest market trend data and competitor trend data and analyze them using AI technology. Also, please recognize the emotions of users from their social media posts and adjust your advice based on the results."

[1314] In this way, the server provides optimal advice to support the user's decision making.

[1315] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1316] Step 1:

[1317] Data Acquisition

[1318] The server retrieves data related to the market conditions desired by the user, the trends of competitors, and the direction of the company's product development from the database.

[1319] Input: A prompt statement specified by the user (e.g., "Please provide data on the market situation, competitor trends, and product development direction of your company.")

[1320] What happens: The server connects to the MySQL database and retrieves the latest data from the "Market Trends" table using the SQL query SELECT FROM Market Trends WHERE Date = CURDATE();

[1321] Output: Obtained market trend data

[1322] Step 2:

[1323] Data organization and analysis

[1324] The server organizes and analyzes the acquired data using AI technology.

[1325] Input: Obtained market trend data

[1326] Specific operation: The server uses TensorFlow to cluster the competitor trend data. Specifically, it uses the K-means clustering algorithm to classify the data into several clusters. For example code, run kmeans = KMeans(n_clusters=5).fit(competitor data).

[1327] Output: Clustered competitor behavior data

[1328] Step 3:

[1329] Advice Generation

[1330] The server generates optimal advice based on the results of the organization and analysis and sends it to the terminal.

[1331] Input: Clustered competitor behavior data

[1332] Specific operation: The server uses PyTorch to build a predictive model for the direction of product development. Specifically, it uses a neural network to train the predictive model and provides the results to the user. For example code, run model = NeuralNetwork().train(product development data).

[1333] Output: Generated advice

[1334] Step 4:

[1335] emotion recognition

[1336] The server uses an emotion engine to recognize the user's emotions.

[1337] Input: User's social media posts

[1338] Specific operation: The server uses IBM Watson to analyze emotions from the content of the user's SNS posts. Specifically, it executes emotion_analysis = watson.analyze(text=user's SNS post).

[1339] Output: Recognized user emotion data

[1340] Step 5:

[1341] Advice adjustment based on emotions

[1342] The server then tailors advice based on the emotions it recognizes to support decision-making.

[1343] Input: Recognized user emotion data, generated advice

[1344] Specific behavior: If the user feels anxious, the server takes that information into account and provides advice to reduce the risk. Specifically, it performs the following conditional branch: if emotion_analysis['emotion'] == 'fear': advice = 'We recommend that you take measures to reduce the risk.'

[1345] Output: Adjusted advice

[1346] (Application example 2)

[1347] 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".

[1348] In the modern manufacturing industry, it is extremely important for businesspeople to receive prompt and accurate advice about market conditions, competitor trends, and the direction of their own company's product development. However, it is difficult to organize and analyze vast amounts of information and make decisions that take into account the emotions of users. In particular, there is no system that provides advice that reflects the emotions of factory managers and workers. For this reason, a system that combines information organization and analysis with emotion recognition is needed.

[1349] 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.

[1350] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions that take into account the vision of the company or industry, the thoughts of the management, and the market situation, a means including an emotion engine for recognizing the emotions of the user, a means for acquiring and analyzing market data and information on competitors in real time, and a means for recognizing the emotions of factory managers and workers and reflecting the results in advice and decision-making. This enables business people to receive prompt and accurate advice on the market situation, the trends of competitors, and the direction of their own product development. Furthermore, since decisions can be made taking into account the emotions of the user, more appropriate advice can be provided.

[1351] "Means of organizing and analyzing large amounts of information" refers to a method for collecting huge amounts of data, organizing it systematically, and analyzing it using advanced algorithms.

[1352] The "means for providing advice based on the results of the organization and analysis" refers to a means for generating and providing optimal advice to a user based on the organized and analyzed data.

[1353] "A means of making decisions that take into account the vision of the company and the industry, the thinking of management, and market conditions" is a means for making optimal decisions by taking into account the company's long-term goals, the intentions of management, and the current market conditions.

[1354] "Means including an emotion engine that recognizes user emotions" refers to means for analyzing emotions from users' actions, comments, and social media posts, and reflecting the results in the system.

[1355] "Means of obtaining and analyzing market data and competitor information in real time" refers to means of collecting market information and competitor trends in real time from the Internet and other data sources and analyzing this information.

[1356] "Means of recognizing the emotions of factory managers and workers and reflecting the results in advice and decision-making" refers to a means of analyzing the emotions of managers and workers in a factory and providing advice and decision-making based on the results.

[1357] The system for carrying out the present invention is configured as follows: The server includes a means for organizing and analyzing large amounts of information, a means for providing advice based on the results of the organization and analysis, a means for making decisions taking into account the vision of the company or industry, the thoughts of the management, and the market situation, a means including an emotion engine for recognizing the emotions of users, a means for acquiring and analyzing market data and information on competitors in real time, and a means for recognizing the emotions of factory managers and workers and reflecting the results in advice and decision-making.

[1358] Program processing explanation

[1359] The server first retrieves market data and competitor information in real time from the internet and other data sources. This data is retrieved from an API using the requests library. Then, an AI model is used to organize and analyze the retrieved data. This AI model is implemented, for example, using a pipeline from the transformers library.

[1360] To recognize user emotions, the emotion engine analyzes the content of social media posts and behavioral patterns. This analysis uses emotion analysis models from the transformers library. The emotion engine extracts emotions from user text and reflects the results in the system.

[1361] As a concrete example, consider a factory manager who is anxious about introducing a new product line. In this case, the emotion of "anxiety" is recognized from the manager's social media posts and behavioral patterns. Taking this emotion into account, the server generates advice that suggests measures to minimize risk.

[1362] Examples and prompts

[1363] As a concrete example, the following scenario can be considered.

[1364] Market Data: {"market_share": "20%"}

[1365] Competitor information: {"trends": "Increased introduction of new product lines"}

[1366] User text: "I'm nervous about introducing a new product line."

[1367] An example of a prompt is as follows:

[1368] user_text = "I'm nervous about introducing a new product line."

[1369] emotion = analyze_emotion(user_text)[0]['label']

[1370] In this way, a system can be built in which the server analyzes market conditions and competitors' activities, recognizes the emotions of managers and workers using an emotion engine, and provides optimal advice.

[1371] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1372] Step 1:

[1373] The server retrieves market data and competitor information in real time from the internet and other data sources. Specifically, it retrieves data from APIs using the requests library. The input for this step is the API endpoint and the output is the market data and competitor information.

[1374] Step 2:

[1375] The server organizes and analyzes the acquired market data and competitor information. Specifically, it analyzes the data using an AI model. For this analysis, it uses the pipeline from the transformers library. The input for this step is the market data and competitor information, and the output is the organized and analyzed data.

[1376] Step 3:

[1377] The server uses an emotion engine to recognize the user's emotions. Specifically, it analyzes the user's social media posts and behavioral patterns to extract emotions. For this analysis, it uses a sentiment analysis model from the transformers library. The input for this step is the user's text data, and the output is the recognized emotion.

[1378] Step 4:

[1379] The server generates advice based on the organized and analyzed data and the recognized emotions. Specifically, it uses an AI model to generate optimal advice. The input of this step is the organized and analyzed data and the recognized emotions, and the output is the generated advice.

[1380] Step 5:

[1381] The server provides the generated advice to the user, specifically, by sending the advice to the user's terminal. The input of this step is the generated advice, and the output is the advice provided to the user.

[1382] Step 6:

[1383] The user makes a decision based on the advice provided, such as introducing a new product line. The input of this step is the advice provided, and the output is the user's decision.

[1384] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1385] 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 making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1386] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1387] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1388] [Fourth embodiment]

[1389] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1390] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1391] 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 wide area network (WAN) and / or a local area network (LAN).

[1392] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1393] 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 the voice according to instructions from the processor 46.

[1394] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1395] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1396] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1397] Fig. 8 shows an example of main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1398] 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.

[1399] 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.

[1400] In the robot 414, 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.

[1401] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1402] "Example 1"

[1403] The system of the present invention uses a database and AI technology as a means for organizing and analyzing large amounts of information. Specifically, data such as industry information and market conditions is stored in the database, and AI technology is used to organize and analyze this data. In addition, as a means for providing advice, optimal advice is provided to users based on data organized and analyzed using AI technology. Furthermore, as a means for making decisions that take into account the vision of the company or industry, the thinking of the management, and the market conditions, these elements are stored as data in a database, and AI technology is used to make decisions that take these elements into consideration.

[1404] "Example 2"

[1405] As a specific example of use, if a manufacturing businessperson requests advice on market conditions, competitor trends, or the direction of their own company's product development, the system will retrieve this information from the database and use AI technology to organize and analyze it. Based on the results, it will provide optimal advice and support decision-making that takes into account the vision, management thinking, and market conditions.

[1406] The process flow of each embodiment will be described below.

[1407] "Example 1"

[1408] Step 1: The user makes a request to the system for information organization and decision-making. This request may be about information such as the market situation in a particular industry, the trends of competitors, or the direction of the company's product development.

[1409] Step 2: The system retrieves the required information from a database, which contains industry information, market conditions, and other data.

[1410] Step 3: The acquired information is organized and analyzed using AI technology. This analysis uses technologies such as machine learning and deep learning.

[1411] Step 4: Based on the analysis results, provide the user with optimal advice, which will help the user organize information and make decisions.

[1412] "Example 2"

[1413] Step 1: A manufacturing business person asks the system for advice on market conditions, competitor trends, and their company's product development direction.

[1414] Step 2: The system retrieves this information from the database and organizes and analyzes it using AI technology.

[1415] Step 3: Based on the analysis results, provide the businessperson with the best advice possible. This advice will help the businessperson make decisions about the market situation, the trends of competitors, and the direction of their own product development.

[1416] Example 1

[1417] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1418] In today's business environment, it is extremely important to efficiently organize and analyze large amounts of information and provide appropriate advice based on the results. However, in conventional systems, data collection, preprocessing, analysis, advice generation, and decision-making support are carried out separately, and there is no integrated system, making efficient information processing and decision-making difficult. In addition, there is a lack of support for making decisions that comprehensively take into account the company or industry vision, management thinking, and market conditions.

[1419] 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.

[1420] In this invention, the server includes a means for collecting data such as industry information and market conditions and storing the data in a database, a means for preprocessing the stored data, a means for analyzing the preprocessed data using a machine learning model, a means for generating optimal advice for users based on the analysis results, and a means for supporting decision-making that takes into account the vision of the company or industry, the thinking of the management, and the market conditions, thereby enabling efficient information processing and integrated decision-making support.

[1421] "Industry intelligence" refers to data and knowledge related to a particular industry, including market trends, competitor actions, and technological innovations.

[1422] "Market conditions" refers to data that describes the current state or trends in a particular market, including supply and demand, price trends, and consumer behavior.

[1423] A "database" is a system for efficiently storing, managing, and searching data, and includes relational database management systems (RDBMS).

[1424] "Preprocessing" is the process of formatting data before data analysis, filling in missing values, removing outliers, normalizing the data, etc.

[1425] A "machine learning model" refers to an algorithm or mathematical model that learns patterns and rules from data and makes predictions or classifications.

[1426] "Analysis" is the process of using data to find patterns and trends and extract meaningful information.

[1427] "Advice" refers to specific suggestions or instructions provided to the user based on the results of the analysis.

[1428] A "vision" indicates the direction or goals that a company or industry aims for in the future.

[1429] "Management thinking" refers to the strategic thinking and decision-making criteria held by company managers.

[1430] "Decision support" is the process of providing assistance to users to make optimal decisions based on data and analysis results.

[1431] This invention is a system that efficiently organizes and analyzes large amounts of information and provides appropriate advice based on the results. A specific embodiment of this system will be described below.

[1432] Data collection and storage

[1433] The server collects data such as industry information and market conditions from the Internet and internal data sources within the company. Specifically, it uses web scraping technology to obtain data from news sites and market research reports. The collected data is stored in a relational database such as MySQL or PostgreSQL.

[1434] Data Preprocessing

[1435] The server preprocesses the accumulated data. Specifically, it complements missing values, removes outliers, normalizes data, etc. It uses Python's pandas library to manipulate the data in data frame format and perform preprocessing.

[1436] Analyzing data

[1437] The server then uses the pre-processed data to perform analytics. It uses machine learning libraries such as TensorFlow and PyTorch to analyze the data for patterns and trends. For example, it uses time-series data to build models that forecast market movements.

[1438] Generating Advice

[1439] The server generates optimal advice for the user based on the analysis results. When the user enters a specific question as a prompt, the server retrieves relevant data and uses the AI ​​model to generate advice.

[1440] Decision support

[1441] The server supports decision-making by taking into account the vision of the company or industry, the thinking of the management, and market conditions. These elements are stored in a database, and AI technology is used to provide information for optimal decision-making.

[1442] Examples and prompts

[1443] Examples

[1444] If a user wants to know when a new product will be released to the market, they can input a prompt like this into the generative AI model:

[1445] Examples of prompt statements

[1446] "What is the best time to bring a new product to market? Please provide an analysis based on current market conditions and historical data."

[1447] Once this prompt is entered, the server will retrieve relevant data from the database, use an AI model to analyze the optimal timing, and provide advice to the user.

[1448] In this way, a system is realized that enables efficient information processing and integrated decision-making support.

[1449] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1450] Step 1:

[1451] Data collection and storage

[1452] The server collects data such as industry information and market conditions from the Internet and internal company data sources. Specifically, it uses web scraping technology to obtain data from news sites and market research reports. Inputs include URLs and API endpoints to be collected. Outputs include the collected data stored in JSON or CSV format. The server periodically runs scheduled jobs to retrieve new data from specified data sources and insert it into the database.

[1453] Step 2:

[1454] Data Preprocessing

[1455] The server preprocesses the accumulated data, i.e., imputing missing values, removing outliers, normalizing data, etc. The input includes raw data read from the database. The output is clean preprocessed data. The server executes the preprocessing script, reads the data from the database, performs the necessary preprocessing, and saves it back to the database.

[1456] Step 3:

[1457] Analyzing data

[1458] The server performs analysis using the preprocessed data. It uses machine learning libraries such as TensorFlow and PyTorch to analyze the data for patterns and trends. The input includes the preprocessed data. The output is an analysis or predictive model. The server trains the machine learning model, evaluates it, and stores the trained model in a database.

[1459] Step 4:

[1460] Generating Advice

[1461] The server generates optimal advice for the user based on the analysis results. When the user inputs a specific question as a prompt, the server retrieves relevant data and generates advice using an AI model. The input includes the prompt from the user. The output is the generated advice provided to the user. In concrete terms, when a user inputs a prompt such as "What is the best timing to launch a new product on the market?", the server retrieves market trend data, calculates the optimal timing using an AI model, and returns the result to the user.

[1462] Step 5:

[1463] Decision support

[1464] The server supports decision-making that takes into account the company and industry vision, the management's thinking, and market conditions. These elements are stored in a database and provide information for optimal decision-making using AI technology. Inputs include data on the company and industry vision, the management's thinking, and market conditions. Outputs generate specific proposals and strategies to support decision-making. In concrete terms, when a manager considers a new business strategy, the server proposes an optimal strategy based on past data and market trends. For example, when a prompt such as "Please tell me the risks and benefits of entering a new market" is entered, the server analyzes the relevant data, evaluates the risks and benefits, and provides the results.

[1465] (Application example 1)

[1466] 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 robot 414 will be referred to as a "terminal".

[1467] Inventory management and optimization at logistics centers are important issues for efficient operation. Conventional methods do not adequately monitor inventory status in real time or forecast demand, resulting in inventory shortages and surpluses. In addition, calculations for efficient picking routes are often done manually, which reduces work efficiency. To solve these issues, an advanced system that utilizes databases and AI technology is needed.

[1468] 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. In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organizing and analysis, a means for making decisions taking into account the vision of the company or industry, the manager's thinking, and the market situation, a means for supporting inventory management and optimization in the logistics center, a means for forecasting demand, a means for proposing the optimal timing and amount of inventory replenishment, and a means for calculating and instructing an efficient picking route. This enables efficient and optimized inventory management in the logistics center.

[1469] "Means of organizing and analyzing large amounts of information" refers to a method of systematically organizing and analyzing large amounts of data, such as industry information and market conditions, using databases and AI technology.

[1470] "Means for providing advice based on the results of the organization and analysis" refers to a method for providing optimal advice to users based on the organized and analyzed data.

[1471] "A means of making decisions that take into account the vision of the company or industry, the thinking of management, and market conditions" is a method for making optimal decisions by taking into account the long-term goals of the company or industry, the thinking of management, and market trends.

[1472] The "means for supporting inventory management and optimization in logistics centers" refers to a method for monitoring inventory status within a logistics center in real time and achieving efficient inventory management and optimization.

[1473] A "demand forecasting means" is a method for predicting future demand based on past data and market conditions.

[1474] The "means for proposing optimal inventory replenishment timing and amount" is a method for proposing optimal inventory replenishment timing and amount based on a demand forecast.

[1475] The "means for calculating and instructing an efficient picking route" is a method for calculating an efficient picking route within a logistics center and instructing the worker on the route.

[1476] This invention is a system that supports inventory management and optimization in a logistics center. The system operates in cooperation with a server, a terminal, and a user.

[1477] Server Roles

[1478] The server includes a means for organizing and analyzing large amounts of information, a means for providing advice based on the results of that organization and analysis, and a means for making decisions that take into account the vision of the company or industry, the thinking of the management, and market conditions. Specifically, it performs the following processes:

[1479] 1. Database management: The server accumulates data on inventory in the distribution center, past sales data, market situation data, etc. in a database. For this purpose, a database management system such as MySQL or PostgreSQL is used.

[1480] 2. Training the AI ​​model: The server trains the demand forecasting model based on the accumulated data, using the Python Scikit-learn library.

[1481] 3. Demand forecasting: Using trained AI models to predict future demand, which helps prevent shortages and overstocks.

[1482] 4. Inventory replenishment proposal: Calculate and propose the optimal timing and amount of inventory replenishment based on the results of demand forecasting.

[1483] 5. Picking route optimization: Calculates efficient picking routes within the distribution center and provides instructions to workers.

[1484] Terminal Roles

[1485] The terminals are smartphones or tablets used by workers in the logistics center. The terminals receive instructions from the server and display them to the workers. Specifically, they perform the following processes:

[1486] 1. View inventory status: View inventory status in real time.

[1487] 2. Displaying the results of the demand forecast: Displaying the results of the demand forecast and providing information to workers.

[1488] 3. Inventory replenishment instructions: Displays the optimal timing and amount of inventory replenishment and gives instructions to workers.

[1489] 4. Picking route instructions: Displays efficient picking routes and instructs workers on them.

[1490] User Roles

[1491] The users are the managers and workers of the logistics center. They receive instructions from the server through their terminals and perform the actual work. Specifically, they perform the following processes:

[1492] 1. Inventory management: Check stock status in real time and replenish stock as needed.

[1493] 2. Check the demand forecast: Check the results of the demand forecast and perform appropriate inventory management.

[1494] 3. Picking: Pick products by following efficient picking routes.

[1495] Examples

[1496] For example, if the inventory of "Product A" is decreasing at a logistics center, the server will predict that demand for "Product A" will increase in the following week based on past sales data and market conditions. As a result, the server will calculate the optimal timing and amount of inventory replenishment and send instructions to the terminal. Workers receive these instructions through their terminals and replenish inventory at the appropriate time. In addition, efficient picking routes are also displayed on the terminals, allowing workers to perform picking work efficiently.

[1497] Examples of prompt statements

[1498] "In order to optimize inventory management at distribution centers, please develop an application that predicts demand based on past sales data and market conditions, and suggests the optimal timing and amount of inventory replenishment."

[1499] By inputting this prompt into a generative AI model, more specific application designs and improvement suggestions can be obtained.

[1500] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1501] Step 1:

[1502] The server accumulates inventory data, past sales data, and market status data from the logistics center in a database. Specifically, it collects data in real time from each sensor and terminal in the logistics center and stores it in a database management system such as MySQL or PostgreSQL. The input is various data (inventory data, sales data, market status data), and the output is the data accumulated in the database.

[1503] Step 2:

[1504] The server trains a demand forecasting model based on the accumulated data. Specifically, it uses Python's Scikit-learn library to build a demand forecasting model using past sales data and market status data as input. The input is the past sales data and market status data accumulated in the database, and the output is the trained demand forecasting model.

[1505] Step 3:

[1506] The server uses the trained demand forecasting model to forecast future demand. Specifically, the server applies the demand forecasting model to future market situation data as input to obtain a demand forecast result. The input is future market situation data, and the output is the demand forecast result.

[1507] Step 4:

[1508] The server calculates and proposes the optimal timing and amount of inventory replenishment based on the results of the demand forecast. Specifically, it generates an optimal inventory replenishment plan using the demand forecast results and current inventory data as input. The inputs are the demand forecast results and current inventory data, and the output is the inventory replenishment plan.

[1509] Step 5:

[1510] The server calculates the most efficient picking route within the distribution center and instructs the workers. Specifically, it inputs the current inventory location data and the picking list, calculates the shortest route, and sends instructions to the terminal. The input is the inventory location data and the picking list, and the output is the optimal picking route.

[1511] Step 6:

[1512] The terminal receives instructions from the server and displays them to the worker. Specifically, it displays the inventory status, demand forecast results, inventory replenishment plans, and picking routes in real time. The input is instruction data from the server, and the output is information to be displayed to the worker.

[1513] Step 7:

[1514] The user receives instructions from the server through the terminal and performs the actual work. Specifically, the user performs inventory management, checking demand forecasts, replenishing stock, and picking work. The input is instruction information from the terminal, and the output is the actual work results.

[1515] Example 2

[1516] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1517] In today's business environment, it is extremely important for companies and individuals to efficiently organize and analyze large amounts of information and make appropriate decisions. However, due to the sheer volume and complexity of information, doing this manually is difficult and requires time and effort. In addition, specialized knowledge and experience are required to obtain appropriate advice, which is also a hurdle for many people. Therefore, there is a demand for a system that can efficiently organize and analyze information and provide appropriate advice.

[1518] 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.

[1519] In this invention, the server includes a means for a user to input a prompt sentence, a means for a terminal to transmit the input prompt sentence to the server, a means for the server to obtain related information from a database, a means for the server to organize and clean the obtained data, a means for the server to analyze the data using a generative AI model, a means for the server to generate advice based on the analysis results, a means for the server to transmit the generated advice to the terminal, a means for the terminal to display advice to the user, and a means for making decisions taking into account the vision of the company or industry, the thinking of the management, and market conditions. This enables the user to efficiently organize and analyze large amounts of information and obtain appropriate advice.

[1520] A "User" is any individual or entity that utilizes the System to input information and receive advice.

[1521] A "prompt sentence" is text that a user enters to ask the system a specific question or for advice.

[1522] A "terminal" is a device through which a user enters prompt statements and receives advice from a server.

[1523] "Server" means a computer system that retrieves information from a database, organizes and analyzes the data, generates advice, and sends it to the terminal.

[1524] A "database" is a collection of information that a server accesses to obtain information.

[1525] A "generative AI model" is an artificial intelligence technique used by the server to analyze data and generate advice.

[1526] "Advice" refers to instructions or suggestions provided to the user based on the results of analysis performed by the server using a generative AI model.

[1527] A "vision" is the direction or goal that a company or industry aims for in the future.

[1528] "Executive thinking" refers to the strategic thinking and decision-making standards held by company executives.

[1529] "Market conditions" refers to the current trends and environment in a particular industry or market.

[1530] A "decision" is a choice or judgment made by a user based on advice provided.

[1531] This invention is a system in which a user inputs a prompt sentence, a server retrieves information from a database, analyzes the data using a generative AI model, generates advice, and provides it to the user. A specific embodiment of this system will be described below.

[1532] First, the user uses a terminal to input a prompt, which is text that the user enters to ask the system a specific question or request advice, such as "Please advise me on the market situation and competitor trends for our new product line."

[1533] The terminal then sends the input prompt to the server, using an HTTP request. The server then queries a database to obtain data related to the prompt, including market conditions, competitor trends, and the server's own product development. The database is typically a database management system such as SQL Server.

[1534] The server organizes the acquired data and cleans unnecessary data. Specifically, it uses Python's Pandas library to shape the data and extract the necessary information. The server then inputs the organized data into a generative AI model (for example, OpenAI's GPT-4) to analyze the data. The generative AI model finds trends and patterns in the data and generates analysis results.

[1535] The server generates advice to provide to the user based on the analysis results of the generative AI model. This advice takes into account the company and industry vision, the management's thinking, and the market situation. The generated advice is sent from the server to the terminal. This communication also uses HTTP requests.

[1536] Finally, the terminal displays the advice received from the server to the user, who can then make a decision based on the advice.

[1537] As a concrete example, consider a manufacturing businessperson considering developing a new product line. The user types into the terminal, "Please provide advice on the market situation and competitor trends for the new product line." The terminal sends this prompt text to the server via an HTTP request, and the server queries SQL Server to obtain relevant market data and competitor information. The server uses Python's Pandas library to clean the data and extract the necessary information. The server inputs the data into a generative AI model (GPT-4) to analyze trends and patterns. Based on the analysis results, the server generates advice to provide to the user and sends it to the terminal via an HTTP response. The terminal displays the advice to the user, and the user makes a decision based on it.

[1538] In this way, the system provides optimal advice to users and supports efficient decision-making.

[1539] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1540] Step 1:

[1541] The user enters a prompt sentence.

[1542] Input: The text that the user has a specific question or request for advice (e.g., "Please provide advice on the market situation and competitor behavior for a new product line")

[1543] Output: The prompt is typed into the terminal.

[1544] Specific actions: The user enters a prompt sentence into the input field of the terminal and presses the send button.

[1545] Step 2:

[1546] The terminal sends the prompt text entered to the server.

[1547] Input: The prompt text entered by the user

[1548] Output: The prompt text is sent to the server as an HTTP request.

[1549] Specific operation: The terminal includes the prompt text in the body of an HTTP request and sends it to the specified endpoint of the server.

[1550] Step 3:

[1551] The server retrieves the relevant information from a database.

[1552] Input: Prompt statement (e.g., "Please advise on the market situation and competitor trends for a new product line.")

[1553] Output: Data from the database on market conditions, competitors' activities, and our own product developments.

[1554] Specific behavior: The server generates an SQL query based on the prompt statement and sends it to the database to retrieve relevant information.

[1555] Step 4:

[1556] Organize and clean the data retrieved by the server.

[1557] Input: Raw data retrieved from the database

[1558] Output: Organized and cleaned data

[1559] What it does: The server uses Python's Pandas library to format the data, remove unnecessary data, and extract the necessary information.

[1560] Step 5:

[1561] The server analyzes the data using a generative AI model.

[1562] Input: Organized and cleaned data

[1563] Output: Analysis results from generative AI models

[1564] What it does: The server feeds the organized data into a generative AI model (e.g. GPT-4) to analyze trends and patterns.

[1565] Step 6:

[1566] The server generates advice based on the analysis results.

[1567] Input: Analysis results from generative AI models

[1568] Output: Advice to give to the user

[1569] Specific operation: Based on the analysis results of the generative AI model, the server generates specific advice to provide to the user.

[1570] Step 7:

[1571] The server transmits the generated advice to the terminal.

[1572] Input: Generated advice

[1573] Output: The advice is sent to the device as an HTTP response.

[1574] Specific operation: The server includes the generated advice in the body of the HTTP response and sends it to the terminal.

[1575] Step 8:

[1576] The terminal displays the advice to the user.

[1577] Input: Advice sent by the server

[1578] Output: Advice displayed to the user

[1579] Specific operation: The device displays the received advice on the user interface so that the user can view it.

[1580] (Application example 2)

[1581] 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 robot 414 will be referred to as a "terminal".

[1582] In modern manufacturing, there is a need to grasp market conditions, competitor trends, and the direction of one's own product development in real time in order to create optimal manufacturing strategies. However, there are still not enough systems in place that can efficiently collect and analyze this information and provide appropriate advice. As a result, manufacturing business people often have difficulty organizing information and making decisions. To solve this problem, a system that uses AI technology to analyze market data and propose optimal manufacturing strategies is needed.

[1583] 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.

[1584] In this invention, the server includes a means for organizing and analyzing a large amount of information, a means for providing advice based on the results of the organization and analysis, a means for making decisions taking into account the vision of the company or industry, the thinking of the management, and the market situation, a means for collecting and analyzing data on the market situation, the trends of competitors, and the direction of the company's product development, and proposing an optimal manufacturing strategy, a means for inputting a prompt sentence using a generative AI model and generating advice based on the analysis results, and a means for displaying and notifying the advice through an application installed on a factory robot. This enables business people in the manufacturing industry to collect and analyze market data in real time and create optimal manufacturing strategies.

[1585] "Means of organizing and analyzing large amounts of information" refers to a function for collecting huge amounts of data, organizing it into an appropriate format, and analyzing it using statistical methods and machine learning algorithms.

[1586] "A means of providing advice based on the results of organization and analysis" is a function for proposing specific courses of action and strategies based on the results of data analysis.

[1587] "A means of making decisions that take into account the vision of the company and the industry, the thinking of management, and market conditions" is a function that allows optimal decision-making by taking into account the company's long-term goals, the intentions of management, and market trends.

[1588] "A means of collecting and analyzing data on market conditions, competitor trends, and the company's own product development direction, and proposing optimal manufacturing strategies" refers to a function that collects market data, competitor information, and the company's own development status in real time, analyzes them, and creates optimal manufacturing plans.

[1589] "A means for inputting a prompt sentence using a generative AI model and generating advice based on the analysis results" refers to a function for inputting a specific prompt sentence to a generative AI model and generating advice based on the resulting analysis results.

[1590] "Means for displaying and notifying advice through an application installed on a factory robot" means a function for visually or audibly displaying and notifying generated advice through software installed on a factory robot.

[1591] A system for carrying out this invention has the following configuration: The server includes means for organizing and analyzing large amounts of information, means for providing advice based on the results of the organization and analysis, means for making decisions taking into account the vision of the company or industry, the thinking of the management, and the market situation, means for collecting and analyzing data on the market situation, the trends of competitors, and the direction of the company's product development, and proposing an optimal manufacturing strategy, means for inputting prompt sentences using a generative AI model and generating advice based on the analysis results, and means for displaying and notifying advice through an application installed on a factory robot.

[1592] Hardware and Software Used

[1593] Hardware: Factory robots, servers, network connections

[1594] Software: Database management systems (e.g. MySQL), AI models (e.g. GPT-4), data analysis tools (e.g. Pandas, NumPy)

[1595] Data processing and calculation flow

[1596] 1. Data collection: The server obtains data on market conditions, competitors' activities, and the company's own product development from a database via the network.

[1597] 2. Data reduction: The server reduces and preprocesses the acquired data using Pandas and NumPy.

[1598] 3. Data analysis: The server inputs the organized data into the AI ​​model (GPT-4) for analysis.

[1599] 4. Advice generation: The server generates optimal manufacturing strategies and advice based on the analysis results.

[1600] 5. Result display: The factory robot displays and notifies the user of advice through a display and voice output.

[1601] Examples

[1602] For example, the following prompt sentence is input to the generative AI model:

[1603] Example prompt:

[1604] Considering the current market situation, competitor trends, and your company's product development direction, please suggest the optimal manufacturing strategy for the next quarter.

[1605] Examples of advice that can be generated include specific manufacturing strategies su...

Claims

1. A means for analyzing accumulated data related to business management using a generative AI model; A means for providing advice to a user for making decisions regarding business management based on the analysis results analyzed by the generating AI model; means for recognizing emotions of the user using an emotion engine; means for adjusting the advice based on the recognized emotions of the user; A system including:

2. The accumulated data is data on at least one of market conditions, trends of competitors, and the direction of the company's product development; The system of claim 1 .

3. The adjusting means adjusts the advice based on a prompt sentence corresponding to the emotion of the user. The system of claim 1 .

Images