System

Abstract

A system is provided.SOLUTION: A system comprising: means for allowing a user to upload a file including management information based on an information format; means for confirming the information format of the uploaded file and automatically generating a database; and means for activating a generative AI model based on the automatically generated database, identifying a management problem, and proposing an optimal management measure.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When it comes to analyzing management data, small and medium-sized enterprises face difficulties in appropriate data management and decision-making due to a shortage of data scientists and engineers. There is also a need for a system that allows users without specialized knowledge to easily upload data and propose effective management measures based on that data. Furthermore, there is a need for a system that can connect with a variety of data sources and present optimal solutions to management issues. [Means for solving the problem]

[0005] The present invention is a system that includes a means for a user to upload a file containing management data based on a data format, a means for checking the data format of the uploaded file and automatically generating a database, and a means for activating a generative AI model based on the automatically generated database, identifying management issues, and proposing optimal management measures. This system allows even users without specialized knowledge to easily build a database and obtain effective management measures. Furthermore, by linking data from multiple data sources, it is possible to analyze more diverse data and improve the accuracy of management measures. Furthermore, by including a means for a user to check the proposed management measures and provide a specific implementation plan, it is possible to support feasible management strategies.

[0006] "Management data" refers to information related to a company's management activities, and includes, for example, financial data, inventory data, sales data, customer data, and the like.

[0007] "Data format" refers to the form or structure in which data is formatted, and includes, for example, specific file formats such as CSV format or Excel format.

[0008] "User" refers to a person who operates a system or an end user, including a person without specific knowledge.

[0009] "Upload" refers to the act of transferring data or files from a terminal to a server.

[0010] A "database" refers to a system for organizing and managing large amounts of data, and has a structure that includes multiple tables and relations.

[0011] "Automatic generation" refers to a process in which data is generated automatically without human intervention.

[0012] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to analyze data and generate solutions to specific problems.

[0013] "Management challenges" refer to management problems and obstacles that a company faces, such as optimizing inventory management, increasing sales, and acquiring new customers.

[0014] "Management measures" refer to specific measures and means for solving specific management issues.

[0015] "Data Source" refers to the origin or source of data and includes data from multiple different sources.

[0016] "Proposal" refers to the act of presenting a solution or plan of action for a particular situation. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] This invention relates to a system that allows users without specialized knowledge to easily upload management data and propose effective management measures based on that data. The system consists of a cloud server, a user terminal, and a generative AI model.

[0039] First, the user prepares a file containing management data from their device. This data typically includes sales data, customer data, inventory data, etc. Once the file is ready, the user uses a web browser to access the cloud server's management screen and log in. After logging in, the user accesses the "Data Upload" section, selects the prepared file, and clicks the "Upload" button.

[0040] The cloud server receives the uploaded file and temporarily stores it. The server then checks whether the received file conforms to the specified data format (e.g., CSV or Excel format). If the format is correct, the server automatically generates a database schema, creates the necessary tables, and stores the data.

[0041] After the database is automatically generated, the cloud server launches a generative AI model. The generative AI model analyzes the data in the database and identifies management issues. This identifies, for example, inventory surpluses or shortages, declining sales trends, and customer behavior patterns. The generative AI model then proposes optimal management measures to address these issues.

[0042] The proposed management measures are displayed on the user's dashboard from the cloud server. The user can access the dashboard using their device and check the proposed content. Specific measures include "optimizing inventory management," "adjusting new product promotion plans," and "optimizing marketing campaigns."

[0043] Specific examples

[0044] Example 1: Inventory management optimization

[0045] Users prepare inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and upload it to a cloud server. The server checks the received data, confirms that it is in the correct format, and then automatically generates a database. A generative AI model analyzes the data and generates a list of products with excess or shortages of stock. Suggested measures include "reducing the order quantity of a specific product" or "considering a new supplier." Users can view these suggestions on a dashboard and take appropriate action.

[0046] Example 2: Optimizing customer segmentation

[0047] Users prepare customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and upload it to a cloud server. The server verifies the data, checks that the format is correct, and then automatically generates a database. A generative AI model analyzes the customer data and classifies customers into multiple segments based on their value. Suggested measures include "implementing special campaigns for high-value customers" and "optimizing targeting strategies for new products." Users can view and implement these measures on the dashboard.

[0048] This system allows even users without specialist knowledge to effectively optimize their business operations through a series of processes: checking the data format, automatically generating a database, analyzing it using the generated AI model and proposing measures, and then having the user check and implement the measures.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] The user prepares a file containing management data from a terminal. The prepared data includes sales data, customer data, inventory data, etc.

[0052] Step 2:

[0053] The user uses a device to access the cloud server's management screen and logs in. By entering their user ID and password on the login screen, they are authenticated by the cloud server.

[0054] Step 3:

[0055] The user goes to the "Data Upload" section on the cloud server management screen, selects the prepared file, and clicks the "Upload" button to transfer the selected file to the server.

[0056] Step 4:

[0057] The server receives the uploaded file and temporarily stores it. Then, the server checks whether the file format matches the specified data format (e.g., CSV or Excel format). If the format is invalid, it displays an error message to the user.

[0058] Step 5:

[0059] After the server verifies the correct data format, it automatically generates a database schema, which defines the database table structure and creates the necessary tables. For example, for customer data, it creates a "customers" table.

[0060] Step 6:

[0061] The server reads the uploaded data, stores the data in an automatically generated table, and verifies that each data record is saved properly.

[0062] Step 7:

[0063] After the database is built, the server launches the generative AI model, which reads the data in the database and begins analyzing it.

[0064] Step 8:

[0065] Generative AI models analyze data and identify business issues, such as declining sales trends or lists of overstocked products.

[0066] Step 9:

[0067] Based on the analysis results, the server proposes specific management measures, such as "reducing the order volume of a specific product" or "reviewing the new customer targeting strategy."

[0068] Step 10:

[0069] The server displays the proposed management measures on the user's dashboard.

[0070] Step 11:

[0071] The user accesses the cloud server using a device and checks the proposed measures on the dashboard. The user understands these measures and decides whether to apply them.

[0072] Step 12:

[0073] The user then implements the proposed business actions as needed, for example, creating a new ordering plan or adjusting a marketing campaign.

[0074] Example 1

[0075] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0076] In today's business environment, many companies are required to effectively utilize massive amounts of management data and implement prompt and appropriate management measures. However, this requires specialized knowledge and expensive analytical tools, making it difficult for small and medium-sized enterprises, in particular, to utilize these effectively. Furthermore, when analyzing data from multiple data sources, it is difficult to ensure accuracy and reliability. This prevents companies from deriving optimal management measures, putting them at risk of losing their competitive edge.

[0077] 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.

[0078] In this invention, the server

[0079] means for a user to upload a file containing management data according to a data format;

[0080] means for checking the data format of the uploaded file and automatically generating a database;

[0081] Based on the automatically generated database, a generative AI model is launched to identify management issues and propose optimal management measures.

[0082] a means for displaying the proposed management measures on a user's dashboard;

[0083] This allows even users without specialized knowledge to easily upload data and implement effective management measures. In addition, linking and analyzing data from multiple data sources improves the accuracy of management measures.

[0084] "Management data" refers to data that includes information related to a company's management situation and business processes, such as sales data, customer data, and inventory data.

[0085] A "file" is a collection of information stored in digital form, generally in a specific data format such as CSV or Excel.

[0086] "Data format" refers to the way data is structured in a particular way, and can refer to standardized formats such as CSV or Excel.

[0087] "User" refers to an individual or company that operates this system to upload management data and receive analysis results and policy proposals.

[0088] A "database" refers to a collection of data stored in an organized manner, and is a system that allows for efficient data retrieval and manipulation.

[0089] A "generative AI model" refers to a model that uses machine learning and artificial intelligence techniques to analyze data and make predictions.

[0090] A "database schema" is a design document that defines the structure and format of data in a database, and indicates the configuration of tables and columns.

[0091] "Management issues" refer to problems a company faces or areas where there is room for improvement, including excess inventory, declining sales, and customer attrition.

[0092] "Management measures" refer to plans and strategies implemented to solve specific management issues, such as optimizing inventory management and adjusting marketing strategies.

[0093] A "dashboard" refers to an interface that allows users to visually check data analysis results and policy proposals.

[0094] This invention relates to a system that allows users without specialized knowledge to easily upload management data and propose effective management measures based on that data. The system consists of a cloud server, a user terminal, and a generative AI model.

[0095] First, the user prepares the management data using their own device. This management data includes sales data, customer data, inventory data, etc., and is generally saved in CSV or Excel format. After preparing this data, the user accesses the cloud server's management screen from a web browser and logs in. After successfully logging in, the user goes to the "Data Upload" section, selects the prepared file, and clicks the "Upload" button.

[0096] The cloud server temporarily stores the received file and checks whether the data format matches the specified format (e.g., CSV or Excel format). If the format is correct, the server automatically generates a database schema, creates the necessary tables, and stores the data. A database system such as MySQL or PostgreSQL is used to generate the database schema.

[0097] After the database is automatically generated, the cloud server launches a generative AI model. This generative AI model is built using machine learning libraries such as Python and TensorFlow. The generative AI model analyzes the data in the database and identifies management issues. For example, it can identify inventory surpluses or shortages, declining sales trends, and customer behavior patterns. Based on the analysis results, it proposes optimal management measures.

[0098] The proposed management measures are displayed on the user's dashboard from the cloud server. The user accesses the dashboard using a device and checks the proposed content. Specific measures include "optimizing inventory management," "adjusting new product promotion plans," and "optimizing marketing campaigns."

[0099] Specific examples

[0100] Example 1: Inventory management optimization

[0101] Users prepare inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and upload it to a cloud server. The server checks the received data, confirms that it is in the correct format, and then automatically generates a database. A generative AI model analyzes the data and generates a list of products with excess or shortages of stock. Suggested measures include "reducing the order quantity of a specific product" or "considering a new supplier." Users can view these suggestions on a dashboard and take appropriate action.

[0102] Example 2: Optimizing customer segmentation

[0103] Users prepare customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and upload it to a cloud server. The server verifies the data, checks that the format is correct, and then automatically generates a database. A generative AI model analyzes the customer data and classifies customers into multiple segments based on their value. Suggested measures include "implementing special campaigns for high-value customers" and "optimizing targeting strategies for new products." Users can view and implement these measures on the dashboard.

[0104] Prompt Sentence Examples

[0105] "Analyze this inventory data to identify overstocked or understocked items and suggest appropriate inventory management methods."

[0106] "Please analyze this customer data, segment customers based on their value, and propose the most appropriate marketing measures for each segment."

[0107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0108] Step 1:

[0109] The user prepares management data from a device. The user prepares a CSV or Excel file containing their company's sales data, customer data, inventory data, etc. on a device such as a PC or tablet. This involves organizing the necessary data into columns and converting it into the appropriate file format. The input data is various management data such as sales, customers, and inventory, and the output data is a CSV or Excel file in which that data is saved.

[0110] Step 2:

[0111] The user logs in to the cloud server and uploads data. The user opens a web browser and accesses the cloud server's management screen. They log in by entering their account information and proceed to the "Data Upload" section. There, they select the prepared data file and click the "Upload" button. The input data is the login information and management data file, and the output data is the management data file uploaded to the cloud server.

[0112] Step 3:

[0113] The server checks the received data and verifies the data format. The server temporarily saves the uploaded file and checks whether the file format matches the specified data format (CSV or Excel format). Specifically, the server checks the name and data type of each column and verifies that the format is correct. The input data is the uploaded management data file, and the output data is the confirmation result of whether the format is correct or incorrect.

[0114] Step 4:

[0115] The server automatically generates the database schema. After verifying that the data format is correct, the server automatically generates the database schema. Specifically, it designs the necessary tables and columns based on the received data and generates a database based on that. The input data is the verified management data file, and the output data is the automatically generated database schema and the data stored in the database.

[0116] Step 5:

[0117] The server launches the generative AI model and performs data analysis. The server launches the generative AI model and analyzes the data in the database. This analysis uses machine learning libraries such as Python and TensorFlow. The generative AI model performs statistical analysis and pattern recognition to identify management issues. The input data is the management data in the database, and the output data is the identified management issues and the analysis results.

[0118] Step 6:

[0119] The server displays the analysis results and management measures on the user's dashboard. After the generative AI model completes its analysis, the server displays the results on the user's dashboard. The analysis results may include, for example, "There is an excess of inventory for a particular product" or "Sales are on a downward trend." Based on this, optimal management measures are proposed. The input data are the analysis results of the generative AI model, and the output data are proposed management measures that are displayed on the user's dashboard.

[0120] Step 7:

[0121] The user checks the proposed management measures and takes the necessary actions. The user accesses the dashboard and checks the proposed management measures. For example, "Optimizing inventory management" displays measures such as "reducing the order quantity of certain products" and "considering new suppliers." The user makes their own management decisions based on these suggestions and takes appropriate actions. The input data are the proposed management measures displayed on the dashboard, and the output data are the specific actions the user will take.

[0122] (Application example 1)

[0123] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0124] There is an increasing need for businesses to be able to easily optimize their operations without specialized knowledge by effectively utilizing management data. However, current systems require users to check complex data formats, generate databases, and use specialized analysis methods, making them difficult to use for many users. Furthermore, there is a lack of clear guidance on how the resulting management measures should be implemented, making it difficult for brick-and-mortar stores to make appropriate decisions. This can delay the rapid resolution of management issues and the implementation of effective management measures.

[0125] 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.

[0126] In this invention, the server includes means for a user to upload a file containing management data based on a data format, means for checking the data format of the uploaded file and automatically generating a database, means for activating a generative AI model based on the automatically generated database, identifying management issues, and proposing optimal management measures, and means for a user to check the proposed management measures on a dashboard via a smartphone.

[0127] This allows users without specialized knowledge to upload management data intuitively, and then easily check and implement specific measures based on that data on their smartphones.

[0128] "Management data" includes information related to a company's management activities, such as sales data, customer data, and inventory data.

[0129] A "data format" refers to the format or structure in which data is stored, and includes formats such as CSV and Excel.

[0130] A "generative AI model" is a pre-trained artificial intelligence algorithm and structure that identifies management issues based on input data and proposes optimal measures.

[0131] A "dashboard" is an interface that allows users to visually check and manipulate information, and is displayed on smartphones and other devices.

[0132] A "database" is a system that efficiently stores and manages data, and is composed of multiple tables and schemas.

[0133] "Automatic generation" means that the system follows specified procedures, eliminating the need for manual operation, and autonomously checks data formats and builds databases.

[0134] "Management measures" refer to specific action plans and strategies implemented to solve a company's management issues.

[0135] "Uploading" is the act of a user transferring their own data from a local environment to a remote environment such as a cloud server.

[0136] "Means" includes processes, techniques, or devices used to achieve a particular end.

[0137] A "proposal" is a solution or action plan that the generative AI model presents to the user based on data analysis.

[0138] This invention relates to a system that allows even users without specialized knowledge to easily upload management data and propose effective management measures based on that data. How this system is implemented will be explained below in detail.

[0139] 1. System Overview

[0140] This system consists of a cloud server, a user device (smartphone), and a generative AI model. Its main functions are as follows:

[0141] Management data upload function

[0142] Data format confirmation function

[0143] Automatic database generation function

[0144] Data analysis and policy proposal function using generative AI

[0145] Dashboard-based policy display function

[0146] 2. Hardware and Software Used

[0147] Hardware:

[0148] Smartphone: Used by users to upload data and review measures.

[0149] Cloud server: Stores data, analyzes data, and performs recommendations.

[0150] software:

[0151] Data format confirmation: Uses Python's Pandas library.

[0152] Database Management: MySQL or PostgreSQL.

[0153] Generative AI model: TensorFlow or PyTorch.

[0154] User interface: Smartphone app using React Native.

[0155] 3. System processing flow

[0156] The main processing flow of this system is as follows:

[0157] Data upload: Users use a smartphone app to upload inventory data and customer data in CSV or Excel format to a cloud server.

[0158] Data format verification: The cloud server uses a Python script (Pandas) to verify the format of the uploaded data.

[0159] Automatic database generation: Once the data is confirmed to be in the correct format, it is automatically stored in a database such as MySQL or PostgreSQL.

[0160] Generative AI analysis: Based on the data stored in the database, generative AI models such as TensorFlow and PyTorch analyze the data.

[0161] Display of measures: Analysis results and proposed measures are displayed on the dashboard of the smartphone app.

[0162] 4. Specific Examples

[0163] Example 1: Sales promotion proposal

[0164] Prompt: "Please suggest the best sales promotion measures based on sales and customer data from the past six months."

[0165] Example 2: Optimizing inventory management

[0166] Prompt: "Based on current inventory data and past sales trends, please suggest the optimal order quantity for this month."

[0167] This allows users without specialized knowledge to intuitively upload management data and easily check and implement specific measures based on that data on their smartphones.

[0168] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0169] Step 1:

[0170] The user prepares management data using a device (smartphone) and launches the application. The file selection screen for uploading opens. The user selects a data file in CSV or Excel format (e.g., inventory data or customer data) from their local storage.

[0171] Input: CSV or Excel format data file

[0172] Output: Selected data files ready to upload

[0173] Step 2:

[0174] The device (smartphone) uploads the selected data file to the cloud server. The file is sent to the server using the HTTP protocol and temporarily stored.

[0175] Input: Selected data file

[0176] Output: Data file uploaded to the server

[0177] Step 3:

[0178] The server checks the format of the received data file using the Python Pandas library. Specifically, it checks whether the matrix structure and data types of the file are correct, and if the format is correct, it proceeds to the next step.

[0179] Input: Data file uploaded to the server

[0180] Output: Format check result (correct / incorrect)

[0181] Step 4:

[0182] Once the data is verified to be in the correct format, the server stores it in a MySQL or PostgreSQL database, automatically generating the database schema and creating the necessary tables and columns.

[0183] Input: Format-checked data file

[0184] Output: Data stored in a database

[0185] Step 5:

[0186] The server runs a generative AI model (TensorFlow or PyTorch) based on the data stored in the database. This model analyzes the data, identifies specific business issues, and proposes optimal management measures, such as analyzing inventory surpluses or shortages, declining sales trends, and customer behavior patterns.

[0187] Input: Data stored in a database

[0188] Output: Analysis results and proposed management measures

[0189] Step 6:

[0190] The proposed management measures are sent from the cloud server to the device (smartphone). The device application displays these measures on the user's dashboard. The user can check the details of the measures through the dashboard.

[0191] Input: Analysis results and proposed management measures

[0192] Output: Business measures displayed on the user's dashboard

[0193] Step 7:

[0194] Users can check the measures on the dashboard and select specific actions, such as "optimizing inventory management" or "adjusting new product promotion plans," to determine specific operations for physical stores.

[0195] Input: Suggestions displayed on the dashboard

[0196] Output: The specific action the user chooses to take

[0197] This processing flow enables users, even without specialized knowledge, to easily upload management data and confirm and implement specific measures based on the results of data analysis.

[0198] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0199] This invention relates to a system that allows users without specialized knowledge to easily manage management data and proposes optimal management measures using a generative AI model. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it has the advantage of being able to adaptively change the proposal content and UI / UX according to the user's emotions. This system consists of a cloud server, a user's device, a generative AI model, and an emotion engine.

[0200] First, the user prepares a file containing management data from their device. This data includes sales data, customer data, inventory data, etc. Once the file is ready, the user logs in to the cloud server's management screen and accesses the "Data Upload" section. Here, the user selects the file and uploads it.

[0201] The server receives the file and checks whether it matches the specified data format (e.g., CSV or Excel). If the format is correct, the server automatically generates a database schema, imports the data, and creates the necessary tables. It then launches a generative AI model to identify management issues based on the data in the database and propose optimal management measures. During this process, the emotion engine collects and analyzes emotion data from the user's device. Emotion data includes facial expressions, tone of voice, and biometric data such as oximeter readings.

[0202] The user's emotional data detected by the emotion engine influences the analysis results of the generative AI model. For example, if the user is feeling stressed, the server will take that emotion into account and simplify the explanation of suggested management measures, presenting only high-priority tasks. The dashboard's UI / UX is also dynamically adjusted based on the emotion engine's data, providing the user with the most comfortable interface.

[0203] Specific examples

[0204] Example 1: Inventory management optimization

[0205] The user prepares inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and uploads it to the server. The server checks that the data is in the correct format and automatically generates a database. The generative AI model analyzes the data and identifies products that are overstocked or understocked. The emotion engine analyzes the user's emotions, and if it determines that the user is feeling stressed, for example, the server simplifies the suggestions and presents them with a focus on high-priority measures (e.g., stopping orders for products with excessive inventory).

[0206] Example 2: Optimizing customer segmentation

[0207] Users prepare customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and upload it to the server. After the data format is confirmed, the server automatically generates a database and imports the data. A generative AI model analyzes the customer data and classifies customers into multiple value-based segments. An emotion engine captures the user's emotions, and if the user expresses positive emotions, for example, the server makes more detailed and strategic marketing suggestions. The color and design of the dashboard are also dynamically adjusted based on the user's emotions.

[0208] In this way, the present invention is a system that not only automatically manages management data and proposes optimal management measures using a generative AI model, but also recognizes and responds to user emotions to make more personalized proposals.

[0209] The processing flow will be explained below.

[0210] Step 1:

[0211] The user prepares a file containing management data from a terminal. The file typically includes sales data, customer data, inventory data, etc.

[0212] Step 2:

[0213] The user uses a terminal to access the cloud server's management screen and logs in. They enter their user ID and password on the login screen to be authenticated.

[0214] Step 3:

[0215] The user goes to the "Data Upload" section on the admin page, selects the prepared file, and clicks the upload button.

[0216] Step 4:

[0217] The server receives the uploaded file and temporarily stores it. The server checks whether the received file conforms to the specified data format (e.g., CSV or Excel format). If the format is inappropriate, an error message is displayed to the user.

[0218] Step 5:

[0219] After the server verifies the correct data format, it automatically generates the database schema, defines the database table structure, and creates the necessary tables, such as "customers" and "inventory."

[0220] Step 6:

[0221] The server stores the uploaded data in an automatically generated table, and each data record is saved appropriately and the database is updated.

[0222] Step 7:

[0223] The cloud server launches the generative AI model, which reads the data from the database and begins analyzing it.

[0224] Step 8:

[0225] The emotion engine acquires emotion data from the user's device, including the user's facial expression, voice tone, heart rate, etc.

[0226] Step 9:

[0227] Generative AI models analyze data to identify business issues, such as declining sales trends, inventory overhangs or shortages, and patterns of customer behavior.

[0228] Step 10:

[0229] The server analyzes the data from the emotion engine and adjusts the suggestions based on the user's emotions. For example, if the user is feeling stressed, the suggested actions will be simplified and only the most important points will be highlighted.

[0230] Step 11:

[0231] Based on the analysis results, the server proposes specific management measures, such as "reducing the order volume of certain products" or "reviewing new customer targeting strategies."

[0232] Step 12:

[0233] The server displays the proposed management measures on the user's dashboard, and the dashboard's UI / UX is also dynamically adjusted based on the emotion engine data.

[0234] Step 13:

[0235] The user accesses the dashboard from a device and checks the proposed measures. The user understands these measures and decides whether to apply them.

[0236] Step 14:

[0237] Users can then implement the proposed business measures as needed, such as reviewing ordering plans or adjusting marketing campaigns.

[0238] In this way, the present invention is a system that manages data and proposes optimal management measures while responding to the user's emotions.

[0239] Example 2

[0240] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0241] Traditionally, managing and analyzing business data required specialized knowledge and experience, making it difficult for average users to easily undertake the task. Furthermore, the lack of appropriate management proposals that took user feelings into consideration can lead to increased stress and burden on users. Furthermore, there was a need for a flexible response to the user's feelings and circumstances regarding the analysis results.

[0242] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to upload a file containing management data based on a data format; means for checking the data format of the uploaded file and automatically generating a database; means for activating a generative AI model based on the automatically generated database, identifying management issues, and proposing optimal management measures; means for acquiring user emotion data and analyzing it with an emotion analysis engine; and means for dynamically adjusting the proposals of the generative AI model based on the user's emotions and adaptively changing the user interface and user experience. This makes it possible for even users without specialized knowledge to easily manage management data, and by combining the generative AI model and the emotion analysis engine, it is possible to propose optimal management measures based on the user's emotions.

[0243] "Management data" refers to numerical values ​​and information related to the operation of a company or organization, including sales data, customer data, inventory data, etc.

[0244] A "data format" is a specification that defines the format and structure for storing data. For example, CSV and Excel formats fall into this category.

[0245] "User" refers to an individual or organization that uses this system. Specifically, the entity that uploads management data and receives analysis results.

[0246] "Upload" refers to the act of a user transferring a data file from their own device to a remote system such as a cloud server.

[0247] "Automatic generation" refers to the system building databases and other structures based on predetermined rules without manual user intervention.

[0248] A "database" is a system for systematically organizing and storing data. It includes relational database management systems (RDBMS).

[0249] A "generative AI model" is a pre-trained artificial intelligence model that performs analysis based on input data and proposes management measures.

[0250] "Emotion data" is information that indicates the user's emotional state, and includes facial expressions, tone of voice, biometric data, and the like.

[0251] An "emotion analysis engine" is software or hardware that analyzes a user's emotional data acquired from a terminal and grasps their emotional state.

[0252] "User interface" refers to the means of interaction between a system and a user, including the screens, buttons, and dashboards that users operate.

[0253] "User experience" refers to the satisfaction and ease of use that users feel when using a system, and is influenced by factors such as the system's intuitive usability and visual design.

[0254] This invention relates to a system that allows users without specialized knowledge to easily manage management data and propose optimal management measures using a generative AI model. Furthermore, by combining it with an emotion analysis engine that recognizes user emotions, it has the advantage of being able to adaptively change the proposal content and UI / UX according to the user's emotions. This system consists of a cloud server, a user's device, a generative AI model, and an emotion analysis engine.

[0255] User preparation and upload of data files

[0256] First, the user prepares a file containing management data from a device (such as a PC or tablet). The file includes sales data, customer data, inventory data, etc. This file is saved in CSV or Excel format using Microsoft Excel or Google Sheets.

[0257] Next, the user logs in to the cloud server's administration screen using a web browser (e.g., Google Chrome or Firefox). After logging in, the user accesses the "Data Upload" section, opens a file selection dialog, and uploads the prepared file.

[0258] Server checks and imports data format

[0259] The server receives the uploaded file. It then uses the Python library pandas to verify that the data format of the file is correct. Once this verification is complete, the server automatically generates a database schema and populates it with the data. This database is typically a relational database management system (RDBMS) such as MySQL or PostgreSQL. The server then creates the appropriate tables and inserts the data.

[0260] Identifying and proposing management issues using generative AI models

[0261] After the server completes the generation of the database schema, it launches a generative AI model (e.g., OpenAI's GPT-4). The generative AI model identifies business issues based on the data in the database and proposes optimal business measures. An example of a prompt sentence used here is as follows:

[0262] "Based on current inventory data, identify excess or shortage items and suggest the best course of action."

[0263] Analyzing user emotions using an emotion analysis engine

[0264] The emotion analysis engine acquires emotion data from the user's device, including facial expressions (camera), tone of voice (microphone), and biometric data such as oximetry. Software such as Affectiva or Microsoft Azure Emotion API is used for emotion analysis.

[0265] The user's emotional data detected by the emotion analysis engine influences the analysis results of the generative AI model. For example, if the user is feeling stressed, the generative AI model will simplify its suggestions and present only high-priority tasks. The dashboard's UI / UX is also dynamically adjusted based on the data from the emotion analysis engine, providing the user with the most comfortable interface.

[0266] Specific examples

[0267] Example 1: Inventory management optimization

[0268] The user prepares inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and uploads it to the server. The server checks that the data is in the correct format and automatically generates a database. A generative AI model analyzes the data and identifies products that are overstocked or understocked. The sentiment analysis engine analyzes the user's emotions, and if it determines that the user is feeling stressed, for example, the server simplifies its suggestions and focuses on high-priority measures (e.g., stopping orders for products with excessive inventory).

[0269] Example 2: Optimizing customer segmentation

[0270] The user prepares customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and uploads it to the server. Once the data format has been confirmed, the server automatically generates a database and imports the data. A generative AI model analyzes the customer data and classifies customers into multiple segments based on their value. A sentiment analysis engine obtains the user's emotions, and if the user expresses positive emotions, for example, the server makes more detailed and strategic marketing proposals. The color and design of the dashboard are also dynamically adjusted based on the user's emotions. In this way, the present invention is a system that not only automatically manages management data and proposes optimal management measures using a generative AI model, but also recognizes and responds to user emotions to make more personalized proposals.

[0271] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0272] Step 1:

[0273] The user prepares the business data.

[0274] Users use a device (such as a PC or tablet) to input management data into an application such as Microsoft Excel or Google Sheets. Once the data is input, the file is saved in CSV or Excel format. The input in this case is a data file (e.g., sales data, customer data, inventory data) created using data editing software such as Excel. The output is a prepared management data file.

[0275] Step 2:

[0276] A user uploads a data file to a cloud server.

[0277] The user logs in to the cloud server's management screen using a web browser (e.g., Google Chrome or Firefox). After logging in, the user accesses the "Data Upload" section, opens the file selection dialog, selects the prepared file, and presses the upload button to send it to the server. The input is the management data file, and the output is the file saved on the server.

[0278] Step 3:

[0279] The server checks the data format of the uploaded file.

[0280] The server receives the uploaded file and checks the data format using Python's pandas library. Specifically, it checks the consistency of the data according to the CSV or Excel format and checks whether required columns (e.g., product ID, inventory amount, purchase price, etc.) are present. The input is the uploaded management data file, and the output is the verification result of whether the format is correct.

[0281] Step 4:

[0282] The server automatically generates the database schema and populates it with data.

[0283] The server automatically generates a database schema based on a data file that has been validated for correct formatting. The database used may be, for example, MySQL or PostgreSQL. The server creates the appropriate tables and inserts the data from the file into them. The input is the validated data file; the output is the constructed database schema and the inserted data.

[0284] Step 5:

[0285] The server launches the generative AI model to identify management issues.

[0286] The server launches a generative AI model (e.g., OpenAI GPT-4) and analyzes the data in the database. For example, the following prompt is input to the generative AI model: "Based on current inventory data, please identify any excess or shortage of products and propose the optimal solution." The input is the management data in the database and the prompt, and the output is the analysis results and proposals from the generative AI model.

[0287] Step 6:

[0288] The emotion analysis engine acquires and analyzes the user's emotion data.

[0289] The emotion analysis engine acquires and analyzes biometric data such as facial expressions (camera), tone of voice (microphone), and oximeter data from the user's device. Software such as Affectiva or Microsoft Azure Emotion API is used for emotion analysis. The input is the user's emotional data, and the output is the analyzed emotional state.

[0290] Step 7:

[0291] The server dynamically adjusts the suggestions based on the results of the generative AI model and sentiment analysis engine.

[0292] The server combines the analysis results of the generative AI model with the emotional data from the emotion analysis engine to dynamically adjust the management policy proposals according to the user's emotional state. For example, if the user is feeling stressed, the proposals will be simplified and only high-priority tasks will be presented. The color and design of the dashboard will also be dynamically changed based on the emotional data. The inputs are the generative AI model's proposals and the results of the emotion analysis, and the output is the adjusted proposals and modified UI / UX.

[0293] (Application example 2)

[0294] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0295] Conventional business management systems make it difficult for users without specialized knowledge to properly manage data and plan management policies. Furthermore, they lack the ability to provide personalized suggestions and adjust the interface to take user emotions into account, resulting in a poor user experience. Therefore, there is a need for a system that can easily manage management data, propose optimal management policies using generative AI models, and dynamically adjust the proposal content and user interface according to user emotions.

[0296] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to upload a file containing management data based on a data format, means for checking the data format of the uploaded file and automatically generating a database, means for activating a generative AI model based on the automatically generated database to identify management issues and propose optimal management measures, and means for analyzing the user's facial expressions and tone of voice and dynamically adjusting the proposal content and user interface based on their emotions. This enables users to easily manage management data and receive proposals for optimal management measures without having specialized knowledge, and improves the user experience by adjusting the proposal content and user interface to be personalized according to the user's emotions.

[0297] "Management data" refers to sales data, customer data, inventory data, etc., necessary for business activities.

[0298] "Data format" refers to the format of data that is organized according to a specific format or structure, such as CSV format or Excel format.

[0299] "Means for users to upload" refers to a function that allows users to select files through an interface and send them to the cloud server.

[0300] "Automatically generated database" refers to a database environment automatically generated by the server based on uploaded data.

[0301] "Generative AI model" refers to an artificial intelligence model used to analyze data uploaded by users, identify management issues, and propose optimal management measures.

[0302] "Management issues" refer to problems a company faces or areas that need improvement.

[0303] "Optimal management measures" refer to specific measures for improving management proposed based on the generative AI model.

[0304] "Means for analyzing a user's facial expressions and tone of voice" refers to technology or software for collecting and analyzing a user's facial expressions and tone of voice using a camera or microphone.

[0305] "Means for dynamically adjusting suggested content and user interface based on emotions" refers to technology that optimizes suggested content and interface design in real time based on analyzed user emotional data.

[0306] This invention relates to a system that efficiently manages a company's management data and proposes optimal management measures using a generative AI model. Furthermore, it has the advantage of analyzing the user's emotions and dynamically adjusting the proposal content and user interface based on those emotions. This system consists of a cloud server, a user device, a generative AI model, and an emotion recognition engine.

[0307] System configuration

[0308] Hardware

[0309] Cloud server: receives, stores, and analyzes data, and runs generative AI models.

[0310] User devices: Smartphones and PCs are mainly used to upload data, collect emotion data, and display the interface.

[0311] software

[0312] Data management software: Pandas, Flask, etc., used to check data formats and automatically generate and manage databases.

[0313] Generative AI model: Used to analyze management data, identify management issues, and propose optimal management measures.

[0314] Emotion Recognition Engine: Software that processes data from the camera and microphone to analyze the user's facial expressions and tone of voice.

[0315] Data flow

[0316] 1. Upload your data

[0317] Users upload sales data, customer data, inventory data, etc. in CSV or Excel format from their devices to the cloud server.

[0318] The uploaded file is checked on the server side to see if the data format is correct.

[0319] 2. Automatic database generation

[0320] Once the data is confirmed to be in the correct format, the server automatically generates a database schema to incorporate the uploaded data.

[0321] Creates the necessary tables and checks the integrity of the data.

[0322] 3. Analysis of generative AI models

[0323] The server launches the generative AI model and analyzes the management data in the database.

[0324] Identify management issues and propose optimal management measures.

[0325] 4. Emotional Data Collection and Analysis

[0326] The user's device uses a camera and microphone to collect facial expressions and tone of voice, which are then analyzed using an emotion recognition engine.

[0327] Emotional data (e.g., stress, joy, interest, etc.) is captured in real time and transmitted to a server.

[0328] 5. Dynamic suggestions and user interface adjustments

[0329] The server dynamically adjusts the recommendations and dashboard interface based on the acquired emotional data.

[0330] For example, if the user is feeling stressed, the suggestions will be simplified and only high-priority management measures will be presented.

[0331] Considering emotions improves the user experience.

[0332] Specific examples

[0333] 1. Optimizing inventory management

[0334] The user prepares inventory data in CSV format and uploads it to the cloud server.

[0335] The server checks the data format and automatically generates the database.

[0336] Generative AI models analyze inventory data to identify overstocked or understocked items.

[0337] If the user is feeling stressed, the suggestions will be brief and will focus on stopping orders for excess inventory items.

[0338] 2. Optimizing customer segmentation

[0339] The user prepares customer data in Excel format and uploads it to the cloud server.

[0340] After the data format is confirmed, the server automatically creates and populates the database.

[0341] A generative AI model analyzes customer data and categorizes customers into segments.

[0342] If the user indicates positive sentiment, the server will provide more detailed marketing suggestions.

[0343] Prompt Sentence Examples

[0344] python

[0345] camera_feed = get_camera_feed() Gets the camera feed from a smartphone

[0346] audio_feed = get_audio_feed() Gets the smartphone's microphone audio

[0347] file_path = 'path / to / user_upload.csv'

[0348] suggestions, ui_ux_config = main(file_path, camera_feed, audio_feed)

[0349] print("Business policy proposals: ", suggestions)

[0350] print("UI / UX settings: ", ui_ux_config)

[0351] This allows users to easily manage management data without specialized knowledge and receive optimal management policy proposals from generative AI models.Furthermore, personalized proposals based on emotions and user interface adjustments improve the user experience.

[0352] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0353] Step 1:

[0354] The user prepares management data in CSV or Excel format, logs in to the cloud server's management screen, and accesses the "Data Upload" section. Here, the user selects the file and uploads it to the cloud server. The input for this step is the CSV or Excel file, and the output is a notification that the file has been uploaded to the cloud server.

[0355] Step 2:

[0356] The server receives the uploaded file and checks its data format. Specifically, it uses Pandas to read CSV or Excel files and checks the format for consistency. The input of this step is the uploaded file, and the output is the format check result. If the format is correct, it proceeds to the next step.

[0357] Step 3:

[0358] The server automatically generates the database schema and populates the database with data. Specifically, it uses Flask to generate the database and inserts data from Pandas into the database. The input for this step is the verified data file, and the output is the generated database and stored data.

[0359] Step 4:

[0360] The server launches the generative AI model and analyzes the data in the database. The generative AI model identifies management issues as a result of the analysis and proposes optimal management measures. The input for this step is the data in the database, and the output is proposed management measures.

[0361] Step 5:

[0362] The user device uses a camera and microphone to collect facial expressions and tone of voice, which are then analyzed by an emotion recognition engine. Specifically, the EmotionEngine is used to acquire and analyze emotional data. The input of this step is the user's facial and voice data, and the output is emotional data.

[0363] Step 6:

[0364] The server receives the acquired emotional data and dynamically adjusts the proposals and user interface based on that data. Specifically, it changes the UI / UX settings based on the emotional data to provide the user with an optimal interface. The input of this step is emotional data, and the output is an adjusted UI / UX proposal.

[0365] Step 7:

[0366] The adjusted proposal and user interface are displayed to the user. The user checks the provided management measures and takes necessary actions. The input of this step is the adjusted proposal from the server, and the output is the user's decision and action.

[0367] This allows users to easily manage management data without specialized knowledge and receive optimal management proposals from generative AI models. Personalization based on emotion recognition also improves the user experience.

[0368] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0369] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0370] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0371] [Second embodiment]

[0372] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0373] 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.

[0374] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0375] 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.

[0376] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0377] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0378] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0379] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0384] This invention relates to a system that allows users without specialized knowledge to easily upload management data and propose effective management measures based on that data. The system consists of a cloud server, a user terminal, and a generative AI model.

[0385] First, the user prepares a file containing management data from their device. This data typically includes sales data, customer data, inventory data, etc. Once the file is ready, the user uses a web browser to access the cloud server's management screen and log in. After logging in, the user accesses the "Data Upload" section, selects the prepared file, and clicks the "Upload" button.

[0386] The cloud server receives the uploaded file and temporarily stores it. The server then checks whether the received file conforms to the specified data format (e.g., CSV or Excel format). If the format is correct, the server automatically generates a database schema, creates the necessary tables, and stores the data.

[0387] After the database is automatically generated, the cloud server launches a generative AI model. The generative AI model analyzes the data in the database and identifies management issues. This identifies, for example, inventory surpluses or shortages, declining sales trends, and customer behavior patterns. The generative AI model then proposes optimal management measures to address these issues.

[0388] The proposed management measures are displayed on the user's dashboard from the cloud server. The user can access the dashboard using their device and check the proposed content. Specific measures include "optimizing inventory management," "adjusting new product promotion plans," and "optimizing marketing campaigns."

[0389] Specific examples

[0390] Example 1: Inventory management optimization

[0391] Users prepare inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and upload it to a cloud server. The server checks the received data, confirms that it is in the correct format, and then automatically generates a database. A generative AI model analyzes the data and generates a list of products with excess or shortages of stock. Suggested measures include "reducing the order quantity of a specific product" or "considering a new supplier." Users can view these suggestions on a dashboard and take appropriate action.

[0392] Example 2: Optimizing customer segmentation

[0393] Users prepare customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and upload it to a cloud server. The server verifies the data, checks that the format is correct, and then automatically generates a database. A generative AI model analyzes the customer data and classifies customers into multiple segments based on their value. Suggested measures include "implementing special campaigns for high-value customers" and "optimizing targeting strategies for new products." Users can view and implement these measures on the dashboard.

[0394] This system allows even users without specialist knowledge to effectively optimize their business operations through a series of processes: checking the data format, automatically generating a database, analyzing it using the generated AI model and proposing measures, and then having the user check and implement the measures.

[0395] The processing flow will be explained below.

[0396] Step 1:

[0397] The user prepares a file containing management data from a terminal. The prepared data includes sales data, customer data, inventory data, etc.

[0398] Step 2:

[0399] The user uses a device to access the cloud server's management screen and logs in. By entering their user ID and password on the login screen, they are authenticated by the cloud server.

[0400] Step 3:

[0401] The user goes to the "Data Upload" section on the cloud server management screen, selects the prepared file, and clicks the "Upload" button to transfer the selected file to the server.

[0402] Step 4:

[0403] The server receives the uploaded file and temporarily stores it. Then, the server checks whether the file format matches the specified data format (e.g., CSV or Excel format). If the format is invalid, it displays an error message to the user.

[0404] Step 5:

[0405] After the server verifies the correct data format, it automatically generates a database schema, which defines the database table structure and creates the necessary tables. For example, for customer data, it creates a "customers" table.

[0406] Step 6:

[0407] The server reads the uploaded data, stores the data in an automatically generated table, and verifies that each data record is saved properly.

[0408] Step 7:

[0409] After the database is built, the server launches the generative AI model, which reads the data in the database and begins analyzing it.

[0410] Step 8:

[0411] Generative AI models analyze data and identify business issues, such as declining sales trends or lists of overstocked products.

[0412] Step 9:

[0413] Based on the analysis results, the server proposes specific management measures, such as "reducing the order volume of a specific product" or "reviewing the new customer targeting strategy."

[0414] Step 10:

[0415] The server displays the proposed management measures on the user's dashboard.

[0416] Step 11:

[0417] The user accesses the cloud server using a device and checks the proposed measures on the dashboard. The user understands these measures and decides whether to apply them.

[0418] Step 12:

[0419] The user then implements the proposed business actions as needed, for example, creating a new ordering plan or adjusting a marketing campaign.

[0420] Example 1

[0421] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0422] In today's business environment, many companies are required to effectively utilize massive amounts of management data and implement prompt and appropriate management measures. However, this requires specialized knowledge and expensive analytical tools, making it difficult for small and medium-sized enterprises, in particular, to utilize these effectively. Furthermore, when analyzing data from multiple data sources, it is difficult to ensure accuracy and reliability. This prevents companies from deriving optimal management measures, putting them at risk of losing their competitive edge.

[0423] 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.

[0424] In this invention, the server

[0425] means for a user to upload a file containing management data according to a data format;

[0426] means for checking the data format of the uploaded file and automatically generating a database;

[0427] Based on the automatically generated database, a generative AI model is launched to identify management issues and propose optimal management measures.

[0428] a means for displaying the proposed management measures on a user's dashboard;

[0429] This allows even users without specialized knowledge to easily upload data and implement effective management measures. In addition, linking and analyzing data from multiple data sources improves the accuracy of management measures.

[0430] "Management data" refers to data that includes information related to a company's management situation and business processes, such as sales data, customer data, and inventory data.

[0431] A "file" is a collection of information stored in digital form, generally in a specific data format such as CSV or Excel.

[0432] "Data format" refers to the way data is structured in a particular way, and can refer to standardized formats such as CSV or Excel.

[0433] "User" refers to an individual or company that operates this system to upload management data and receive analysis results and policy proposals.

[0434] A "database" refers to a collection of data stored in an organized manner, and is a system that allows for efficient data retrieval and manipulation.

[0435] A "generative AI model" refers to a model that uses machine learning and artificial intelligence techniques to analyze data and make predictions.

[0436] A "database schema" is a design document that defines the structure and format of data in a database, and indicates the configuration of tables and columns.

[0437] "Management issues" refer to problems a company faces or areas where there is room for improvement, including excess inventory, declining sales, and customer attrition.

[0438] "Management measures" refer to plans and strategies implemented to solve specific management issues, such as optimizing inventory management and adjusting marketing strategies.

[0439] A "dashboard" refers to an interface that allows users to visually check data analysis results and policy proposals.

[0440] This invention relates to a system that allows users without specialized knowledge to easily upload management data and propose effective management measures based on that data. The system consists of a cloud server, a user terminal, and a generative AI model.

[0441] First, the user prepares the management data using their own device. This management data includes sales data, customer data, inventory data, etc., and is generally saved in CSV or Excel format. After preparing this data, the user accesses the cloud server's management screen from a web browser and logs in. After successfully logging in, the user goes to the "Data Upload" section, selects the prepared file, and clicks the "Upload" button.

[0442] The cloud server temporarily stores the received file and checks whether the data format matches the specified format (e.g., CSV or Excel format). If the format is correct, the server automatically generates a database schema, creates the necessary tables, and stores the data. A database system such as MySQL or PostgreSQL is used to generate the database schema.

[0443] After the database is automatically generated, the cloud server launches a generative AI model. This generative AI model is built using machine learning libraries such as Python and TensorFlow. The generative AI model analyzes the data in the database and identifies management issues. For example, it can identify inventory surpluses or shortages, declining sales trends, and customer behavior patterns. Based on the analysis results, it proposes optimal management measures.

[0444] The proposed management measures are displayed on the user's dashboard from the cloud server. The user accesses the dashboard using a device and checks the proposed content. Specific measures include "optimizing inventory management," "adjusting new product promotion plans," and "optimizing marketing campaigns."

[0445] Specific examples

[0446] Example 1: Inventory management optimization

[0447] Users prepare inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and upload it to a cloud server. The server checks the received data, confirms that it is in the correct format, and then automatically generates a database. A generative AI model analyzes the data and generates a list of products with excess or shortages of stock. Suggested measures include "reducing the order quantity of a specific product" or "considering a new supplier." Users can view these suggestions on a dashboard and take appropriate action.

[0448] Example 2: Optimizing customer segmentation

[0449] Users prepare customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and upload it to a cloud server. The server verifies the data, checks that the format is correct, and then automatically generates a database. A generative AI model analyzes the customer data and classifies customers into multiple segments based on their value. Suggested measures include "implementing special campaigns for high-value customers" and "optimizing targeting strategies for new products." Users can view and implement these measures on the dashboard.

[0450] Prompt Sentence Examples

[0451] "Analyze this inventory data to identify overstocked or understocked items and suggest appropriate inventory management methods."

[0452] "Please analyze this customer data, segment customers based on their value, and propose the most appropriate marketing measures for each segment."

[0453] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0454] Step 1:

[0455] The user prepares management data from a device. The user prepares a CSV or Excel file containing their company's sales data, customer data, inventory data, etc. on a device such as a PC or tablet. This involves organizing the necessary data into columns and converting it into the appropriate file format. The input data is various management data such as sales, customers, and inventory, and the output data is a CSV or Excel file in which that data is saved.

[0456] Step 2:

[0457] The user logs in to the cloud server and uploads data. The user opens a web browser and accesses the cloud server's management screen. They log in by entering their account information and proceed to the "Data Upload" section. There, they select the prepared data file and click the "Upload" button. The input data is the login information and management data file, and the output data is the management data file uploaded to the cloud server.

[0458] Step 3:

[0459] The server checks the received data and verifies the data format. The server temporarily saves the uploaded file and checks whether the file format matches the specified data format (CSV or Excel format). Specifically, the server checks the name and data type of each column and verifies that the format is correct. The input data is the uploaded management data file, and the output data is the confirmation result of whether the format is correct or incorrect.

[0460] Step 4:

[0461] The server automatically generates the database schema. After verifying that the data format is correct, the server automatically generates the database schema. Specifically, it designs the necessary tables and columns based on the received data and generates a database based on that. The input data is the verified management data file, and the output data is the automatically generated database schema and the data stored in the database.

[0462] Step 5:

[0463] The server launches the generative AI model and performs data analysis. The server launches the generative AI model and analyzes the data in the database. This analysis uses machine learning libraries such as Python and TensorFlow. The generative AI model performs statistical analysis and pattern recognition to identify management issues. The input data is the management data in the database, and the output data is the identified management issues and the analysis results.

[0464] Step 6:

[0465] The server displays the analysis results and management measures on the user's dashboard. After the generative AI model completes its analysis, the server displays the results on the user's dashboard. The analysis results may include, for example, "There is an excess of inventory for a particular product" or "Sales are on a downward trend." Based on this, optimal management measures are proposed. The input data are the analysis results of the generative AI model, and the output data are proposed management measures that are displayed on the user's dashboard.

[0466] Step 7:

[0467] The user checks the proposed management measures and takes the necessary actions. The user accesses the dashboard and checks the proposed management measures. For example, "Optimizing inventory management" displays measures such as "reducing the order quantity of certain products" and "considering new suppliers." The user makes their own management decisions based on these suggestions and takes appropriate actions. The input data are the proposed management measures displayed on the dashboard, and the output data are the specific actions the user will take.

[0468] (Application example 1)

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

[0470] There is an increasing need for businesses to be able to easily optimize their operations without specialized knowledge by effectively utilizing management data. However, current systems require users to check complex data formats, generate databases, and use specialized analysis methods, making them difficult to use for many users. Furthermore, there is a lack of clear guidance on how the resulting management measures should be implemented, making it difficult for brick-and-mortar stores to make appropriate decisions. This can delay the rapid resolution of management issues and the implementation of effective management measures.

[0471] 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.

[0472] In this invention, the server includes means for a user to upload a file containing management data based on a data format, means for checking the data format of the uploaded file and automatically generating a database, means for activating a generative AI model based on the automatically generated database, identifying management issues, and proposing optimal management measures, and means for a user to check the proposed management measures on a dashboard via a smartphone.

[0473] This allows users without specialized knowledge to upload management data intuitively, and then easily check and implement specific measures based on that data on their smartphones.

[0474] "Management data" includes information related to a company's management activities, such as sales data, customer data, and inventory data.

[0475] A "data format" refers to the format or structure in which data is stored, and includes formats such as CSV and Excel.

[0476] A "generative AI model" is a pre-trained artificial intelligence algorithm and structure that identifies management issues based on input data and proposes optimal measures.

[0477] A "dashboard" is an interface that allows users to visually check and manipulate information, and is displayed on smartphones and other devices.

[0478] A "database" is a system that efficiently stores and manages data, and is composed of multiple tables and schemas.

[0479] "Automatic generation" means that the system follows specified procedures, eliminating the need for manual operation, and autonomously checks data formats and builds databases.

[0480] "Management measures" refer to specific action plans and strategies implemented to solve a company's management issues.

[0481] "Uploading" is the act of a user transferring their own data from a local environment to a remote environment such as a cloud server.

[0482] "Means" includes processes, techniques, or devices used to achieve a particular end.

[0483] A "proposal" is a solution or action plan that the generative AI model presents to the user based on data analysis.

[0484] This invention relates to a system that allows even users without specialized knowledge to easily upload management data and propose effective management measures based on that data. How this system is implemented will be explained below in detail.

[0485] 1. System Overview

[0486] This system consists of a cloud server, a user device (smartphone), and a generative AI model. Its main functions are as follows:

[0487] Management data upload function

[0488] Data format confirmation function

[0489] Automatic database generation function

[0490] Data analysis and policy proposal function using generative AI

[0491] Dashboard-based policy display function

[0492] 2. Hardware and Software Used

[0493] Hardware:

[0494] Smartphone: Used by users to upload data and review measures.

[0495] Cloud server: Stores data, analyzes data, and performs recommendations.

[0496] software:

[0497] Data format confirmation: Uses Python's Pandas library.

[0498] Database Management: MySQL or PostgreSQL.

[0499] Generative AI model: TensorFlow or PyTorch.

[0500] User interface: Smartphone app using React Native.

[0501] 3. System processing flow

[0502] The main processing flow of this system is as follows:

[0503] Data upload: Users use a smartphone app to upload inventory data and customer data in CSV or Excel format to a cloud server.

[0504] Data format verification: The cloud server uses a Python script (Pandas) to verify the format of the uploaded data.

[0505] Automatic database generation: Once the data is confirmed to be in the correct format, it is automatically stored in a database such as MySQL or PostgreSQL.

[0506] Generative AI analysis: Based on the data stored in the database, generative AI models such as TensorFlow and PyTorch analyze the data.

[0507] Display of measures: Analysis results and proposed measures are displayed on the dashboard of the smartphone app.

[0508] 4. Specific Examples

[0509] Example 1: Sales promotion proposal

[0510] Prompt: "Please suggest the best sales promotion measures based on sales and customer data from the past six months."

[0511] Example 2: Optimizing inventory management

[0512] Prompt: "Based on current inventory data and past sales trends, please suggest the optimal order quantity for this month."

[0513] This allows users without specialized knowledge to intuitively upload management data and easily check and implement specific measures based on that data on their smartphones.

[0514] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0515] Step 1:

[0516] The user prepares management data using a device (smartphone) and launches the application. The file selection screen for uploading opens. The user selects a data file in CSV or Excel format (e.g., inventory data or customer data) from their local storage.

[0517] Input: CSV or Excel format data file

[0518] Output: Selected data files ready to upload

[0519] Step 2:

[0520] The device (smartphone) uploads the selected data file to the cloud server. The file is sent to the server using the HTTP protocol and temporarily stored.

[0521] Input: Selected data file

[0522] Output: Data file uploaded to the server

[0523] Step 3:

[0524] The server checks the format of the received data file using the Python Pandas library. Specifically, it checks whether the matrix structure and data types of the file are correct, and if the format is correct, it proceeds to the next step.

[0525] Input: Data file uploaded to the server

[0526] Output: Format check result (correct / incorrect)

[0527] Step 4:

[0528] Once the data is verified to be in the correct format, the server stores it in a MySQL or PostgreSQL database, automatically generating the database schema and creating the necessary tables and columns.

[0529] Input: Format-checked data file

[0530] Output: Data stored in a database

[0531] Step 5:

[0532] The server runs a generative AI model (TensorFlow or PyTorch) based on the data stored in the database. This model analyzes the data, identifies specific business issues, and proposes optimal management measures, such as analyzing inventory surpluses or shortages, declining sales trends, and customer behavior patterns.

[0533] Input: Data stored in a database

[0534] Output: Analysis results and proposed management measures

[0535] Step 6:

[0536] The proposed management measures are sent from the cloud server to the device (smartphone). The device application displays these measures on the user's dashboard. The user can check the details of the measures through the dashboard.

[0537] Input: Analysis results and proposed management measures

[0538] Output: Business measures displayed on the user's dashboard

[0539] Step 7:

[0540] Users can check the measures on the dashboard and select specific actions, such as "optimizing inventory management" or "adjusting new product promotion plans," to determine specific operations for physical stores.

[0541] Input: Suggestions displayed on the dashboard

[0542] Output: The specific action the user chooses to take

[0543] This processing flow enables users, even without specialized knowledge, to easily upload management data and confirm and implement specific measures based on the results of data analysis.

[0544] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0545] This invention relates to a system that allows users without specialized knowledge to easily manage management data and proposes optimal management measures using a generative AI model. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it has the advantage of being able to adaptively change the proposal content and UI / UX according to the user's emotions. This system consists of a cloud server, a user's device, a generative AI model, and an emotion engine.

[0546] First, the user prepares a file containing management data from their device. This data includes sales data, customer data, inventory data, etc. Once the file is ready, the user logs in to the cloud server's management screen and accesses the "Data Upload" section. Here, the user selects the file and uploads it.

[0547] The server receives the file and checks whether it matches the specified data format (e.g., CSV or Excel). If the format is correct, the server automatically generates a database schema, imports the data, and creates the necessary tables. It then launches a generative AI model to identify management issues based on the data in the database and propose optimal management measures. During this process, the emotion engine collects and analyzes emotion data from the user's device. Emotion data includes facial expressions, tone of voice, and biometric data such as oximeter readings.

[0548] The user's emotional data detected by the emotion engine influences the analysis results of the generative AI model. For example, if the user is feeling stressed, the server will take that emotion into account and simplify the explanation of suggested management measures, presenting only high-priority tasks. The dashboard's UI / UX is also dynamically adjusted based on the emotion engine's data, providing the user with the most comfortable interface.

[0549] Specific examples

[0550] Example 1: Inventory management optimization

[0551] The user prepares inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and uploads it to the server. The server checks that the data is in the correct format and automatically generates a database. The generative AI model analyzes the data and identifies products that are overstocked or understocked. The emotion engine analyzes the user's emotions, and if it determines that the user is feeling stressed, for example, the server simplifies the suggestions and presents them with a focus on high-priority measures (e.g., stopping orders for products with excessive inventory).

[0552] Example 2: Optimizing customer segmentation

[0553] Users prepare customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and upload it to the server. After the data format is confirmed, the server automatically generates a database and imports the data. A generative AI model analyzes the customer data and classifies customers into multiple value-based segments. An emotion engine captures the user's emotions, and if the user expresses positive emotions, for example, the server makes more detailed and strategic marketing suggestions. The color and design of the dashboard are also dynamically adjusted based on the user's emotions.

[0554] In this way, the present invention is a system that not only automatically manages management data and proposes optimal management measures using a generative AI model, but also recognizes and responds to user emotions to make more personalized proposals.

[0555] The processing flow will be explained below.

[0556] Step 1:

[0557] The user prepares a file containing management data from a terminal. The file typically includes sales data, customer data, inventory data, etc.

[0558] Step 2:

[0559] The user uses a terminal to access the cloud server's management screen and logs in. They enter their user ID and password on the login screen to be authenticated.

[0560] Step 3:

[0561] The user goes to the "Data Upload" section on the admin page, selects the prepared file, and clicks the upload button.

[0562] Step 4:

[0563] The server receives the uploaded file and temporarily stores it. The server checks whether the received file conforms to the specified data format (e.g., CSV or Excel format). If the format is inappropriate, an error message is displayed to the user.

[0564] Step 5:

[0565] After the server verifies the correct data format, it automatically generates the database schema, defines the database table structure, and creates the necessary tables, such as "customers" and "inventory."

[0566] Step 6:

[0567] The server stores the uploaded data in an automatically generated table, and each data record is saved appropriately and the database is updated.

[0568] Step 7:

[0569] The cloud server launches the generative AI model, which reads the data from the database and begins analyzing it.

[0570] Step 8:

[0571] The emotion engine acquires emotion data from the user's device, including the user's facial expression, voice tone, heart rate, etc.

[0572] Step 9:

[0573] Generative AI models analyze data to identify business issues, such as declining sales trends, inventory overhangs or shortages, and patterns of customer behavior.

[0574] Step 10:

[0575] The server analyzes the data from the emotion engine and adjusts the suggestions based on the user's emotions. For example, if the user is feeling stressed, the suggested actions will be simplified and only the most important points will be highlighted.

[0576] Step 11:

[0577] Based on the analysis results, the server proposes specific management measures, such as "reducing the order volume of certain products" or "reviewing new customer targeting strategies."

[0578] Step 12:

[0579] The server displays the proposed management measures on the user's dashboard, and the dashboard's UI / UX is also dynamically adjusted based on the emotion engine data.

[0580] Step 13:

[0581] The user accesses the dashboard from a device and checks the proposed measures. The user understands these measures and decides whether to apply them.

[0582] Step 14:

[0583] Users can then implement the proposed business measures as needed, such as reviewing ordering plans or adjusting marketing campaigns.

[0584] In this way, the present invention is a system that manages data and proposes optimal management measures while responding to the user's emotions.

[0585] Example 2

[0586] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0587] Traditionally, managing and analyzing business data required specialized knowledge and experience, making it difficult for average users to easily undertake the task. Furthermore, the lack of appropriate management proposals that took user feelings into consideration can lead to increased stress and burden on users. Furthermore, there was a need for a flexible response to the user's feelings and circumstances regarding the analysis results.

[0588] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to upload a file containing management data based on a data format; means for checking the data format of the uploaded file and automatically generating a database; means for activating a generative AI model based on the automatically generated database, identifying management issues, and proposing optimal management measures; means for acquiring user emotion data and analyzing it with an emotion analysis engine; and means for dynamically adjusting the proposals of the generative AI model based on the user's emotions and adaptively changing the user interface and user experience. This makes it possible for even users without specialized knowledge to easily manage management data, and by combining the generative AI model and the emotion analysis engine, it is possible to propose optimal management measures based on the user's emotions.

[0589] "Management data" refers to numerical values ​​and information related to the operation of a company or organization, including sales data, customer data, inventory data, etc.

[0590] A "data format" is a specification that defines the format and structure for storing data. For example, CSV and Excel formats fall into this category.

[0591] "User" refers to an individual or organization that uses this system. Specifically, the entity that uploads management data and receives analysis results.

[0592] "Upload" refers to the act of a user transferring a data file from their own device to a remote system such as a cloud server.

[0593] "Automatic generation" refers to the system building databases and other structures based on predetermined rules without manual user intervention.

[0594] A "database" is a system for systematically organizing and storing data. It includes relational database management systems (RDBMS).

[0595] A "generative AI model" is a pre-trained artificial intelligence model that performs analysis based on input data and proposes management measures.

[0596] "Emotion data" is information that indicates the user's emotional state, and includes facial expressions, tone of voice, biometric data, and the like.

[0597] An "emotion analysis engine" is software or hardware that analyzes a user's emotional data acquired from a terminal and grasps their emotional state.

[0598] "User interface" refers to the means of interaction between a system and a user, including the screens, buttons, and dashboards that users operate.

[0599] "User experience" refers to the satisfaction and ease of use that users feel when using a system, and is influenced by factors such as the system's intuitive usability and visual design.

[0600] This invention relates to a system that allows users without specialized knowledge to easily manage management data and propose optimal management measures using a generative AI model. Furthermore, by combining it with an emotion analysis engine that recognizes user emotions, it has the advantage of being able to adaptively change the proposal content and UI / UX according to the user's emotions. This system consists of a cloud server, a user's device, a generative AI model, and an emotion analysis engine.

[0601] User preparation and upload of data files

[0602] First, the user prepares a file containing management data from a device (such as a PC or tablet). The file includes sales data, customer data, inventory data, etc. This file is saved in CSV or Excel format using Microsoft Excel or Google Sheets.

[0603] Next, the user logs in to the cloud server's administration screen using a web browser (e.g., Google Chrome or Firefox). After logging in, the user accesses the "Data Upload" section, opens a file selection dialog, and uploads the prepared file.

[0604] Server checks and imports data format

[0605] The server receives the uploaded file. It then uses the Python library pandas to verify that the data format of the file is correct. Once this verification is complete, the server automatically generates a database schema and populates it with the data. This database is typically a relational database management system (RDBMS) such as MySQL or PostgreSQL. The server then creates the appropriate tables and inserts the data.

[0606] Identifying and proposing management issues using generative AI models

[0607] After the server completes the generation of the database schema, it launches a generative AI model (e.g., OpenAI's GPT-4). The generative AI model identifies business issues based on the data in the database and proposes optimal business measures. An example of a prompt sentence used here is as follows:

[0608] "Based on current inventory data, identify excess or shortage items and suggest the best course of action."

[0609] Analyzing user emotions using an emotion analysis engine

[0610] The emotion analysis engine acquires emotion data from the user's device, including facial expressions (camera), tone of voice (microphone), and biometric data such as oximetry. Software such as Affectiva or Microsoft Azure Emotion API is used for emotion analysis.

[0611] The user's emotional data detected by the emotion analysis engine influences the analysis results of the generative AI model. For example, if the user is feeling stressed, the generative AI model will simplify its suggestions and present only high-priority tasks. The dashboard's UI / UX is also dynamically adjusted based on the data from the emotion analysis engine, providing the user with the most comfortable interface.

[0612] Specific examples

[0613] Example 1: Inventory management optimization

[0614] The user prepares inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and uploads it to the server. The server checks that the data is in the correct format and automatically generates a database. A generative AI model analyzes the data and identifies products that are overstocked or understocked. The sentiment analysis engine analyzes the user's emotions, and if it determines that the user is feeling stressed, for example, the server simplifies its suggestions and focuses on high-priority measures (e.g., stopping orders for products with excessive inventory).

[0615] Example 2: Optimizing customer segmentation

[0616] The user prepares customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and uploads it to the server. Once the data format has been confirmed, the server automatically generates a database and imports the data. A generative AI model analyzes the customer data and classifies customers into multiple segments based on their value. A sentiment analysis engine obtains the user's emotions, and if the user expresses positive emotions, for example, the server makes more detailed and strategic marketing proposals. The color and design of the dashboard are also dynamically adjusted based on the user's emotions. In this way, the present invention is a system that not only automatically manages management data and proposes optimal management measures using a generative AI model, but also recognizes and responds to user emotions to make more personalized proposals.

[0617] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0618] Step 1:

[0619] The user prepares the business data.

[0620] Users use a device (such as a PC or tablet) to input management data into an application such as Microsoft Excel or Google Sheets. Once the data is input, the file is saved in CSV or Excel format. The input in this case is a data file (e.g., sales data, customer data, inventory data) created using data editing software such as Excel. The output is a prepared management data file.

[0621] Step 2:

[0622] A user uploads a data file to a cloud server.

[0623] The user logs in to the cloud server's management screen using a web browser (e.g., Google Chrome or Firefox). After logging in, the user accesses the "Data Upload" section, opens the file selection dialog, selects the prepared file, and presses the upload button to send it to the server. The input is the management data file, and the output is the file saved on the server.

[0624] Step 3:

[0625] The server checks the data format of the uploaded file.

[0626] The server receives the uploaded file and checks the data format using Python's pandas library. Specifically, it checks the consistency of the data according to the CSV or Excel format and checks whether required columns (e.g., product ID, inventory amount, purchase price, etc.) are present. The input is the uploaded management data file, and the output is the verification result of whether the format is correct.

[0627] Step 4:

[0628] The server automatically generates the database schema and populates it with data.

[0629] The server automatically generates a database schema based on a data file that has been validated for correct formatting. The database used may be, for example, MySQL or PostgreSQL. The server creates the appropriate tables and inserts the data from the file into them. The input is the validated data file; the output is the constructed database schema and the inserted data.

[0630] Step 5:

[0631] The server launches the generative AI model to identify management issues.

[0632] The server launches a generative AI model (e.g., OpenAI GPT-4) and analyzes the data in the database. For example, the following prompt is input to the generative AI model: "Based on current inventory data, please identify any excess or shortage of products and propose the optimal solution." The input is the management data in the database and the prompt, and the output is the analysis results and proposals from the generative AI model.

[0633] Step 6:

[0634] The emotion analysis engine acquires and analyzes the user's emotion data.

[0635] The emotion analysis engine acquires and analyzes biometric data such as facial expressions (camera), tone of voice (microphone), and oximeter data from the user's device. Software such as Affectiva or Microsoft Azure Emotion API is used for emotion analysis. The input is the user's emotional data, and the output is the analyzed emotional state.

[0636] Step 7:

[0637] The server dynamically adjusts the suggestions based on the results of the generative AI model and sentiment analysis engine.

[0638] The server combines the analysis results of the generative AI model with the emotional data from the emotion analysis engine to dynamically adjust the management policy proposals according to the user's emotional state. For example, if the user is feeling stressed, the proposals will be simplified and only high-priority tasks will be presented. The color and design of the dashboard will also be dynamically changed based on the emotional data. The inputs are the generative AI model's proposals and the results of the emotion analysis, and the output is the adjusted proposals and modified UI / UX.

[0639] (Application example 2)

[0640] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0641] Conventional business management systems make it difficult for users without specialized knowledge to properly manage data and plan management policies. Furthermore, they lack the ability to provide personalized suggestions and adjust the interface to take user emotions into account, resulting in a poor user experience. Therefore, there is a need for a system that can easily manage management data, propose optimal management policies using generative AI models, and dynamically adjust the proposal content and user interface according to user emotions.

[0642] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to upload a file containing management data based on a data format, means for checking the data format of the uploaded file and automatically generating a database, means for activating a generative AI model based on the automatically generated database to identify management issues and propose optimal management measures, and means for analyzing the user's facial expressions and tone of voice and dynamically adjusting the proposal content and user interface based on their emotions. This enables users to easily manage management data and receive proposals for optimal management measures without having specialized knowledge, and improves the user experience by adjusting the proposal content and user interface to be personalized according to the user's emotions.

[0643] "Management data" refers to sales data, customer data, inventory data, etc., necessary for business activities.

[0644] "Data format" refers to the format of data that is organized according to a specific format or structure, such as CSV format or Excel format.

[0645] "Means for users to upload" refers to a function that allows users to select files through an interface and send them to the cloud server.

[0646] "Automatically generated database" refers to a database environment automatically generated by the server based on uploaded data.

[0647] "Generative AI model" refers to an artificial intelligence model used to analyze data uploaded by users, identify management issues, and propose optimal management measures.

[0648] "Management issues" refer to problems a company faces or areas that need improvement.

[0649] "Optimal management measures" refer to specific measures for improving management proposed based on the generative AI model.

[0650] "Means for analyzing a user's facial expressions and tone of voice" refers to technology or software for collecting and analyzing a user's facial expressions and tone of voice using a camera or microphone.

[0651] "Means for dynamically adjusting suggested content and user interface based on emotions" refers to technology that optimizes suggested content and interface design in real time based on analyzed user emotional data.

[0652] This invention relates to a system that efficiently manages a company's management data and proposes optimal management measures using a generative AI model. Furthermore, it has the advantage of analyzing the user's emotions and dynamically adjusting the proposal content and user interface based on those emotions. This system consists of a cloud server, a user device, a generative AI model, and an emotion recognition engine.

[0653] System configuration

[0654] Hardware

[0655] Cloud server: receives, stores, and analyzes data, and runs generative AI models.

[0656] User devices: Smartphones and PCs are mainly used to upload data, collect emotion data, and display the interface.

[0657] software

[0658] Data management software: Pandas, Flask, etc., used to check data formats and automatically generate and manage databases.

[0659] Generative AI model: Used to analyze management data, identify management issues, and propose optimal management measures.

[0660] Emotion Recognition Engine: Software that processes data from the camera and microphone to analyze the user's facial expressions and tone of voice.

[0661] Data flow

[0662] 1. Upload your data

[0663] Users upload sales data, customer data, inventory data, etc. in CSV or Excel format from their devices to the cloud server.

[0664] The uploaded file is checked on the server side to see if the data format is correct.

[0665] 2. Automatic database generation

[0666] Once the data is confirmed to be in the correct format, the server automatically generates a database schema to incorporate the uploaded data.

[0667] Creates the necessary tables and checks the integrity of the data.

[0668] 3. Analysis of generative AI models

[0669] The server launches the generative AI model and analyzes the management data in the database.

[0670] Identify management issues and propose optimal management measures.

[0671] 4. Emotional Data Collection and Analysis

[0672] The user's device uses a camera and microphone to collect facial expressions and tone of voice, which are then analyzed using an emotion recognition engine.

[0673] Emotional data (e.g., stress, joy, interest, etc.) is captured in real time and transmitted to a server.

[0674] 5. Dynamic suggestions and user interface adjustments

[0675] The server dynamically adjusts the recommendations and dashboard interface based on the acquired emotional data.

[0676] For example, if the user is feeling stressed, the suggestions will be simplified and only high-priority management measures will be presented.

[0677] Considering emotions improves the user experience.

[0678] Specific examples

[0679] 1. Optimizing inventory management

[0680] The user prepares inventory data in CSV format and uploads it to the cloud server.

[0681] The server checks the data format and automatically generates the database.

[0682] Generative AI models analyze inventory data to identify overstocked or understocked items.

[0683] If the user is feeling stressed, the suggestions will be brief and will focus on stopping orders for excess inventory items.

[0684] 2. Optimizing customer segmentation

[0685] The user prepares customer data in Excel format and uploads it to the cloud server.

[0686] After the data format is confirmed, the server automatically creates and populates the database.

[0687] A generative AI model analyzes customer data and categorizes customers into segments.

[0688] If the user indicates positive sentiment, the server will provide more detailed marketing suggestions.

[0689] Prompt Sentence Examples

[0690] python

[0691] camera_feed = get_camera_feed() Gets the camera feed from a smartphone

[0692] audio_feed = get_audio_feed() Gets the smartphone's microphone audio

[0693] file_path = 'path / to / user_upload.csv'

[0694] suggestions, ui_ux_config = main(file_path, camera_feed, audio_feed)

[0695] print("Business policy proposals: ", suggestions)

[0696] print("UI / UX settings: ", ui_ux_config)

[0697] This allows users to easily manage management data without specialized knowledge and receive optimal management policy proposals from generative AI models.Furthermore, personalized proposals based on emotions and user interface adjustments improve the user experience.

[0698] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0699] Step 1:

[0700] The user prepares management data in CSV or Excel format, logs in to the cloud server's management screen, and accesses the "Data Upload" section. Here, the user selects the file and uploads it to the cloud server. The input for this step is the CSV or Excel file, and the output is a notification that the file has been uploaded to the cloud server.

[0701] Step 2:

[0702] The server receives the uploaded file and checks its data format. Specifically, it uses Pandas to read CSV or Excel files and checks the format for consistency. The input of this step is the uploaded file, and the output is the format check result. If the format is correct, it proceeds to the next step.

[0703] Step 3:

[0704] The server automatically generates the database schema and populates the database with data. Specifically, it uses Flask to generate the database and inserts data from Pandas into the database. The input for this step is the verified data file, and the output is the generated database and stored data.

[0705] Step 4:

[0706] The server launches the generative AI model and analyzes the data in the database. The generative AI model identifies management issues as a result of the analysis and proposes optimal management measures. The input for this step is the data in the database, and the output is proposed management measures.

[0707] Step 5:

[0708] The user device uses a camera and microphone to collect facial expressions and tone of voice, which are then analyzed by an emotion recognition engine. Specifically, the EmotionEngine is used to acquire and analyze emotional data. The input of this step is the user's facial and voice data, and the output is emotional data.

[0709] Step 6:

[0710] The server receives the acquired emotional data and dynamically adjusts the proposals and user interface based on that data. Specifically, it changes the UI / UX settings based on the emotional data to provide the user with an optimal interface. The input of this step is emotional data, and the output is an adjusted UI / UX proposal.

[0711] Step 7:

[0712] The adjusted proposal and user interface are displayed to the user. The user checks the provided management measures and takes necessary actions. The input of this step is the adjusted proposal from the server, and the output is the user's decision and action.

[0713] This allows users to easily manage management data without specialized knowledge and receive optimal management proposals from generative AI models. Personalization based on emotion recognition also improves the user experience.

[0714] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0715] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0716] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0717] [Third embodiment]

[0718] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0719] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0720] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0721] 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.

[0722] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0723] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0724] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0729] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0730] This invention relates to a system that allows users without specialized knowledge to easily upload management data and propose effective management measures based on that data. The system consists of a cloud server, a user terminal, and a generative AI model.

[0731] First, the user prepares a file containing management data from their device. This data typically includes sales data, customer data, inventory data, etc. Once the file is ready, the user uses a web browser to access the cloud server's management screen and log in. After logging in, the user accesses the "Data Upload" section, selects the prepared file, and clicks the "Upload" button.

[0732] The cloud server receives the uploaded file and temporarily stores it. The server then checks whether the received file conforms to the specified data format (e.g., CSV or Excel format). If the format is correct, the server automatically generates a database schema, creates the necessary tables, and stores the data.

[0733] After the database is automatically generated, the cloud server launches a generative AI model. The generative AI model analyzes the data in the database and identifies management issues. This identifies, for example, inventory surpluses or shortages, declining sales trends, and customer behavior patterns. The generative AI model then proposes optimal management measures to address these issues.

[0734] The proposed management measures are displayed on the user's dashboard from the cloud server. The user can access the dashboard using their device and check the proposed content. Specific measures include "optimizing inventory management," "adjusting new product promotion plans," and "optimizing marketing campaigns."

[0735] Specific examples

[0736] Example 1: Inventory management optimization

[0737] Users prepare inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and upload it to a cloud server. The server checks the received data, confirms that it is in the correct format, and then automatically generates a database. A generative AI model analyzes the data and generates a list of products with excess or shortages of stock. Suggested measures include "reducing the order quantity of a specific product" or "considering a new supplier." Users can view these suggestions on a dashboard and take appropriate action.

[0738] Example 2: Optimizing customer segmentation

[0739] Users prepare customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and upload it to a cloud server. The server verifies the data, checks that the format is correct, and then automatically generates a database. A generative AI model analyzes the customer data and classifies customers into multiple segments based on their value. Suggested measures include "implementing special campaigns for high-value customers" and "optimizing targeting strategies for new products." Users can view and implement these measures on the dashboard.

[0740] This system allows even users without specialist knowledge to effectively optimize their business operations through a series of processes: checking the data format, automatically generating a database, analyzing it using the generated AI model and proposing measures, and then having the user check and implement the measures.

[0741] The processing flow will be explained below.

[0742] Step 1:

[0743] The user prepares a file containing management data from a terminal. The prepared data includes sales data, customer data, inventory data, etc.

[0744] Step 2:

[0745] The user uses a device to access the cloud server's management screen and logs in. By entering their user ID and password on the login screen, they are authenticated by the cloud server.

[0746] Step 3:

[0747] The user goes to the "Data Upload" section on the cloud server management screen, selects the prepared file, and clicks the "Upload" button to transfer the selected file to the server.

[0748] Step 4:

[0749] The server receives the uploaded file and temporarily stores it. Then, the server checks whether the file format matches the specified data format (e.g., CSV or Excel format). If the format is invalid, it displays an error message to the user.

[0750] Step 5:

[0751] After the server verifies the correct data format, it automatically generates a database schema, which defines the database table structure and creates the necessary tables. For example, for customer data, it creates a "customers" table.

[0752] Step 6:

[0753] The server reads the uploaded data, stores the data in an automatically generated table, and verifies that each data record is saved properly.

[0754] Step 7:

[0755] After the database is built, the server launches the generative AI model, which reads the data in the database and begins analyzing it.

[0756] Step 8:

[0757] Generative AI models analyze data and identify business issues, such as declining sales trends or lists of overstocked products.

[0758] Step 9:

[0759] Based on the analysis results, the server proposes specific management measures, such as "reducing the order volume of a specific product" or "reviewing the new customer targeting strategy."

[0760] Step 10:

[0761] The server displays the proposed management measures on the user's dashboard.

[0762] Step 11:

[0763] The user accesses the cloud server using a device and checks the proposed measures on the dashboard. The user understands these measures and decides whether to apply them.

[0764] Step 12:

[0765] The user then implements the proposed business actions as needed, for example, creating a new ordering plan or adjusting a marketing campaign.

[0766] Example 1

[0767] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0768] In today's business environment, many companies are required to effectively utilize massive amounts of management data and implement prompt and appropriate management measures. However, this requires specialized knowledge and expensive analytical tools, making it difficult for small and medium-sized enterprises, in particular, to utilize these effectively. Furthermore, when analyzing data from multiple data sources, it is difficult to ensure accuracy and reliability. This prevents companies from deriving optimal management measures, putting them at risk of losing their competitive edge.

[0769] 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.

[0770] In this invention, the server

[0771] means for a user to upload a file containing management data according to a data format;

[0772] means for checking the data format of the uploaded file and automatically generating a database;

[0773] Based on the automatically generated database, a generative AI model is launched to identify management issues and propose optimal management measures.

[0774] a means for displaying the proposed management measures on a user's dashboard;

[0775] This allows even users without specialized knowledge to easily upload data and implement effective management measures. In addition, linking and analyzing data from multiple data sources improves the accuracy of management measures.

[0776] "Management data" refers to data that includes information related to a company's management situation and business processes, such as sales data, customer data, and inventory data.

[0777] A "file" is a collection of information stored in digital form, generally in a specific data format such as CSV or Excel.

[0778] "Data format" refers to the way data is structured in a particular way, and can refer to standardized formats such as CSV or Excel.

[0779] "User" refers to an individual or company that operates this system to upload management data and receive analysis results and policy proposals.

[0780] A "database" refers to a collection of data stored in an organized manner, and is a system that allows for efficient data retrieval and manipulation.

[0781] A "generative AI model" refers to a model that uses machine learning and artificial intelligence techniques to analyze data and make predictions.

[0782] A "database schema" is a design document that defines the structure and format of data in a database, and indicates the configuration of tables and columns.

[0783] "Management issues" refer to problems a company faces or areas where there is room for improvement, including excess inventory, declining sales, and customer attrition.

[0784] "Management measures" refer to plans and strategies implemented to solve specific management issues, such as optimizing inventory management and adjusting marketing strategies.

[0785] A "dashboard" refers to an interface that allows users to visually check data analysis results and policy proposals.

[0786] This invention relates to a system that allows users without specialized knowledge to easily upload management data and propose effective management measures based on that data. The system consists of a cloud server, a user terminal, and a generative AI model.

[0787] First, the user prepares the management data using their own device. This management data includes sales data, customer data, inventory data, etc., and is generally saved in CSV or Excel format. After preparing this data, the user accesses the cloud server's management screen from a web browser and logs in. After successfully logging in, the user goes to the "Data Upload" section, selects the prepared file, and clicks the "Upload" button.

[0788] The cloud server temporarily stores the received file and checks whether the data format matches the specified format (e.g., CSV or Excel format). If the format is correct, the server automatically generates a database schema, creates the necessary tables, and stores the data. A database system such as MySQL or PostgreSQL is used to generate the database schema.

[0789] After the database is automatically generated, the cloud server launches a generative AI model. This generative AI model is built using machine learning libraries such as Python and TensorFlow. The generative AI model analyzes the data in the database and identifies management issues. For example, it can identify inventory surpluses or shortages, declining sales trends, and customer behavior patterns. Based on the analysis results, it proposes optimal management measures.

[0790] The proposed management measures are displayed on the user's dashboard from the cloud server. The user accesses the dashboard using a device and checks the proposed content. Specific measures include "optimizing inventory management," "adjusting new product promotion plans," and "optimizing marketing campaigns."

[0791] Specific examples

[0792] Example 1: Inventory management optimization

[0793] Users prepare inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and upload it to a cloud server. The server checks the received data, confirms that it is in the correct format, and then automatically generates a database. A generative AI model analyzes the data and generates a list of products with excess or shortages of stock. Suggested measures include "reducing the order quantity of a specific product" or "considering a new supplier." Users can view these suggestions on a dashboard and take appropriate action.

[0794] Example 2: Optimizing customer segmentation

[0795] Users prepare customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and upload it to a cloud server. The server verifies the data, checks that the format is correct, and then automatically generates a database. A generative AI model analyzes the customer data and classifies customers into multiple segments based on their value. Suggested measures include "implementing special campaigns for high-value customers" and "optimizing targeting strategies for new products." Users can view and implement these measures on the dashboard.

[0796] Prompt Sentence Examples

[0797] "Analyze this inventory data to identify overstocked or understocked items and suggest appropriate inventory management methods."

[0798] "Please analyze this customer data, segment customers based on their value, and propose the most appropriate marketing measures for each segment."

[0799] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0800] Step 1:

[0801] The user prepares management data from a device. The user prepares a CSV or Excel file containing their company's sales data, customer data, inventory data, etc. on a device such as a PC or tablet. This involves organizing the necessary data into columns and converting it into the appropriate file format. The input data is various management data such as sales, customers, and inventory, and the output data is a CSV or Excel file in which that data is saved.

[0802] Step 2:

[0803] The user logs in to the cloud server and uploads data. The user opens a web browser and accesses the cloud server's management screen. They log in by entering their account information and proceed to the "Data Upload" section. There, they select the prepared data file and click the "Upload" button. The input data is the login information and management data file, and the output data is the management data file uploaded to the cloud server.

[0804] Step 3:

[0805] The server checks the received data and verifies the data format. The server temporarily saves the uploaded file and checks whether the file format matches the specified data format (CSV or Excel format). Specifically, the server checks the name and data type of each column and verifies that the format is correct. The input data is the uploaded management data file, and the output data is the confirmation result of whether the format is correct or incorrect.

[0806] Step 4:

[0807] The server automatically generates the database schema. After verifying that the data format is correct, the server automatically generates the database schema. Specifically, it designs the necessary tables and columns based on the received data and generates a database based on that. The input data is the verified management data file, and the output data is the automatically generated database schema and the data stored in the database.

[0808] Step 5:

[0809] The server launches the generative AI model and performs data analysis. The server launches the generative AI model and analyzes the data in the database. This analysis uses machine learning libraries such as Python and TensorFlow. The generative AI model performs statistical analysis and pattern recognition to identify management issues. The input data is the management data in the database, and the output data is the identified management issues and the analysis results.

[0810] Step 6:

[0811] The server displays the analysis results and management measures on the user's dashboard. After the generative AI model completes its analysis, the server displays the results on the user's dashboard. The analysis results may include, for example, "There is an excess of inventory for a particular product" or "Sales are on a downward trend." Based on this, optimal management measures are proposed. The input data are the analysis results of the generative AI model, and the output data are proposed management measures that are displayed on the user's dashboard.

[0812] Step 7:

[0813] The user checks the proposed management measures and takes the necessary actions. The user accesses the dashboard and checks the proposed management measures. For example, "Optimizing inventory management" displays measures such as "reducing the order quantity of certain products" and "considering new suppliers." The user makes their own management decisions based on these suggestions and takes appropriate actions. The input data are the proposed management measures displayed on the dashboard, and the output data are the specific actions the user will take.

[0814] (Application example 1)

[0815] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0816] There is an increasing need for businesses to be able to easily optimize their operations without specialized knowledge by effectively utilizing management data. However, current systems require users to check complex data formats, generate databases, and use specialized analysis methods, making them difficult to use for many users. Furthermore, there is a lack of clear guidance on how the resulting management measures should be implemented, making it difficult for brick-and-mortar stores to make appropriate decisions. This can delay the rapid resolution of management issues and the implementation of effective management measures.

[0817] 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.

[0818] In this invention, the server includes means for a user to upload a file containing management data based on a data format, means for checking the data format of the uploaded file and automatically generating a database, means for activating a generative AI model based on the automatically generated database, identifying management issues, and proposing optimal management measures, and means for a user to check the proposed management measures on a dashboard via a smartphone.

[0819] This allows users without specialized knowledge to upload management data intuitively, and then easily check and implement specific measures based on that data on their smartphones.

[0820] "Management data" includes information related to a company's management activities, such as sales data, customer data, and inventory data.

[0821] A "data format" refers to the format or structure in which data is stored, and includes formats such as CSV and Excel.

[0822] A "generative AI model" is a pre-trained artificial intelligence algorithm and structure that identifies management issues based on input data and proposes optimal measures.

[0823] A "dashboard" is an interface that allows users to visually check and manipulate information, and is displayed on smartphones and other devices.

[0824] A "database" is a system that efficiently stores and manages data, and is composed of multiple tables and schemas.

[0825] "Automatic generation" means that the system follows specified procedures, eliminating the need for manual operation, and autonomously checks data formats and builds databases.

[0826] "Management measures" refer to specific action plans and strategies implemented to solve a company's management issues.

[0827] "Uploading" is the act of a user transferring their own data from a local environment to a remote environment such as a cloud server.

[0828] "Means" includes processes, techniques, or devices used to achieve a particular end.

[0829] A "proposal" is a solution or action plan that the generative AI model presents to the user based on data analysis.

[0830] This invention relates to a system that allows even users without specialized knowledge to easily upload management data and propose effective management measures based on that data. How this system is implemented will be explained below in detail.

[0831] 1. System Overview

[0832] This system consists of a cloud server, a user device (smartphone), and a generative AI model. Its main functions are as follows:

[0833] Management data upload function

[0834] Data format confirmation function

[0835] Automatic database generation function

[0836] Data analysis and policy proposal function using generative AI

[0837] Dashboard-based policy display function

[0838] 2. Hardware and Software Used

[0839] Hardware:

[0840] Smartphone: Used by users to upload data and review measures.

[0841] Cloud server: Stores data, analyzes data, and performs recommendations.

[0842] software:

[0843] Data format confirmation: Uses Python's Pandas library.

[0844] Database Management: MySQL or PostgreSQL.

[0845] Generative AI model: TensorFlow or PyTorch.

[0846] User interface: Smartphone app using React Native.

[0847] 3. System processing flow

[0848] The main processing flow of this system is as follows:

[0849] Data upload: Users use a smartphone app to upload inventory data and customer data in CSV or Excel format to a cloud server.

[0850] Data format verification: The cloud server uses a Python script (Pandas) to verify the format of the uploaded data.

[0851] Automatic database generation: Once the data is confirmed to be in the correct format, it is automatically stored in a database such as MySQL or PostgreSQL.

[0852] Generative AI analysis: Based on the data stored in the database, generative AI models such as TensorFlow and PyTorch analyze the data.

[0853] Display of measures: Analysis results and proposed measures are displayed on the dashboard of the smartphone app.

[0854] 4. Specific Examples

[0855] Example 1: Sales promotion proposal

[0856] Prompt: "Please suggest the best sales promotion measures based on sales and customer data from the past six months."

[0857] Example 2: Optimizing inventory management

[0858] Prompt: "Based on current inventory data and past sales trends, please suggest the optimal order quantity for this month."

[0859] This allows users without specialized knowledge to intuitively upload management data and easily check and implement specific measures based on that data on their smartphones.

[0860] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0861] Step 1:

[0862] The user prepares management data using a device (smartphone) and launches the application. The file selection screen for uploading opens. The user selects a data file in CSV or Excel format (e.g., inventory data or customer data) from their local storage.

[0863] Input: CSV or Excel format data file

[0864] Output: Selected data files ready to upload

[0865] Step 2:

[0866] The device (smartphone) uploads the selected data file to the cloud server. The file is sent to the server using the HTTP protocol and temporarily stored.

[0867] Input: Selected data file

[0868] Output: Data file uploaded to the server

[0869] Step 3:

[0870] The server checks the format of the received data file using the Python Pandas library. Specifically, it checks whether the matrix structure and data types of the file are correct, and if the format is correct, it proceeds to the next step.

[0871] Input: Data file uploaded to the server

[0872] Output: Format check result (correct / incorrect)

[0873] Step 4:

[0874] Once the data is verified to be in the correct format, the server stores it in a MySQL or PostgreSQL database, automatically generating the database schema and creating the necessary tables and columns.

[0875] Input: Format-checked data file

[0876] Output: Data stored in a database

[0877] Step 5:

[0878] The server runs a generative AI model (TensorFlow or PyTorch) based on the data stored in the database. This model analyzes the data, identifies specific business issues, and proposes optimal management measures, such as analyzing inventory surpluses or shortages, declining sales trends, and customer behavior patterns.

[0879] Input: Data stored in a database

[0880] Output: Analysis results and proposed management measures

[0881] Step 6:

[0882] The proposed management measures are sent from the cloud server to the device (smartphone). The device application displays these measures on the user's dashboard. The user can check the details of the measures through the dashboard.

[0883] Input: Analysis results and proposed management measures

[0884] Output: Business measures displayed on the user's dashboard

[0885] Step 7:

[0886] Users can check the measures on the dashboard and select specific actions, such as "optimizing inventory management" or "adjusting new product promotion plans," to determine specific operations for physical stores.

[0887] Input: Suggestions displayed on the dashboard

[0888] Output: The specific action the user chooses to take

[0889] This processing flow enables users, even without specialized knowledge, to easily upload management data and confirm and implement specific measures based on the results of data analysis.

[0890] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0891] This invention relates to a system that allows users without specialized knowledge to easily manage management data and proposes optimal management measures using a generative AI model. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it has the advantage of being able to adaptively change the proposal content and UI / UX according to the user's emotions. This system consists of a cloud server, a user's device, a generative AI model, and an emotion engine.

[0892] First, the user prepares a file containing management data from their device. This data includes sales data, customer data, inventory data, etc. Once the file is ready, the user logs in to the cloud server's management screen and accesses the "Data Upload" section. Here, the user selects the file and uploads it.

[0893] The server receives the file and checks whether it matches the specified data format (e.g., CSV or Excel). If the format is correct, the server automatically generates a database schema, imports the data, and creates the necessary tables. It then launches a generative AI model to identify management issues based on the data in the database and propose optimal management measures. During this process, the emotion engine collects and analyzes emotion data from the user's device. Emotion data includes facial expressions, tone of voice, and biometric data such as oximeter readings.

[0894] The user's emotional data detected by the emotion engine influences the analysis results of the generative AI model. For example, if the user is feeling stressed, the server will take that emotion into account and simplify the explanation of suggested management measures, presenting only high-priority tasks. The dashboard's UI / UX is also dynamically adjusted based on the emotion engine's data, providing the user with the most comfortable interface.

[0895] Specific examples

[0896] Example 1: Inventory management optimization

[0897] The user prepares inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and uploads it to the server. The server checks that the data is in the correct format and automatically generates a database. The generative AI model analyzes the data and identifies products that are overstocked or understocked. The emotion engine analyzes the user's emotions, and if it determines that the user is feeling stressed, for example, the server simplifies the suggestions and presents them with a focus on high-priority measures (e.g., stopping orders for products with excessive inventory).

[0898] Example 2: Optimizing customer segmentation

[0899] Users prepare customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and upload it to the server. After the data format is confirmed, the server automatically generates a database and imports the data. A generative AI model analyzes the customer data and classifies customers into multiple value-based segments. An emotion engine captures the user's emotions, and if the user expresses positive emotions, for example, the server makes more detailed and strategic marketing suggestions. The color and design of the dashboard are also dynamically adjusted based on the user's emotions.

[0900] In this way, the present invention is a system that not only automatically manages management data and proposes optimal management measures using a generative AI model, but also recognizes and responds to user emotions to make more personalized proposals.

[0901] The processing flow will be explained below.

[0902] Step 1:

[0903] The user prepares a file containing management data from a terminal. The file typically includes sales data, customer data, inventory data, etc.

[0904] Step 2:

[0905] The user uses a terminal to access the cloud server's management screen and logs in. They enter their user ID and password on the login screen to be authenticated.

[0906] Step 3:

[0907] The user goes to the "Data Upload" section on the admin page, selects the prepared file, and clicks the upload button.

[0908] Step 4:

[0909] The server receives the uploaded file and temporarily stores it. The server checks whether the received file conforms to the specified data format (e.g., CSV or Excel format). If the format is inappropriate, an error message is displayed to the user.

[0910] Step 5:

[0911] After the server verifies the correct data format, it automatically generates the database schema, defines the database table structure, and creates the necessary tables, such as "customers" and "inventory."

[0912] Step 6:

[0913] The server stores the uploaded data in an automatically generated table, and each data record is saved appropriately and the database is updated.

[0914] Step 7:

[0915] The cloud server launches the generative AI model, which reads the data from the database and begins analyzing it.

[0916] Step 8:

[0917] The emotion engine acquires emotion data from the user's device, including the user's facial expression, voice tone, heart rate, etc.

[0918] Step 9:

[0919] Generative AI models analyze data to identify business issues, such as declining sales trends, inventory overhangs or shortages, and patterns of customer behavior.

[0920] Step 10:

[0921] The server analyzes the data from the emotion engine and adjusts the suggestions based on the user's emotions. For example, if the user is feeling stressed, the suggested actions will be simplified and only the most important points will be highlighted.

[0922] Step 11:

[0923] Based on the analysis results, the server proposes specific management measures, such as "reducing the order volume of certain products" or "reviewing new customer targeting strategies."

[0924] Step 12:

[0925] The server displays the proposed management measures on the user's dashboard, and the dashboard's UI / UX is also dynamically adjusted based on the emotion engine data.

[0926] Step 13:

[0927] The user accesses the dashboard from a device and checks the proposed measures. The user understands these measures and decides whether to apply them.

[0928] Step 14:

[0929] Users can then implement the proposed business measures as needed, such as reviewing ordering plans or adjusting marketing campaigns.

[0930] In this way, the present invention is a system that manages data and proposes optimal management measures while responding to the user's emotions.

[0931] Example 2

[0932] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0933] Traditionally, managing and analyzing business data required specialized knowledge and experience, making it difficult for average users to easily undertake the task. Furthermore, the lack of appropriate management proposals that took user feelings into consideration can lead to increased stress and burden on users. Furthermore, there was a need for a flexible response to the user's feelings and circumstances regarding the analysis results.

[0934] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to upload a file containing management data based on a data format; means for checking the data format of the uploaded file and automatically generating a database; means for activating a generative AI model based on the automatically generated database, identifying management issues, and proposing optimal management measures; means for acquiring user emotion data and analyzing it with an emotion analysis engine; and means for dynamically adjusting the proposals of the generative AI model based on the user's emotions and adaptively changing the user interface and user experience. This makes it possible for even users without specialized knowledge to easily manage management data, and by combining the generative AI model and the emotion analysis engine, it is possible to propose optimal management measures based on the user's emotions.

[0935] "Management data" refers to numerical values ​​and information related to the operation of a company or organization, including sales data, customer data, inventory data, etc.

[0936] A "data format" is a specification that defines the format and structure for storing data. For example, CSV and Excel formats fall into this category.

[0937] "User" refers to an individual or organization that uses this system. Specifically, the entity that uploads management data and receives analysis results.

[0938] "Upload" refers to the act of a user transferring a data file from their own device to a remote system such as a cloud server.

[0939] "Automatic generation" refers to the system building databases and other structures based on predetermined rules without manual user intervention.

[0940] A "database" is a system for systematically organizing and storing data. It includes relational database management systems (RDBMS).

[0941] A "generative AI model" is a pre-trained artificial intelligence model that performs analysis based on input data and proposes management measures.

[0942] "Emotion data" is information that indicates the user's emotional state, and includes facial expressions, tone of voice, biometric data, and the like.

[0943] An "emotion analysis engine" is software or hardware that analyzes a user's emotional data acquired from a terminal and grasps their emotional state.

[0944] "User interface" refers to the means of interaction between a system and a user, including the screens, buttons, and dashboards that users operate.

[0945] "User experience" refers to the satisfaction and ease of use that users feel when using a system, and is influenced by factors such as the system's intuitive usability and visual design.

[0946] This invention relates to a system that allows users without specialized knowledge to easily manage management data and propose optimal management measures using a generative AI model. Furthermore, by combining it with an emotion analysis engine that recognizes user emotions, it has the advantage of being able to adaptively change the proposal content and UI / UX according to the user's emotions. This system consists of a cloud server, a user's device, a generative AI model, and an emotion analysis engine.

[0947] User preparation and upload of data files

[0948] First, the user prepares a file containing management data from a device (such as a PC or tablet). The file includes sales data, customer data, inventory data, etc. This file is saved in CSV or Excel format using Microsoft Excel or Google Sheets.

[0949] Next, the user logs in to the cloud server's administration screen using a web browser (e.g., Google Chrome or Firefox). After logging in, the user accesses the "Data Upload" section, opens a file selection dialog, and uploads the prepared file.

[0950] Server checks and imports data format

[0951] The server receives the uploaded file. It then uses the Python library pandas to verify that the data format of the file is correct. Once this verification is complete, the server automatically generates a database schema and populates it with the data. This database is typically a relational database management system (RDBMS) such as MySQL or PostgreSQL. The server then creates the appropriate tables and inserts the data.

[0952] Identifying and proposing management issues using generative AI models

[0953] After the server completes the generation of the database schema, it launches a generative AI model (e.g., OpenAI's GPT-4). The generative AI model identifies business issues based on the data in the database and proposes optimal business measures. An example of a prompt sentence used here is as follows:

[0954] "Based on current inventory data, identify excess or shortage items and suggest the best course of action."

[0955] Analyzing user emotions using an emotion analysis engine

[0956] The emotion analysis engine acquires emotion data from the user's device, including facial expressions (camera), tone of voice (microphone), and biometric data such as oximetry. Software such as Affectiva or Microsoft Azure Emotion API is used for emotion analysis.

[0957] The user's emotional data detected by the emotion analysis engine influences the analysis results of the generative AI model. For example, if the user is feeling stressed, the generative AI model will simplify its suggestions and present only high-priority tasks. The dashboard's UI / UX is also dynamically adjusted based on the data from the emotion analysis engine, providing the user with the most comfortable interface.

[0958] Specific examples

[0959] Example 1: Inventory management optimization

[0960] The user prepares inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and uploads it to the server. The server checks that the data is in the correct format and automatically generates a database. A generative AI model analyzes the data and identifies products that are overstocked or understocked. The sentiment analysis engine analyzes the user's emotions, and if it determines that the user is feeling stressed, for example, the server simplifies its suggestions and focuses on high-priority measures (e.g., stopping orders for products with excessive inventory).

[0961] Example 2: Optimizing customer segmentation

[0962] The user prepares customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and uploads it to the server. Once the data format has been confirmed, the server automatically generates a database and imports the data. A generative AI model analyzes the customer data and classifies customers into multiple segments based on their value. A sentiment analysis engine obtains the user's emotions, and if the user expresses positive emotions, for example, the server makes more detailed and strategic marketing proposals. The color and design of the dashboard are also dynamically adjusted based on the user's emotions. In this way, the present invention is a system that not only automatically manages management data and proposes optimal management measures using a generative AI model, but also recognizes and responds to user emotions to make more personalized proposals.

[0963] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0964] Step 1:

[0965] The user prepares the business data.

[0966] Users use a device (such as a PC or tablet) to input management data into an application such as Microsoft Excel or Google Sheets. Once the data is input, the file is saved in CSV or Excel format. The input in this case is a data file (e.g., sales data, customer data, inventory data) created using data editing software such as Excel. The output is a prepared management data file.

[0967] Step 2:

[0968] A user uploads a data file to a cloud server.

[0969] The user logs in to the cloud server's management screen using a web browser (e.g., Google Chrome or Firefox). After logging in, the user accesses the "Data Upload" section, opens the file selection dialog, selects the prepared file, and presses the upload button to send it to the server. The input is the management data file, and the output is the file saved on the server.

[0970] Step 3:

[0971] The server checks the data format of the uploaded file.

[0972] The server receives the uploaded file and checks the data format using Python's pandas library. Specifically, it checks the consistency of the data according to the CSV or Excel format and checks whether required columns (e.g., product ID, inventory amount, purchase price, etc.) are present. The input is the uploaded management data file, and the output is the verification result of whether the format is correct.

[0973] Step 4:

[0974] The server automatically generates the database schema and populates it with data.

[0975] The server automatically generates a database schema based on a data file that has been validated for correct formatting. The database used may be, for example, MySQL or PostgreSQL. The server creates the appropriate tables and inserts the data from the file into them. The input is the validated data file; the output is the constructed database schema and the inserted data.

[0976] Step 5:

[0977] The server launches the generative AI model to identify management issues.

[0978] The server launches a generative AI model (e.g., OpenAI GPT-4) and analyzes the data in the database. For example, the following prompt is input to the generative AI model: "Based on current inventory data, please identify any excess or shortage of products and propose the optimal solution." The input is the management data in the database and the prompt, and the output is the analysis results and proposals from the generative AI model.

[0979] Step 6:

[0980] The emotion analysis engine acquires and analyzes the user's emotion data.

[0981] The emotion analysis engine acquires and analyzes biometric data such as facial expressions (camera), tone of voice (microphone), and oximeter data from the user's device. Software such as Affectiva or Microsoft Azure Emotion API is used for emotion analysis. The input is the user's emotional data, and the output is the analyzed emotional state.

[0982] Step 7:

[0983] The server dynamically adjusts the suggestions based on the results of the generative AI model and sentiment analysis engine.

[0984] The server combines the analysis results of the generative AI model with the emotional data from the emotion analysis engine to dynamically adjust the management policy proposals according to the user's emotional state. For example, if the user is feeling stressed, the proposals will be simplified and only high-priority tasks will be presented. The color and design of the dashboard will also be dynamically changed based on the emotional data. The inputs are the generative AI model's proposals and the results of the emotion analysis, and the output is the adjusted proposals and modified UI / UX.

[0985] (Application example 2)

[0986] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0987] Conventional business management systems make it difficult for users without specialized knowledge to properly manage data and plan management policies. Furthermore, they lack the ability to provide personalized suggestions and adjust the interface to take user emotions into account, resulting in a poor user experience. Therefore, there is a need for a system that can easily manage management data, propose optimal management policies using generative AI models, and dynamically adjust the proposal content and user interface according to user emotions.

[0988] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to upload a file containing management data based on a data format, means for checking the data format of the uploaded file and automatically generating a database, means for activating a generative AI model based on the automatically generated database to identify management issues and propose optimal management measures, and means for analyzing the user's facial expressions and tone of voice and dynamically adjusting the proposal content and user interface based on their emotions. This enables users to easily manage management data and receive proposals for optimal management measures without having specialized knowledge, and improves the user experience by adjusting the proposal content and user interface to be personalized according to the user's emotions.

[0989] "Management data" refers to sales data, customer data, inventory data, etc., necessary for business activities.

[0990] "Data format" refers to the format of data that is organized according to a specific format or structure, such as CSV format or Excel format.

[0991] "Means for users to upload" refers to a function that allows users to select files through an interface and send them to the cloud server.

[0992] "Automatically generated database" refers to a database environment automatically generated by the server based on uploaded data.

[0993] "Generative AI model" refers to an artificial intelligence model used to analyze data uploaded by users, identify management issues, and propose optimal management measures.

[0994] "Management issues" refer to problems a company faces or areas that need improvement.

[0995] "Optimal management measures" refer to specific measures for improving management proposed based on the generative AI model.

[0996] "Means for analyzing a user's facial expressions and tone of voice" refers to technology or software for collecting and analyzing a user's facial expressions and tone of voice using a camera or microphone.

[0997] "Means for dynamically adjusting suggested content and user interface based on emotions" refers to technology that optimizes suggested content and interface design in real time based on analyzed user emotional data.

[0998] This invention relates to a system that efficiently manages a company's management data and proposes optimal management measures using a generative AI model. Furthermore, it has the advantage of analyzing the user's emotions and dynamically adjusting the proposal content and user interface based on those emotions. This system consists of a cloud server, a user device, a generative AI model, and an emotion recognition engine.

[0999] System configuration

[1000] Hardware

[1001] Cloud server: receives, stores, and analyzes data, and runs generative AI models.

[1002] User devices: Smartphones and PCs are mainly used to upload data, collect emotion data, and display the interface.

[1003] software

[1004] Data management software: Pandas, Flask, etc., used to check data formats and automatically generate and manage databases.

[1005] Generative AI model: Used to analyze management data, identify management issues, and propose optimal management measures.

[1006] Emotion Recognition Engine: Software that processes data from the camera and microphone to analyze the user's facial expressions and tone of voice.

[1007] Data flow

[1008] 1. Upload your data

[1009] Users upload sales data, customer data, inventory data, etc. in CSV or Excel format from their devices to the cloud server.

[1010] The uploaded file is checked on the server side to see if the data format is correct.

[1011] 2. Automatic database generation

[1012] Once the data is confirmed to be in the correct format, the server automatically generates a database schema to incorporate the uploaded data.

[1013] Creates the necessary tables and checks the integrity of the data.

[1014] 3. Analysis of generative AI models

[1015] The server launches the generative AI model and analyzes the management data in the database.

[1016] Identify management issues and propose optimal management measures.

[1017] 4. Emotional Data Collection and Analysis

[1018] The user's device uses a camera and microphone to collect facial expressions and tone of voice, which are then analyzed using an emotion recognition engine.

[1019] Emotional data (e.g., stress, joy, interest, etc.) is captured in real time and transmitted to a server.

[1020] 5. Dynamic suggestions and user interface adjustments

[1021] The server dynamically adjusts the recommendations and dashboard interface based on the acquired emotional data.

[1022] For example, if the user is feeling stressed, the suggestions will be simplified and only high-priority management measures will be presented.

[1023] Considering emotions improves the user experience.

[1024] Specific examples

[1025] 1. Optimizing inventory management

[1026] The user prepares inventory data in CSV format and uploads it to the cloud server.

[1027] The server checks the data format and automatically generates the database.

[1028] Generative AI models analyze inventory data to identify overstocked or understocked items.

[1029] If the user is feeling stressed, the suggestions will be brief and will focus on stopping orders for excess inventory items.

[1030] 2. Optimizing customer segmentation

[1031] The user prepares customer data in Excel format and uploads it to the cloud server.

[1032] After the data format is confirmed, the server automatically creates and populates the database.

[1033] A generative AI model analyzes customer data and categorizes customers into segments.

[1034] If the user indicates positive sentiment, the server will provide more detailed marketing suggestions.

[1035] Prompt Sentence Examples

[1036] python

[1037] camera_feed = get_camera_feed() Gets the camera feed from a smartphone

[1038] audio_feed = get_audio_feed() Gets the smartphone's microphone audio

[1039] file_path = 'path / to / user_upload.csv'

[1040] suggestions, ui_ux_config = main(file_path, camera_feed, audio_feed)

[1041] print("Business policy proposals: ", suggestions)

[1042] print("UI / UX settings: ", ui_ux_config)

[1043] This allows users to easily manage management data without specialized knowledge and receive optimal management policy proposals from generative AI models.Furthermore, personalized proposals based on emotions and user interface adjustments improve the user experience.

[1044] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1045] Step 1:

[1046] The user prepares management data in CSV or Excel format, logs in to the cloud server's management screen, and accesses the "Data Upload" section. Here, the user selects the file and uploads it to the cloud server. The input for this step is the CSV or Excel file, and the output is a notification that the file has been uploaded to the cloud server.

[1047] Step 2:

[1048] The server receives the uploaded file and checks its data format. Specifically, it uses Pandas to read CSV or Excel files and checks the format for consistency. The input of this step is the uploaded file, and the output is the format check result. If the format is correct, it proceeds to the next step.

[1049] Step 3:

[1050] The server automatically generates the database schema and populates the database with data. Specifically, it uses Flask to generate the database and inserts data from Pandas into the database. The input for this step is the verified data file, and the output is the generated database and stored data.

[1051] Step 4:

[1052] The server launches the generative AI model and analyzes the data in the database. The generative AI model identifies management issues as a result of the analysis and proposes optimal management measures. The input for this step is the data in the database, and the output is proposed management measures.

[1053] Step 5:

[1054] The user device uses a camera and microphone to collect facial expressions and tone of voice, which are then analyzed by an emotion recognition engine. Specifically, the EmotionEngine is used to acquire and analyze emotional data. The input of this step is the user's facial and voice data, and the output is emotional data.

[1055] Step 6:

[1056] The server receives the acquired emotional data and dynamically adjusts the proposals and user interface based on that data. Specifically, it changes the UI / UX settings based on the emotional data to provide the user with an optimal interface. The input of this step is emotional data, and the output is an adjusted UI / UX proposal.

[1057] Step 7:

[1058] The adjusted proposal and user interface are displayed to the user. The user checks the provided management measures and takes necessary actions. The input of this step is the adjusted proposal from the server, and the output is the user's decision and action.

[1059] This allows users to easily manage management data without specialized knowledge and receive optimal management proposals from generative AI models. Personalization based on emotion recognition also improves the user experience.

[1060] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1061] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1062] 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.

[1063] [Fourth embodiment]

[1064] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1065] 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.

[1066] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1067] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1068] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1069] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1070] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1071] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1072] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1073] 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.

[1074] 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.

[1075] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1076] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1077] This invention relates to a system that allows users without specialized knowledge to easily upload management data and propose effective management measures based on that data. The system consists of a cloud server, a user terminal, and a generative AI model.

[1078] First, the user prepares a file containing management data from their device. This data typically includes sales data, customer data, inventory data, etc. Once the file is ready, the user uses a web browser to access the cloud server's management screen and log in. After logging in, the user accesses the "Data Upload" section, selects the prepared file, and clicks the "Upload" button.

[1079] The cloud server receives the uploaded file and temporarily stores it. The server then checks whether the received file conforms to the specified data format (e.g., CSV or Excel format). If the format is correct, the server automatically generates a database schema, creates the necessary tables, and stores the data.

[1080] After the database is automatically generated, the cloud server launches a generative AI model. The generative AI model analyzes the data in the database and identifies management issues. This identifies, for example, inventory surpluses or shortages, declining sales trends, and customer behavior patterns. The generative AI model then proposes optimal management measures to address these issues.

[1081] The proposed management measures are displayed on the user's dashboard from the cloud server. The user can access the dashboard using their device and check the proposed content. Specific measures include "optimizing inventory management," "adjusting new product promotion plans," and "optimizing marketing campaigns."

[1082] Specific examples

[1083] Example 1: Inventory management optimization

[1084] Users prepare inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and upload it to a cloud server. The server checks the received data, confirms that it is in the correct format, and then automatically generates a database. A generative AI model analyzes the data and generates a list of products with excess or shortages of stock. Suggested measures include "reducing the order quantity of a specific product" or "considering a new supplier." Users can view these suggestions on a dashboard and take appropriate action.

[1085] Example 2: Optimizing customer segmentation

[1086] Users prepare customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and upload it to a cloud server. The server verifies the data, checks that the format is correct, and then automatically generates a database. A generative AI model analyzes the customer data and classifies customers into multiple segments based on their value. Suggested measures include "implementing special campaigns for high-value customers" and "optimizing targeting strategies for new products." Users can view and implement these measures on the dashboard.

[1087] This system allows even users without specialist knowledge to effectively optimize their business operations through a series of processes: checking the data format, automatically generating a database, analyzing it using the generated AI model and proposing measures, and then having the user check and implement the measures.

[1088] The processing flow will be explained below.

[1089] Step 1:

[1090] The user prepares a file containing management data from a terminal. The prepared data includes sales data, customer data, inventory data, etc.

[1091] Step 2:

[1092] The user uses a device to access the cloud server's management screen and logs in. By entering their user ID and password on the login screen, they are authenticated by the cloud server.

[1093] Step 3:

[1094] The user goes to the "Data Upload" section on the cloud server management screen, selects the prepared file, and clicks the "Upload" button to transfer the selected file to the server.

[1095] Step 4:

[1096] The server receives the uploaded file and temporarily stores it. Then, the server checks whether the file format matches the specified data format (e.g., CSV or Excel format). If the format is invalid, it displays an error message to the user.

[1097] Step 5:

[1098] After the server verifies the correct data format, it automatically generates a database schema, which defines the database table structure and creates the necessary tables. For example, for customer data, it creates a "customers" table.

[1099] Step 6:

[1100] The server reads the uploaded data, stores the data in an automatically generated table, and verifies that each data record is saved properly.

[1101] Step 7:

[1102] After the database is built, the server launches the generative AI model, which reads the data in the database and begins analyzing it.

[1103] Step 8:

[1104] Generative AI models analyze data and identify business issues, such as declining sales trends or lists of overstocked products.

[1105] Step 9:

[1106] Based on the analysis results, the server proposes specific management measures, such as "reducing the order volume of a specific product" or "reviewing the new customer targeting strategy."

[1107] Step 10:

[1108] The server displays the proposed management measures on the user's dashboard.

[1109] Step 11:

[1110] The user accesses the cloud server using a device and checks the proposed measures on the dashboard. The user understands these measures and decides whether to apply them.

[1111] Step 12:

[1112] The user then implements the proposed business actions as needed, for example, creating a new ordering plan or adjusting a marketing campaign.

[1113] Example 1

[1114] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1115] In today's business environment, many companies are required to effectively utilize massive amounts of management data and implement prompt and appropriate management measures. However, this requires specialized knowledge and expensive analytical tools, making it difficult for small and medium-sized enterprises, in particular, to utilize these effectively. Furthermore, when analyzing data from multiple data sources, it is difficult to ensure accuracy and reliability. This prevents companies from deriving optimal management measures, putting them at risk of losing their competitive edge.

[1116] 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.

[1117] In this invention, the server

[1118] means for a user to upload a file containing management data according to a data format;

[1119] means for checking the data format of the uploaded file and automatically generating a database;

[1120] Based on the automatically generated database, a generative AI model is launched to identify management issues and propose optimal management measures.

[1121] a means for displaying the proposed management measures on a user's dashboard;

[1122] This allows even users without specialized knowledge to easily upload data and implement effective management measures. In addition, linking and analyzing data from multiple data sources improves the accuracy of management measures.

[1123] "Management data" refers to data that includes information related to a company's management situation and business processes, such as sales data, customer data, and inventory data.

[1124] A "file" is a collection of information stored in digital form, generally in a specific data format such as CSV or Excel.

[1125] "Data format" refers to the way data is structured in a particular way, and can refer to standardized formats such as CSV or Excel.

[1126] "User" refers to an individual or company that operates this system to upload management data and receive analysis results and policy proposals.

[1127] A "database" refers to a collection of data stored in an organized manner, and is a system that allows for efficient data retrieval and manipulation.

[1128] A "generative AI model" refers to a model that uses machine learning and artificial intelligence techniques to analyze data and make predictions.

[1129] A "database schema" is a design document that defines the structure and format of data in a database, and indicates the configuration of tables and columns.

[1130] "Management issues" refer to problems a company faces or areas where there is room for improvement, including excess inventory, declining sales, and customer attrition.

[1131] "Management measures" refer to plans and strategies implemented to solve specific management issues, such as optimizing inventory management and adjusting marketing strategies.

[1132] A "dashboard" refers to an interface that allows users to visually check data analysis results and policy proposals.

[1133] This invention relates to a system that allows users without specialized knowledge to easily upload management data and propose effective management measures based on that data. The system consists of a cloud server, a user terminal, and a generative AI model.

[1134] First, the user prepares the management data using their own device. This management data includes sales data, customer data, inventory data, etc., and is generally saved in CSV or Excel format. After preparing this data, the user accesses the cloud server's management screen from a web browser and logs in. After successfully logging in, the user goes to the "Data Upload" section, selects the prepared file, and clicks the "Upload" button.

[1135] The cloud server temporarily stores the received file and checks whether the data format matches the specified format (e.g., CSV or Excel format). If the format is correct, the server automatically generates a database schema, creates the necessary tables, and stores the data. A database system such as MySQL or PostgreSQL is used to generate the database schema.

[1136] After the database is automatically generated, the cloud server launches a generative AI model. This generative AI model is built using machine learning libraries such as Python and TensorFlow. The generative AI model analyzes the data in the database and identifies management issues. For example, it can identify inventory surpluses or shortages, declining sales trends, and customer behavior patterns. Based on the analysis results, it proposes optimal management measures.

[1137] The proposed management measures are displayed on the user's dashboard from the cloud server. The user accesses the dashboard using a device and checks the proposed content. Specific measures include "optimizing inventory management," "adjusting new product promotion plans," and "optimizing marketing campaigns."

[1138] Specific examples

[1139] Example 1: Inventory management optimization

[1140] Users prepare inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and upload it to a cloud server. The server checks the received data, confirms that it is in the correct format, and then automatically generates a database. A generative AI model analyzes the data and generates a list of products with excess or shortages of stock. Suggested measures include "reducing the order quantity of a specific product" or "considering a new supplier." Users can view these suggestions on a dashboard and take appropriate action.

[1141] Example 2: Optimizing customer segmentation

[1142] Users prepare customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and upload it to a cloud server. The server verifies the data, checks that the format is correct, and then automatically generates a database. A generative AI model analyzes the customer data and classifies customers into multiple segments based on their value. Suggested measures include "implementing special campaigns for high-value customers" and "optimizing targeting strategies for new products." Users can view and implement these measures on the dashboard.

[1143] Prompt Sentence Examples

[1144] "Analyze this inventory data to identify overstocked or understocked items and suggest appropriate inventory management methods."

[1145] "Please analyze this customer data, segment customers based on their value, and propose the most appropriate marketing measures for each segment."

[1146] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1147] Step 1:

[1148] The user prepares management data from a device. The user prepares a CSV or Excel file containing their company's sales data, customer data, inventory data, etc. on a device such as a PC or tablet. This involves organizing the necessary data into columns and converting it into the appropriate file format. The input data is various management data such as sales, customers, and inventory, and the output data is a CSV or Excel file in which that data is saved.

[1149] Step 2:

[1150] The user logs in to the cloud server and uploads data. The user opens a web browser and accesses the cloud server's management screen. They log in by entering their account information and proceed to the "Data Upload" section. There, they select the prepared data file and click the "Upload" button. The input data is the login information and management data file, and the output data is the management data file uploaded to the cloud server.

[1151] Step 3:

[1152] The server checks the received data and verifies the data format. The server temporarily saves the uploaded file and checks whether the file format matches the specified data format (CSV or Excel format). Specifically, the server checks the name and data type of each column and verifies that the format is correct. The input data is the uploaded management data file, and the output data is the confirmation result of whether the format is correct or incorrect.

[1153] Step 4:

[1154] The server automatically generates the database schema. After verifying that the data format is correct, the server automatically generates the database schema. Specifically, it designs the necessary tables and columns based on the received data and generates a database based on that. The input data is the verified management data file, and the output data is the automatically generated database schema and the data stored in the database.

[1155] Step 5:

[1156] The server launches the generative AI model and performs data analysis. The server launches the generative AI model and analyzes the data in the database. This analysis uses machine learning libraries such as Python and TensorFlow. The generative AI model performs statistical analysis and pattern recognition to identify management issues. The input data is the management data in the database, and the output data is the identified management issues and the analysis results.

[1157] Step 6:

[1158] The server displays the analysis results and management measures on the user's dashboard. After the generative AI model completes its analysis, the server displays the results on the user's dashboard. The analysis results may include, for example, "There is an excess of inventory for a particular product" or "Sales are on a downward trend." Based on this, optimal management measures are proposed. The input data are the analysis results of the generative AI model, and the output data are proposed management measures that are displayed on the user's dashboard.

[1159] Step 7:

[1160] The user checks the proposed management measures and takes the necessary actions. The user accesses the dashboard and checks the proposed management measures. For example, "Optimizing inventory management" displays measures such as "reducing the order quantity of certain products" and "considering new suppliers." The user makes their own management decisions based on these suggestions and takes appropriate actions. The input data are the proposed management measures displayed on the dashboard, and the output data are the specific actions the user will take.

[1161] (Application example 1)

[1162] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1163] There is an increasing need for businesses to be able to easily optimize their operations without specialized knowledge by effectively utilizing management data. However, current systems require users to check complex data formats, generate databases, and use specialized analysis methods, making them difficult to use for many users. Furthermore, there is a lack of clear guidance on how the resulting management measures should be implemented, making it difficult for brick-and-mortar stores to make appropriate decisions. This can delay the rapid resolution of management issues and the implementation of effective management measures.

[1164] 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.

[1165] In this invention, the server includes means for a user to upload a file containing management data based on a data format, means for checking the data format of the uploaded file and automatically generating a database, means for activating a generative AI model based on the automatically generated database, identifying management issues, and proposing optimal management measures, and means for a user to check the proposed management measures on a dashboard via a smartphone.

[1166] This allows users without specialized knowledge to upload management data intuitively, and then easily check and implement specific measures based on that data on their smartphones.

[1167] "Management data" includes information related to a company's management activities, such as sales data, customer data, and inventory data.

[1168] A "data format" refers to the format or structure in which data is stored, and includes formats such as CSV and Excel.

[1169] A "generative AI model" is a pre-trained artificial intelligence algorithm and structure that identifies management issues based on input data and proposes optimal measures.

[1170] A "dashboard" is an interface that allows users to visually check and manipulate information, and is displayed on smartphones and other devices.

[1171] A "database" is a system that efficiently stores and manages data, and is composed of multiple tables and schemas.

[1172] "Automatic generation" means that the system follows specified procedures, eliminating the need for manual operation, and autonomously checks data formats and builds databases.

[1173] "Management measures" refer to specific action plans and strategies implemented to solve a company's management issues.

[1174] "Uploading" is the act of a user transferring their own data from a local environment to a remote environment such as a cloud server.

[1175] "Means" includes processes, techniques, or devices used to achieve a particular end.

[1176] A "proposal" is a solution or action plan that the generative AI model presents to the user based on data analysis.

[1177] This invention relates to a system that allows even users without specialized knowledge to easily upload management data and propose effective management measures based on that data. How this system is implemented will be explained below in detail.

[1178] 1. System Overview

[1179] This system consists of a cloud server, a user device (smartphone), and a generative AI model. Its main functions are as follows:

[1180] Management data upload function

[1181] Data format confirmation function

[1182] Automatic database generation function

[1183] Data analysis and policy proposal function using generative AI

[1184] Dashboard-based policy display function

[1185] 2. Hardware and Software Used

[1186] Hardware:

[1187] Smartphone: Used by users to upload data and review measures.

[1188] Cloud server: Stores data, analyzes data, and performs recommendations.

[1189] software:

[1190] Data format confirmation: Uses Python's Pandas library.

[1191] Database Management: MySQL or PostgreSQL.

[1192] Generative AI model: TensorFlow or PyTorch.

[1193] User interface: Smartphone app using React Native.

[1194] 3. System processing flow

[1195] The main processing flow of this system is as follows:

[1196] Data upload: Users use a smartphone app to upload inventory data and customer data in CSV or Excel format to a cloud server.

[1197] Data format verification: The cloud server uses a Python script (Pandas) to verify the format of the uploaded data.

[1198] Automatic database generation: Once the data is confirmed to be in the correct format, it is automatically stored in a database such as MySQL or PostgreSQL.

[1199] Generative AI analysis: Based on the data stored in the database, generative AI models such as TensorFlow and PyTorch analyze the data.

[1200] Display of measures: Analysis results and proposed measures are displayed on the dashboard of the smartphone app.

[1201] 4. Specific Examples

[1202] Example 1: Sales promotion proposal

[1203] Prompt: "Please suggest the best sales promotion measures based on sales and customer data from the past six months."

[1204] Example 2: Optimizing inventory management

[1205] Prompt: "Based on current inventory data and past sales trends, please suggest the optimal order quantity for this month."

[1206] This allows users without specialized knowledge to intuitively upload management data and easily check and implement specific measures based on that data on their smartphones.

[1207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1208] Step 1:

[1209] The user prepares management data using a device (smartphone) and launches the application. The file selection screen for uploading opens. The user selects a data file in CSV or Excel format (e.g., inventory data or customer data) from their local storage.

[1210] Input: CSV or Excel format data file

[1211] Output: Selected data files ready to upload

[1212] Step 2:

[1213] The device (smartphone) uploads the selected data file to the cloud server. The file is sent to the server using the HTTP protocol and temporarily stored.

[1214] Input: Selected data file

[1215] Output: Data file uploaded to the server

[1216] Step 3:

[1217] The server checks the format of the received data file using the Python Pandas library. Specifically, it checks whether the matrix structure and data types of the file are correct, and if the format is correct, it proceeds to the next step.

[1218] Input: Data file uploaded to the server

[1219] Output: Format check result (correct / incorrect)

[1220] Step 4:

[1221] Once the data is verified to be in the correct format, the server stores it in a MySQL or PostgreSQL database, automatically generating the database schema and creating the necessary tables and columns.

[1222] Input: Format-checked data file

[1223] Output: Data stored in a database

[1224] Step 5:

[1225] The server runs a generative AI model (TensorFlow or PyTorch) based on the data stored in the database. This model analyzes the data, identifies specific business issues, and proposes optimal management measures, such as analyzing inventory surpluses or shortages, declining sales trends, and customer behavior patterns.

[1226] Input: Data stored in a database

[1227] Output: Analysis results and proposed management measures

[1228] Step 6:

[1229] The proposed management measures are sent from the cloud server to the device (smartphone). The device application displays these measures on the user's dashboard. The user can check the details of the measures through the dashboard.

[1230] Input: Analysis results and proposed management measures

[1231] Output: Business measures displayed on the user's dashboard

[1232] Step 7:

[1233] Users can check the measures on the dashboard and select specific actions, such as "optimizing inventory management" or "adjusting new product promotion plans," to determine specific operations for physical stores.

[1234] Input: Suggestions displayed on the dashboard

[1235] Output: The specific action the user chooses to take

[1236] This processing flow enables users, even without specialized knowledge, to easily upload management data and confirm and implement specific measures based on the results of data analysis.

[1237] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1238] This invention relates to a system that allows users without specialized knowledge to easily manage management data and proposes optimal management measures using a generative AI model. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it has the advantage of being able to adaptively change the proposal content and UI / UX according to the user's emotions. This system consists of a cloud server, a user's device, a generative AI model, and an emotion engine.

[1239] First, the user prepares a file containing management data from their device. This data includes sales data, customer data, inventory data, etc. Once the file is ready, the user logs in to the cloud server's management screen and accesses the "Data Upload" section. Here, the user selects the file and uploads it.

[1240] The server receives the file and checks whether it matches the specified data format (e.g., CSV or Excel). If the format is correct, the server automatically generates a database schema, imports the data, and creates the necessary tables. It then launches a generative AI model to identify management issues based on the data in the database and propose optimal management measures. During this process, the emotion engine collects and analyzes emotion data from the user's device. Emotion data includes facial expressions, tone of voice, and biometric data such as oximeter readings.

[1241] The user's emotional data detected by the emotion engine influences the analysis results of the generative AI model. For example, if the user is feeling stressed, the server will take that emotion into account and simplify the explanation of suggested management measures, presenting only high-priority tasks. The dashboard's UI / UX is also dynamically adjusted based on the emotion engine's data, providing the user with the most comfortable interface.

[1242] Specific examples

[1243] Example 1: Inventory management optimization

[1244] The user prepares inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and uploads it to the server. The server checks that the data is in the correct format and automatically generates a database. The generative AI model analyzes the data and identifies products that are overstocked or understocked. The emotion engine analyzes the user's emotions, and if it determines that the user is feeling stressed, for example, the server simplifies the suggestions and presents them with a focus on high-priority measures (e.g., stopping orders for products with excessive inventory).

[1245] Example 2: Optimizing customer segmentation

[1246] Users prepare customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and upload it to the server. After the data format is confirmed, the server automatically generates a database and imports the data. A generative AI model analyzes the customer data and classifies customers into multiple value-based segments. An emotion engine captures the user's emotions, and if the user expresses positive emotions, for example, the server makes more detailed and strategic marketing suggestions. The color and design of the dashboard are also dynamically adjusted based on the user's emotions.

[1247] In this way, the present invention is a system that not only automatically manages management data and proposes optimal management measures using a generative AI model, but also recognizes and responds to user emotions to make more personalized proposals.

[1248] The processing flow will be explained below.

[1249] Step 1:

[1250] The user prepares a file containing management data from a terminal. The file typically includes sales data, customer data, inventory data, etc.

[1251] Step 2:

[1252] The user uses a terminal to access the cloud server's management screen and logs in. They enter their user ID and password on the login screen to be authenticated.

[1253] Step 3:

[1254] The user goes to the "Data Upload" section on the admin page, selects the prepared file, and clicks the upload button.

[1255] Step 4:

[1256] The server receives the uploaded file and temporarily stores it. The server checks whether the received file conforms to the specified data format (e.g., CSV or Excel format). If the format is inappropriate, an error message is displayed to the user.

[1257] Step 5:

[1258] After the server verifies the correct data format, it automatically generates the database schema, defines the database table structure, and creates the necessary tables, such as "customers" and "inventory."

[1259] Step 6:

[1260] The server stores the uploaded data in an automatically generated table, and each data record is saved appropriately and the database is updated.

[1261] Step 7:

[1262] The cloud server launches the generative AI model, which reads the data from the database and begins analyzing it.

[1263] Step 8:

[1264] The emotion engine acquires emotion data from the user's device, including the user's facial expression, voice tone, heart rate, etc.

[1265] Step 9:

[1266] Generative AI models analyze data to identify business issues, such as declining sales trends, inventory overhangs or shortages, and patterns of customer behavior.

[1267] Step 10:

[1268] The server analyzes the data from the emotion engine and adjusts the suggestions based on the user's emotions. For example, if the user is feeling stressed, the suggested actions will be simplified and only the most important points will be highlighted.

[1269] Step 11:

[1270] Based on the analysis results, the server proposes specific management measures, such as "reducing the order volume of certain products" or "reviewing new customer targeting strategies."

[1271] Step 12:

[1272] The server displays the proposed management measures on the user's dashboard, and the dashboard's UI / UX is also dynamically adjusted based on the emotion engine data.

[1273] Step 13:

[1274] The user accesses the dashboard from a device and checks the proposed measures. The user understands these measures and decides whether to apply them.

[1275] Step 14:

[1276] Users can then implement the proposed business measures as needed, such as reviewing ordering plans or adjusting marketing campaigns.

[1277] In this way, the present invention is a system that manages data and proposes optimal management measures while responding to the user's emotions.

[1278] Example 2

[1279] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1280] Traditionally, managing and analyzing business data required specialized knowledge and experience, making it difficult for average users to easily undertake the task. Furthermore, the lack of appropriate management proposals that took user feelings into consideration can lead to increased stress and burden on users. Furthermore, there was a need for a flexible response to the user's feelings and circumstances regarding the analysis results.

[1281] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to upload a file containing management data based on a data format; means for checking the data format of the uploaded file and automatically generating a database; means for activating a generative AI model based on the automatically generated database, identifying management issues, and proposing optimal management measures; means for acquiring user emotion data and analyzing it with an emotion analysis engine; and means for dynamically adjusting the proposals of the generative AI model based on the user's emotions and adaptively changing the user interface and user experience. This makes it possible for even users without specialized knowledge to easily manage management data, and by combining the generative AI model and the emotion analysis engine, it is possible to propose optimal management measures based on the user's emotions.

[1282] "Management data" refers to numerical values ​​and information related to the operation of a company or organization, including sales data, customer data, inventory data, etc.

[1283] A "data format" is a specification that defines the format and structure for storing data. For example, CSV and Excel formats fall into this category.

[1284] "User" refers to an individual or organization that uses this system. Specifically, the entity that uploads management data and receives analysis results.

[1285] "Upload" refers to the act of a user transferring a data file from their own device to a remote system such as a cloud server.

[1286] "Automatic generation" refers to the system building databases and other structures based on predetermined rules without manual user intervention.

[1287] A "database" is a system for systematically organizing and storing data. It includes relational database management systems (RDBMS).

[1288] A "generative AI model" is a pre-trained artificial intelligence model that performs analysis based on input data and proposes management measures.

[1289] "Emotion data" is information that indicates the user's emotional state, and includes facial expressions, tone of voice, biometric data, and the like.

[1290] An "emotion analysis engine" is software or hardware that analyzes a user's emotional data acquired from a terminal and grasps their emotional state.

[1291] "User interface" refers to the means of interaction between a system and a user, including the screens, buttons, and dashboards that users operate.

[1292] "User experience" refers to the satisfaction and ease of use that users feel when using a system, and is influenced by factors such as the system's intuitive usability and visual design.

[1293] This invention relates to a system that allows users without specialized knowledge to easily manage management data and propose optimal management measures using a generative AI model. Furthermore, by combining it with an emotion analysis engine that recognizes user emotions, it has the advantage of being able to adaptively change the proposal content and UI / UX according to the user's emotions. This system consists of a cloud server, a user's device, a generative AI model, and an emotion analysis engine.

[1294] User preparation and upload of data files

[1295] First, the user prepares a file containing management data from a device (such as a PC or tablet). The file includes sales data, customer data, inventory data, etc. This file is saved in CSV or Excel format using Microsoft Excel or Google Sheets.

[1296] Next, the user logs in to the cloud server's administration screen using a web browser (e.g., Google Chrome or Firefox). After logging in, the user accesses the "Data Upload" section, opens a file selection dialog, and uploads the prepared file.

[1297] Server checks and imports data format

[1298] The server receives the uploaded file. It then uses the Python library pandas to verify that the data format of the file is correct. Once this verification is complete, the server automatically generates a database schema and populates it with the data. This database is typically a relational database management system (RDBMS) such as MySQL or PostgreSQL. The server then creates the appropriate tables and inserts the data.

[1299] Identifying and proposing management issues using generative AI models

[1300] After the server completes the generation of the database schema, it launches a generative AI model (e.g., OpenAI's GPT-4). The generative AI model identifies business issues based on the data in the database and proposes optimal business measures. An example of a prompt sentence used here is as follows:

[1301] "Based on current inventory data, identify excess or shortage items and suggest the best course of action."

[1302] Analyzing user emotions using an emotion analysis engine

[1303] The emotion analysis engine acquires emotion data from the user's device, including facial expressions (camera), tone of voice (microphone), and biometric data such as oximetry. Software such as Affectiva or Microsoft Azure Emotion API is used for emotion analysis.

[1304] The user's emotional data detected by the emotion analysis engine influences the analysis results of the generative AI model. For example, if the user is feeling stressed, the generative AI model will simplify its suggestions and present only high-priority tasks. The dashboard's UI / UX is also dynamically adjusted based on the data from the emotion analysis engine, providing the user with the most comfortable interface.

[1305] Specific examples

[1306] Example 1: Inventory management optimization

[1307] The user prepares inventory data (product ID, stock quantity, purchase price, etc.) in CSV format and uploads it to the server. The server checks that the data is in the correct format and automatically generates a database. A generative AI model analyzes the data and identifies products that are overstocked or understocked. The sentiment analysis engine analyzes the user's emotions, and if it determines that the user is feeling stressed, for example, the server simplifies its suggestions and focuses on high-priority measures (e.g., stopping orders for products with excessive inventory).

[1308] Example 2: Optimizing customer segmentation

[1309] The user prepares customer data (purchase history, behavioral data, demographic information, etc.) in Excel format and uploads it to the server. Once the data format has been confirmed, the server automatically generates a database and imports the data. A generative AI model analyzes the customer data and classifies customers into multiple segments based on their value. A sentiment analysis engine obtains the user's emotions, and if the user expresses positive emotions, for example, the server makes more detailed and strategic marketing proposals. The color and design of the dashboard are also dynamically adjusted based on the user's emotions. In this way, the present invention is a system that not only automatically manages management data and proposes optimal management measures using a generative AI model, but also recognizes and responds to user emotions to make more personalized proposals.

[1310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1311] Step 1:

[1312] The user prepares the business data.

[1313] Users use a device (such as a PC or tablet) to input management data into an application such as Microsoft Excel or Google Sheets. Once the data is input, the file is saved in CSV or Excel format. The input in this case is a data file (e.g., sales data, customer data, inventory data) created using data editing software such as Excel. The output is a prepared management data file.

[1314] Step 2:

[1315] A user uploads a data file to a cloud server.

[1316] The user logs in to the cloud server's management screen using a web browser (e.g., Google Chrome or Firefox). After logging in, the user accesses the "Data Upload" section, opens the file selection dialog, selects the prepared file, and presses the upload button to send it to the server. The input is the management data file, and the output is the file saved on the server.

[1317] Step 3:

[1318] The server checks the data format of the uploaded file.

[1319] The server receives the uploaded file and checks the data format using Python's pandas library. Specifically, it checks the consistency of the data according to the CSV or Excel format and checks whether required columns (e.g., product ID, inventory amount, purchase price, etc.) are present. The input is the uploaded management data file, and the output is the verification result of whether the format is correct.

[1320] Step 4:

[1321] The server automatically generates the database schema and populates it with data.

[1322] The server automatically generates a database schema based on a data file that has been validated for correct formatting. The database used may be, for example, MySQL or PostgreSQL. The server creates the appropriate tables and inserts the data from the file into them. The input is the validated data file; the output is the constructed database schema and the inserted data.

[1323] Step 5:

[1324] The server launches the generative AI model to identify management issues.

[1325] The server launches a generative AI model (e.g., OpenAI GPT-4) and analyzes the data in the database. For example, the following prompt is input to the generative AI model: "Based on current inventory data, please identify any excess or shortage of products and propose the optimal solution." The input is the management data in the database and the prompt, and the output is the analysis results and proposals from the generative AI model.

[1326] Step 6:

[1327] The emotion analysis engine acquires and analyzes the user's emotion data.

[1328] The emotion analysis engine acquires and analyzes biometric data such as facial expressions (camera), tone of voice (microphone), and oximeter data from the user's device. Software such as Affectiva or Microsoft Azure Emotion API is used for emotion analysis. The input is the user's emotional data, and the output is the analyzed emotional state.

[1329] Step 7:

[1330] The server dynamically adjusts the suggestions based on the results of the generative AI model and sentiment analysis engine.

[1331] The server combines the analysis results of the generative AI model with the emotional data from the emotion analysis engine to dynamically adjust the management policy proposals according to the user's emotional state. For example, if the user is feeling stressed, the proposals will be simplified and only high-priority tasks will be presented. The color and design of the dashboard will also be dynamically changed based on the emotional data. The inputs are the generative AI model's proposals and the results of the emotion analysis, and the output is the adjusted proposals and modified UI / UX.

[1332] (Application example 2)

[1333] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1334] Conventional business management systems make it difficult for users without specialized knowledge to properly manage data and plan management policies. Furthermore, they lack the ability to provide personalized suggestions and adjust the interface to take user emotions into account, resulting in a poor user experience. Therefore, there is a need for a system that can easily manage management data, propose optimal management policies using generative AI models, and dynamically adjust the proposal content and user interface according to user emotions.

[1335] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to upload a file containing management data based on a data format, means for checking the data format of the uploaded file and automatically generating a database, means for activating a generative AI model based on the automatically generated database to identify management issues and propose optimal management measures, and means for analyzing the user's facial expressions and tone of voice and dynamically adjusting the proposal content and user interface based on their emotions. This enables users to easily manage management data and receive proposals for optimal management measures without having specialized knowledge, and improves the user experience by adjusting the proposal content and user interface to be personalized according to the user's emotions.

[1336] "Management data" refers to sales data, customer data, inventory data, etc., necessary for business activities.

[1337] "Data format" refers to the format of data that is organized according to a specific format or structure, such as CSV format or Excel format.

[1338] "Means for users to upload" refers to a function that allows users to select files through an interface and send them to the cloud server.

[1339] "Automatically generated database" refers to a database environment automatically generated by the server based on uploaded data.

[1340] "Generative AI model" refers to an artificial intelligence model used to analyze data uploaded by users, identify management issues, and propose optimal management measures.

[1341] "Management issues" refer to problems a company faces or areas that need improvement.

[1342] "Optimal management measures" refer to specific measures for improving management proposed based on the generative AI model.

[1343] "Means for analyzing a user's facial expressions and tone of voice" refers to technology or software for collecting and analyzing a user's facial expressions and tone of voice using a camera or microphone.

[1344] "Means for dynamically adjusting suggested content and user interface based on emotions" refers to technology that optimizes suggested content and interface design in real time based on analyzed user emotional data.

[1345] This invention relates to a system that efficiently manages a company's management data and proposes optimal management measures using a generative AI model. Furthermore, it has the advantage of analyzing the user's emotions and dynamically adjusting the proposal content and user interface based on those emotions. This system consists of a cloud server, a user device, a generative AI model, and an emotion recognition engine.

[1346] System configuration

[1347] Hardware

[1348] Cloud server: receives, stores, and analyzes data, and runs generative AI models.

[1349] User devices: Smartphones and PCs are mainly used to upload data, collect emotion data, and display the interface.

[1350] software

[1351] Data management software: Pandas, Flask, etc., used to check data formats and automatically generate and manage databases.

[1352] Generative AI model: Used to analyze management data, identify management issues, and propose optimal management measures.

[1353] Emotion Recognition Engine: Software that processes data from the camera and microphone to analyze the user's facial expressions and tone of voice.

[1354] Data flow

[1355] 1. Upload your data

[1356] Users upload sales data, customer data, inventory data, etc. in CSV or Excel format from their devices to the cloud server.

[1357] The uploaded file is checked on the server side to see if the data format is correct.

[1358] 2. Automatic database generation

[1359] Once the data is confirmed to be in the correct format, the server automatically generates a database schema to incorporate the uploaded data.

[1360] Creates the necessary tables and checks the integrity of the data.

[1361] 3. Analysis of generative AI models

[1362] The server launches the generative AI model and analyzes the management data in the database.

[1363] Identify management issues and propose optimal management measures.

[1364] 4. Emotional Data Collection and Analysis

[1365] The user's device uses a camera and microphone to collect facial expressions and tone of voice, which are then analyzed using an emotion recognition engine.

[1366] Emotional data (e.g., stress, joy, interest, etc.) is captured in real time and transmitted to a server.

[1367] 5. Dynamic suggestions and user interface adjustments

[1368] The server dynamically adjusts the recommendations and dashboard interface based on the acquired emotional data.

[1369] For example, if the user is feeling stressed, the suggestions will be simplified and only high-priority management measures will be presented.

[1370] Considering emotions improves the user experience.

[1371] Specific examples

[1372] 1. Optimizing inventory management

[1373] The user prepares inventory data in CSV format and uploads it to the cloud server.

[1374] The server checks the data format and automatically generates the database.

[1375] Generative AI models analyze inventory data to identify overstocked or understocked items.

[1376] If the user is feeling stressed, the suggestions will be brief and will focus on stopping orders for excess inventory items.

[1377] 2. Optimizing customer segmentation

[1378] The user prepares customer data in Excel format and uploads it to the cloud server.

[1379] After the data format is confirmed, the server automatically creates and populates the database.

[1380] A generative AI model analyzes customer data and categorizes customers into segments.

[1381] If the user indicates positive sentiment, the server will provide more detailed marketing suggestions.

[1382] Prompt Sentence Examples

[1383] python

[1384] camera_feed = get_camera_feed() Gets the camera feed from a smartphone

[1385] audio_feed = get_audio_feed() Gets the smartphone's microphone audio

[1386] file_path = 'path / to / user_upload.csv'

[1387] suggestions, ui_ux_config = main(file_path, camera_feed, audio_feed)

[1388] print("Business policy proposals: ", suggestions)

[1389] print("UI / UX settings: ", ui_ux_config)

[1390] This allows users to easily manage management data without specialized knowledge and receive optimal management policy proposals from generative AI models.Furthermore, personalized proposals based on emotions and user interface adjustments improve the user experience.

[1391] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1392] Step 1:

[1393] The user prepares management data in CSV or Excel format, logs in to the cloud server's management screen, and accesses the "Data Upload" section. Here, the user selects the file and uploads it to the cloud server. The input for this step is the CSV or Excel file, and the output is a notification that the file has been uploaded to the cloud server.

[1394] Step 2:

[1395] The server receives the uploaded file and checks its data format. Specifically, it uses Pandas to read CSV or Excel files and checks the format for consistency. The input of this step is the uploaded file, and the output is the format check result. If the format is correct, it proceeds to the next step.

[1396] Step 3:

[1397] The server automatically generates the database schema and populates the database with data. Specifically, it uses Flask to generate the database and inserts data from Pandas into the database. The input for this step is the verified data file, and the output is the generated database and stored data.

[1398] Step 4:

[1399] The server launches the generative AI model and analyzes the data in the database. The generative AI model identifies management issues as a result of the analysis and proposes optimal management measures. The input for this step is the data in the database, and the output is proposed management measures.

[1400] Step 5:

[1401] The user device uses a camera and microphone to collect facial expressions and tone of voice, which are then analyzed by an emotion recognition engine. Specifically, the EmotionEngine is used to acquire and analyze emotional data. The input of this step is the user's facial and voice data, and the output is emotional data.

[1402] Step 6:

[1403] The server receives the acquired emotional data and dynamically adjusts the proposals and user interface based on that data. Specifically, it changes the UI / UX settings based on the emotional data to provide the user with an optimal interface. The input of this step is emotional data, and the output is an adjusted UI / UX proposal.

[1404] Step 7:

[1405] The adjusted proposal and user interface are displayed to the user. The user checks the provided management measures and takes necessary actions. The input of this step is the adjusted proposal from the server, and the output is the user's decision and action.

[1406] This allows users to easily manage management data without specialized knowledge and receive optimal management proposals from generative AI models. Personalization based on emotion recognition also improves the user experience.

[1407] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1408] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1409] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1410] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1411] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1412] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1413] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1414] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1415] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1416] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1417] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1418] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1419] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1420] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1421] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1422] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1423] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1424] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1425] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1426] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1427] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1428] The following is further disclosed regarding the above embodiment.

[1429] (Claim 1)

[1430] means for a user to upload a file containing management data according to a data format;

[1431] means for checking the data format of the uploaded file and automatically generating a database;

[1432] Based on the automatically generated database, a generative AI model is launched to identify management issues and propose optimal management measures.

[1433] A system including:

[1434] (Claim 2)

[1435] The system of claim 1, further comprising means for linking data from multiple data sources to analyze a wider variety of data and improve the accuracy of management policies.

[1436] (Claim 3)

[1437] 10. The system of claim 1, further comprising means for a user to review the proposed business measures and provide a specific implementation plan.

[1438] "Example 1"

[1439] (Claim 1)

[1440] means for a user to upload a file containing management data according to a data format;

[1441] means for checking the data format of the uploaded file and automatically generating a database;

[1442] Based on the automatically generated database, a generative AI model is launched to identify management issues and propose optimal management measures.

[1443] a means for displaying the proposed management measures on a user's dashboard;

[1444] A system including:

[1445] (Claim 2)

[1446] The system of claim 1, further comprising means for linking data from multiple data sources to analyze a wider variety of data and improve the accuracy of management policies.

[1447] (Claim 3)

[1448] 10. The system of claim 1, further comprising means for a user to review the proposed business measures and provide a specific implementation plan.

[1449] "Application Example 1"

[1450] (Claim 1)

[1451] means for a user to upload a file containing management data according to a data format;

[1452] means for checking the data format of the uploaded file and automatically generating a database;

[1453] Based on the automatically generated database, a generative AI model is launched to identify management issues and propose optimal management measures.

[1454] A means for allowing a user to check the proposed management measures on a dashboard via a smartphone;

[1455] A system including:

[1456] (Claim 2)

[1457] The system of claim 1, further comprising means for linking data from multiple data sources to analyze a wider variety of data and improve the accuracy of management policies.

[1458] (Claim 3)

[1459] 10. The system of claim 1, further comprising means for a user to review the proposed business measures and provide a specific implementation plan.

[1460] "Example 2: Combining Emotion Engines"

[1461] (Claim 1)

[1462] means for a user to upload a file containing management data according to a data format;

[1463] means for checking the data format of the uploaded file and automatically generating a database;

[1464] A means for launching a generative artificial intelligence model based on an automatically generated database, identifying management issues, and proposing optimal management measures;

[1465] A means for acquiring user emotion data and analyzing it with an emotion analysis engine;

[1466] means for dynamically adjusting the generative artificial intelligence model's proposals based on user sentiment to adaptively change the user interface and user experience;

[1467] A system including:

[1468] (Claim 2)

[1469] The system of claim 1, further comprising means for linking data from multiple data sources to analyze a wider variety of data and improve the accuracy of management policies.

[1470] (Claim 3)

[1471] 10. The system of claim 1, further comprising means for a user to review the proposed business measures and provide a specific implementation plan.

[1472] "Application example 2 when combining emotion engines"

[1473] (Claim 1)

[1474] means for a user to upload a file containing management data according to a data format;

[1475] means for checking the data format of the uploaded file and automatically generating a database;

[1476] Based on the automatically generated database, a generative AI model is launched to identify management issues and propose optimal management measures.

[1477] A means for analyzing a user's facial expression and tone of voice and dynamically adjusting the content of suggestions and the user interface based on the user's emotions;

[1478] A system including:

[1479] (Claim 2)

[1480] By linking data from multiple data sources, it is possible to analyze a wider variety of data and improve the accuracy of management measures.

[1481] 10. The system of claim 1.

[1482] (Claim 3)

[1483] including a means for users to review proposed management measures and provide specific implementation plans;

[1484] 10. The system of claim 1. [Explanation of symbols]

[1485] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for a user to upload a file containing management data according to a data format; means for checking the data format of the uploaded file and automatically generating a database; Based on the automatically generated database, a generative AI model is launched to identify management issues and propose optimal management measures. A system including:

2. 2. The system according to claim 1, further comprising means for linking data from a plurality of data sources to analyze a wider variety of data and improve the accuracy of management measures.

3. 10. The system of claim 1, further comprising means for a user to confirm the proposed business measures and provide a specific implementation plan.

Images