System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting data, a means for classifying the collected data by merchandise, a means for analyzing a common pattern from the classified data and generating summary data, a means for generating automatic calculation based on the analysis result, a means for displaying the automatically generated calculation data on a terminal, and a means for storing the generated calculation data on a cloud and performing access control.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] Currently, in many companies, creating estimates is done manually, and the process from data acquisition to analysis, generation of estimates, and sharing it is time-consuming and labor-intensive. For this reason, improving the efficiency of estimate creation and reducing the workload have become important issues. There is also a need to provide an environment where estimates can be made quickly regardless of location by utilizing mobile devices. However, current systems do not adequately meet these needs. [Means for solving the problem]

[0005] To solve the above problems, the present invention proposes the following means. It provides a system including a means for collecting data, a means for classifying the collected data by product, a means for analyzing common patterns from the classified data and generating summary data, a means for automatically generating trial calculations based on the analysis results, a means for displaying the automatically generated trial calculation data on a terminal, and a means for storing the generated trial calculation data in the cloud and controlling access to it. This system streamlines the creation of trial calculations, reduces the workload, and creates an environment where trial calculations can be performed quickly regardless of location.

[0006] "Means of collecting data" refers to the function for obtaining and saving past approval data from business systems.

[0007] "Means for classifying by product" refers to the function of classifying collected data based on specific attributes (e.g., mobile, data, etc.).

[0008] "Means for analyzing patterns" is a function for extracting and analyzing useful patterns from classified data.

[0009] The "means for generating summary data" is a function for creating summarized data based on the analyzed patterns.

[0010] "Means for generating automatic estimates" refers to a function that mechanically calculates and generates estimates based on the analysis results.

[0011] The "means for displaying on a terminal" is a function for displaying the automatically generated trial calculation data on a terminal operated by a user.

[0012] "Means for storing on the cloud" refers to a function that stores the generated estimate data on a remote server and makes it accessible online.

[0013] "Means for access control" refers to a function that sets access permissions for stored data so that only specific users can operate or view it. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The system of this invention collects data, classifies it by product, analyzes the data for common patterns, generates summary data, and automatically generates estimates based on the analysis results, displays them on a terminal, stores them in the cloud, and controls access.

[0036] Program processing

[0037] Data collection and classification

[0038] Server: Obtains approval data for the past month from the business system. This data is stored in a specific database. The data is then classified based on product category. Data is separated into categories such as "mobile" and "data."

[0039] Pattern analysis and summary data generation

[0040] Server: Based on the classified data, machine learning algorithms are used to analyze patterns. For example, cluster analysis of historical data is performed to identify common trading patterns. Summary data is generated based on the analysis results and saved in an appropriate format such as JSON.

[0041] Generate automatic estimates

[0042] Server: Based on the results of pattern analysis, the server uses robotics process automation (RPA) technology to automatically generate estimates. Specifically, it performs sales forecasts and cost calculations based on the collected pattern information. This reduces the effort required for manual calculations.

[0043] View and Share

[0044] On the device: The user opens the app, which retrieves and displays the estimated data generated by the server in real time. The user can then make any necessary corrections based on this data.

[0045] Cloud Storage and Access Control

[0046] Server: The generated trial data is stored in cloud storage and made accessible in real time. At the same time, access permissions are set for each data item, allowing specific users (e.g., SC members) to view and edit it.

[0047] Specific examples

[0048] User A's operation

[0049] User A: Launches the smartphone app and requests the past month's worth of mobile approval data.

[0050] Terminal: The request is sent to the server.

[0051] Server: Searches for data in the mobile category and sends it to User A's device.

[0052] Data analysis and calculation generation

[0053] Server: Analyzes the transmitted data using a machine learning algorithm and extracts the top 10 patterns. Furthermore, automatically generates a trial calculation based on these patterns and sends it to User A's device.

[0054] User A checks and corrects

[0055] User A: Checks the estimated data and corrects some of the figures. The corrected data is sent back to the server and saved in cloud storage.

[0056] Data sharing

[0057] Server: The revised estimate data is saved in the cloud and notified to all SC members. SC members can check the revisions on their own devices and make additional revisions or comments as necessary.

[0058] In this way, the present invention streamlines the entire process of creating estimates and significantly reduces the workload. Estimates can be performed quickly regardless of location, which also contributes to improving the business environment.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] Server: Obtains approval data for the past month from the business system. The obtained data is stored in a specific database.

[0062] Step 2:

[0063] Server: Classifies the stored data based on "product category." Data is stored separately for each category, such as "mobile" and "data."

[0064] Step 3:

[0065] Device: A user launches the app and requests data for a specific product category (e.g., mobile). The device uses the API to send the data request to the server.

[0066] Step 4:

[0067] Server: In response to the request, the server filters specific product data and returns it to the terminal. The returned data is numerical data categorized based on product category.

[0068] Step 5:

[0069] Server: Based on the received data, machine learning algorithms are used to analyze patterns, specifically cluster analysis, to extract common trading patterns.

[0070] Step 6:

[0071] Server: Generates summary data based on the analysis results. The summary data is saved in a format such as JSON and includes the top 10 patterns for each product.

[0072] Step 7:

[0073] Server: Automatically generates estimates based on pattern analysis, including sales forecasts and cost calculations, using robotic process automation (RPA) technology.

[0074] Step 8:

[0075] Server: The generated estimation data is stored in a database and cloud storage. The stored data can be accessed in real time.

[0076] Step 9:

[0077] Device: The user checks the estimated data generated through the app. The estimated data displayed on the screen can be corrected or supplemented as needed.

[0078] Step 10:

[0079] User: Checks the estimated data and corrects any necessary parts. The corrected data is sent back to the server and saved in cloud storage.

[0080] Step 11:

[0081] Server: Saves the final estimation data in the cloud and sets access permissions. Sends notifications to specific SC members to grant access.

[0082] Step 12:

[0083] SC members (users): Receive notifications and access the estimated data on the cloud. After making any necessary corrections or comments, they save it as the final version.

[0084] Example 1

[0085] 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."

[0086] Currently, many companies and organizations handle large amounts of data, but it is difficult to efficiently collect and analyze that data, quickly perform calculations, and provide users with the necessary information. In particular, there is a demand for a system that can centrally perform data classification, pattern analysis, automatic calculation generation, display, storage, and access management. The object of this invention is to provide a system that solves these problems.

[0087] 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.

[0088] In this invention, the server includes means for collecting information from business systems, means for classifying the collected information by product group, means for analyzing recurring patterns in the classified information and generating summary information, means for generating automatic calculations based on the analysis results, means for displaying the automatically generated calculation information on a terminal, means for storing the generated calculation information in a cloud environment and managing access, means for analyzing information using a machine learning algorithm and extracting common patterns, and means for automatically generating sales forecasts and cost calculations using robotics process automation technology. This enables efficient collection, classification, and analysis of data, as well as rapid generation of estimates, sharing, and management.

[0089] "Business system" is a general term for software and hardware used on a daily basis by companies and organizations for management, operation, and monitoring.

[0090] "Information" refers to all data collected, categorized, analyzed, and generated, including, in particular, decision-making data relating to commercial products.

[0091] A "product group" refers to a collection of products that belong to the same or similar category, including products with specific attributes such as "mobile" or "data."

[0092] "Classification" refers to the process of separating collected information into different categories based on specific criteria (e.g., product groups).

[0093] A "pattern" refers to a common trend or recurring phenomenon found in collected and classified information.

[0094] "Analytics" refers to the methods and techniques used to extract meaningful patterns and trends from collected and classified information.

[0095] "Summary information" refers to data that succinctly summarizes the results of analyzed patterns and provides actionable insights.

[0096] "Automatic calculation" refers to calculation processing that is automatically performed by a computer program based on the analysis results, and includes the generation of trial calculations.

[0097] A "terminal" is a device operated by a user, and refers to a computer such as a smartphone, tablet, or PC.

[0098] "Cloud environment" refers to a virtualized infrastructure for data storage and computing services delivered over the Internet.

[0099] "Access management" refers to the ability to set and control access rights to data and systems.

[0100] A "machine learning algorithm" is one of the algorithms used in data analysis, and is a technology for extracting patterns and trends from large amounts of data.

[0101] "Robotics process automation technology" refers to technology for automating routine business processes, and in this case specifically refers to the automation of sales forecasts and cost calculations.

[0102] The system of the present invention collects information from business systems, classifies it by product group, analyzes patterns using machine learning algorithms, generates summary information, generates automatic calculations using robotics process automation technology, displays the results on a terminal, stores them in a cloud environment, and manages access.

[0103] Specifically, the following hardware and software are used:

[0104] 1. Server

[0105] The server collects information from the business system, for example, by retrieving data via API and storing it in a database such as PostgreSQL.

[0106] The server categorizes the collected information into product groups using SQL queries based on the product attributes.

[0107] The server uses machine learning algorithms (e.g., Scikit-learn) to analyze patterns in the classified information and extract common patterns, using cluster analysis or other applicable analytical techniques.

[0108] The server generates summary information based on the analysis results and saves it in JSON format using the Python json library.

[0109] The server uses a robotics process automation tool (e.g., UiPath) to perform sales forecasting and cost calculations and generate automated calculations.

[0110] The server uploads the generated calculation information to a cloud environment (e.g., AWS (registered trademark) S3), generates a URL, and notifies the user. AWS SDK is used for saving.

[0111] 2. Terminal

[0112] A user uses a device (smartphone, tablet, PC, etc.) to request information from a server. The request is made using the HTTP protocol.

[0113] Receives responses from the server and displays them on the screen. For example, this is implemented using front-end technologies such as JavaScript (registered trademark) or React.

[0114] 3. Users

[0115] The user launches the smartphone app from their device and requests approval data for products from the past month.

[0116] The user checks the received data and corrects the values ​​as necessary. The corrected data is then sent back to the server and stored in the cloud environment.

[0117] For example, you can invoke a generative AI model using a prompt like this:

[0118] This system retrieves the past month's worth of approval data from a specific business system, classifies it by product group, and then performs pattern analysis using a machine learning algorithm. Based on the analysis results, it automatically generates trial calculations and displays them on the user's device. The final trial calculation data is stored in the cloud and managed with access control for specific users. Please explain in detail how the program in this system processes data.

[0119] This invention enables efficient collection and classification of data, analysis and rapid generation of estimates, as well as the sharing and management of this information in a unified manner, thereby improving work efficiency and accuracy.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Step 1:

[0122] Data collection

[0123] Server: Obtains approval data for the past month from the business system's API. Specifically, it sends an API request and receives the response data in JSON format.

[0124] Input: API request to business system

[0125] Output: Acquired approval data in JSON format

[0126] Specific operation: Use the curl command or the requests library to retrieve data via "https: / / api.example.com / getData" and insert the received JSON data into the database (PostgreSQL).

[0127] Step 2:

[0128] Data Classification

[0129] Server: Classify the acquired data based on product category (e.g., "Mobile" or "Data").

[0130] Input: Approval data obtained in Step 1

[0131] Output: Data categorized by product category

[0132] Specific operation: Issues an SQL query, categorizes the data using a command such as "SELECT FROM Approval Data WHERE Category = 'Mobile'", and inserts each category into a separate table.

[0133] Step 3:

[0134] Pattern Analysis

[0135] Server: Uses machine learning algorithms (e.g., Scikit-learn) to analyze frequent patterns from the classified data.

[0136] Input: Product data classified in Step 2

[0137] Output: Pattern data obtained by analysis

[0138] What it does: Use code like "from sklearn.cluster import KMeans" to apply cluster analysis to classified data to identify frequent patterns. The results of this analysis are temporarily saved.

[0139] Step 4:

[0140] Summary Data Generation

[0141] Server: Generates summary data based on the analysis results. The generated summary data is saved in JSON format.

[0142] Input: Pattern data analyzed in step 3

[0143] Output: Summary data in JSON format

[0144] Specific operation: Based on the acquired pattern data, summary data is generated using Python's JSON library as "summary_data = json.dumps(analysis results)" and saved in the database.

[0145] Step 5:

[0146] Automatic calculation generation

[0147] Server: Uses robotics process automation tools (e.g., UiPath) to perform sales forecasts and cost calculations, and automatically generate estimates.

[0148] Input: Summary data generated in step 4

[0149] Output: Automatically generated trial data

[0150] Specific operation: Launch an RPA tool such as UiPath, perform sales forecasts and cost calculations using code such as "RPA_tool.calculate_sales_forecast(pattern data)", and save the results.

[0151] Step 6:

[0152] Viewing Data

[0153] Terminal: The user uses the terminal to request estimated data from the server and displays the received estimated data.

[0154] Input: Data request from user

[0155] Output: Estimated data displayed on the terminal

[0156] Specific operation: Sends an HTTP request, receives and processes the JSON response from the server, and retrieves the data using code such as "fetch('server URL / estimated data').then(response => response.json())" and displays it in HTML or JavaScript.

[0157] Step 7:

[0158] Cloud Storage

[0159] Server: The generated estimate data is saved in a cloud environment (e.g., AWS S3). After saving, a public URL is generated and notified to the user.

[0160] Input: Estimated data generated in Step 5

[0161] Output: Estimated data stored in the cloud environment and its public URL

[0162] Specific operation: Using the AWS SDK, upload the data as follows: "s3_client.upload_file('estimated_data.json', 'mybucket', 'estimated_data.json')" and generate a public URL.

[0163] Step 8:

[0164] Access Control

[0165] Server: Sets access permissions for the estimation data stored in the cloud environment and notifies specific users.

[0166] Input: Estimation data stored in the cloud environment

[0167] Output: Access permissions set and notified users

[0168] Specific operation: Create an IAM policy, set permissions for each user as follows: "IAM_policy = create_policy('Access permission', users=['UserA', 'SC_member'])", and send a notification email.

[0169] In this way, by clarifying the specific operations at each processing step and their inputs and outputs, the system enables efficient data collection, classification, analysis, automatic calculation generation, display, storage, and access management.

[0170] (Application example 1)

[0171] 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."

[0172] Traditional sales forecasting and inventory management in brick-and-mortar stores relied on manual analysis and predictions, resulting in inefficiency and low accuracy. Furthermore, analyzing large amounts of data to timely replenish inventory and forecast sales placed a heavy burden on human resources. Furthermore, a lack of real-time data sharing and access control sometimes led to delays in management decisions. This resulted in inventory shortages and surpluses, lost sales opportunities, and reduced overall store operational efficiency.

[0173] 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.

[0174] In this invention, the server includes means for collecting data, means for classifying the collected data by product category, means for analyzing common patterns from the classified data and generating summary data, means for automatically generating trial calculations based on the analysis results, means for displaying the automatically generated trial calculation data on a terminal, means for storing the generated trial calculation data on the cloud and controlling access to it, means for collecting sales data and inventory data from physical stores from POS systems, means for analyzing purchasing patterns based on the collected data using a machine learning algorithm and generating summary data, means for automatically generating sales forecasts and inventory replenishment plans based on the analysis results, and means for displaying the generated sales forecast and inventory replenishment plan data on a terminal in real time, thereby enabling efficient and highly accurate sales forecasts and inventory management.

[0175] "Means of collecting data" refers to systems or devices for collecting necessary information from outside, such as POS systems and sensors.

[0176] A "categorization method" refers to an algorithm or software that organizes and classifies collected data into specific categories.

[0177] "Means for analyzing common patterns and generating summary data" refers to techniques that use statistical or machine learning techniques to extract specific patterns or trends from collected data and generate summarized information based on them.

[0178] "Means for generating automated estimates" refers to programs or algorithms for automatically calculating sales forecasts, inventory replenishment plans, etc. based on the analysis results.

[0179] "Means for displaying on the terminal" refers to the display or screen display technology that allows users to view and manipulate the results of calculations and analyses.

[0180] "Means for storing data on the cloud and controlling access" refers to a technology for storing generated data on a remote server via the Internet and managing access rights to that data.

[0181] "Means for collecting sales and inventory data from POS systems" refers to programs or interfaces for periodically obtaining sales records and inventory information from physical store POS systems.

[0182] "Means of analyzing purchasing patterns using machine learning algorithms" refers to a technology that utilizes AI technology to analyze patterns of customer purchasing behavior and sales trends.

[0183] "Means for automatically generating sales forecasts and inventory replenishment plans" refers to an algorithm that automatically calculates future sales and required inventory levels based on the analysis results, and generates an appropriate replenishment plan.

[0184] "Means for displaying on the terminal in real time" refers to real-time display technology that allows users to instantly view the results of calculations and analyses.

[0185] This invention is a system for improving the efficiency of sales forecasting and inventory management in physical stores, and includes the following elements.

[0186] System Configuration and Hardware

[0187] 1. POS system: Hardware for collecting sales and inventory data from physical stores.

[0188] 2. Server: A computer system for data collection, classification, pattern analysis, estimate generation, cloud storage, and access control.

[0189] 3. Terminal: A device such as a smartphone or tablet that allows users to check and modify the estimated data.

[0190] Software and Algorithms

[0191] 1. Data collection program (Python): Obtains sales and inventory data from the POS system in JSON format and sends it to the server.

[0192] 2. Data classification algorithm: Divide the collected data into product categories.

[0193] 3. Machine learning algorithms (scikit-learn, pandas): Analyze purchasing patterns and generate summary data.

[0194] 4. RPA tool (UiPath): Automatically generates sales forecasts and inventory replenishment plans based on analysis results.

[0195] 5. Cloud storage (AWS S3) and access control tools (AWS IAM): Store generated data in the cloud and set access permissions.

[0196] 6. Smartphone app (React Native): Displays summary data and estimates in real time and allows users to make corrections.

[0197] Data processing and calculation

[0198] server

[0199] Receives data sent from the POS system and classifies it by product category.

[0200] Machine learning algorithms are used to analyze data and extract common purchasing patterns.

[0201] Sales forecasts and inventory replenishment plans are automatically generated based on the extracted patterns.

[0202] Terminal

[0203] Receives estimated data sent from the server and displays it in real time.

[0204] The user checks and corrects the calculation results and sends the corrections to the server.

[0205] Cloud

[0206] The generated data is stored in the cloud and users can access the data based on the set access permissions.

[0207] Specific examples

[0208] 1. User A (store manager) opens the Store Management Assistant app on his smartphone and requests sales data for the food category for the past month.

[0209] 2. The server retrieves data from the POS system and analyzes it using machine learning algorithms.

[0210] 3. Sales forecasts and inventory replenishment plans are automatically generated and displayed in real time on User A's smartphone.

[0211] 4. User A checks the forecast, corrects some of the inventory quantities, and sends it back to the server.

[0212] 5. The corrected data is saved in the cloud and notified to other administrators.

[0213] Prompt Sentence Examples

[0214] "Analyze purchasing patterns for food categories based on sales data from the past month."

[0215] "Please prepare a sales forecast and inventory replenishment plan for the next month."

[0216] In this way, the system automates complex data analysis and calculations, improving the efficiency and accuracy of sales forecasting and inventory management in physical stores.

[0217] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0218] Step 1:

[0219] Input: Sales and inventory data from the POS system for the past month (JSON format)

[0220] Processing: The server uses a data collection program (Python) to acquire sales and inventory data from the POS system. The acquired data is stored in a database.

[0221] Output: Sales and inventory data stored in a database in JSON format.

[0222] Specific operation: A data request is made from the POS system, and the returned data is stored in the server's database.

[0223] Step 2:

[0224] Input: Sales and inventory data stored in a database

[0225] Processing: The server uses a data classification algorithm to classify sales and inventory data by product category.

[0226] Output: Data categorized by product category

[0227] Specific operation: Use a data frame to classify data based on product ID and category information.

[0228] Step 3:

[0229] Input: Data categorized by product category

[0230] Processing: The server analyzes the classified data using machine learning algorithms (scikit-learn, pandas), extracts purchasing patterns, and generates summary data.

[0231] Output: Summary data including purchasing patterns (JSON format)

[0232] Specific operations: Perform clustering and time series analysis to extract trends and patterns from data and generate summarized data.

[0233] Step 4:

[0234] Input: Summary data including purchasing patterns (JSON format)

[0235] Processing: The server uses an RPA tool (UiPath) to automatically generate sales forecasts and inventory replenishment plans based on the analysis results.

[0236] Output: Sales forecast and inventory replenishment plan data (JSON format)

[0237] Specific operation: Based on the prediction results of the machine learning model, sales forecasts and inventory replenishment schedules are calculated and data is generated.

[0238] Step 5:

[0239] Input: Automatically generated sales forecast and inventory replenishment plan data (JSON format)

[0240] Processing: The server stores the generated estimate data in cloud storage (AWS S3) and sets appropriate permissions using an access control tool (AWS IAM).

[0241] Output: Prediction data stored in the cloud and access permission settings

[0242] Specific behavior: Upload data to cloud storage and assign access permissions to specific users or roles.

[0243] Step 6:

[0244] Input: User request (e.g., sales data for food categories for the past month)

[0245] Processing: The server retrieves the corresponding data from the cloud storage in response to the request and sends it to the requesting terminal.

[0246] Output: Data sent to the terminal

[0247] Specific operation: Receives a user request, retrieves data from the cloud, and sends it to the specified device.

[0248] Step 7:

[0249] Input: Sales forecast and inventory replenishment plan data (JSON format)

[0250] Processing: The terminal displays sales forecast and inventory replenishment planning data in real time, allowing users to make necessary corrections.

[0251] Output: Corrected data

[0252] Specific behavior: Display data in a UI and allow users to change values ​​and conditions through the interface.

[0253] Step 8:

[0254] Input: Corrected data

[0255] Processing: The device sends the data modified by the user back to the server, and the server updates the data stored in the cloud.

[0256] Output: Updated cloud storage data

[0257] Specific behavior: User modifications are sent to the server, data in the cloud storage is updated, and users with appropriate permissions are notified.

[0258] In this way, a system is realized in which servers, terminals, and the cloud work together to perform efficient and highly accurate sales forecasts and inventory management.

[0259] 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.

[0260] The system of this invention collects data, classifies it by product, analyzes common patterns from the data, and generates summary data. It then generates automated estimates based on the analysis results, displays them on the device, stores them in the cloud, and controls access. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is possible to analyze user emotions and adjust the display content and format of the estimate data.

[0261] Program processing

[0262] Data collection and classification

[0263] Server: Obtains approval data for the past month from the business system and stores it in a database. The data is then classified based on product category. Data is stored separately for each category, such as "Mobile" and "Data."

[0264] Pattern analysis and summary data generation

[0265] Server: Based on the classified data, machine learning algorithms are used to analyze patterns. For example, cluster analysis is used to extract common trading patterns. Summary data is generated based on the analysis results and saved in a format such as JSON.

[0266] Generate automatic estimates

[0267] Server: Based on the results of pattern analysis, the server uses robotics process automation (RPA) technology to automatically generate estimates. Specifically, it performs sales forecasts and cost calculations based on the collected pattern information, and automatically generates estimates.

[0268] View and Share

[0269] On the device: The user opens the app, which retrieves and displays the estimated data generated by the server in real time. The user can then make any necessary corrections based on this data.

[0270] Incorporating an emotion engine

[0271] Device: When the user checks the estimated data, the emotion engine recognizes the user's emotions from their facial expressions and voice. The emotion engine uses a machine learning model to analyze the user's emotions (e.g., joy, anger, surprise, etc.).

[0272] Emotion-based display adjustment

[0273] Server: Receives the analysis results of the emotion engine and adjusts the display content and format according to the user's emotions. For example, if the user expresses dissatisfaction, the server may highlight the details of the estimated data.

[0274] Cloud Storage and Access Control

[0275] Server: The generated trial data is stored in cloud storage and made accessible in real time. At the same time, access permissions are set for each data item, allowing specific users (e.g., SC members) to view and edit it.

[0276] Storing and using emotional data

[0277] Server: Analyzed user emotion data is stored on the cloud, and the emotional history is used to optimize the creation and provision of estimated data. For example, it implements functions such as proposing the most suitable data format for a user based on their past emotional history.

[0278] Specific examples

[0279] User A's operation

[0280] User A: Launches the smartphone app and requests the past month's worth of mobile approval data.

[0281] Terminal: The request is sent to the server.

[0282] Server: Searches for data in the mobile category and sends it to User A's device.

[0283] Data analysis and calculation generation

[0284] Server: Analyzes the transmitted data using a machine learning algorithm and extracts the top 10 patterns. Furthermore, automatically generates a trial calculation based on these patterns and sends it to User A's device.

[0285] User A checks and corrects

[0286] User A: When checking the estimated data, the emotion engine analyzes User A's facial expressions to determine their emotions. If User A expresses surprise, the display content is adjusted to address the reason for the surprise. For example, a detailed explanation may be added.

[0287] User A: Makes the necessary corrections, sends the corrected version back to the server, and saves it in cloud storage.

[0288] Data sharing

[0289] Server: The revised estimate data is saved in the cloud and notified to all SC members. SC members can check the revisions on their own devices and make additional revisions or comments as necessary.

[0290] In this way, the present invention streamlines the entire process of creating estimates and significantly reduces the workload. Furthermore, the introduction of an emotion engine enables flexible responses based on the user's emotions, contributing to an improved business environment.

[0291] The processing flow will be explained below.

[0292] Step 1:

[0293] Server: Obtains approval data for the past month from the business system. The obtained data is stored in a specific database.

[0294] Step 2:

[0295] Server: Classifies the stored data based on "product category." Data is stored separately for each category, such as "mobile" and "data."

[0296] Step 3:

[0297] Device: A user launches the app and requests data for a specific product category (e.g., mobile). The device uses the API to send the data request to the server.

[0298] Step 4:

[0299] Server: In response to the request, the server filters specific product data and returns it to the terminal. The returned data is numerical data categorized based on product category.

[0300] Step 5:

[0301] Server: Based on the received data, machine learning algorithms are used to analyze patterns, specifically cluster analysis, to extract common trading patterns.

[0302] Step 6:

[0303] Server: Generates summary data based on the analysis results. The summary data is saved in a format such as JSON and includes the top 10 patterns for each product.

[0304] Step 7:

[0305] Server: Automatically generates estimates based on pattern analysis, including sales forecasts and cost calculations, using robotic process automation (RPA) technology.

[0306] Step 8:

[0307] Server: The generated estimation data is stored in a database and cloud storage. The stored data can be accessed in real time.

[0308] Step 9:

[0309] Device: The user checks the estimated data generated through the app. The estimated data displayed on the screen can be corrected or supplemented as needed.

[0310] Step 10:

[0311] User: Checks the estimated data and corrects any necessary parts. The corrected data is sent back to the server and saved in cloud storage.

[0312] Step 11:

[0313] Server: The emotion engine recognizes and analyzes the user's emotions from their facial expressions and voice. Based on the analysis results, the user's emotional state is determined.

[0314] Step 12:

[0315] Server: Based on the analyzed emotion data, adjust the content and format of the displayed estimated data. For example, if the user expresses dissatisfaction or confusion, display additional explanations.

[0316] Step 13:

[0317] Server: Stores emotion data on the cloud and manages the user's emotion history. Based on past emotion data, the algorithm that optimizes the estimation process is updated.

[0318] Step 14:

[0319] Server: Sets access permissions for the estimation data and emotion data and notifies specific SC members. Apply access control to SC members.

[0320] Step 15:

[0321] SC members (users): Receive notifications and access the estimated data and sentiment analysis data in the cloud. After making any necessary corrections or comments, they save the data as the final version.

[0322] Example 2

[0323] 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."

[0324] Existing data analysis systems collect and classify data, but often do not display or adjust the data appropriately, taking user emotions into account. Furthermore, there are issues with insufficient sharing of analysis results and access control, making it difficult for specific users to quickly obtain or modify the data they need. Furthermore, there is a lack of mechanisms for effectively utilizing user emotion data.

[0325] 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 collecting data, means for classifying the collected data by product, means for analyzing common patterns from the classified data and generating summary data, means for generating automatic trial calculations based on the analysis results, means for displaying the automatically generated trial calculation data on a terminal, means for storing the generated trial calculation data on the cloud and performing access control, means for recognizing user emotions and adjusting the display content and format of the trial calculation data, and means for analyzing user emotion data and storing it on the cloud. This enables seamless processing from data analysis to trial calculation generation and display adjustment according to the user's emotions. In addition, sharing and access control of generated data are strengthened, allowing specific users to quickly obtain and modify the data they need.

[0326] "Means for collecting data" refers to a device or program that has the function of acquiring and storing necessary data from business systems and external data sources.

[0327] "Means for classifying by product" refers to a device or program that provides the function of classifying and organizing acquired data based on specific criteria (e.g., product category, industry, etc.).

[0328] "Means for analyzing patterns and generating summary data" refers to a device or program that has the function of analyzing common trading patterns based on classified data using machine learning algorithms and statistical methods, and summarizing the results to create summary data.

[0329] The "means for generating automatic estimates" refers to a device or program that automatically performs sales forecasts, cost calculations, etc. based on the analysis results and generates estimate results.

[0330] The "means for displaying trial calculation data on a terminal" refers to a device or program having the function of transmitting the generated trial calculation data to a user's terminal in real time and displaying it.

[0331] "Means for storing the generated trial data on the cloud and controlling access" refers to a device or program that stores the generated trial data in cloud storage and has the function of setting and managing access rights for specific users.

[0332] "Means for recognizing the user's emotions and adjusting the display content and format of the trial calculation data" refers to a device or program that analyzes the user's emotions from their facial expressions, voice, etc., and adaptively changes the display content and format of the trial calculation data based on the results.

[0333] The "means for analyzing user emotion data and storing it in the cloud" refers to a device or program that has the function of storing the analyzed user emotion data in a cloud environment and using it for future data analysis and display adjustment.

[0334] The system of the present invention collects data, classifies it by product type, analyzes the data for common patterns, and generates summary data. It then generates automated estimates based on the analysis results, displays them on the device, stores them in the cloud, and controls access. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is possible to analyze user emotions and adjust the display content and format of the estimate data.

[0335] Data collection

[0336] Server: Obtains approval data for the past month from the business system. A specific method for this is to collect data using the business system's API. The collected data is stored in a database. Specific databases used include MySQL (registered trademark) and PostgreSQL.

[0337] Data Classification

[0338] Server: Collected data is classified based on product category. For example, data is divided into categories such as "mobile" and "data," and each category is tagged and saved.

[0339] Pattern Analysis

[0340] Server: Using Python's SciKit-Learn library, machine learning algorithms are used to analyze patterns based on the classified data, for example, using cluster analysis to extract common trading patterns.

[0341] Summary Data Generation

[0342] Server: Generates summary data based on the analysis results. The generated summary data is saved in JSON format and stored in a separate table in the database.

[0343] Generate automatic estimates

[0344] Server: Use an RPA tool (e.g., Blue Prism) to generate automatic estimates based on the summary data. Specifically, run a sales forecast model based on the pattern information, automatically input the estimate results into an Excel template, and generate a report.

[0345] Display of estimated data

[0346] Device: The user launches the app on their smartphone and requests estimated data. The requested data is sent to the server, which returns the estimated data to the device. The user can then check the estimated data in real time on the app.

[0347] Emotion Engine Analysis

[0348] Device: The device uses a built-in camera and microphone to analyze the user's emotions in real time. It uses Google Cloud's emotion recognition API to identify emotions from the user's facial expressions and voice.

[0349] Emotion-based display adjustment

[0350] Server: Based on the results of the emotion engine's analysis, the server adjusts the display content and format of the estimated data. For example, if surprise is detected, the server automatically adds a detailed explanation of the estimated data.

[0351] Cloud Storage and Access Control

[0352] Server: The generated and modified estimation data is stored in a cloud storage service such as AWS S3, and replicated to multiple regions to facilitate data backup and recovery after storage. IAM user policies are used to set access permissions for data stored in the cloud, allowing specific users (e.g., SC members) to view and modify the data.

[0353] Storing and using emotional data

[0354] Server: Analyzed emotion data is stored in a cloud environment and managed as user emotion history data. The emotion history is used to propose the optimal format and display method for the next and subsequent trial calculation data creation.

[0355] Specific examples

[0356] Example prompt: "Request mobile payment data for the past month."

[0357] User A launches the app on their smartphone and requests mobile payment data for the past month.

[0358] A request is sent to the server, data in the mobile category is searched and sent to User A's device.

[0359] The transmitted data is analyzed using a machine learning algorithm to extract the top 10 patterns. Furthermore, Blue Prism automatically generates estimates, and the results are sent to User A's device.

[0360] When User A checks the estimated data, the emotion engine analyzes their emotions from their facial expressions and voice, and adjusts the displayed estimated data as necessary.

[0361] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0362] Step 1: Data collection

[0363] Server: Obtain approval data for the past month from the business system via API. The API endpoint and authentication information of the business system are required as input. The data obtained from the API is saved in a database (e.g., MySQL). The output is the approval data saved in the database.

[0364] Specifically, a scheduled job is executed at a fixed time every day to collect new data from the business system.

[0365] Step 2: Data Classification

[0366] Server: Classifies the payment data stored in the database by product category. The original payment data stored in the database is required as input. Using SQL queries, the data is classified and tagged into categories such as "mobile" and "data." The output is the classified and tagged data.

[0367] Specific operations include filtering and tagging based on product categories.

[0368] Step 3: Pattern analysis

[0369] Server: Uses Python's SciKit-Learn library to analyze the classified data using machine learning algorithms to find patterns. The tagged data is required as input. Cluster analysis is performed to extract common trading patterns. The output is the pattern data as the analysis results.

[0370] Specifically, cluster analysis is performed, and representative transaction patterns for each cluster are extracted and saved.

[0371] Step 4: Summary data generation

[0372] Server: Generates summary data from the analyzed pattern data. Pattern data is required as input. Transaction summaries for each pattern are compiled and summary data is generated in JSON format. The output is the generated summary data.

[0373] Specifically, the data is aggregated, an overview of each pattern is summarized, and the results are saved in a JSON format file.

[0374] Step 5: Generate an automatic estimate

[0375] Server: Uses an RPA tool (e.g. Blue Prism) to generate automated estimates based on summary data. Requires summary data as input. Runs a sales forecasting model and automatically populates an Excel template with estimate results. Output is the generated estimate report.

[0376] Specifically, the predictive model is executed and the results are automatically reflected in the Excel template.

[0377] Step 6: View the estimated data

[0378] Terminal: The user launches the smartphone app and requests estimated data. The user's request (e.g., the past month's worth of mobile data) is required as input. The server responds to the request and returns the estimated data to the terminal. The output is the estimated data displayed on the user's terminal.

[0379] Specifically, data is retrieved from the server via an HTTP request and displayed in the app.

[0380] Step 7: Emotion Engine Analysis

[0381] Device: Analyzes user emotions in real time using the built-in camera and microphone. User facial expressions and voice are required as input. Google Cloud's emotion recognition API is used to analyze user emotions. The output is recognized emotion data.

[0382] Specifically, the process involves capturing facial expressions and voice, sending them to an API, and analyzing emotions.

[0383] Step 8: Emotion-Based Display Adjustment

[0384] Server: Adjusts the display content and format of the estimated data based on the analysis results of the emotion engine. It requires recognized emotion data as input. For example, if surprise emotion is detected, it highlights the details of the estimated data. The output is the adjusted display of the estimated data.

[0385] As a specific operation, a customization process for the display content is executed, and the adjustment results are sent to the terminal.

[0386] Step 9: Save your data to the cloud

[0387] Server: Stores generated and modified estimate data in cloud storage (e.g., AWS S3). Requires generated or modified estimate data as input. Data is stored in cloud storage and replicated across multiple regions. Output is estimate data stored in the cloud.

[0388] Specifically, data is stored and backed up on the cloud.

[0389] Step 10: Access Control

[0390] Server: Sets access permissions for data stored in cloud storage. Access permission information and target data are required as input. IAM user policies are used to set permissions so that specific users can access the data. The output is the set access permissions.

[0391] Specific operations include setting access control lists (ACLs) and policies.

[0392] Step 11: Storing and Using Emotional Data

[0393] Server: Analyzed emotion data is stored in the cloud and managed as emotion history data. Analyzed emotion data is required as input. Based on the emotion history, the optimal format and display method are proposed for the next and subsequent trial calculation data creation. The output is the stored emotion history data.

[0394] Specifically, emotion data is saved and historical data is analyzed to help provide future data.

[0395] (Application example 2)

[0396] 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."

[0397] Conventional systems were able to efficiently collect and classify data and generate automatic estimates, but they had problems with a fixed user interface and lacked the flexibility to respond based on user emotions. Furthermore, there was no way to adjust the display format of the generated estimate data based on the user's emotions, resulting in a limited user experience. Therefore, there is a need for a system that optimizes data management and display and provides dynamic responses based on the user's emotions.

[0398] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data, means for classifying the collected data by product type, means for analyzing common patterns from the classified data and generating summary data, means for automatically generating trial calculations based on the analysis results, means for displaying the automatically generated trial calculation data on a terminal, means for storing the generated trial calculation data on the cloud and controlling access to it, means for analyzing the user's emotions using emotion recognition means, and means for adjusting the display content and format of the trial calculation data based on the user's emotions. This makes it possible to adjust the display content according to the user's emotions, thereby providing a more flexible and optimized data management system.

[0399] "Means of collecting data" refers to the function of automatically acquiring past transaction data and business data and storing it in the system.

[0400] "Means for classifying by product" is a function that divides collected data into categories and classifies them into specific product groups.

[0401] "Means for analyzing patterns and generating summary data" refers to a function that uses machine learning algorithms to extract common patterns from collected and classified data, summarizes them, and generates summary data.

[0402] The "means for generating automatic estimates" is a function that performs sales forecasts and cost calculations based on the analyzed pattern data, and automatically generates estimates.

[0403] "Means for displaying on a terminal" is a function for displaying the generated trial calculation data on the user's terminal in real time.

[0404] "Means for storing data on the cloud and controlling access" refers to a function for storing the generated estimate data in cloud storage and setting access rights for specific users.

[0405] The "emotion recognition means" is a function that recognizes and analyzes the user's emotions from facial expressions and voice data.

[0406] The "means for adjusting the display content and format" is a function for dynamically adjusting the display format and content of the trial calculation data according to the recognized user's emotions.

[0407] The present invention relates to a smart logistics management system in a logistics center. Next, an embodiment of the present invention will be described in detail.

[0408] System Configuration

[0409] Program processing

[0410] Data collection and classification

[0411] The server retrieves the past month's worth of transaction data from the logistics center's business system and stores it in a database. The data is then classified by product and managed by category, such as "mobile devices" or "consumables."

[0412] Pattern analysis and summary data generation

[0413] The server uses machine learning algorithms to analyze patterns based on the classified data. For example, it uses cluster analysis to extract common transaction patterns at the distribution center. It then generates summary data based on the analysis results and saves them in a format such as JSON.

[0414] Generate automatic estimates

[0415] Based on the analysis results, the server uses robotics process automation (RPA) technology to forecast sales and optimize inventory, automatically generating trial data.

[0416] View and Share

[0417] The device (smart glasses or robot) receives and displays the estimated data generated by the server in real time according to the user's instructions. The user can then work based on this data and make any necessary corrections.

[0418] Incorporating an emotion engine

[0419] When the user checks the estimated data on the device, the emotion engine installed in the smart glasses or robot recognizes the user's emotions from their facial expressions and voice.

[0420] Emotion-based display adjustment

[0421] The server receives the analysis results from the emotion engine and dynamically adjusts the display content and format of the trial calculation data in accordance with the user's emotions.

[0422] Cloud Storage and Access Control

[0423] The generated estimate data is stored in cloud storage, and access control is performed in real time, allowing only specific users to access and modify the data.

[0424] Storing and using emotional data

[0425] The server stores the user's emotion data in the cloud, analyzes past emotion history, and optimizes the creation and provision of trial data, thereby proposing the most suitable display format for the user.

[0426] Specific examples

[0427] User B's operation

[0428] User B puts on the smart glasses and launches the inventory management app. He makes a request to check inventory data for the past month, and the device sends this request to the server. The server retrieves the inventory data and sends it to User B's device.

[0429] Data analysis and calculation generation

[0430] The server analyzes the received data using a machine learning algorithm and extracts the top 10 patterns of data. It then automatically generates a trial calculation based on these patterns and sends it to User B's device.

[0431] User B checks and corrects

[0432] When User B checks the estimated data, the emotion engine analyzes User B's facial expressions to determine their emotions. If User B expresses dissatisfaction, the displayed content is adjusted to address the reason for dissatisfaction. For example, a detailed explanation may be added. After making any necessary corrections, the revised version is sent back to the server and saved in cloud storage.

[0433] Data sharing

[0434] The server saves the revised estimate data in the cloud and notifies specific users (e.g., logistics center managers). The managers can check the revisions on their own devices and make additional revisions or comments as necessary.

[0435] Prompt Sentence Examples

[0436] "Write a Python program that collects inventory data from the past month, analyzes it for the most common patterns, and displays the results as a summary. Also, add the ability to adjust the display based on user sentiment."

[0437] This invention aims to improve data management and work efficiency in logistics centers, and enables flexible responses based on user emotions.

[0438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0439] Step 1: Data collection

[0440] The server retrieves the past month's worth of transaction data from the logistics center's business system via API. The input is the business system's API endpoint and authentication token, and the output is JSON-formatted transaction data. Specifically, it makes an API request, parses the JSON data returned as a response, and saves it in the database.

[0441] Step 2: Data Classification

[0442] The server categorizes the collected data by product. The input is transaction data stored in a database, and the output is a dataset categorized by product. Specifically, the data is filtered based on product category information, and each category is saved as a separate dataset.

[0443] Step 3: Pattern analysis and summary data generation

[0444] The server uses a machine learning algorithm to analyze patterns based on the classified data. The input is a data set classified by product type, and the output is summary data based on the pattern analysis. Specifically, it performs cluster analysis, extracts transaction patterns, summarizes each pattern, and saves them as summary data.

[0445] Step 4: Generate an automatic estimate

[0446] The server performs sales forecasting and inventory optimization based on the pattern analysis results, and automatically generates trial calculation data. The input is the pattern analysis results, and the output is automatically generated trial calculation data. Specifically, RPA technology is used to apply sales forecasting algorithms and inventory optimization algorithms, calculate and save the trial calculation results.

[0447] Step 5: View the estimated data

[0448] The terminal (smart glasses or robot) receives and displays the estimated data generated from the server in real time at the user's command. The input is a request for estimated data from the server, and the output is the estimated data displayed on the user's terminal. Specifically, an HTTP request is sent, and the estimated data is received and displayed in real time.

[0449] Step 6: Emotion recognition and display adjustment

[0450] When the user checks the estimated data on the device, the emotion engine installed in the smart glasses or robot recognizes the emotion from the user's facial expression and voice. The input is the user's facial expression data and voice data, and the output is analyzed emotion data. Specifically, the user's facial expression and voice are captured using a camera or microphone, and then analyzed using an emotion recognition algorithm.

[0451] Step 7: Adjust content based on emotions

[0452] The server receives the analysis results from the emotion engine and dynamically adjusts the display content and format of the trial calculation data according to the user's emotions. The inputs are emotion data and trial calculation data, and the output is the adjusted display of the trial calculation data. Specifically, if the user expresses dissatisfaction, the server makes adjustments such as displaying additional detailed explanations.

[0453] Step 8: Cloud Storage and Access Control

[0454] The server stores the generated trial calculation data and emotion data in cloud storage and performs access control in real time. The inputs are the trial calculation data and emotion data, and the output is the data stored on the cloud and the access permissions that are set. Specifically, the data is uploaded using a cloud API and access permissions are set for specific users.

[0455] Step 9: Storing and optimizing emotional data

[0456] The server stores the user's emotional data in the cloud, analyzes past emotional history, and optimizes the creation and provision of trial data. The inputs are emotional data and past emotional history, and the output is optimized trial data. Specifically, it uses an analytical algorithm to analyze past emotional data and propose future display content.

[0457] 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.

[0458] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0459] 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.

[0460] [Second embodiment]

[0461] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0462] 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.

[0463] 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).

[0464] 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.

[0465] 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.

[0466] 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).

[0467] 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.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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."

[0473] The system of this invention collects data, classifies it by product, analyzes the data for common patterns, generates summary data, and automatically generates estimates based on the analysis results, displays them on a terminal, stores them in the cloud, and controls access.

[0474] Program processing

[0475] Data collection and classification

[0476] Server: Obtains approval data for the past month from the business system. This data is stored in a specific database. The data is then classified based on product category. Data is separated into categories such as "mobile" and "data."

[0477] Pattern analysis and summary data generation

[0478] Server: Based on the classified data, machine learning algorithms are used to analyze patterns. For example, cluster analysis of historical data is performed to identify common trading patterns. Summary data is generated based on the analysis results and saved in an appropriate format such as JSON.

[0479] Generate automatic estimates

[0480] Server: Based on the results of pattern analysis, the server uses robotics process automation (RPA) technology to automatically generate estimates. Specifically, it performs sales forecasts and cost calculations based on the collected pattern information. This reduces the effort required for manual calculations.

[0481] View and Share

[0482] On the device: The user opens the app, which retrieves and displays the estimated data generated by the server in real time. The user can then make any necessary corrections based on this data.

[0483] Cloud Storage and Access Control

[0484] Server: The generated trial data is stored in cloud storage and made accessible in real time. At the same time, access permissions are set for each data item, allowing specific users (e.g., SC members) to view and edit it.

[0485] Specific examples

[0486] User A's operation

[0487] User A: Launches the smartphone app and requests the past month's worth of mobile approval data.

[0488] Terminal: The request is sent to the server.

[0489] Server: Searches for data in the mobile category and sends it to User A's device.

[0490] Data analysis and calculation generation

[0491] Server: Analyzes the transmitted data using a machine learning algorithm and extracts the top 10 patterns. Furthermore, automatically generates a trial calculation based on these patterns and sends it to User A's device.

[0492] User A checks and corrects

[0493] User A: Checks the estimated data and corrects some of the figures. The corrected data is sent back to the server and saved in cloud storage.

[0494] Data sharing

[0495] Server: The revised estimate data is saved in the cloud and notified to all SC members. SC members can check the revisions on their own devices and make additional revisions or comments as necessary.

[0496] In this way, the present invention streamlines the entire process of creating estimates and significantly reduces the workload. Estimates can be performed quickly regardless of location, which also contributes to improving the business environment.

[0497] The processing flow will be explained below.

[0498] Step 1:

[0499] Server: Obtains approval data for the past month from the business system. The obtained data is stored in a specific database.

[0500] Step 2:

[0501] Server: Classifies the stored data based on "product category." Data is stored separately for each category, such as "mobile" and "data."

[0502] Step 3:

[0503] Device: A user launches the app and requests data for a specific product category (e.g., mobile). The device uses the API to send the data request to the server.

[0504] Step 4:

[0505] Server: In response to the request, the server filters specific product data and returns it to the terminal. The returned data is numerical data categorized based on product category.

[0506] Step 5:

[0507] Server: Based on the received data, machine learning algorithms are used to analyze patterns, specifically cluster analysis, to extract common trading patterns.

[0508] Step 6:

[0509] Server: Generates summary data based on the analysis results. The summary data is saved in a format such as JSON and includes the top 10 patterns for each product.

[0510] Step 7:

[0511] Server: Automatically generates estimates based on pattern analysis, including sales forecasts and cost calculations, using robotic process automation (RPA) technology.

[0512] Step 8:

[0513] Server: The generated estimation data is stored in a database and cloud storage. The stored data can be accessed in real time.

[0514] Step 9:

[0515] Device: The user checks the estimated data generated through the app. The estimated data displayed on the screen can be corrected or supplemented as needed.

[0516] Step 10:

[0517] User: Checks the estimated data and corrects any necessary parts. The corrected data is sent back to the server and saved in cloud storage.

[0518] Step 11:

[0519] Server: Saves the final estimation data in the cloud and sets access permissions. Sends notifications to specific SC members to grant access.

[0520] Step 12:

[0521] SC members (users): Receive notifications and access the estimated data on the cloud. After making any necessary corrections or comments, they save it as the final version.

[0522] Example 1

[0523] 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."

[0524] Currently, many companies and organizations handle large amounts of data, but it is difficult to efficiently collect and analyze that data, quickly perform calculations, and provide users with the necessary information. In particular, there is a demand for a system that can centrally perform data classification, pattern analysis, automatic calculation generation, display, storage, and access management. The object of this invention is to provide a system that solves these problems.

[0525] 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.

[0526] In this invention, the server includes means for collecting information from business systems, means for classifying the collected information by product group, means for analyzing recurring patterns in the classified information and generating summary information, means for generating automatic calculations based on the analysis results, means for displaying the automatically generated calculation information on a terminal, means for storing the generated calculation information in a cloud environment and managing access, means for analyzing information using a machine learning algorithm and extracting common patterns, and means for automatically generating sales forecasts and cost calculations using robotics process automation technology. This enables efficient collection, classification, and analysis of data, as well as rapid generation of estimates, sharing, and management.

[0527] "Business system" is a general term for software and hardware used on a daily basis by companies and organizations for management, operation, and monitoring.

[0528] "Information" refers to all data collected, categorized, analyzed, and generated, including, in particular, decision-making data relating to commercial products.

[0529] A "product group" refers to a collection of products that belong to the same or similar category, including products with specific attributes such as "mobile" or "data."

[0530] "Classification" refers to the process of separating collected information into different categories based on specific criteria (e.g., product groups).

[0531] A "pattern" refers to a common trend or recurring phenomenon found in collected and classified information.

[0532] "Analytics" refers to the methods and techniques used to extract meaningful patterns and trends from collected and classified information.

[0533] "Summary information" refers to data that succinctly summarizes the results of analyzed patterns and provides actionable insights.

[0534] "Automatic calculation" refers to calculation processing that is automatically performed by a computer program based on the analysis results, and includes the generation of trial calculations.

[0535] A "terminal" is a device operated by a user, and refers to a computer such as a smartphone, tablet, or PC.

[0536] "Cloud environment" refers to a virtualized infrastructure for data storage and computing services delivered over the Internet.

[0537] "Access management" refers to the ability to set and control access rights to data and systems.

[0538] A "machine learning algorithm" is one of the algorithms used in data analysis, and is a technology for extracting patterns and trends from large amounts of data.

[0539] "Robotics process automation technology" refers to technology for automating routine business processes, and in this case specifically refers to the automation of sales forecasts and cost calculations.

[0540] The system of the present invention collects information from business systems, classifies it by product group, analyzes patterns using machine learning algorithms, generates summary information, generates automatic calculations using robotics process automation technology, displays the results on a terminal, stores them in a cloud environment, and manages access.

[0541] Specifically, the following hardware and software are used:

[0542] 1. Server

[0543] The server collects information from the business system, for example, by retrieving data via API and storing it in a database such as PostgreSQL.

[0544] The server categorizes the collected information into product groups using SQL queries based on the product attributes.

[0545] The server uses machine learning algorithms (e.g., Scikit-learn) to analyze patterns in the classified information and extract common patterns, using cluster analysis or other applicable analytical techniques.

[0546] The server generates summary information based on the analysis results and saves it in JSON format using the Python json library.

[0547] The server uses a robotics process automation tool (e.g., UiPath) to perform sales forecasting and cost calculations and generate automated calculations.

[0548] The server uploads the generated calculation information to a cloud environment (e.g., AWS S3), generates a URL, and notifies the user. AWS SDK is used for saving.

[0549] 2. Terminal

[0550] A user uses a device (smartphone, tablet, PC, etc.) to request information from a server. The request is made using the HTTP protocol.

[0551] Receives the response from the server and displays it on the screen. For example, this is implemented using front-end technologies such as JavaScript or React.

[0552] 3. Users

[0553] The user launches the smartphone app from their device and requests approval data for products from the past month.

[0554] The user checks the received data and corrects the values ​​as necessary. The corrected data is then sent back to the server and stored in the cloud environment.

[0555] For example, you can invoke a generative AI model using a prompt like this:

[0556] This system retrieves the past month's worth of approval data from a specific business system, classifies it by product group, and then performs pattern analysis using a machine learning algorithm. Based on the analysis results, it automatically generates trial calculations and displays them on the user's device. The final trial calculation data is stored in the cloud and managed with access control for specific users. Please explain in detail how the program in this system processes data.

[0557] This invention enables efficient collection and classification of data, analysis and rapid generation of estimates, as well as the sharing and management of this information in a unified manner, thereby improving work efficiency and accuracy.

[0558] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0559] Step 1:

[0560] Data collection

[0561] Server: Obtains approval data for the past month from the business system's API. Specifically, it sends an API request and receives the response data in JSON format.

[0562] Input: API request to business system

[0563] Output: Acquired approval data in JSON format

[0564] Specific operation: Use the curl command or the requests library to retrieve data via "https: / / api.example.com / getData" and insert the received JSON data into the database (PostgreSQL).

[0565] Step 2:

[0566] Data Classification

[0567] Server: Classify the acquired data based on product category (e.g., "Mobile" or "Data").

[0568] Input: Approval data obtained in Step 1

[0569] Output: Data categorized by product category

[0570] Specific operation: Issues an SQL query, categorizes the data using a command such as "SELECT FROM Approval Data WHERE Category = 'Mobile'", and inserts each category into a separate table.

[0571] Step 3:

[0572] Pattern Analysis

[0573] Server: Uses machine learning algorithms (e.g., Scikit-learn) to analyze frequent patterns from the classified data.

[0574] Input: Product data classified in Step 2

[0575] Output: Pattern data obtained by analysis

[0576] What it does: Use code like "from sklearn.cluster import KMeans" to apply cluster analysis to classified data to identify frequent patterns. The results of this analysis are temporarily saved.

[0577] Step 4:

[0578] Summary Data Generation

[0579] Server: Generates summary data based on the analysis results. The generated summary data is saved in JSON format.

[0580] Input: Pattern data analyzed in step 3

[0581] Output: Summary data in JSON format

[0582] Specific operation: Based on the acquired pattern data, summary data is generated using Python's JSON library as "summary_data = json.dumps(analysis results)" and saved in the database.

[0583] Step 5:

[0584] Automatic calculation generation

[0585] Server: Uses robotics process automation tools (e.g., UiPath) to perform sales forecasts and cost calculations, and automatically generate estimates.

[0586] Input: Summary data generated in step 4

[0587] Output: Automatically generated trial data

[0588] Specific operation: Launch an RPA tool such as UiPath, perform sales forecasts and cost calculations using code such as "RPA_tool.calculate_sales_forecast(pattern data)", and save the results.

[0589] Step 6:

[0590] Viewing Data

[0591] Terminal: The user uses the terminal to request estimated data from the server and displays the received estimated data.

[0592] Input: Data request from user

[0593] Output: Estimated data displayed on the terminal

[0594] Specific operation: Sends an HTTP request, receives and processes the JSON response from the server, and retrieves the data using code such as "fetch('server URL / estimated data').then(response => response.json())" and displays it in HTML or JavaScript.

[0595] Step 7:

[0596] Cloud Storage

[0597] Server: The generated estimate data is saved in a cloud environment (e.g., AWS S3). After saving, a public URL is generated and notified to the user.

[0598] Input: Estimated data generated in Step 5

[0599] Output: Estimated data stored in the cloud environment and its public URL

[0600] Specific operation: Using the AWS SDK, upload the data as follows: "s3_client.upload_file('estimated_data.json', 'mybucket', 'estimated_data.json')" and generate a public URL.

[0601] Step 8:

[0602] Access Control

[0603] Server: Sets access permissions for the estimation data stored in the cloud environment and notifies specific users.

[0604] Input: Estimation data stored in the cloud environment

[0605] Output: Access permissions set and notified users

[0606] Specific operation: Create an IAM policy, set permissions for each user as follows: "IAM_policy = create_policy('Access permission', users=['UserA', 'SC_member'])", and send a notification email.

[0607] In this way, by clarifying the specific operations at each processing step and their inputs and outputs, the system enables efficient data collection, classification, analysis, automatic calculation generation, display, storage, and access management.

[0608] (Application example 1)

[0609] 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."

[0610] Traditional sales forecasting and inventory management in brick-and-mortar stores relied on manual analysis and predictions, resulting in inefficiency and low accuracy. Furthermore, analyzing large amounts of data to timely replenish inventory and forecast sales placed a heavy burden on human resources. Furthermore, a lack of real-time data sharing and access control sometimes led to delays in management decisions. This resulted in inventory shortages and surpluses, lost sales opportunities, and reduced overall store operational efficiency.

[0611] 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.

[0612] In this invention, the server includes means for collecting data, means for classifying the collected data by product category, means for analyzing common patterns from the classified data and generating summary data, means for automatically generating trial calculations based on the analysis results, means for displaying the automatically generated trial calculation data on a terminal, means for storing the generated trial calculation data on the cloud and controlling access to it, means for collecting sales data and inventory data from physical stores from POS systems, means for analyzing purchasing patterns based on the collected data using a machine learning algorithm and generating summary data, means for automatically generating sales forecasts and inventory replenishment plans based on the analysis results, and means for displaying the generated sales forecast and inventory replenishment plan data on a terminal in real time, thereby enabling efficient and highly accurate sales forecasts and inventory management.

[0613] "Means of collecting data" refers to systems or devices for collecting necessary information from outside, such as POS systems and sensors.

[0614] A "categorization method" refers to an algorithm or software that organizes and classifies collected data into specific categories.

[0615] "Means for analyzing common patterns and generating summary data" refers to techniques that use statistical or machine learning techniques to extract specific patterns or trends from collected data and generate summarized information based on them.

[0616] "Means for generating automated estimates" refers to programs or algorithms for automatically calculating sales forecasts, inventory replenishment plans, etc. based on the analysis results.

[0617] "Means for displaying on the terminal" refers to the display or screen display technology that allows users to view and manipulate the results of calculations and analyses.

[0618] "Means for storing data on the cloud and controlling access" refers to a technology for storing generated data on a remote server via the Internet and managing access rights to that data.

[0619] "Means for collecting sales and inventory data from POS systems" refers to programs or interfaces for periodically obtaining sales records and inventory information from physical store POS systems.

[0620] "Means of analyzing purchasing patterns using machine learning algorithms" refers to a technology that utilizes AI technology to analyze patterns of customer purchasing behavior and sales trends.

[0621] "Means for automatically generating sales forecasts and inventory replenishment plans" refers to an algorithm that automatically calculates future sales and required inventory levels based on the analysis results, and generates an appropriate replenishment plan.

[0622] "Means for displaying on the terminal in real time" refers to real-time display technology that allows users to instantly view the results of calculations and analyses.

[0623] This invention is a system for improving the efficiency of sales forecasting and inventory management in physical stores, and includes the following elements.

[0624] System Configuration and Hardware

[0625] 1. POS system: Hardware for collecting sales and inventory data from physical stores.

[0626] 2. Server: A computer system for data collection, classification, pattern analysis, estimate generation, cloud storage, and access control.

[0627] 3. Terminal: A device such as a smartphone or tablet that allows users to check and modify the estimated data.

[0628] Software and Algorithms

[0629] 1. Data collection program (Python): Obtains sales and inventory data from the POS system in JSON format and sends it to the server.

[0630] 2. Data classification algorithm: Divide the collected data into product categories.

[0631] 3. Machine learning algorithms (scikit-learn, pandas): Analyze purchasing patterns and generate summary data.

[0632] 4. RPA tool (UiPath): Automatically generates sales forecasts and inventory replenishment plans based on analysis results.

[0633] 5. Cloud storage (AWS S3) and access control tools (AWS IAM): Store generated data in the cloud and set access permissions.

[0634] 6. Smartphone app (React Native): Displays summary data and estimates in real time and allows users to make corrections.

[0635] Data processing and calculation

[0636] server

[0637] Receives data sent from the POS system and classifies it by product category.

[0638] Machine learning algorithms are used to analyze data and extract common purchasing patterns.

[0639] Sales forecasts and inventory replenishment plans are automatically generated based on the extracted patterns.

[0640] Terminal

[0641] Receives estimated data sent from the server and displays it in real time.

[0642] The user checks and corrects the calculation results and sends the corrections to the server.

[0643] Cloud

[0644] The generated data is stored in the cloud and users can access the data based on the set access permissions.

[0645] Specific examples

[0646] 1. User A (store manager) opens the Store Management Assistant app on his smartphone and requests sales data for the food category for the past month.

[0647] 2. The server retrieves data from the POS system and analyzes it using machine learning algorithms.

[0648] 3. Sales forecasts and inventory replenishment plans are automatically generated and displayed in real time on User A's smartphone.

[0649] 4. User A checks the forecast, corrects some of the inventory quantities, and sends it back to the server.

[0650] 5. The corrected data is saved in the cloud and notified to other administrators.

[0651] Prompt Sentence Examples

[0652] "Analyze purchasing patterns for food categories based on sales data from the past month."

[0653] "Please prepare a sales forecast and inventory replenishment plan for the next month."

[0654] In this way, the system automates complex data analysis and calculations, improving the efficiency and accuracy of sales forecasting and inventory management in physical stores.

[0655] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0656] Step 1:

[0657] Input: Sales and inventory data from the POS system for the past month (JSON format)

[0658] Processing: The server uses a data collection program (Python) to acquire sales and inventory data from the POS system. The acquired data is stored in a database.

[0659] Output: Sales and inventory data stored in a database in JSON format.

[0660] Specific operation: A data request is made from the POS system, and the returned data is stored in the server's database.

[0661] Step 2:

[0662] Input: Sales and inventory data stored in a database

[0663] Processing: The server uses a data classification algorithm to classify sales and inventory data by product category.

[0664] Output: Data categorized by product category

[0665] Specific operation: Use a data frame to classify data based on product ID and category information.

[0666] Step 3:

[0667] Input: Data categorized by product category

[0668] Processing: The server analyzes the classified data using machine learning algorithms (scikit-learn, pandas), extracts purchasing patterns, and generates summary data.

[0669] Output: Summary data including purchasing patterns (JSON format)

[0670] Specific operations: Perform clustering and time series analysis to extract trends and patterns from data and generate summarized data.

[0671] Step 4:

[0672] Input: Summary data including purchasing patterns (JSON format)

[0673] Processing: The server uses an RPA tool (UiPath) to automatically generate sales forecasts and inventory replenishment plans based on the analysis results.

[0674] Output: Sales forecast and inventory replenishment plan data (JSON format)

[0675] Specific operation: Based on the prediction results of the machine learning model, sales forecasts and inventory replenishment schedules are calculated and data is generated.

[0676] Step 5:

[0677] Input: Automatically generated sales forecast and inventory replenishment plan data (JSON format)

[0678] Processing: The server stores the generated estimate data in cloud storage (AWS S3) and sets appropriate permissions using an access control tool (AWS IAM).

[0679] Output: Prediction data stored in the cloud and access permission settings

[0680] Specific behavior: Upload data to cloud storage and assign access permissions to specific users or roles.

[0681] Step 6:

[0682] Input: User request (e.g., sales data for food categories for the past month)

[0683] Processing: The server retrieves the corresponding data from the cloud storage in response to the request and sends it to the requesting terminal.

[0684] Output: Data sent to the terminal

[0685] Specific operation: Receives a user request, retrieves data from the cloud, and sends it to the specified device.

[0686] Step 7:

[0687] Input: Sales forecast and inventory replenishment plan data (JSON format)

[0688] Processing: The terminal displays sales forecast and inventory replenishment planning data in real time, allowing users to make necessary corrections.

[0689] Output: Corrected data

[0690] Specific behavior: Display data in a UI and allow users to change values ​​and conditions through the interface.

[0691] Step 8:

[0692] Input: Corrected data

[0693] Processing: The device sends the data modified by the user back to the server, and the server updates the data stored in the cloud.

[0694] Output: Updated cloud storage data

[0695] Specific behavior: User modifications are sent to the server, data in the cloud storage is updated, and users with appropriate permissions are notified.

[0696] In this way, a system is realized in which servers, terminals, and the cloud work together to perform efficient and highly accurate sales forecasts and inventory management.

[0697] 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.

[0698] The system of this invention collects data, classifies it by product, analyzes common patterns from the data, and generates summary data. It then generates automated estimates based on the analysis results, displays them on the device, stores them in the cloud, and controls access. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is possible to analyze user emotions and adjust the display content and format of the estimate data.

[0699] Program processing

[0700] Data collection and classification

[0701] Server: Obtains approval data for the past month from the business system and stores it in a database. The data is then classified based on product category. Data is stored separately for each category, such as "Mobile" and "Data."

[0702] Pattern analysis and summary data generation

[0703] Server: Based on the classified data, machine learning algorithms are used to analyze patterns. For example, cluster analysis is used to extract common trading patterns. Summary data is generated based on the analysis results and saved in a format such as JSON.

[0704] Generate automatic estimates

[0705] Server: Based on the results of pattern analysis, the server uses robotics process automation (RPA) technology to automatically generate estimates. Specifically, it performs sales forecasts and cost calculations based on the collected pattern information, and automatically generates estimates.

[0706] View and Share

[0707] On the device: The user opens the app, which retrieves and displays the estimated data generated by the server in real time. The user can then make any necessary corrections based on this data.

[0708] Incorporating an emotion engine

[0709] Device: When the user checks the estimated data, the emotion engine recognizes the user's emotions from their facial expressions and voice. The emotion engine uses a machine learning model to analyze the user's emotions (e.g., joy, anger, surprise, etc.).

[0710] Emotion-based display adjustment

[0711] Server: Receives the analysis results of the emotion engine and adjusts the display content and format according to the user's emotions. For example, if the user expresses dissatisfaction, the server may highlight the details of the estimated data.

[0712] Cloud Storage and Access Control

[0713] Server: The generated trial data is stored in cloud storage and made accessible in real time. At the same time, access permissions are set for each data item, allowing specific users (e.g., SC members) to view and edit it.

[0714] Storing and using emotional data

[0715] Server: Analyzed user emotion data is stored on the cloud, and the emotional history is used to optimize the creation and provision of estimated data. For example, it implements functions such as proposing the most suitable data format for a user based on their past emotional history.

[0716] Specific examples

[0717] User A's operation

[0718] User A: Launches the smartphone app and requests the past month's worth of mobile approval data.

[0719] Terminal: The request is sent to the server.

[0720] Server: Searches for data in the mobile category and sends it to User A's device.

[0721] Data analysis and calculation generation

[0722] Server: Analyzes the transmitted data using a machine learning algorithm and extracts the top 10 patterns. Furthermore, automatically generates a trial calculation based on these patterns and sends it to User A's device.

[0723] User A checks and corrects

[0724] User A: When checking the estimated data, the emotion engine analyzes User A's facial expressions to determine their emotions. If User A expresses surprise, the display content is adjusted to address the reason for the surprise. For example, a detailed explanation may be added.

[0725] User A: Makes the necessary corrections, sends the corrected version back to the server, and saves it in cloud storage.

[0726] Data sharing

[0727] Server: The revised estimate data is saved in the cloud and notified to all SC members. SC members can check the revisions on their own devices and make additional revisions or comments as necessary.

[0728] In this way, the present invention streamlines the entire process of creating estimates and significantly reduces the workload. Furthermore, the introduction of an emotion engine enables flexible responses based on the user's emotions, contributing to an improved business environment.

[0729] The processing flow will be explained below.

[0730] Step 1:

[0731] Server: Obtains approval data for the past month from the business system. The obtained data is stored in a specific database.

[0732] Step 2:

[0733] Server: Classifies the stored data based on "product category." Data is stored separately for each category, such as "mobile" and "data."

[0734] Step 3:

[0735] Device: A user launches the app and requests data for a specific product category (e.g., mobile). The device uses the API to send the data request to the server.

[0736] Step 4:

[0737] Server: In response to the request, the server filters specific product data and returns it to the terminal. The returned data is numerical data categorized based on product category.

[0738] Step 5:

[0739] Server: Based on the received data, machine learning algorithms are used to analyze patterns, specifically cluster analysis, to extract common trading patterns.

[0740] Step 6:

[0741] Server: Generates summary data based on the analysis results. The summary data is saved in a format such as JSON and includes the top 10 patterns for each product.

[0742] Step 7:

[0743] Server: Automatically generates estimates based on pattern analysis, including sales forecasts and cost calculations, using robotic process automation (RPA) technology.

[0744] Step 8:

[0745] Server: The generated estimation data is stored in a database and cloud storage. The stored data can be accessed in real time.

[0746] Step 9:

[0747] Device: The user checks the estimated data generated through the app. The estimated data displayed on the screen can be corrected or supplemented as needed.

[0748] Step 10:

[0749] User: Checks the estimated data and corrects any necessary parts. The corrected data is sent back to the server and saved in cloud storage.

[0750] Step 11:

[0751] Server: The emotion engine recognizes and analyzes the user's emotions from their facial expressions and voice. Based on the analysis results, the user's emotional state is determined.

[0752] Step 12:

[0753] Server: Based on the analyzed emotion data, adjust the content and format of the displayed estimated data. For example, if the user expresses dissatisfaction or confusion, display additional explanations.

[0754] Step 13:

[0755] Server: Stores emotion data on the cloud and manages the user's emotion history. Based on past emotion data, the algorithm that optimizes the estimation process is updated.

[0756] Step 14:

[0757] Server: Sets access permissions for the estimation data and emotion data and notifies specific SC members. Apply access control to SC members.

[0758] Step 15:

[0759] SC members (users): Receive notifications and access the estimated data and sentiment analysis data in the cloud. After making any necessary corrections or comments, they save the data as the final version.

[0760] Example 2

[0761] 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."

[0762] Existing data analysis systems collect and classify data, but often do not display or adjust the data appropriately, taking user emotions into account. Furthermore, there are issues with insufficient sharing of analysis results and access control, making it difficult for specific users to quickly obtain or modify the data they need. Furthermore, there is a lack of mechanisms for effectively utilizing user emotion data.

[0763] 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 collecting data, means for classifying the collected data by product, means for analyzing common patterns from the classified data and generating summary data, means for generating automatic trial calculations based on the analysis results, means for displaying the automatically generated trial calculation data on a terminal, means for storing the generated trial calculation data on the cloud and performing access control, means for recognizing user emotions and adjusting the display content and format of the trial calculation data, and means for analyzing user emotion data and storing it on the cloud. This enables seamless processing from data analysis to trial calculation generation and display adjustment according to the user's emotions. In addition, sharing and access control of generated data are strengthened, allowing specific users to quickly obtain and modify the data they need.

[0764] "Means for collecting data" refers to a device or program that has the function of acquiring and storing necessary data from business systems and external data sources.

[0765] "Means for classifying by product" refers to a device or program that provides the function of classifying and organizing acquired data based on specific criteria (e.g., product category, industry, etc.).

[0766] "Means for analyzing patterns and generating summary data" refers to a device or program that has the function of analyzing common trading patterns based on classified data using machine learning algorithms and statistical methods, and summarizing the results to create summary data.

[0767] The "means for generating automatic estimates" refers to a device or program that automatically performs sales forecasts, cost calculations, etc. based on the analysis results and generates estimate results.

[0768] The "means for displaying trial calculation data on a terminal" refers to a device or program having the function of transmitting the generated trial calculation data to a user's terminal in real time and displaying it.

[0769] "Means for storing the generated trial data on the cloud and controlling access" refers to a device or program that stores the generated trial data in cloud storage and has the function of setting and managing access rights for specific users.

[0770] "Means for recognizing the user's emotions and adjusting the display content and format of the trial calculation data" refers to a device or program that analyzes the user's emotions from their facial expressions, voice, etc., and adaptively changes the display content and format of the trial calculation data based on the results.

[0771] The "means for analyzing user emotion data and storing it in the cloud" refers to a device or program that has the function of storing the analyzed user emotion data in a cloud environment and using it for future data analysis and display adjustment.

[0772] The system of the present invention collects data, classifies it by product type, analyzes the data for common patterns, and generates summary data. It then generates automated estimates based on the analysis results, displays them on the device, stores them in the cloud, and controls access. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is possible to analyze user emotions and adjust the display content and format of the estimate data.

[0773] Data collection

[0774] Server: Obtain approval data for the past month from the business system. This is done by using the business system's API to collect the data. The collected data is stored in a database. Examples of databases that can be used include MySQL and PostgreSQL.

[0775] Data Classification

[0776] Server: Collected data is classified based on product category. For example, data is divided into categories such as "mobile" and "data," and each category is tagged and saved.

[0777] Pattern Analysis

[0778] Server: Using Python's SciKit-Learn library, machine learning algorithms are used to analyze patterns based on the classified data, for example, using cluster analysis to extract common trading patterns.

[0779] Summary Data Generation

[0780] Server: Generates summary data based on the analysis results. The generated summary data is saved in JSON format and stored in a separate table in the database.

[0781] Generate automatic estimates

[0782] Server: Use an RPA tool (e.g., Blue Prism) to generate automatic estimates based on the summary data. Specifically, run a sales forecast model based on the pattern information, automatically input the estimate results into an Excel template, and generate a report.

[0783] Display of estimated data

[0784] Device: The user launches the app on their smartphone and requests estimated data. The requested data is sent to the server, which returns the estimated data to the device. The user can then check the estimated data in real time on the app.

[0785] Emotion Engine Analysis

[0786] Device: The device uses a built-in camera and microphone to analyze the user's emotions in real time. It uses Google Cloud's emotion recognition API to identify emotions from the user's facial expressions and voice.

[0787] Emotion-based display adjustment

[0788] Server: Based on the results of the emotion engine's analysis, the server adjusts the display content and format of the estimated data. For example, if surprise is detected, the server automatically adds a detailed explanation of the estimated data.

[0789] Cloud Storage and Access Control

[0790] Server: The generated and modified estimation data is stored in a cloud storage service such as AWS S3, and replicated to multiple regions to facilitate data backup and recovery after storage. IAM user policies are used to set access permissions for data stored in the cloud, allowing specific users (e.g., SC members) to view and modify the data.

[0791] Storing and using emotional data

[0792] Server: Analyzed emotion data is stored in a cloud environment and managed as user emotion history data. The emotion history is used to propose the optimal format and display method for the next and subsequent trial calculation data creation.

[0793] Specific examples

[0794] Example prompt: "Request mobile payment data for the past month."

[0795] User A launches the app on their smartphone and requests mobile payment data for the past month.

[0796] A request is sent to the server, data in the mobile category is searched and sent to User A's device.

[0797] The transmitted data is analyzed using a machine learning algorithm to extract the top 10 patterns. Furthermore, Blue Prism automatically generates estimates, and the results are sent to User A's device.

[0798] When User A checks the estimated data, the emotion engine analyzes their emotions from their facial expressions and voice, and adjusts the displayed estimated data as necessary.

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

[0800] Step 1: Data collection

[0801] Server: Obtain approval data for the past month from the business system via API. The API endpoint and authentication information of the business system are required as input. The data obtained from the API is saved in a database (e.g., MySQL). The output is the approval data saved in the database.

[0802] Specifically, a scheduled job is executed at a fixed time every day to collect new data from the business system.

[0803] Step 2: Data Classification

[0804] Server: Classifies the payment data stored in the database by product category. The original payment data stored in the database is required as input. Using SQL queries, the data is classified and tagged into categories such as "mobile" and "data." The output is the classified and tagged data.

[0805] Specific operations include filtering and tagging based on product categories.

[0806] Step 3: Pattern analysis

[0807] Server: Uses Python's SciKit-Learn library to analyze the classified data using machine learning algorithms to find patterns. The tagged data is required as input. Cluster analysis is performed to extract common trading patterns. The output is the pattern data as the analysis results.

[0808] Specifically, cluster analysis is performed, and representative transaction patterns for each cluster are extracted and saved.

[0809] Step 4: Summary data generation

[0810] Server: Generates summary data from the analyzed pattern data. Pattern data is required as input. Transaction summaries for each pattern are compiled and summary data is generated in JSON format. The output is the generated summary data.

[0811] Specifically, the data is aggregated, an overview of each pattern is summarized, and the results are saved in a JSON format file.

[0812] Step 5: Generate an automatic estimate

[0813] Server: Uses an RPA tool (e.g. Blue Prism) to generate automated estimates based on summary data. Requires summary data as input. Runs a sales forecasting model and automatically populates an Excel template with estimate results. Output is the generated estimate report.

[0814] Specifically, the predictive model is executed and the results are automatically reflected in the Excel template.

[0815] Step 6: View the estimated data

[0816] Terminal: The user launches the smartphone app and requests estimated data. The user's request (e.g., the past month's worth of mobile data) is required as input. The server responds to the request and returns the estimated data to the terminal. The output is the estimated data displayed on the user's terminal.

[0817] Specifically, data is retrieved from the server via an HTTP request and displayed in the app.

[0818] Step 7: Emotion Engine Analysis

[0819] Device: Analyzes user emotions in real time using the built-in camera and microphone. User facial expressions and voice are required as input. Google Cloud's emotion recognition API is used to analyze user emotions. The output is recognized emotion data.

[0820] Specifically, the process involves capturing facial expressions and voice, sending them to an API, and analyzing emotions.

[0821] Step 8: Emotion-Based Display Adjustment

[0822] Server: Adjusts the display content and format of the estimated data based on the analysis results of the emotion engine. It requires recognized emotion data as input. For example, if surprise emotion is detected, it highlights the details of the estimated data. The output is the adjusted display of the estimated data.

[0823] As a specific operation, a customization process for the display content is executed, and the adjustment results are sent to the terminal.

[0824] Step 9: Save your data to the cloud

[0825] Server: Stores generated and modified estimate data in cloud storage (e.g., AWS S3). Requires generated or modified estimate data as input. Data is stored in cloud storage and replicated across multiple regions. Output is estimate data stored in the cloud.

[0826] Specifically, data is stored and backed up on the cloud.

[0827] Step 10: Access Control

[0828] Server: Sets access permissions for data stored in cloud storage. Access permission information and target data are required as input. IAM user policies are used to set permissions so that specific users can access the data. The output is the set access permissions.

[0829] Specific operations include setting access control lists (ACLs) and policies.

[0830] Step 11: Storing and Using Emotional Data

[0831] Server: Analyzed emotion data is stored in the cloud and managed as emotion history data. Analyzed emotion data is required as input. Based on the emotion history, the optimal format and display method are proposed for the next and subsequent trial calculation data creation. The output is the stored emotion history data.

[0832] Specifically, emotion data is saved and historical data is analyzed to help provide future data.

[0833] (Application example 2)

[0834] 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."

[0835] Conventional systems were able to efficiently collect and classify data and generate automatic estimates, but they had problems with a fixed user interface and lacked the flexibility to respond based on user emotions. Furthermore, there was no way to adjust the display format of the generated estimate data based on the user's emotions, resulting in a limited user experience. Therefore, there is a need for a system that optimizes data management and display and provides dynamic responses based on the user's emotions.

[0836] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data, means for classifying the collected data by product type, means for analyzing common patterns from the classified data and generating summary data, means for automatically generating trial calculations based on the analysis results, means for displaying the automatically generated trial calculation data on a terminal, means for storing the generated trial calculation data on the cloud and controlling access to it, means for analyzing the user's emotions using emotion recognition means, and means for adjusting the display content and format of the trial calculation data based on the user's emotions. This makes it possible to adjust the display content according to the user's emotions, thereby providing a more flexible and optimized data management system.

[0837] "Means of collecting data" refers to the function of automatically acquiring past transaction data and business data and storing it in the system.

[0838] "Means for classifying by product" is a function that divides collected data into categories and classifies them into specific product groups.

[0839] "Means for analyzing patterns and generating summary data" refers to a function that uses machine learning algorithms to extract common patterns from collected and classified data, summarizes them, and generates summary data.

[0840] The "means for generating automatic estimates" is a function that performs sales forecasts and cost calculations based on the analyzed pattern data, and automatically generates estimates.

[0841] "Means for displaying on a terminal" is a function for displaying the generated trial calculation data on the user's terminal in real time.

[0842] "Means for storing data on the cloud and controlling access" refers to a function for storing the generated estimate data in cloud storage and setting access rights for specific users.

[0843] The "emotion recognition means" is a function that recognizes and analyzes the user's emotions from facial expressions and voice data.

[0844] The "means for adjusting the display content and format" is a function for dynamically adjusting the display format and content of the trial calculation data according to the recognized user's emotions.

[0845] The present invention relates to a smart logistics management system in a logistics center. Next, an embodiment of the present invention will be described in detail.

[0846] System Configuration

[0847] Program processing

[0848] Data collection and classification

[0849] The server retrieves the past month's worth of transaction data from the logistics center's business system and stores it in a database. The data is then classified by product and managed by category, such as "mobile devices" or "consumables."

[0850] Pattern analysis and summary data generation

[0851] The server uses machine learning algorithms to analyze patterns based on the classified data. For example, it uses cluster analysis to extract common transaction patterns at the distribution center. It then generates summary data based on the analysis results and saves them in a format such as JSON.

[0852] Generate automatic estimates

[0853] Based on the analysis results, the server uses robotics process automation (RPA) technology to forecast sales and optimize inventory, automatically generating trial data.

[0854] View and Share

[0855] The device (smart glasses or robot) receives and displays the estimated data generated by the server in real time according to the user's instructions. The user can then work based on this data and make any necessary corrections.

[0856] Incorporating an emotion engine

[0857] When the user checks the estimated data on the device, the emotion engine installed in the smart glasses or robot recognizes the user's emotions from their facial expressions and voice.

[0858] Emotion-based display adjustment

[0859] The server receives the analysis results from the emotion engine and dynamically adjusts the display content and format of the trial calculation data in accordance with the user's emotions.

[0860] Cloud Storage and Access Control

[0861] The generated estimate data is stored in cloud storage, and access control is performed in real time, allowing only specific users to access and modify the data.

[0862] Storing and using emotional data

[0863] The server stores the user's emotion data in the cloud, analyzes past emotion history, and optimizes the creation and provision of trial data, thereby proposing the most suitable display format for the user.

[0864] Specific examples

[0865] User B's operation

[0866] User B puts on the smart glasses and launches the inventory management app. He makes a request to check inventory data for the past month, and the device sends this request to the server. The server retrieves the inventory data and sends it to User B's device.

[0867] Data analysis and calculation generation

[0868] The server analyzes the received data using a machine learning algorithm and extracts the top 10 patterns of data. It then automatically generates a trial calculation based on these patterns and sends it to User B's device.

[0869] User B checks and corrects

[0870] When User B checks the estimated data, the emotion engine analyzes User B's facial expressions to determine their emotions. If User B expresses dissatisfaction, the displayed content is adjusted to address the reason for dissatisfaction. For example, a detailed explanation may be added. After making any necessary corrections, the revised version is sent back to the server and saved in cloud storage.

[0871] Data sharing

[0872] The server saves the revised estimate data in the cloud and notifies specific users (e.g., logistics center managers). The managers can check the revisions on their own devices and make additional revisions or comments as necessary.

[0873] Prompt Sentence Examples

[0874] "Write a Python program that collects inventory data from the past month, analyzes it for the most common patterns, and displays the results as a summary. Also, add the ability to adjust the display based on user sentiment."

[0875] This invention aims to improve data management and work efficiency in logistics centers, and enables flexible responses based on user emotions.

[0876] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0877] Step 1: Data collection

[0878] The server retrieves the past month's worth of transaction data from the logistics center's business system via API. The input is the business system's API endpoint and authentication token, and the output is JSON-formatted transaction data. Specifically, it makes an API request, parses the JSON data returned as a response, and saves it in the database.

[0879] Step 2: Data Classification

[0880] The server categorizes the collected data by product. The input is transaction data stored in a database, and the output is a dataset categorized by product. Specifically, the data is filtered based on product category information, and each category is saved as a separate dataset.

[0881] Step 3: Pattern analysis and summary data generation

[0882] The server uses a machine learning algorithm to analyze patterns based on the classified data. The input is a data set classified by product type, and the output is summary data based on the pattern analysis. Specifically, it performs cluster analysis, extracts transaction patterns, summarizes each pattern, and saves them as summary data.

[0883] Step 4: Generate an automatic estimate

[0884] The server performs sales forecasting and inventory optimization based on the pattern analysis results, and automatically generates trial calculation data. The input is the pattern analysis results, and the output is automatically generated trial calculation data. Specifically, RPA technology is used to apply sales forecasting algorithms and inventory optimization algorithms, calculate and save the trial calculation results.

[0885] Step 5: View the estimated data

[0886] The terminal (smart glasses or robot) receives and displays the estimated data generated from the server in real time at the user's command. The input is a request for estimated data from the server, and the output is the estimated data displayed on the user's terminal. Specifically, an HTTP request is sent, and the estimated data is received and displayed in real time.

[0887] Step 6: Emotion recognition and display adjustment

[0888] When the user checks the estimated data on the device, the emotion engine installed in the smart glasses or robot recognizes the emotion from the user's facial expression and voice. The input is the user's facial expression data and voice data, and the output is analyzed emotion data. Specifically, the user's facial expression and voice are captured using a camera or microphone, and then analyzed using an emotion recognition algorithm.

[0889] Step 7: Adjust content based on emotions

[0890] The server receives the analysis results from the emotion engine and dynamically adjusts the display content and format of the trial calculation data according to the user's emotions. The inputs are emotion data and trial calculation data, and the output is the adjusted display of the trial calculation data. Specifically, if the user expresses dissatisfaction, the server makes adjustments such as displaying additional detailed explanations.

[0891] Step 8: Cloud Storage and Access Control

[0892] The server stores the generated trial calculation data and emotion data in cloud storage and performs access control in real time. The inputs are the trial calculation data and emotion data, and the output is the data stored on the cloud and the access permissions that are set. Specifically, the data is uploaded using a cloud API and access permissions are set for specific users.

[0893] Step 9: Storing and optimizing emotional data

[0894] The server stores the user's emotional data in the cloud, analyzes past emotional history, and optimizes the creation and provision of trial data. The inputs are emotional data and past emotional history, and the output is optimized trial data. Specifically, it uses an analytical algorithm to analyze past emotional data and propose future display content.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] [Third embodiment]

[0899] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0900] 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.

[0901] 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).

[0902] 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.

[0903] 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.

[0904] 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).

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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."

[0911] The system of this invention collects data, classifies it by product, analyzes the data for common patterns, generates summary data, and automatically generates estimates based on the analysis results, displays them on a terminal, stores them in the cloud, and controls access.

[0912] Program processing

[0913] Data collection and classification

[0914] Server: Obtains approval data for the past month from the business system. This data is stored in a specific database. The data is then classified based on product category. Data is separated into categories such as "mobile" and "data."

[0915] Pattern analysis and summary data generation

[0916] Server: Based on the classified data, machine learning algorithms are used to analyze patterns. For example, cluster analysis of historical data is performed to identify common trading patterns. Summary data is generated based on the analysis results and saved in an appropriate format such as JSON.

[0917] Generate automatic estimates

[0918] Server: Based on the results of pattern analysis, the server uses robotics process automation (RPA) technology to automatically generate estimates. Specifically, it performs sales forecasts and cost calculations based on the collected pattern information. This reduces the effort required for manual calculations.

[0919] View and Share

[0920] On the device: The user opens the app, which retrieves and displays the estimated data generated by the server in real time. The user can then make any necessary corrections based on this data.

[0921] Cloud Storage and Access Control

[0922] Server: The generated trial data is stored in cloud storage and made accessible in real time. At the same time, access permissions are set for each data item, allowing specific users (e.g., SC members) to view and edit it.

[0923] Specific examples

[0924] User A's operation

[0925] User A: Launches the smartphone app and requests the past month's worth of mobile approval data.

[0926] Terminal: The request is sent to the server.

[0927] Server: Searches for data in the mobile category and sends it to User A's device.

[0928] Data analysis and calculation generation

[0929] Server: Analyzes the transmitted data using a machine learning algorithm and extracts the top 10 patterns. Furthermore, automatically generates a trial calculation based on these patterns and sends it to User A's device.

[0930] User A checks and corrects

[0931] User A: Checks the estimated data and corrects some of the figures. The corrected data is sent back to the server and saved in cloud storage.

[0932] Data sharing

[0933] Server: The revised estimate data is saved in the cloud and notified to all SC members. SC members can check the revisions on their own devices and make additional revisions or comments as necessary.

[0934] In this way, the present invention streamlines the entire process of creating estimates and significantly reduces the workload. Estimates can be performed quickly regardless of location, which also contributes to improving the business environment.

[0935] The processing flow will be explained below.

[0936] Step 1:

[0937] Server: Obtains approval data for the past month from the business system. The obtained data is stored in a specific database.

[0938] Step 2:

[0939] Server: Classifies the stored data based on "product category." Data is stored separately for each category, such as "mobile" and "data."

[0940] Step 3:

[0941] Device: A user launches the app and requests data for a specific product category (e.g., mobile). The device uses the API to send the data request to the server.

[0942] Step 4:

[0943] Server: In response to the request, the server filters specific product data and returns it to the terminal. The returned data is numerical data categorized based on product category.

[0944] Step 5:

[0945] Server: Based on the received data, machine learning algorithms are used to analyze patterns, specifically cluster analysis, to extract common trading patterns.

[0946] Step 6:

[0947] Server: Generates summary data based on the analysis results. The summary data is saved in a format such as JSON and includes the top 10 patterns for each product.

[0948] Step 7:

[0949] Server: Automatically generates estimates based on pattern analysis, including sales forecasts and cost calculations, using robotic process automation (RPA) technology.

[0950] Step 8:

[0951] Server: The generated estimation data is stored in a database and cloud storage. The stored data can be accessed in real time.

[0952] Step 9:

[0953] Device: The user checks the estimated data generated through the app. The estimated data displayed on the screen can be corrected or supplemented as needed.

[0954] Step 10:

[0955] User: Checks the estimated data and corrects any necessary parts. The corrected data is sent back to the server and saved in cloud storage.

[0956] Step 11:

[0957] Server: Saves the final estimation data in the cloud and sets access permissions. Sends notifications to specific SC members to grant access.

[0958] Step 12:

[0959] SC members (users): Receive notifications and access the estimated data on the cloud. After making any necessary corrections or comments, they save it as the final version.

[0960] Example 1

[0961] 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."

[0962] Currently, many companies and organizations handle large amounts of data, but it is difficult to efficiently collect and analyze that data, quickly perform calculations, and provide users with the necessary information. In particular, there is a demand for a system that can centrally perform data classification, pattern analysis, automatic calculation generation, display, storage, and access management. The object of this invention is to provide a system that solves these problems.

[0963] 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.

[0964] In this invention, the server includes means for collecting information from business systems, means for classifying the collected information by product group, means for analyzing recurring patterns in the classified information and generating summary information, means for generating automatic calculations based on the analysis results, means for displaying the automatically generated calculation information on a terminal, means for storing the generated calculation information in a cloud environment and managing access, means for analyzing information using a machine learning algorithm and extracting common patterns, and means for automatically generating sales forecasts and cost calculations using robotics process automation technology. This enables efficient collection, classification, and analysis of data, as well as rapid generation of estimates, sharing, and management.

[0965] "Business system" is a general term for software and hardware used on a daily basis by companies and organizations for management, operation, and monitoring.

[0966] "Information" refers to all data collected, categorized, analyzed, and generated, including, in particular, decision-making data relating to commercial products.

[0967] A "product group" refers to a collection of products that belong to the same or similar category, including products with specific attributes such as "mobile" or "data."

[0968] "Classification" refers to the process of separating collected information into different categories based on specific criteria (e.g., product groups).

[0969] A "pattern" refers to a common trend or recurring phenomenon found in collected and classified information.

[0970] "Analytics" refers to the methods and techniques used to extract meaningful patterns and trends from collected and classified information.

[0971] "Summary information" refers to data that succinctly summarizes the results of analyzed patterns and provides actionable insights.

[0972] "Automatic calculation" refers to calculation processing that is automatically performed by a computer program based on the analysis results, and includes the generation of trial calculations.

[0973] A "terminal" is a device operated by a user, and refers to a computer such as a smartphone, tablet, or PC.

[0974] "Cloud environment" refers to a virtualized infrastructure for data storage and computing services delivered over the Internet.

[0975] "Access management" refers to the ability to set and control access rights to data and systems.

[0976] A "machine learning algorithm" is one of the algorithms used in data analysis, and is a technology for extracting patterns and trends from large amounts of data.

[0977] "Robotics process automation technology" refers to technology for automating routine business processes, and in this case specifically refers to the automation of sales forecasts and cost calculations.

[0978] The system of the present invention collects information from business systems, classifies it by product group, analyzes patterns using machine learning algorithms, generates summary information, generates automatic calculations using robotics process automation technology, displays the results on a terminal, stores them in a cloud environment, and manages access.

[0979] Specifically, the following hardware and software are used:

[0980] 1. Server

[0981] The server collects information from the business system, for example, by retrieving data via API and storing it in a database such as PostgreSQL.

[0982] The server categorizes the collected information into product groups using SQL queries based on the product attributes.

[0983] The server uses machine learning algorithms (e.g., Scikit-learn) to analyze patterns in the classified information and extract common patterns, using cluster analysis or other applicable analytical techniques.

[0984] The server generates summary information based on the analysis results and saves it in JSON format using the Python json library.

[0985] The server uses a robotics process automation tool (e.g., UiPath) to perform sales forecasting and cost calculations and generate automated calculations.

[0986] The server uploads the generated calculation information to a cloud environment (e.g., AWS S3), generates a URL, and notifies the user. AWS SDK is used for saving.

[0987] 2. Terminal

[0988] A user uses a device (smartphone, tablet, PC, etc.) to request information from a server. The request is made using the HTTP protocol.

[0989] Receives the response from the server and displays it on the screen. For example, this is implemented using front-end technologies such as JavaScript or React.

[0990] 3. Users

[0991] The user launches the smartphone app from their device and requests approval data for products from the past month.

[0992] The user checks the received data and corrects the values ​​as necessary. The corrected data is then sent back to the server and stored in the cloud environment.

[0993] For example, you can invoke a generative AI model using a prompt like this:

[0994] This system retrieves the past month's worth of approval data from a specific business system, classifies it by product group, and then performs pattern analysis using a machine learning algorithm. Based on the analysis results, it automatically generates trial calculations and displays them on the user's device. The final trial calculation data is stored in the cloud and managed with access control for specific users. Please explain in detail how the program in this system processes data.

[0995] This invention enables efficient collection and classification of data, analysis and rapid generation of estimates, as well as the sharing and management of this information in a unified manner, thereby improving work efficiency and accuracy.

[0996] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0997] Step 1:

[0998] Data collection

[0999] Server: Obtains approval data for the past month from the business system's API. Specifically, it sends an API request and receives the response data in JSON format.

[1000] Input: API request to business system

[1001] Output: Acquired approval data in JSON format

[1002] Specific operation: Use the curl command or the requests library to retrieve data via "https: / / api.example.com / getData" and insert the received JSON data into the database (PostgreSQL).

[1003] Step 2:

[1004] Data Classification

[1005] Server: Classify the acquired data based on product category (e.g., "Mobile" or "Data").

[1006] Input: Approval data obtained in Step 1

[1007] Output: Data categorized by product category

[1008] Specific operation: Issues an SQL query, categorizes the data using a command such as "SELECT FROM Approval Data WHERE Category = 'Mobile'", and inserts each category into a separate table.

[1009] Step 3:

[1010] Pattern Analysis

[1011] Server: Uses machine learning algorithms (e.g., Scikit-learn) to analyze frequent patterns from the classified data.

[1012] Input: Product data classified in Step 2

[1013] Output: Pattern data obtained by analysis

[1014] What it does: Use code like "from sklearn.cluster import KMeans" to apply cluster analysis to classified data to identify frequent patterns. The results of this analysis are temporarily saved.

[1015] Step 4:

[1016] Summary Data Generation

[1017] Server: Generates summary data based on the analysis results. The generated summary data is saved in JSON format.

[1018] Input: Pattern data analyzed in step 3

[1019] Output: Summary data in JSON format

[1020] Specific operation: Based on the acquired pattern data, summary data is generated using Python's JSON library as "summary_data = json.dumps(analysis results)" and saved in the database.

[1021] Step 5:

[1022] Automatic calculation generation

[1023] Server: Uses robotics process automation tools (e.g., UiPath) to perform sales forecasts and cost calculations, and automatically generate estimates.

[1024] Input: Summary data generated in step 4

[1025] Output: Automatically generated trial data

[1026] Specific operation: Launch an RPA tool such as UiPath, perform sales forecasts and cost calculations using code such as "RPA_tool.calculate_sales_forecast(pattern data)", and save the results.

[1027] Step 6:

[1028] Viewing Data

[1029] Terminal: The user uses the terminal to request estimated data from the server and displays the received estimated data.

[1030] Input: Data request from user

[1031] Output: Estimated data displayed on the terminal

[1032] Specific operation: Sends an HTTP request, receives and processes the JSON response from the server, and retrieves the data using code such as "fetch('server URL / estimated data').then(response => response.json())" and displays it in HTML or JavaScript.

[1033] Step 7:

[1034] Cloud Storage

[1035] Server: The generated estimate data is saved in a cloud environment (e.g., AWS S3). After saving, a public URL is generated and notified to the user.

[1036] Input: Estimated data generated in Step 5

[1037] Output: Estimated data stored in the cloud environment and its public URL

[1038] Specific operation: Using the AWS SDK, upload the data as follows: "s3_client.upload_file('estimated_data.json', 'mybucket', 'estimated_data.json')" and generate a public URL.

[1039] Step 8:

[1040] Access Control

[1041] Server: Sets access permissions for the estimation data stored in the cloud environment and notifies specific users.

[1042] Input: Estimation data stored in the cloud environment

[1043] Output: Access permissions set and notified users

[1044] Specific operation: Create an IAM policy, set permissions for each user as follows: "IAM_policy = create_policy('Access permission', users=['UserA', 'SC_member'])", and send a notification email.

[1045] In this way, by clarifying the specific operations at each processing step and their inputs and outputs, the system enables efficient data collection, classification, analysis, automatic calculation generation, display, storage, and access management.

[1046] (Application example 1)

[1047] 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."

[1048] Traditional sales forecasting and inventory management in brick-and-mortar stores relied on manual analysis and predictions, resulting in inefficiency and low accuracy. Furthermore, analyzing large amounts of data to timely replenish inventory and forecast sales placed a heavy burden on human resources. Furthermore, a lack of real-time data sharing and access control sometimes led to delays in management decisions. This resulted in inventory shortages and surpluses, lost sales opportunities, and reduced overall store operational efficiency.

[1049] 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.

[1050] In this invention, the server includes means for collecting data, means for classifying the collected data by product category, means for analyzing common patterns from the classified data and generating summary data, means for automatically generating trial calculations based on the analysis results, means for displaying the automatically generated trial calculation data on a terminal, means for storing the generated trial calculation data on the cloud and controlling access to it, means for collecting sales data and inventory data from physical stores from POS systems, means for analyzing purchasing patterns based on the collected data using a machine learning algorithm and generating summary data, means for automatically generating sales forecasts and inventory replenishment plans based on the analysis results, and means for displaying the generated sales forecast and inventory replenishment plan data on a terminal in real time, thereby enabling efficient and highly accurate sales forecasts and inventory management.

[1051] "Means of collecting data" refers to systems or devices for collecting necessary information from outside, such as POS systems and sensors.

[1052] A "categorization method" refers to an algorithm or software that organizes and classifies collected data into specific categories.

[1053] "Means for analyzing common patterns and generating summary data" refers to techniques that use statistical or machine learning techniques to extract specific patterns or trends from collected data and generate summarized information based on them.

[1054] "Means for generating automated estimates" refers to programs or algorithms for automatically calculating sales forecasts, inventory replenishment plans, etc. based on the analysis results.

[1055] "Means for displaying on the terminal" refers to the display or screen display technology that allows users to view and manipulate the results of calculations and analyses.

[1056] "Means for storing data on the cloud and controlling access" refers to a technology for storing generated data on a remote server via the Internet and managing access rights to that data.

[1057] "Means for collecting sales and inventory data from POS systems" refers to programs or interfaces for periodically obtaining sales records and inventory information from physical store POS systems.

[1058] "Means of analyzing purchasing patterns using machine learning algorithms" refers to a technology that utilizes AI technology to analyze patterns of customer purchasing behavior and sales trends.

[1059] "Means for automatically generating sales forecasts and inventory replenishment plans" refers to an algorithm that automatically calculates future sales and required inventory levels based on the analysis results, and generates an appropriate replenishment plan.

[1060] "Means for displaying on the terminal in real time" refers to real-time display technology that allows users to instantly view the results of calculations and analyses.

[1061] This invention is a system for improving the efficiency of sales forecasting and inventory management in physical stores, and includes the following elements.

[1062] System Configuration and Hardware

[1063] 1. POS system: Hardware for collecting sales and inventory data from physical stores.

[1064] 2. Server: A computer system for data collection, classification, pattern analysis, estimate generation, cloud storage, and access control.

[1065] 3. Terminal: A device such as a smartphone or tablet that allows users to check and modify the estimated data.

[1066] Software and Algorithms

[1067] 1. Data collection program (Python): Obtains sales and inventory data from the POS system in JSON format and sends it to the server.

[1068] 2. Data classification algorithm: Divide the collected data into product categories.

[1069] 3. Machine learning algorithms (scikit-learn, pandas): Analyze purchasing patterns and generate summary data.

[1070] 4. RPA tool (UiPath): Automatically generates sales forecasts and inventory replenishment plans based on analysis results.

[1071] 5. Cloud storage (AWS S3) and access control tools (AWS IAM): Store generated data in the cloud and set access permissions.

[1072] 6. Smartphone app (React Native): Displays summary data and estimates in real time and allows users to make corrections.

[1073] Data processing and calculation

[1074] server

[1075] Receives data sent from the POS system and classifies it by product category.

[1076] Machine learning algorithms are used to analyze data and extract common purchasing patterns.

[1077] Sales forecasts and inventory replenishment plans are automatically generated based on the extracted patterns.

[1078] Terminal

[1079] Receives estimated data sent from the server and displays it in real time.

[1080] The user checks and corrects the calculation results and sends the corrections to the server.

[1081] Cloud

[1082] The generated data is stored in the cloud and users can access the data based on the set access permissions.

[1083] Specific examples

[1084] 1. User A (store manager) opens the Store Management Assistant app on his smartphone and requests sales data for the food category for the past month.

[1085] 2. The server retrieves data from the POS system and analyzes it using machine learning algorithms.

[1086] 3. Sales forecasts and inventory replenishment plans are automatically generated and displayed in real time on User A's smartphone.

[1087] 4. User A checks the forecast, corrects some of the inventory quantities, and sends it back to the server.

[1088] 5. The corrected data is saved in the cloud and notified to other administrators.

[1089] Prompt Sentence Examples

[1090] "Analyze purchasing patterns for food categories based on sales data from the past month."

[1091] "Please prepare a sales forecast and inventory replenishment plan for the next month."

[1092] In this way, the system automates complex data analysis and calculations, improving the efficiency and accuracy of sales forecasting and inventory management in physical stores.

[1093] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1094] Step 1:

[1095] Input: Sales and inventory data from the POS system for the past month (JSON format)

[1096] Processing: The server uses a data collection program (Python) to acquire sales and inventory data from the POS system. The acquired data is stored in a database.

[1097] Output: Sales and inventory data stored in a database in JSON format.

[1098] Specific operation: A data request is made from the POS system, and the returned data is stored in the server's database.

[1099] Step 2:

[1100] Input: Sales and inventory data stored in a database

[1101] Processing: The server uses a data classification algorithm to classify sales and inventory data by product category.

[1102] Output: Data categorized by product category

[1103] Specific operation: Use a data frame to classify data based on product ID and category information.

[1104] Step 3:

[1105] Input: Data categorized by product category

[1106] Processing: The server analyzes the classified data using machine learning algorithms (scikit-learn, pandas), extracts purchasing patterns, and generates summary data.

[1107] Output: Summary data including purchasing patterns (JSON format)

[1108] Specific operations: Perform clustering and time series analysis to extract trends and patterns from data and generate summarized data.

[1109] Step 4:

[1110] Input: Summary data including purchasing patterns (JSON format)

[1111] Processing: The server uses an RPA tool (UiPath) to automatically generate sales forecasts and inventory replenishment plans based on the analysis results.

[1112] Output: Sales forecast and inventory replenishment plan data (JSON format)

[1113] Specific operation: Based on the prediction results of the machine learning model, sales forecasts and inventory replenishment schedules are calculated and data is generated.

[1114] Step 5:

[1115] Input: Automatically generated sales forecast and inventory replenishment plan data (JSON format)

[1116] Processing: The server stores the generated estimate data in cloud storage (AWS S3) and sets appropriate permissions using an access control tool (AWS IAM).

[1117] Output: Prediction data stored in the cloud and access permission settings

[1118] Specific behavior: Upload data to cloud storage and assign access permissions to specific users or roles.

[1119] Step 6:

[1120] Input: User request (e.g., sales data for food categories for the past month)

[1121] Processing: The server retrieves the corresponding data from the cloud storage in response to the request and sends it to the requesting terminal.

[1122] Output: Data sent to the terminal

[1123] Specific operation: Receives a user request, retrieves data from the cloud, and sends it to the specified device.

[1124] Step 7:

[1125] Input: Sales forecast and inventory replenishment plan data (JSON format)

[1126] Processing: The terminal displays sales forecast and inventory replenishment planning data in real time, allowing users to make necessary corrections.

[1127] Output: Corrected data

[1128] Specific behavior: Display data in a UI and allow users to change values ​​and conditions through the interface.

[1129] Step 8:

[1130] Input: Corrected data

[1131] Processing: The device sends the data modified by the user back to the server, and the server updates the data stored in the cloud.

[1132] Output: Updated cloud storage data

[1133] Specific behavior: User modifications are sent to the server, data in the cloud storage is updated, and users with appropriate permissions are notified.

[1134] In this way, a system is realized in which servers, terminals, and the cloud work together to perform efficient and highly accurate sales forecasts and inventory management.

[1135] 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.

[1136] The system of this invention collects data, classifies it by product, analyzes common patterns from the data, and generates summary data. It then generates automated estimates based on the analysis results, displays them on the device, stores them in the cloud, and controls access. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is possible to analyze user emotions and adjust the display content and format of the estimate data.

[1137] Program processing

[1138] Data collection and classification

[1139] Server: Obtains approval data for the past month from the business system and stores it in a database. The data is then classified based on product category. Data is stored separately for each category, such as "Mobile" and "Data."

[1140] Pattern analysis and summary data generation

[1141] Server: Based on the classified data, machine learning algorithms are used to analyze patterns. For example, cluster analysis is used to extract common trading patterns. Summary data is generated based on the analysis results and saved in a format such as JSON.

[1142] Generate automatic estimates

[1143] Server: Based on the results of pattern analysis, the server uses robotics process automation (RPA) technology to automatically generate estimates. Specifically, it performs sales forecasts and cost calculations based on the collected pattern information, and automatically generates estimates.

[1144] View and Share

[1145] On the device: The user opens the app, which retrieves and displays the estimated data generated by the server in real time. The user can then make any necessary corrections based on this data.

[1146] Incorporating an emotion engine

[1147] Device: When the user checks the estimated data, the emotion engine recognizes the user's emotions from their facial expressions and voice. The emotion engine uses a machine learning model to analyze the user's emotions (e.g., joy, anger, surprise, etc.).

[1148] Emotion-based display adjustment

[1149] Server: Receives the analysis results of the emotion engine and adjusts the display content and format according to the user's emotions. For example, if the user expresses dissatisfaction, the server may highlight the details of the estimated data.

[1150] Cloud Storage and Access Control

[1151] Server: The generated trial data is stored in cloud storage and made accessible in real time. At the same time, access permissions are set for each data item, allowing specific users (e.g., SC members) to view and edit it.

[1152] Storing and using emotional data

[1153] Server: Analyzed user emotion data is stored on the cloud, and the emotional history is used to optimize the creation and provision of estimated data. For example, it implements functions such as proposing the most suitable data format for a user based on their past emotional history.

[1154] Specific examples

[1155] User A's operation

[1156] User A: Launches the smartphone app and requests the past month's worth of mobile approval data.

[1157] Terminal: The request is sent to the server.

[1158] Server: Searches for data in the mobile category and sends it to User A's device.

[1159] Data analysis and calculation generation

[1160] Server: Analyzes the transmitted data using a machine learning algorithm and extracts the top 10 patterns. Furthermore, automatically generates a trial calculation based on these patterns and sends it to User A's device.

[1161] User A checks and corrects

[1162] User A: When checking the estimated data, the emotion engine analyzes User A's facial expressions to determine their emotions. If User A expresses surprise, the display content is adjusted to address the reason for the surprise. For example, a detailed explanation may be added.

[1163] User A: Makes the necessary corrections, sends the corrected version back to the server, and saves it in cloud storage.

[1164] Data sharing

[1165] Server: The revised estimate data is saved in the cloud and notified to all SC members. SC members can check the revisions on their own devices and make additional revisions or comments as necessary.

[1166] In this way, the present invention streamlines the entire process of creating estimates and significantly reduces the workload. Furthermore, the introduction of an emotion engine enables flexible responses based on the user's emotions, contributing to an improved business environment.

[1167] The processing flow will be explained below.

[1168] Step 1:

[1169] Server: Obtains approval data for the past month from the business system. The obtained data is stored in a specific database.

[1170] Step 2:

[1171] Server: Classifies the stored data based on "product category." Data is stored separately for each category, such as "mobile" and "data."

[1172] Step 3:

[1173] Device: A user launches the app and requests data for a specific product category (e.g., mobile). The device uses the API to send the data request to the server.

[1174] Step 4:

[1175] Server: In response to the request, the server filters specific product data and returns it to the terminal. The returned data is numerical data categorized based on product category.

[1176] Step 5:

[1177] Server: Based on the received data, machine learning algorithms are used to analyze patterns, specifically cluster analysis, to extract common trading patterns.

[1178] Step 6:

[1179] Server: Generates summary data based on the analysis results. The summary data is saved in a format such as JSON and includes the top 10 patterns for each product.

[1180] Step 7:

[1181] Server: Automatically generates estimates based on pattern analysis, including sales forecasts and cost calculations, using robotic process automation (RPA) technology.

[1182] Step 8:

[1183] Server: The generated estimation data is stored in a database and cloud storage. The stored data can be accessed in real time.

[1184] Step 9:

[1185] Device: The user checks the estimated data generated through the app. The estimated data displayed on the screen can be corrected or supplemented as needed.

[1186] Step 10:

[1187] User: Checks the estimated data and corrects any necessary parts. The corrected data is sent back to the server and saved in cloud storage.

[1188] Step 11:

[1189] Server: The emotion engine recognizes and analyzes the user's emotions from their facial expressions and voice. Based on the analysis results, the user's emotional state is determined.

[1190] Step 12:

[1191] Server: Based on the analyzed emotion data, adjust the content and format of the displayed estimated data. For example, if the user expresses dissatisfaction or confusion, display additional explanations.

[1192] Step 13:

[1193] Server: Stores emotion data on the cloud and manages the user's emotion history. Based on past emotion data, the algorithm that optimizes the estimation process is updated.

[1194] Step 14:

[1195] Server: Sets access permissions for the estimation data and emotion data and notifies specific SC members. Apply access control to SC members.

[1196] Step 15:

[1197] SC members (users): Receive notifications and access the estimated data and sentiment analysis data in the cloud. After making any necessary corrections or comments, they save the data as the final version.

[1198] Example 2

[1199] 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."

[1200] Existing data analysis systems collect and classify data, but often do not display or adjust the data appropriately, taking user emotions into account. Furthermore, there are issues with insufficient sharing of analysis results and access control, making it difficult for specific users to quickly obtain or modify the data they need. Furthermore, there is a lack of mechanisms for effectively utilizing user emotion data.

[1201] 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 collecting data, means for classifying the collected data by product, means for analyzing common patterns from the classified data and generating summary data, means for generating automatic trial calculations based on the analysis results, means for displaying the automatically generated trial calculation data on a terminal, means for storing the generated trial calculation data on the cloud and performing access control, means for recognizing user emotions and adjusting the display content and format of the trial calculation data, and means for analyzing user emotion data and storing it on the cloud. This enables seamless processing from data analysis to trial calculation generation and display adjustment according to the user's emotions. In addition, sharing and access control of generated data are strengthened, allowing specific users to quickly obtain and modify the data they need.

[1202] "Means for collecting data" refers to a device or program that has the function of acquiring and storing necessary data from business systems and external data sources.

[1203] "Means for classifying by product" refers to a device or program that provides the function of classifying and organizing acquired data based on specific criteria (e.g., product category, industry, etc.).

[1204] "Means for analyzing patterns and generating summary data" refers to a device or program that has the function of analyzing common trading patterns based on classified data using machine learning algorithms and statistical methods, and summarizing the results to create summary data.

[1205] The "means for generating automatic estimates" refers to a device or program that automatically performs sales forecasts, cost calculations, etc. based on the analysis results and generates estimate results.

[1206] The "means for displaying trial calculation data on a terminal" refers to a device or program having the function of transmitting the generated trial calculation data to a user's terminal in real time and displaying it.

[1207] "Means for storing the generated trial data on the cloud and controlling access" refers to a device or program that stores the generated trial data in cloud storage and has the function of setting and managing access rights for specific users.

[1208] "Means for recognizing the user's emotions and adjusting the display content and format of the trial calculation data" refers to a device or program that analyzes the user's emotions from their facial expressions, voice, etc., and adaptively changes the display content and format of the trial calculation data based on the results.

[1209] The "means for analyzing user emotion data and storing it in the cloud" refers to a device or program that has the function of storing the analyzed user emotion data in a cloud environment and using it for future data analysis and display adjustment.

[1210] The system of the present invention collects data, classifies it by product type, analyzes the data for common patterns, and generates summary data. It then generates automated estimates based on the analysis results, displays them on the device, stores them in the cloud, and controls access. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is possible to analyze user emotions and adjust the display content and format of the estimate data.

[1211] Data collection

[1212] Server: Obtain approval data for the past month from the business system. This is done by using the business system's API to collect the data. The collected data is stored in a database. Examples of databases that can be used include MySQL and PostgreSQL.

[1213] Data Classification

[1214] Server: Collected data is classified based on product category. For example, data is divided into categories such as "mobile" and "data," and each category is tagged and saved.

[1215] Pattern Analysis

[1216] Server: Using Python's SciKit-Learn library, machine learning algorithms are used to analyze patterns based on the classified data, for example, using cluster analysis to extract common trading patterns.

[1217] Summary Data Generation

[1218] Server: Generates summary data based on the analysis results. The generated summary data is saved in JSON format and stored in a separate table in the database.

[1219] Generate automatic estimates

[1220] Server: Use an RPA tool (e.g., Blue Prism) to generate automatic estimates based on the summary data. Specifically, run a sales forecast model based on the pattern information, automatically input the estimate results into an Excel template, and generate a report.

[1221] Display of estimated data

[1222] Device: The user launches the app on their smartphone and requests estimated data. The requested data is sent to the server, which returns the estimated data to the device. The user can then check the estimated data in real time on the app.

[1223] Emotion Engine Analysis

[1224] Device: The device uses a built-in camera and microphone to analyze the user's emotions in real time. It uses Google Cloud's emotion recognition API to identify emotions from the user's facial expressions and voice.

[1225] Emotion-based display adjustment

[1226] Server: Based on the results of the emotion engine's analysis, the server adjusts the display content and format of the estimated data. For example, if surprise is detected, the server automatically adds a detailed explanation of the estimated data.

[1227] Cloud Storage and Access Control

[1228] Server: The generated and modified estimation data is stored in a cloud storage service such as AWS S3, and replicated to multiple regions to facilitate data backup and recovery after storage. IAM user policies are used to set access permissions for data stored in the cloud, allowing specific users (e.g., SC members) to view and modify the data.

[1229] Storing and using emotional data

[1230] Server: Analyzed emotion data is stored in a cloud environment and managed as user emotion history data. The emotion history is used to propose the optimal format and display method for the next and subsequent trial calculation data creation.

[1231] Specific examples

[1232] Example prompt: "Request mobile payment data for the past month."

[1233] User A launches the app on their smartphone and requests mobile payment data for the past month.

[1234] A request is sent to the server, data in the mobile category is searched and sent to User A's device.

[1235] The transmitted data is analyzed using a machine learning algorithm to extract the top 10 patterns. Furthermore, Blue Prism automatically generates estimates, and the results are sent to User A's device.

[1236] When User A checks the estimated data, the emotion engine analyzes their emotions from their facial expressions and voice, and adjusts the displayed estimated data as necessary.

[1237] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1238] Step 1: Data collection

[1239] Server: Obtain approval data for the past month from the business system via API. The API endpoint and authentication information of the business system are required as input. The data obtained from the API is saved in a database (e.g., MySQL). The output is the approval data saved in the database.

[1240] Specifically, a scheduled job is executed at a fixed time every day to collect new data from the business system.

[1241] Step 2: Data Classification

[1242] Server: Classifies the payment data stored in the database by product category. The original payment data stored in the database is required as input. Using SQL queries, the data is classified and tagged into categories such as "mobile" and "data." The output is the classified and tagged data.

[1243] Specific operations include filtering and tagging based on product categories.

[1244] Step 3: Pattern analysis

[1245] Server: Uses Python's SciKit-Learn library to analyze the classified data using machine learning algorithms to find patterns. The tagged data is required as input. Cluster analysis is performed to extract common trading patterns. The output is the pattern data as the analysis results.

[1246] Specifically, cluster analysis is performed, and representative transaction patterns for each cluster are extracted and saved.

[1247] Step 4: Summary data generation

[1248] Server: Generates summary data from the analyzed pattern data. Pattern data is required as input. Transaction summaries for each pattern are compiled and summary data is generated in JSON format. The output is the generated summary data.

[1249] Specifically, the data is aggregated, an overview of each pattern is summarized, and the results are saved in a JSON format file.

[1250] Step 5: Generate an automatic estimate

[1251] Server: Uses an RPA tool (e.g. Blue Prism) to generate automated estimates based on summary data. Requires summary data as input. Runs a sales forecasting model and automatically populates an Excel template with estimate results. Output is the generated estimate report.

[1252] Specifically, the predictive model is executed and the results are automatically reflected in the Excel template.

[1253] Step 6: View the estimated data

[1254] Terminal: The user launches the smartphone app and requests estimated data. The user's request (e.g., the past month's worth of mobile data) is required as input. The server responds to the request and returns the estimated data to the terminal. The output is the estimated data displayed on the user's terminal.

[1255] Specifically, data is retrieved from the server via an HTTP request and displayed in the app.

[1256] Step 7: Emotion Engine Analysis

[1257] Device: Analyzes user emotions in real time using the built-in camera and microphone. User facial expressions and voice are required as input. Google Cloud's emotion recognition API is used to analyze user emotions. The output is recognized emotion data.

[1258] Specifically, the process involves capturing facial expressions and voice, sending them to an API, and analyzing emotions.

[1259] Step 8: Emotion-Based Display Adjustment

[1260] Server: Adjusts the display content and format of the estimated data based on the analysis results of the emotion engine. It requires recognized emotion data as input. For example, if surprise emotion is detected, it highlights the details of the estimated data. The output is the adjusted display of the estimated data.

[1261] As a specific operation, a customization process for the display content is executed, and the adjustment results are sent to the terminal.

[1262] Step 9: Save your data to the cloud

[1263] Server: Stores generated and modified estimate data in cloud storage (e.g., AWS S3). Requires generated or modified estimate data as input. Data is stored in cloud storage and replicated across multiple regions. Output is estimate data stored in the cloud.

[1264] Specifically, data is stored and backed up on the cloud.

[1265] Step 10: Access Control

[1266] Server: Sets access permissions for data stored in cloud storage. Access permission information and target data are required as input. IAM user policies are used to set permissions so that specific users can access the data. The output is the set access permissions.

[1267] Specific operations include setting access control lists (ACLs) and policies.

[1268] Step 11: Storing and Using Emotional Data

[1269] Server: Analyzed emotion data is stored in the cloud and managed as emotion history data. Analyzed emotion data is required as input. Based on the emotion history, the optimal format and display method are proposed for the next and subsequent trial calculation data creation. The output is the stored emotion history data.

[1270] Specifically, emotion data is saved and historical data is analyzed to help provide future data.

[1271] (Application example 2)

[1272] 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."

[1273] Conventional systems were able to efficiently collect and classify data and generate automatic estimates, but they had problems with a fixed user interface and lacked the flexibility to respond based on user emotions. Furthermore, there was no way to adjust the display format of the generated estimate data based on the user's emotions, resulting in a limited user experience. Therefore, there is a need for a system that optimizes data management and display and provides dynamic responses based on the user's emotions.

[1274] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data, means for classifying the collected data by product type, means for analyzing common patterns from the classified data and generating summary data, means for automatically generating trial calculations based on the analysis results, means for displaying the automatically generated trial calculation data on a terminal, means for storing the generated trial calculation data on the cloud and controlling access to it, means for analyzing the user's emotions using emotion recognition means, and means for adjusting the display content and format of the trial calculation data based on the user's emotions. This makes it possible to adjust the display content according to the user's emotions, thereby providing a more flexible and optimized data management system.

[1275] "Means of collecting data" refers to the function of automatically acquiring past transaction data and business data and storing it in the system.

[1276] "Means for classifying by product" is a function that divides collected data into categories and classifies them into specific product groups.

[1277] "Means for analyzing patterns and generating summary data" refers to a function that uses machine learning algorithms to extract common patterns from collected and classified data, summarizes them, and generates summary data.

[1278] The "means for generating automatic estimates" is a function that performs sales forecasts and cost calculations based on the analyzed pattern data, and automatically generates estimates.

[1279] "Means for displaying on a terminal" is a function for displaying the generated trial calculation data on the user's terminal in real time.

[1280] "Means for storing data on the cloud and controlling access" refers to a function for storing the generated estimate data in cloud storage and setting access rights for specific users.

[1281] The "emotion recognition means" is a function that recognizes and analyzes the user's emotions from facial expressions and voice data.

[1282] The "means for adjusting the display content and format" is a function for dynamically adjusting the display format and content of the trial calculation data according to the recognized user's emotions.

[1283] The present invention relates to a smart logistics management system in a logistics center. Next, an embodiment of the present invention will be described in detail.

[1284] System Configuration

[1285] Program processing

[1286] Data collection and classification

[1287] The server retrieves the past month's worth of transaction data from the logistics center's business system and stores it in a database. The data is then classified by product and managed by category, such as "mobile devices" or "consumables."

[1288] Pattern analysis and summary data generation

[1289] The server uses machine learning algorithms to analyze patterns based on the classified data. For example, it uses cluster analysis to extract common transaction patterns at the distribution center. It then generates summary data based on the analysis results and saves them in a format such as JSON.

[1290] Generate automatic estimates

[1291] Based on the analysis results, the server uses robotics process automation (RPA) technology to forecast sales and optimize inventory, automatically generating trial data.

[1292] View and Share

[1293] The device (smart glasses or robot) receives and displays the estimated data generated by the server in real time according to the user's instructions. The user can then work based on this data and make any necessary corrections.

[1294] Incorporating an emotion engine

[1295] When the user checks the estimated data on the device, the emotion engine installed in the smart glasses or robot recognizes the user's emotions from their facial expressions and voice.

[1296] Emotion-based display adjustment

[1297] The server receives the analysis results from the emotion engine and dynamically adjusts the display content and format of the trial calculation data in accordance with the user's emotions.

[1298] Cloud Storage and Access Control

[1299] The generated estimate data is stored in cloud storage, and access control is performed in real time, allowing only specific users to access and modify the data.

[1300] Storing and using emotional data

[1301] The server stores the user's emotion data in the cloud, analyzes past emotion history, and optimizes the creation and provision of trial data, thereby proposing the most suitable display format for the user.

[1302] Specific examples

[1303] User B's operation

[1304] User B puts on the smart glasses and launches the inventory management app. He makes a request to check inventory data for the past month, and the device sends this request to the server. The server retrieves the inventory data and sends it to User B's device.

[1305] Data analysis and calculation generation

[1306] The server analyzes the received data using a machine learning algorithm and extracts the top 10 patterns of data. It then automatically generates a trial calculation based on these patterns and sends it to User B's device.

[1307] User B checks and corrects

[1308] When User B checks the estimated data, the emotion engine analyzes User B's facial expressions to determine their emotions. If User B expresses dissatisfaction, the displayed content is adjusted to address the reason for dissatisfaction. For example, a detailed explanation may be added. After making any necessary corrections, the revised version is sent back to the server and saved in cloud storage.

[1309] Data sharing

[1310] The server saves the revised estimate data in the cloud and notifies specific users (e.g., logistics center managers). The managers can check the revisions on their own devices and make additional revisions or comments as necessary.

[1311] Prompt Sentence Examples

[1312] "Write a Python program that collects inventory data from the past month, analyzes it for the most common patterns, and displays the results as a summary. Also, add the ability to adjust the display based on user sentiment."

[1313] This invention aims to improve data management and work efficiency in logistics centers, and enables flexible responses based on user emotions.

[1314] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1315] Step 1: Data collection

[1316] The server retrieves the past month's worth of transaction data from the logistics center's business system via API. The input is the business system's API endpoint and authentication token, and the output is JSON-formatted transaction data. Specifically, it makes an API request, parses the JSON data returned as a response, and saves it in the database.

[1317] Step 2: Data Classification

[1318] The server categorizes the collected data by product. The input is transaction data stored in a database, and the output is a dataset categorized by product. Specifically, the data is filtered based on product category information, and each category is saved as a separate dataset.

[1319] Step 3: Pattern analysis and summary data generation

[1320] The server uses a machine learning algorithm to analyze patterns based on the classified data. The input is a data set classified by product type, and the output is summary data based on the pattern analysis. Specifically, it performs cluster analysis, extracts transaction patterns, summarizes each pattern, and saves them as summary data.

[1321] Step 4: Generate an automatic estimate

[1322] The server performs sales forecasting and inventory optimization based on the pattern analysis results, and automatically generates trial calculation data. The input is the pattern analysis results, and the output is automatically generated trial calculation data. Specifically, RPA technology is used to apply sales forecasting algorithms and inventory optimization algorithms, calculate and save the trial calculation results.

[1323] Step 5: View the estimated data

[1324] The terminal (smart glasses or robot) receives and displays the estimated data generated from the server in real time at the user's command. The input is a request for estimated data from the server, and the output is the estimated data displayed on the user's terminal. Specifically, an HTTP request is sent, and the estimated data is received and displayed in real time.

[1325] Step 6: Emotion recognition and display adjustment

[1326] When the user checks the estimated data on the device, the emotion engine installed in the smart glasses or robot recognizes the emotion from the user's facial expression and voice. The input is the user's facial expression data and voice data, and the output is analyzed emotion data. Specifically, the user's facial expression and voice are captured using a camera or microphone, and then analyzed using an emotion recognition algorithm.

[1327] Step 7: Adjust content based on emotions

[1328] The server receives the analysis results from the emotion engine and dynamically adjusts the display content and format of the trial calculation data according to the user's emotions. The inputs are emotion data and trial calculation data, and the output is the adjusted display of the trial calculation data. Specifically, if the user expresses dissatisfaction, the server makes adjustments such as displaying additional detailed explanations.

[1329] Step 8: Cloud Storage and Access Control

[1330] The server stores the generated trial calculation data and emotion data in cloud storage and performs access control in real time. The inputs are the trial calculation data and emotion data, and the output is the data stored on the cloud and the access permissions that are set. Specifically, the data is uploaded using a cloud API and access permissions are set for specific users.

[1331] Step 9: Storing and optimizing emotional data

[1332] The server stores the user's emotional data in the cloud, analyzes past emotional history, and optimizes the creation and provision of trial data. The inputs are emotional data and past emotional history, and the output is optimized trial data. Specifically, it uses an analytical algorithm to analyze past emotional data and propose future display content.

[1333] 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.

[1334] 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.

[1335] 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.

[1336] [Fourth embodiment]

[1337] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1338] 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.

[1339] 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).

[1340] 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.

[1341] 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.

[1342] 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).

[1343] 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.

[1344] 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.

[1345] 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.

[1346] 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.

[1347] 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.

[1348] 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.

[1349] 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."

[1350] The system of this invention collects data, classifies it by product, analyzes the data for common patterns, generates summary data, and automatically generates estimates based on the analysis results, displays them on a terminal, stores them in the cloud, and controls access.

[1351] Program processing

[1352] Data collection and classification

[1353] Server: Obtains approval data for the past month from the business system. This data is stored in a specific database. The data is then classified based on product category. Data is separated into categories such as "mobile" and "data."

[1354] Pattern analysis and summary data generation

[1355] Server: Based on the classified data, machine learning algorithms are used to analyze patterns. For example, cluster analysis of historical data is performed to identify common trading patterns. Summary data is generated based on the analysis results and saved in an appropriate format such as JSON.

[1356] Generate automatic estimates

[1357] Server: Based on the results of pattern analysis, the server uses robotics process automation (RPA) technology to automatically generate estimates. Specifically, it performs sales forecasts and cost calculations based on the collected pattern information. This reduces the effort required for manual calculations.

[1358] View and Share

[1359] On the device: The user opens the app, which retrieves and displays the estimated data generated by the server in real time. The user can then make any necessary corrections based on this data.

[1360] Cloud Storage and Access Control

[1361] Server: The generated trial data is stored in cloud storage and made accessible in real time. At the same time, access permissions are set for each data item, allowing specific users (e.g., SC members) to view and edit it.

[1362] Specific examples

[1363] User A's operation

[1364] User A: Launches the smartphone app and requests the past month's worth of mobile approval data.

[1365] Terminal: The request is sent to the server.

[1366] Server: Searches for data in the mobile category and sends it to User A's device.

[1367] Data analysis and calculation generation

[1368] Server: Analyzes the transmitted data using a machine learning algorithm and extracts the top 10 patterns. Furthermore, automatically generates a trial calculation based on these patterns and sends it to User A's device.

[1369] User A checks and corrects

[1370] User A: Checks the estimated data and corrects some of the figures. The corrected data is sent back to the server and saved in cloud storage.

[1371] Data sharing

[1372] Server: The revised estimate data is saved in the cloud and notified to all SC members. SC members can check the revisions on their own devices and make additional revisions or comments as necessary.

[1373] In this way, the present invention streamlines the entire process of creating estimates and significantly reduces the workload. Estimates can be performed quickly regardless of location, which also contributes to improving the business environment.

[1374] The processing flow will be explained below.

[1375] Step 1:

[1376] Server: Obtains approval data for the past month from the business system. The obtained data is stored in a specific database.

[1377] Step 2:

[1378] Server: Classifies the stored data based on "product category." Data is stored separately for each category, such as "mobile" and "data."

[1379] Step 3:

[1380] Device: A user launches the app and requests data for a specific product category (e.g., mobile). The device uses the API to send the data request to the server.

[1381] Step 4:

[1382] Server: In response to the request, the server filters specific product data and returns it to the terminal. The returned data is numerical data categorized based on product category.

[1383] Step 5:

[1384] Server: Based on the received data, machine learning algorithms are used to analyze patterns, specifically cluster analysis, to extract common trading patterns.

[1385] Step 6:

[1386] Server: Generates summary data based on the analysis results. The summary data is saved in a format such as JSON and includes the top 10 patterns for each product.

[1387] Step 7:

[1388] Server: Automatically generates estimates based on pattern analysis, including sales forecasts and cost calculations, using robotic process automation (RPA) technology.

[1389] Step 8:

[1390] Server: The generated estimation data is stored in a database and cloud storage. The stored data can be accessed in real time.

[1391] Step 9:

[1392] Device: The user checks the estimated data generated through the app. The estimated data displayed on the screen can be corrected or supplemented as needed.

[1393] Step 10:

[1394] User: Checks the estimated data and corrects any necessary parts. The corrected data is sent back to the server and saved in cloud storage.

[1395] Step 11:

[1396] Server: Saves the final estimation data in the cloud and sets access permissions. Sends notifications to specific SC members to grant access.

[1397] Step 12:

[1398] SC members (users): Receive notifications and access the estimated data on the cloud. After making any necessary corrections or comments, they save it as the final version.

[1399] Example 1

[1400] 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."

[1401] Currently, many companies and organizations handle large amounts of data, but it is difficult to efficiently collect and analyze that data, quickly perform calculations, and provide users with the necessary information. In particular, there is a demand for a system that can centrally perform data classification, pattern analysis, automatic calculation generation, display, storage, and access management. The object of this invention is to provide a system that solves these problems.

[1402] 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.

[1403] In this invention, the server includes means for collecting information from business systems, means for classifying the collected information by product group, means for analyzing recurring patterns in the classified information and generating summary information, means for generating automatic calculations based on the analysis results, means for displaying the automatically generated calculation information on a terminal, means for storing the generated calculation information in a cloud environment and managing access, means for analyzing information using a machine learning algorithm and extracting common patterns, and means for automatically generating sales forecasts and cost calculations using robotics process automation technology. This enables efficient collection, classification, and analysis of data, as well as rapid generation of estimates, sharing, and management.

[1404] "Business system" is a general term for software and hardware used on a daily basis by companies and organizations for management, operation, and monitoring.

[1405] "Information" refers to all data collected, categorized, analyzed, and generated, including, in particular, decision-making data relating to commercial products.

[1406] A "product group" refers to a collection of products that belong to the same or similar category, including products with specific attributes such as "mobile" or "data."

[1407] "Classification" refers to the process of separating collected information into different categories based on specific criteria (e.g., product groups).

[1408] A "pattern" refers to a common trend or recurring phenomenon found in collected and classified information.

[1409] "Analytics" refers to the methods and techniques used to extract meaningful patterns and trends from collected and classified information.

[1410] "Summary information" refers to data that succinctly summarizes the results of analyzed patterns and provides actionable insights.

[1411] "Automatic calculation" refers to calculation processing that is automatically performed by a computer program based on the analysis results, and includes the generation of trial calculations.

[1412] A "terminal" is a device operated by a user, and refers to a computer such as a smartphone, tablet, or PC.

[1413] "Cloud environment" refers to a virtualized infrastructure for data storage and computing services delivered over the Internet.

[1414] "Access management" refers to the ability to set and control access rights to data and systems.

[1415] A "machine learning algorithm" is one of the algorithms used in data analysis, and is a technology for extracting patterns and trends from large amounts of data.

[1416] "Robotics process automation technology" refers to technology for automating routine business processes, and in this case specifically refers to the automation of sales forecasts and cost calculations.

[1417] The system of the present invention collects information from business systems, classifies it by product group, analyzes patterns using machine learning algorithms, generates summary information, generates automatic calculations using robotics process automation technology, displays the results on a terminal, stores them in a cloud environment, and manages access.

[1418] Specifically, the following hardware and software are used:

[1419] 1. Server

[1420] The server collects information from the business system, for example, by retrieving data via API and storing it in a database such as PostgreSQL.

[1421] The server categorizes the collected information into product groups using SQL queries based on the product attributes.

[1422] The server uses machine learning algorithms (e.g., Scikit-learn) to analyze patterns in the classified information and extract common patterns, using cluster analysis or other applicable analytical techniques.

[1423] The server generates summary information based on the analysis results and saves it in JSON format using the Python json library.

[1424] The server uses a robotics process automation tool (e.g., UiPath) to perform sales forecasting and cost calculations and generate automated calculations.

[1425] The server uploads the generated calculation information to a cloud environment (e.g., AWS S3), generates a URL, and notifies the user. AWS SDK is used for saving.

[1426] 2. Terminal

[1427] A user uses a device (smartphone, tablet, PC, etc.) to request information from a server. The request is made using the HTTP protocol.

[1428] Receives the response from the server and displays it on the screen. For example, this is implemented using front-end technologies such as JavaScript or React.

[1429] 3. Users

[1430] The user launches the smartphone app from their device and requests approval data for products from the past month.

[1431] The user checks the received data and corrects the values ​​as necessary. The corrected data is then sent back to the server and stored in the cloud environment.

[1432] For example, you can invoke a generative AI model using a prompt like this:

[1433] This system retrieves the past month's worth of approval data from a specific business system, classifies it by product group, and then performs pattern analysis using a machine learning algorithm. Based on the analysis results, it automatically generates trial calculations and displays them on the user's device. The final trial calculation data is stored in the cloud and managed with access control for specific users. Please explain in detail how the program in this system processes data.

[1434] This invention enables efficient collection and classification of data, analysis and rapid generation of estimates, as well as the sharing and management of this information in a unified manner, thereby improving work efficiency and accuracy.

[1435] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1436] Step 1:

[1437] Data collection

[1438] Server: Obtains approval data for the past month from the business system's API. Specifically, it sends an API request and receives the response data in JSON format.

[1439] Input: API request to business system

[1440] Output: Acquired approval data in JSON format

[1441] Specific operation: Use the curl command or the requests library to retrieve data via "https: / / api.example.com / getData" and insert the received JSON data into the database (PostgreSQL).

[1442] Step 2:

[1443] Data Classification

[1444] Server: Classify the acquired data based on product category (e.g., "Mobile" or "Data").

[1445] Input: Approval data obtained in Step 1

[1446] Output: Data categorized by product category

[1447] Specific operation: Issues an SQL query, categorizes the data using a command such as "SELECT FROM Approval Data WHERE Category = 'Mobile'", and inserts each category into a separate table.

[1448] Step 3:

[1449] Pattern Analysis

[1450] Server: Uses machine learning algorithms (e.g., Scikit-learn) to analyze frequent patterns from the classified data.

[1451] Input: Product data classified in Step 2

[1452] Output: Pattern data obtained by analysis

[1453] What it does: Use code like "from sklearn.cluster import KMeans" to apply cluster analysis to classified data to identify frequent patterns. The results of this analysis are temporarily saved.

[1454] Step 4:

[1455] Summary Data Generation

[1456] Server: Generates summary data based on the analysis results. The generated summary data is saved in JSON format.

[1457] Input: Pattern data analyzed in step 3

[1458] Output: Summary data in JSON format

[1459] Specific operation: Based on the acquired pattern data, summary data is generated using Python's JSON library as "summary_data = json.dumps(analysis results)" and saved in the database.

[1460] Step 5:

[1461] Automatic calculation generation

[1462] Server: Uses robotics process automation tools (e.g., UiPath) to perform sales forecasts and cost calculations, and automatically generate estimates.

[1463] Input: Summary data generated in step 4

[1464] Output: Automatically generated trial data

[1465] Specific operation: Launch an RPA tool such as UiPath, perform sales forecasts and cost calculations using code such as "RPA_tool.calculate_sales_forecast(pattern data)", and save the results.

[1466] Step 6:

[1467] Viewing Data

[1468] Terminal: The user uses the terminal to request estimated data from the server and displays the received estimated data.

[1469] Input: Data request from user

[1470] Output: Estimated data displayed on the terminal

[1471] Specific operation: Sends an HTTP request, receives and processes the JSON response from the server, and retrieves the data using code such as "fetch('server URL / estimated data').then(response => response.json())" and displays it in HTML or JavaScript.

[1472] Step 7:

[1473] Cloud Storage

[1474] Server: The generated estimate data is saved in a cloud environment (e.g., AWS S3). After saving, a public URL is generated and notified to the user.

[1475] Input: Estimated data generated in Step 5

[1476] Output: Estimated data stored in the cloud environment and its public URL

[1477] Specific operation: Using the AWS SDK, upload the data as follows: "s3_client.upload_file('estimated_data.json', 'mybucket', 'estimated_data.json')" and generate a public URL.

[1478] Step 8:

[1479] Access Control

[1480] Server: Sets access permissions for the estimation data stored in the cloud environment and notifies specific users.

[1481] Input: Estimation data stored in the cloud environment

[1482] Output: Access permissions set and notified users

[1483] Specific operation: Create an IAM policy, set permissions for each user as follows: "IAM_policy = create_policy('Access permission', users=['UserA', 'SC_member'])", and send a notification email.

[1484] In this way, by clarifying the specific operations at each processing step and their inputs and outputs, the system enables efficient data collection, classification, analysis, automatic calculation generation, display, storage, and access management.

[1485] (Application example 1)

[1486] 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."

[1487] Traditional sales forecasting and inventory management in brick-and-mortar stores relied on manual analysis and predictions, resulting in inefficiency and low accuracy. Furthermore, analyzing large amounts of data to timely replenish inventory and forecast sales placed a heavy burden on human resources. Furthermore, a lack of real-time data sharing and access control sometimes led to delays in management decisions. This resulted in inventory shortages and surpluses, lost sales opportunities, and reduced overall store operational efficiency.

[1488] 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.

[1489] In this invention, the server includes means for collecting data, means for classifying the collected data by product category, means for analyzing common patterns from the classified data and generating summary data, means for automatically generating trial calculations based on the analysis results, means for displaying the automatically generated trial calculation data on a terminal, means for storing the generated trial calculation data on the cloud and controlling access to it, means for collecting sales data and inventory data from physical stores from POS systems, means for analyzing purchasing patterns based on the collected data using a machine learning algorithm and generating summary data, means for automatically generating sales forecasts and inventory replenishment plans based on the analysis results, and means for displaying the generated sales forecast and inventory replenishment plan data on a terminal in real time, thereby enabling efficient and highly accurate sales forecasts and inventory management.

[1490] "Means of collecting data" refers to systems or devices for collecting necessary information from outside, such as POS systems and sensors.

[1491] A "categorization method" refers to an algorithm or software that organizes and classifies collected data into specific categories.

[1492] "Means for analyzing common patterns and generating summary data" refers to techniques that use statistical or machine learning techniques to extract specific patterns or trends from collected data and generate summarized information based on them.

[1493] "Means for generating automated estimates" refers to programs or algorithms for automatically calculating sales forecasts, inventory replenishment plans, etc. based on the analysis results.

[1494] "Means for displaying on the terminal" refers to the display or screen display technology that allows users to view and manipulate the results of calculations and analyses.

[1495] "Means for storing data on the cloud and controlling access" refers to a technology for storing generated data on a remote server via the Internet and managing access rights to that data.

[1496] "Means for collecting sales and inventory data from POS systems" refers to programs or interfaces for periodically obtaining sales records and inventory information from physical store POS systems.

[1497] "Means of analyzing purchasing patterns using machine learning algorithms" refers to a technology that utilizes AI technology to analyze patterns of customer purchasing behavior and sales trends.

[1498] "Means for automatically generating sales forecasts and inventory replenishment plans" refers to an algorithm that automatically calculates future sales and required inventory levels based on the analysis results, and generates an appropriate replenishment plan.

[1499] "Means for displaying on the terminal in real time" refers to real-time display technology that allows users to instantly view the results of calculations and analyses.

[1500] This invention is a system for improving the efficiency of sales forecasting and inventory management in physical stores, and includes the following elements.

[1501] System Configuration and Hardware

[1502] 1. POS system: Hardware for collecting sales and inventory data from physical stores.

[1503] 2. Server: A computer system for data collection, classification, pattern analysis, estimate generation, cloud storage, and access control.

[1504] 3. Terminal: A device such as a smartphone or tablet that allows users to check and modify the estimated data.

[1505] Software and Algorithms

[1506] 1. Data collection program (Python): Obtains sales and inventory data from the POS system in JSON format and sends it to the server.

[1507] 2. Data classification algorithm: Divide the collected data into product categories.

[1508] 3. Machine learning algorithms (scikit-learn, pandas): Analyze purchasing patterns and generate summary data.

[1509] 4. RPA tool (UiPath): Automatically generates sales forecasts and inventory replenishment plans based on analysis results.

[1510] 5. Cloud storage (AWS S3) and access control tools (AWS IAM): Store generated data in the cloud and set access permissions.

[1511] 6. Smartphone app (React Native): Displays summary data and estimates in real time and allows users to make corrections.

[1512] Data processing and calculation

[1513] server

[1514] Receives data sent from the POS system and classifies it by product category.

[1515] Machine learning algorithms are used to analyze data and extract common purchasing patterns.

[1516] Sales forecasts and inventory replenishment plans are automatically generated based on the extracted patterns.

[1517] Terminal

[1518] Receives estimated data sent from the server and displays it in real time.

[1519] The user checks and corrects the calculation results and sends the corrections to the server.

[1520] Cloud

[1521] The generated data is stored in the cloud and users can access the data based on the set access permissions.

[1522] Specific examples

[1523] 1. User A (store manager) opens the Store Management Assistant app on his smartphone and requests sales data for the food category for the past month.

[1524] 2. The server retrieves data from the POS system and analyzes it using machine learning algorithms.

[1525] 3. Sales forecasts and inventory replenishment plans are automatically generated and displayed in real time on User A's smartphone.

[1526] 4. User A checks the forecast, corrects some of the inventory quantities, and sends it back to the server.

[1527] 5. The corrected data is saved in the cloud and notified to other administrators.

[1528] Prompt Sentence Examples

[1529] "Analyze purchasing patterns for food categories based on sales data from the past month."

[1530] "Please prepare a sales forecast and inventory replenishment plan for the next month."

[1531] In this way, the system automates complex data analysis and calculations, improving the efficiency and accuracy of sales forecasting and inventory management in physical stores.

[1532] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1533] Step 1:

[1534] Input: Sales and inventory data from the POS system for the past month (JSON format)

[1535] Processing: The server uses a data collection program (Python) to acquire sales and inventory data from the POS system. The acquired data is stored in a database.

[1536] Output: Sales and inventory data stored in a database in JSON format.

[1537] Specific operation: A data request is made from the POS system, and the returned data is stored in the server's database.

[1538] Step 2:

[1539] Input: Sales and inventory data stored in a database

[1540] Processing: The server uses a data classification algorithm to classify sales and inventory data by product category.

[1541] Output: Data categorized by product category

[1542] Specific operation: Use a data frame to classify data based on product ID and category information.

[1543] Step 3:

[1544] Input: Data categorized by product category

[1545] Processing: The server analyzes the classified data using machine learning algorithms (scikit-learn, pandas), extracts purchasing patterns, and generates summary data.

[1546] Output: Summary data including purchasing patterns (JSON format)

[1547] Specific operations: Perform clustering and time series analysis to extract trends and patterns from data and generate summarized data.

[1548] Step 4:

[1549] Input: Summary data including purchasing patterns (JSON format)

[1550] Processing: The server uses an RPA tool (UiPath) to automatically generate sales forecasts and inventory replenishment plans based on the analysis results.

[1551] Output: Sales forecast and inventory replenishment plan data (JSON format)

[1552] Specific operation: Based on the prediction results of the machine learning model, sales forecasts and inventory replenishment schedules are calculated and data is generated.

[1553] Step 5:

[1554] Input: Automatically generated sales forecast and inventory replenishment plan data (JSON format)

[1555] Processing: The server stores the generated estimate data in cloud storage (AWS S3) and sets appropriate permissions using an access control tool (AWS IAM).

[1556] Output: Prediction data stored in the cloud and access permission settings

[1557] Specific behavior: Upload data to cloud storage and assign access permissions to specific users or roles.

[1558] Step 6:

[1559] Input: User request (e.g., sales data for food categories for the past month)

[1560] Processing: The server retrieves the corresponding data from the cloud storage in response to the request and sends it to the requesting terminal.

[1561] Output: Data sent to the terminal

[1562] Specific operation: Receives a user request, retrieves data from the cloud, and sends it to the specified device.

[1563] Step 7:

[1564] Input: Sales forecast and inventory replenishment plan data (JSON format)

[1565] Processing: The terminal displays sales forecast and inventory replenishment planning data in real time, allowing users to make necessary corrections.

[1566] Output: Corrected data

[1567] Specific behavior: Display data in a UI and allow users to change values ​​and conditions through the interface.

[1568] Step 8:

[1569] Input: Corrected data

[1570] Processing: The device sends the data modified by the user back to the server, and the server updates the data stored in the cloud.

[1571] Output: Updated cloud storage data

[1572] Specific behavior: User modifications are sent to the server, data in the cloud storage is updated, and users with appropriate permissions are notified.

[1573] In this way, a system is realized in which servers, terminals, and the cloud work together to perform efficient and highly accurate sales forecasts and inventory management.

[1574] 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.

[1575] The system of this invention collects data, classifies it by product, analyzes common patterns from the data, and generates summary data. It then generates automated estimates based on the analysis results, displays them on the device, stores them in the cloud, and controls access. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is possible to analyze user emotions and adjust the display content and format of the estimate data.

[1576] Program processing

[1577] Data collection and classification

[1578] Server: Obtains approval data for the past month from the business system and stores it in a database. The data is then classified based on product category. Data is stored separately for each category, such as "Mobile" and "Data."

[1579] Pattern analysis and summary data generation

[1580] Server: Based on the classified data, machine learning algorithms are used to analyze patterns. For example, cluster analysis is used to extract common trading patterns. Summary data is generated based on the analysis results and saved in a format such as JSON.

[1581] Generate automatic estimates

[1582] Server: Based on the results of pattern analysis, the server uses robotics process automation (RPA) technology to automatically generate estimates. Specifically, it performs sales forecasts and cost calculations based on the collected pattern information, and automatically generates estimates.

[1583] View and Share

[1584] On the device: The user opens the app, which retrieves and displays the estimated data generated by the server in real time. The user can then make any necessary corrections based on this data.

[1585] Incorporating an emotion engine

[1586] Device: When the user checks the estimated data, the emotion engine recognizes the user's emotions from their facial expressions and voice. The emotion engine uses a machine learning model to analyze the user's emotions (e.g., joy, anger, surprise, etc.).

[1587] Emotion-based display adjustment

[1588] Server: Receives the analysis results of the emotion engine and adjusts the display content and format according to the user's emotions. For example, if the user expresses dissatisfaction, the server may highlight the details of the estimated data.

[1589] Cloud Storage and Access Control

[1590] Server: The generated trial data is stored in cloud storage and made accessible in real time. At the same time, access permissions are set for each data item, allowing specific users (e.g., SC members) to view and edit it.

[1591] Storing and using emotional data

[1592] Server: Analyzed user emotion data is stored on the cloud, and the emotional history is used to optimize the creation and provision of estimated data. For example, it implements functions such as proposing the most suitable data format for a user based on their past emotional history.

[1593] Specific examples

[1594] User A's operation

[1595] User A: Launches the smartphone app and requests the past month's worth of mobile approval data.

[1596] Terminal: The request is sent to the server.

[1597] Server: Searches for data in the mobile category and sends it to User A's device.

[1598] Data analysis and calculation generation

[1599] Server: Analyzes the transmitted data using a machine learning algorithm and extracts the top 10 patterns. Furthermore, automatically generates a trial calculation based on these patterns and sends it to User A's device.

[1600] User A checks and corrects

[1601] User A: When checking the estimated data, the emotion engine analyzes User A's facial expressions to determine their emotions. If User A expresses surprise, the display content is adjusted to address the reason for the surprise. For example, a detailed explanation may be added.

[1602] User A: Makes the necessary corrections, sends the corrected version back to the server, and saves it in cloud storage.

[1603] Data sharing

[1604] Server: The revised estimate data is saved in the cloud and notified to all SC members. SC members can check the revisions on their own devices and make additional revisions or comments as necessary.

[1605] In this way, the present invention streamlines the entire process of creating estimates and significantly reduces the workload. Furthermore, the introduction of an emotion engine enables flexible responses based on the user's emotions, contributing to an improved business environment.

[1606] The processing flow will be explained below.

[1607] Step 1:

[1608] Server: Obtains approval data for the past month from the business system. The obtained data is stored in a specific database.

[1609] Step 2:

[1610] Server: Classifies the stored data based on "product category." Data is stored separately for each category, such as "mobile" and "data."

[1611] Step 3:

[1612] Device: A user launches the app and requests data for a specific product category (e.g., mobile). The device uses the API to send the data request to the server.

[1613] Step 4:

[1614] Server: In response to the request, the server filters specific product data and returns it to the terminal. The returned data is numerical data categorized based on product category.

[1615] Step 5:

[1616] Server: Based on the received data, machine learning algorithms are used to analyze patterns, specifically cluster analysis, to extract common trading patterns.

[1617] Step 6:

[1618] Server: Generates summary data based on the analysis results. The summary data is saved in a format such as JSON and includes the top 10 patterns for each product.

[1619] Step 7:

[1620] Server: Automatically generates estimates based on pattern analysis, including sales forecasts and cost calculations, using robotic process automation (RPA) technology.

[1621] Step 8:

[1622] Server: The generated estimation data is stored in a database and cloud storage. The stored data can be accessed in real time.

[1623] Step 9:

[1624] Device: The user checks the estimated data generated through the app. The estimated data displayed on the screen can be corrected or supplemented as needed.

[1625] Step 10:

[1626] User: Checks the estimated data and corrects any necessary parts. The corrected data is sent back to the server and saved in cloud storage.

[1627] Step 11:

[1628] Server: The emotion engine recognizes and analyzes the user's emotions from their facial expressions and voice. Based on the analysis results, the user's emotional state is determined.

[1629] Step 12:

[1630] Server: Based on the analyzed emotion data, adjust the content and format of the displayed estimated data. For example, if the user expresses dissatisfaction or confusion, display additional explanations.

[1631] Step 13:

[1632] Server: Stores emotion data on the cloud and manages the user's emotion history. Based on past emotion data, the algorithm that optimizes the estimation process is updated.

[1633] Step 14:

[1634] Server: Sets access permissions for the estimation data and emotion data and notifies specific SC members. Apply access control to SC members.

[1635] Step 15:

[1636] SC members (users): Receive notifications and access the estimated data and sentiment analysis data in the cloud. After making any necessary corrections or comments, they save the data as the final version.

[1637] Example 2

[1638] 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."

[1639] Existing data analysis systems collect and classify data, but often do not display or adjust the data appropriately, taking user emotions into account. Furthermore, there are issues with insufficient sharing of analysis results and access control, making it difficult for specific users to quickly obtain or modify the data they need. Furthermore, there is a lack of mechanisms for effectively utilizing user emotion data.

[1640] 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 collecting data, means for classifying the collected data by product, means for analyzing common patterns from the classified data and generating summary data, means for generating automatic trial calculations based on the analysis results, means for displaying the automatically generated trial calculation data on a terminal, means for storing the generated trial calculation data on the cloud and performing access control, means for recognizing user emotions and adjusting the display content and format of the trial calculation data, and means for analyzing user emotion data and storing it on the cloud. This enables seamless processing from data analysis to trial calculation generation and display adjustment according to the user's emotions. In addition, sharing and access control of generated data are strengthened, allowing specific users to quickly obtain and modify the data they need.

[1641] "Means for collecting data" refers to a device or program that has the function of acquiring and storing necessary data from business systems and external data sources.

[1642] "Means for classifying by product" refers to a device or program that provides the function of classifying and organizing acquired data based on specific criteria (e.g., product category, industry, etc.).

[1643] "Means for analyzing patterns and generating summary data" refers to a device or program that has the function of analyzing common trading patterns based on classified data using machine learning algorithms and statistical methods, and summarizing the results to create summary data.

[1644] The "means for generating automatic estimates" refers to a device or program that automatically performs sales forecasts, cost calculations, etc. based on the analysis results and generates estimate results.

[1645] The "means for displaying trial calculation data on a terminal" refers to a device or program having the function of transmitting the generated trial calculation data to a user's terminal in real time and displaying it.

[1646] "Means for storing the generated trial data on the cloud and controlling access" refers to a device or program that stores the generated trial data in cloud storage and has the function of setting and managing access rights for specific users.

[1647] "Means for recognizing the user's emotions and adjusting the display content and format of the trial calculation data" refers to a device or program that analyzes the user's emotions from their facial expressions, voice, etc., and adaptively changes the display content and format of the trial calculation data based on the results.

[1648] The "means for analyzing user emotion data and storing it in the cloud" refers to a device or program that has the function of storing the analyzed user emotion data in a cloud environment and using it for future data analysis and display adjustment.

[1649] The system of the present invention collects data, classifies it by product type, analyzes the data for common patterns, and generates summary data. It then generates automated estimates based on the analysis results, displays them on the device, stores them in the cloud, and controls access. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is possible to analyze user emotions and adjust the display content and format of the estimate data.

[1650] Data collection

[1651] Server: Obtain approval data for the past month from the business system. This is done by using the business system's API to collect the data. The collected data is stored in a database. Examples of databases that can be used include MySQL and PostgreSQL.

[1652] Data Classification

[1653] Server: Collected data is classified based on product category. For example, data is divided into categories such as "mobile" and "data," and each category is tagged and saved.

[1654] Pattern Analysis

[1655] Server: Using Python's SciKit-Learn library, machine learning algorithms are used to analyze patterns based on the classified data, for example, using cluster analysis to extract common trading patterns.

[1656] Summary Data Generation

[1657] Server: Generates summary data based on the analysis results. The generated summary data is saved in JSON format and stored in a separate table in the database.

[1658] Generate automatic estimates

[1659] Server: Use an RPA tool (e.g., Blue Prism) to generate automatic estimates based on the summary data. Specifically, run a sales forecast model based on the pattern information, automatically input the estimate results into an Excel template, and generate a report.

[1660] Display of estimated data

[1661] Device: The user launches the app on their smartphone and requests estimated data. The requested data is sent to the server, which returns the estimated data to the device. The user can then check the estimated data in real time on the app.

[1662] Emotion Engine Analysis

[1663] Device: The device uses a built-in camera and microphone to analyze the user's emotions in real time. It uses Google Cloud's emotion recognition API to identify emotions from the user's facial expressions and voice.

[1664] Emotion-based display adjustment

[1665] Server: Based on the results of the emotion engine's analysis, the server adjusts the display content and format of the estimated data. For example, if surprise is detected, the server automatically adds a detailed explanation of the estimated data.

[1666] Cloud Storage and Access Control

[1667] Server: The generated and modified estimation data is stored in a cloud storage service such as AWS S3, and replicated to multiple regions to facilitate data backup and recovery after storage. IAM user policies are used to set access permissions for data stored in the cloud, allowing specific users (e.g., SC members) to view and modify the data.

[1668] Storing and using emotional data

[1669] Server: Analyzed emotion data is stored in a cloud environment and managed as user emotion history data. The emotion history is used to propose the optimal format and display method for the next and subsequent trial calculation data creation.

[1670] Specific examples

[1671] Example prompt: "Request mobile payment data for the past month."

[1672] User A launches the app on their smartphone and requests mobile payment data for the past month.

[1673] A request is sent to the server, data in the mobile category is searched and sent to User A's device.

[1674] The transmitted data is analyzed using a machine learning algorithm to extract the top 10 patterns. Furthermore, Blue Prism automatically generates estimates, and the results are sent to User A's device.

[1675] When User A checks the estimated data, the emotion engine analyzes their emotions from their facial expressions and voice, and adjusts the displayed estimated data as necessary.

[1676] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1677] Step 1: Data collection

[1678] Server: Obtain approval data for the past month from the business system via API. The API endpoint and authentication information of the business system are required as input. The data obtained from the API is saved in a database (e.g., MySQL). The output is the approval data saved in the database.

[1679] Specifically, a scheduled job is executed at a fixed time every day to collect new data from the business system.

[1680] Step 2: Data Classification

[1681] Server: Classifies the payment data stored in the database by product category. The original payment data stored in the database is required as input. Using SQL queries, the data is classified and tagged into categories such as "mobile" and "data." The output is the classified and tagged data.

[1682] Specific operations include filtering and tagging based on product categories.

[1683] Step 3: Pattern analysis

[1684] Server: Uses Python's SciKit-Learn library to analyze the classified data using machine learning algorithms to find patterns. The tagged data is required as input. Cluster analysis is performed to extract common trading patterns. The output is the pattern data as the analysis results.

[1685] Specifically, cluster analysis is performed, and representative transaction patterns for each cluster are extracted and saved.

[1686] Step 4: Summary data generation

[1687] Server: Generates summary data from the analyzed pattern data. Pattern data is required as input. Transaction summaries for each pattern are compiled and summary data is generated in JSON format. The output is the generated summary data.

[1688] Specifically, the data is aggregated, an overview of each pattern is summarized, and the results are saved in a JSON format file.

[1689] Step 5: Generate an automatic estimate

[1690] Server: Uses an RPA tool (e.g. Blue Prism) to generate automated estimates based on summary data. Requires summary data as input. Runs a sales forecasting model and automatically populates an Excel template with estimate results. Output is the generated estimate report.

[1691] Specifically, the predictive model is executed and the results are automatically reflected in the Excel template.

[1692] Step 6: View the estimated data

[1693] Terminal: The user launches the smartphone app and requests estimated data. The user's request (e.g., the past month's worth of mobile data) is required as input. The server responds to the request and returns the estimated data to the terminal. The output is the estimated data displayed on the user's terminal.

[1694] Specifically, data is retrieved from the server via an HTTP request and displayed in the app.

[1695] Step 7: Emotion Engine Analysis

[1696] Device: Analyzes user emotions in real time using the built-in camera and microphone. User facial expressions and voice are required as input. Google Cloud's emotion recognition API is used to analyze user emotions. The output is recognized emotion data.

[1697] Specifically, the process involves capturing facial expressions and voice, sending them to an API, and analyzing emotions.

[1698] Step 8: Emotion-Based Display Adjustment

[1699] Server: Adjusts the display content and format of the estimated data based on the analysis results of the emotion engine. It requires recognized emotion data as input. For example, if surprise emotion is detected, it highlights the details of the estimated data. The output is the adjusted display of the estimated data.

[1700] As a specific operation, a customization process for the display content is executed, and the adjustment results are sent to the terminal.

[1701] Step 9: Save your data to the cloud

[1702] Server: Stores generated and modified estimate data in cloud storage (e.g., AWS S3). Requires generated or modified estimate data as input. Data is stored in cloud storage and replicated across multiple regions. Output is estimate data stored in the cloud.

[1703] Specifically, data is stored and backed up on the cloud.

[1704] Step 10: Access Control

[1705] Server: Sets access permissions for data stored in cloud storage. Access permission information and target data are required as input. IAM user policies are used to set permissions so that specific users can access the data. The output is the set access permissions.

[1706] Specific operations include setting access control lists (ACLs) and policies.

[1707] Step 11: Storing and Using Emotional Data

[1708] Server: Analyzed emotion data is stored in the cloud and managed as emotion history data. Analyzed emotion data is required as input. Based on the emotion history, the optimal format and display method are proposed for the next and subsequent trial calculation data creation. The output is the stored emotion history data.

[1709] Specifically, emotion data is saved and historical data is analyzed to help provide future data.

[1710] (Application example 2)

[1711] 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."

[1712] Conventional systems were able to efficiently collect and classify data and generate automatic estimates, but they had problems with a fixed user interface and lacked the flexibility to respond based on user emotions. Furthermore, there was no way to adjust the display format of the generated estimate data based on the user's emotions, resulting in a limited user experience. Therefore, there is a need for a system that optimizes data management and display and provides dynamic responses based on the user's emotions.

[1713] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data, means for classifying the collected data by product type, means for analyzing common patterns from the classified data and generating summary data, means for automatically generating trial calculations based on the analysis results, means for displaying the automatically generated trial calculation data on a terminal, means for storing the generated trial calculation data on the cloud and controlling access to it, means for analyzing the user's emotions using emotion recognition means, and means for adjusting the display content and format of the trial calculation data based on the user's emotions. This makes it possible to adjust the display content according to the user's emotions, thereby providing a more flexible and optimized data management system.

[1714] "Means of collecting data" refers to the function of automatically acquiring past transaction data and business data and storing it in the system.

[1715] "Means for classifying by product" is a function that divides collected data into categories and classifies them into specific product groups.

[1716] "Means for analyzing patterns and generating summary data" refers to a function that uses machine learning algorithms to extract common patterns from collected and classified data, summarizes them, and generates summary data.

[1717] The "means for generating automatic estimates" is a function that performs sales forecasts and cost calculations based on the analyzed pattern data, and automatically generates estimates.

[1718] "Means for displaying on a terminal" is a function for displaying the generated trial calculation data on the user's terminal in real time.

[1719] "Means for storing data on the cloud and controlling access" refers to a function for storing the generated estimate data in cloud storage and setting access rights for specific users.

[1720] The "emotion recognition means" is a function that recognizes and analyzes the user's emotions from facial expressions and voice data.

[1721] The "means for adjusting the display content and format" is a function for dynamically adjusting the display format and content of the trial calculation data according to the recognized user's emotions.

[1722] The present invention relates to a smart logistics management system in a logistics center. Next, an embodiment of the present invention will be described in detail.

[1723] System Configuration

[1724] Program processing

[1725] Data collection and classification

[1726] The server retrieves the past month's worth of transaction data from the logistics center's business system and stores it in a database. The data is then classified by product and managed by category, such as "mobile devices" or "consumables."

[1727] Pattern analysis and summary data generation

[1728] The server uses machine learning algorithms to analyze patterns based on the classified data. For example, it uses cluster analysis to extract common transaction patterns at the distribution center. It then generates summary data based on the analysis results and saves them in a format such as JSON.

[1729] Generate automatic estimates

[1730] Based on the analysis results, the server uses robotics process automation (RPA) technology to forecast sales and optimize inventory, automatically generating trial data.

[1731] View and Share

[1732] The device (smart glasses or robot) receives and displays the estimated data generated by the server in real time according to the user's instructions. The user can then work based on this data and make any necessary corrections.

[1733] Incorporating an emotion engine

[1734] When the user checks the estimated data on the device, the emotion engine installed in the smart glasses or robot recognizes the user's emotions from their facial expressions and voice.

[1735] Emotion-based display adjustment

[1736] The server receives the analysis results from the emotion engine and dynamically adjusts the display content and format of the trial calculation data in accordance with the user's emotions.

[1737] Cloud Storage and Access Control

[1738] The generated estimate data is stored in cloud storage, and access control is performed in real time, allowing only specific users to access and modify the data.

[1739] Storing and using emotional data

[1740] The server stores the user's emotion data in the cloud, analyzes past emotion history, and optimizes the creation and provision of trial data, thereby proposing the most suitable display format for the user.

[1741] Specific examples

[1742] User B's operation

[1743] User B puts on the smart glasses and launches the inventory management app. He makes a request to check inventory data for the past month, and the device sends this request to the server. The server retrieves the inventory data and sends it to User B's device.

[1744] Data analysis and calculation generation

[1745] The server analyzes the received data using a machine learning algorithm and extracts the top 10 patterns of data. It then automatically generates a trial calculation based on these patterns and sends it to User B's device.

[1746] User B checks and corrects

[1747] When User B checks the estimated data, the emotion engine analyzes User B's facial expressions to determine their emotions. If User B expresses dissatisfaction, the displayed content is adjusted to address the reason for dissatisfaction. For example, a detailed explanation may be added. After making any necessary corrections, the revised version is sent back to the server and saved in cloud storage.

[1748] Data sharing

[1749] The server saves the revised estimate data in the cloud and notifies specific users (e.g., logistics center managers). The managers can check the revisions on their own devices and make additional revisions or comments as necessary.

[1750] Prompt Sentence Examples

[1751] "Write a Python program that collects inventory data from the past month, analyzes it for the most common patterns, and displays the results as a summary. Also, add the ability to adjust the display based on user sentiment."

[1752] This invention aims to improve data management and work efficiency in logistics centers, and enables flexible responses based on user emotions.

[1753] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1754] Step 1: Data collection

[1755] The server retrieves the past month's worth of transaction data from the logistics center's business system via API. The input is the business system's API endpoint and authentication token, and the output is JSON-formatted transaction data. Specifically, it makes an API request, parses the JSON data returned as a response, and saves it in the database.

[1756] Step 2: Data Classification

[1757] The server categorizes the collected data by product. The input is transaction data stored in a database, and the output is a dataset categorized by product. Specifically, the data is filtered based on product category information, and each category is saved as a separate dataset.

[1758] Step 3: Pattern analysis and summary data generation

[1759] The server uses a machine learning algorithm to analyze patterns based on the classified data. The input is a data set classified by product type, and the output is summary data based on the pattern analysis. Specifically, it performs cluster analysis, extracts transaction patterns, summarizes each pattern, and saves them as summary data.

[1760] Step 4: Generate an automatic estimate

[1761] The server performs sales forecasting and inventory optimization based on the pattern analysis results, and automatically generates trial calculation data. The input is the pattern analysis results, and the output is automatically generated trial calculation data. Specifically, RPA technology is used to apply sales forecasting algorithms and inventory optimization algorithms, calculate and save the trial calculation results.

[1762] Step 5: View the estimated data

[1763] The terminal (smart glasses or robot) receives and displays the estimated data generated from the server in real time at the user's command. The input is a request for estimated data from the server, and the output is the estimated data displayed on the user's terminal. Specifically, an HTTP request is sent, and the estimated data is received and displayed in real time.

[1764] Step 6: Emotion recognition and display adjustment

[1765] When the user checks the estimated data on the device, the emotion engine installed in the smart glasses or robot recognizes the emotion from the user's facial expression and voice. The input is the user's facial expression data and voice data, and the output is analyzed emotion data. Specifically, the user's facial expression and voice are captured using a camera or microphone, and then analyzed using an emotion recognition algorithm.

[1766] Step 7: Adjust content based on emotions

[1767] The server receives the analysis results from the emotion engine and dynamically adjusts the display content and format of the trial calculation data according to the user's emotions. The inputs are emotion data and trial calculation data, and the output is the adjusted display of the trial calculation data. Specifically, if the user expresses dissatisfaction, the server makes adjustments such as displaying additional detailed explanations.

[1768] Step 8: Cloud Storage and Access Control

[1769] The server stores the generated trial calculation data and emotion data in cloud storage and performs access control in real time. The inputs are the trial calculation data and emotion data, and the output is the data stored on the cloud and the access permissions that are set. Specifically, the data is uploaded using a cloud API and access permissions are set for specific users.

[1770] Step 9: Storing and optimizing emotional data

[1771] The server stores the user's emotional data in the cloud, analyzes past emotional history, and optimizes the creation and provision of trial data. The inputs are emotional data and past emotional history, and the output is optimized trial data. Specifically, it uses an analytical algorithm to analyze past emotional data and propose future display content.

[1772] 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.

[1773] 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.

[1774] 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.

[1775] 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.

[1776] 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.

[1777] 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.

[1778] 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).

[1779] 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.

[1780] 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."

[1781] 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.

[1782] 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).

[1783] 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.

[1784] 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.

[1785] 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.

[1786] 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.

[1787] 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.

[1788] 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.

[1789] 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.

[1790] 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.

[1791] 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.

[1792] 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.

[1793] The following is further disclosed regarding the above embodiment.

[1794] (Claim 1)

[1795] a means of collecting data;

[1796] A means of classifying collected data by product type,

[1797] A means for analyzing common patterns from the classified data and generating summary data;

[1798] A means for generating automated estimates based on the analysis results;

[1799] A means for displaying the automatically generated trial calculation data on a terminal;

[1800] A means for storing the generated trial calculation data on the cloud and controlling access to it;

[1801] A system including:

[1802] (Claim 2)

[1803] 2. The system according to claim 1, further comprising means for the terminal to request data from the server, and for the server to return data for each product to the terminal in response to the request.

[1804] (Claim 3)

[1805] The system according to claim 1, further comprising means for setting access rights to the trial calculation data stored on the cloud and notifying specific users.

[1806] "Example 1"

[1807] (Claim 1)

[1808] A means of collecting information on business systems;

[1809] A means for categorizing the collected information by product group;

[1810] means for analyzing recurring patterns in the classified information and generating summary information;

[1811] A means for generating automatic calculations based on the analysis results;

[1812] A means for displaying the automatically generated calculation information on a terminal;

[1813] a means for storing the generated computational information in a cloud environment and for access management;

[1814] a means for analyzing information using machine learning algorithms to extract common patterns;

[1815] A means of automatically generating sales forecasts and cost calculations using robotics process automation technology;

[1816] A system including:

[1817] (Claim 2)

[1818] 2. The system of claim 1, further comprising means for the terminal to request information from the server, and for the server to return information by product group to the terminal in response to the request.

[1819] (Claim 3)

[1820] 10. The system of claim 1, further comprising means for setting and notifying specific users of access permissions for computational information stored in the cloud environment.

[1821] "Application Example 1"

[1822] (Claim 1)

[1823] a means of collecting data;

[1824] A means of categorizing the collected data by product category;

[1825] A means for analyzing common patterns from the classified data and generating summary data;

[1826] A means for generating automated estimates based on the analysis results;

[1827] A means for displaying the automatically generated trial calculation data on a terminal;

[1828] A means for storing the generated trial calculation data on the cloud and controlling access to it;

[1829] A means of collecting sales and inventory data from physical stores from POS systems;

[1830] A means for analyzing purchasing patterns based on the collected data using a machine learning algorithm to generate summary data;

[1831] A means for automatically generating sales forecasts and inventory replenishment plans based on the analysis results;

[1832] A means for displaying the generated sales forecast and inventory replenishment plan data on a terminal in real time;

[1833] A system including:

[1834] (Claim 2)

[1835] 2. The system of claim 1, further comprising means for the terminal to request data from the server, and for the server to return data by product category to the terminal in response to the request.

[1836] (Claim 3)

[1837] The system according to claim 1, further comprising means for setting access rights to the trial calculation data stored on the cloud and notifying specific users.

[1838] "Example 2: Combining Emotion Engines"

[1839] (Claim 1)

[1840] a means of collecting data;

[1841] A means of categorizing the collected data by product;

[1842] A means for analyzing common patterns from the classified data and generating summary data;

[1843] A means for generating automated estimates based on the analysis results;

[1844] A means for displaying the automatically generated trial calculation data on a terminal;

[1845] A means for storing the generated trial calculation data on the cloud and controlling access to it;

[1846] A means for recognizing a user's emotions and adjusting the display content and format of the estimated data;

[1847] A means for analyzing user emotion data and storing it in the cloud;

[1848] A system including:

[1849] (Claim 2)

[1850] 2. The system of claim 1, further comprising means for the terminal to request data from the server, and for the server to return product-specific data to the terminal in response to the request.

[1851] (Claim 3)

[1852] The system according to claim 1, further comprising means for setting access rights to the trial calculation data stored on the cloud and notifying specific users.

[1853] "Application example 2 when combining emotion engines"

[1854] (Claim 1)

[1855] a means of collecting data;

[1856] A means of classifying collected data by product type,

[1857] A means for analyzing common patterns from the classified data and generating summary data;

[1858] A means for generating automated estimates based on the analysis results;

[1859] A means for displaying the automatically generated trial calculation data on a terminal;

[1860] A means for storing the generated trial calculation data on the cloud and controlling access to it;

[1861] means for analyzing a user's emotion using emotion recognition means;

[1862] A means for adjusting the display content and format of the trial calculation data based on the user's emotions;

[1863] A system including:

[1864] (Claim 2)

[1865] The system of claim 1 further includes means for the terminal to request data from the server and for the server to return data for each product to the terminal in response to the request, and further includes emotion recognition means for measuring the user's emotions and dynamically adjusting the display content based on the emotions.

[1866] (Claim 3)

[1867] The system of claim 1 includes means for setting access permissions for the estimated data stored on the cloud and notifying specific users, and further stores the user's emotional history on the cloud and uses it to adjust future display content. [Explanation of symbols]

[1868] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting data; A means of classifying collected data by product type, A means for analyzing common patterns from the classified data and generating summary data; A means for generating automated estimates based on the analysis results; A means for displaying the automatically generated trial calculation data on a terminal; A means for storing the generated trial calculation data on the cloud and controlling access to it; A system including:

2. 2. The system according to claim 1, further comprising means for the terminal to request data from the server, and for the server to return data for each product to the terminal in response to the request.

3. The system according to claim 1, further comprising means for setting access rights to the trial calculation data stored on the cloud and notifying specific users of the access rights.

Images