system

Abstract

We provide the system. [Solution] A user input means for inputting store operation data, A server preprocessing means that preprocesses the data received from the user input means, An AI analysis means for analyzing the data preprocessed by the aforementioned preprocessing means, A data extraction means for extracting the analysis results of the aforementioned AI analysis means, A PPT generation means that generates a PPT file based on the extraction results of the data extraction means, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a modern business environment, a large amount of data related to store operations is generated. However, it is difficult to efficiently analyze such data and identify specific improvement points. In addition, in order to effectively present the analysis results, specialized knowledge and time are required, consuming a lot of resources. In such a situation, a system that can automatically extract improvement points of store operations and present them in a visually understandable form is desired.

Means for Solving the Problems

[0005] The present invention solves the above problems by the following means.

[0006] The system includes a user input means for inputting store operation data, a server pre-processing means for pre-processing the data received from the user input means, an AI analysis means for analyzing the data pre-processed by the pre-processing means, a data extraction means for extracting the analysis results of the AI ​​analysis means, and a PPT generation means for generating a PPT file based on the extraction results of the data extraction means.

[0007] The PPT generation means has the function of automatically generating slides using templates, and the AI ​​analysis means has the function of analyzing data using natural language processing models and machine learning models. This system allows users to easily identify areas for improvement in store operations and obtain materials for developing concrete action plans without requiring advanced expertise or a great deal of time.

[0008] "Store operation data" refers to various data related to store operations, such as sales, inventory, and customer feedback.

[0009] "User input means" refers to interfaces or devices that allow users to input store operation data into the system.

[0010] "Server preprocessing means" refers to a function within the server that cleans the data received from the user input means, and performs tasks such as imputing missing values ​​and standardizing the data.

[0011] "AI analysis methods" refer to artificial intelligence algorithms and machine learning models used to analyze pre-processed data.

[0012] "Data extraction means" refers to a function that organizes the analysis results of AI analysis means and extracts them according to a specific format.

[0013] "PPT generation method" refers to a function that automatically generates a PowerPoint presentation based on the extracted data.

[0014] "Template" refers to a predefined format or layout used by the PPT generation means when automatically generating slides.

[0015] "Natural language processing model" refers to an algorithm or tool for analyzing text data and extracting meaning and information from it.

[0016] "Machine learning model" refers to an algorithm that learns based on a dataset and performs prediction or classification.

[0017] "Visualization data" refers to data that visually displays analysis results in the form of graphs, charts, etc.

Brief Explanation of Drawings

[0018] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10]Shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0022] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] As shown in Figure 1, the 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.

[0029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0031] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0032] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0039] This document describes a specific example of a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. The system for implementing the present invention includes a user input means, a server pre-processing means, an AI analysis means, a data extraction means, and a PowerPoint generation means.

[0040] Overall system flow

[0041] User input means

[0042] The user input mechanism is an interface for users to provide store operation data to the system. Through this interface, users upload sales data, customer feedback, inventory data, and so on. This interface can be implemented, for example, as a web application or a mobile application.

[0043] Server Preprocessing Means

[0044] The server preprocessing mechanism has the function of preprocessing data received from the user input mechanism. Preprocessing includes imputing missing values, removing outliers, and standardizing data. For example, if there are missing values ​​in sales data, the server imputates the missing values ​​with the average value of past data. For outliers, statistical methods of data are used to identify the outliers, and the data is removed or corrected as necessary.

[0045] AI analysis means

[0046] AI analysis tools analyze pre-processed data. Natural language processing models and machine learning models are used for this analysis. The natural language processing model analyzes text data from customer feedback to extract specific keywords and trends. For example, it detects trends such as "slow service" and "high prices." The machine learning model performs time-series analysis of sales data to identify seasonality and trends. It also identifies the causes of sudden increases or decreases in sales.

[0047] Data extraction means

[0048] The data extraction tool has the function of extracting and organizing the analysis results of the AI ​​analysis tool. For example, it classifies the analysis results into categories such as "points for increasing sales," "areas for improvement in customer service," and "points for optimizing inventory management." Furthermore, it generates graphs and charts to visualize the data. For sales data, it creates line graphs and bar graphs, and for customer feedback, it generates pie charts showing the ratio of positive to negative feedback.

[0049] PPT generation means

[0050] The PPT generation means automatically generates a presentation in PowerPoint format based on the results obtained from the data extraction means. The slides are generated using pre-configured templates. The templates include title slides, various analysis result slides, proposal slides, etc. For example, the "Areas for Improvement in Customer Service" slide will contain the analysis results of customer feedback and related graphs, and the "Points for Increasing Sales" slide will contain sales data trends and their interpretations.

[0051] Specific examples

[0052] For example, suppose a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and fills in or corrects missing or outlier values. Next, an AI analysis tool analyzes the data, extracts trends in customer feedback such as "the service is slow" or "the price is high," and identifies seasonality and trends through time-series analysis of sales data. Subsequently, a data extraction tool organizes the analysis results and generates visualized data. Finally, a PPT generation tool creates a PPT file based on these results and makes it available for the user to download.

[0053] In this way, the system of the present invention can automatically extract points for improvement in store operations and generate materials that present concrete action plans simply by having the user input data. This enables the streamlining and optimization of store operations.

[0054] The following describes the processing flow.

[0055] Step 1:

[0056] Users upload store operation data to the system through an interface. The data, including sales data, customer feedback, and inventory data, is provided in CSV and Excel file formats.

[0057] Step 2:

[0058] The server receives data files uploaded by users. During this process, it also verifies the file format and performs security checks. For example, it checks if the file extension is CSV or XLSX and then performs a virus scan.

[0059] Step 3:

[0060] The server preprocesses the received data. Specifically, if missing values ​​exist, they are imputed using the mean or mode of past data. If outliers are detected, they are removed or corrected using statistical methods.

[0061] Step 4:

[0062] The server inputs pre-processed data into the AI ​​model. Natural language processing (NLP) and machine learning (ML) models are applied to store operation data. For example, the NLP model analyzes text data of customer feedback to extract specific trends and patterns. The ML model performs time-series analysis of sales data to identify seasonality and trends.

[0063] Step 5:

[0064] The server extracts the output results of the AI ​​model using data extraction methods. In this process, important analysis results are categorized into "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management." In addition, bar graphs, line graphs, pie charts, etc., are generated to visualize the analysis results.

[0065] Step 6:

[0066] The server uses a template to generate a PowerPoint file. Each slide in the PowerPoint file contains extracted data and visualizations. For example, "Areas for Improvement in Customer Service" displays customer feedback trends and related graphs, while "Points for Increasing Sales" includes sales data trend graphs and detailed analysis.

[0067] Step 7:

[0068] The server generates the final PPT file and saves it for the user to download. The file is either stored in cloud storage or provided directly to the user.

[0069] Step 8:

[0070] Users can download PowerPoint files from the system and use them as reference material to understand specific areas for improvement in store operations and to develop necessary action plans.

[0071] Through the above processing steps, this system enables users to efficiently analyze store operation data, identify areas for improvement, and generate effective presentation materials.

[0072] (Example 1)

[0073] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0074] Analyzing traditional store operation data, identifying areas for improvement, and compiling them into presentations was a manual process that required considerable effort and time. Furthermore, the accuracy of the analysis and the quality of the result visualization depended heavily on the skills of the person performing the analysis, leading to significant inconsistencies. This resulted in a challenge in achieving sufficient efficiency and optimization of store operations.

[0075] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0076] In this invention, the server includes a user input means for inputting store operation data, a data processing means for pre-processing the data received from the user input means, an artificial intelligence analysis means for analyzing the data pre-processed by the data processing means, a data extraction means for extracting, organizing, and visualizing the analysis results of the artificial intelligence analysis means, a generation means for automatically generating a presentation in PowerPoint format based on the organized and visualized results of the data extraction means, and a means for enabling the user to download the PowerPoint file generated by the generation means. This makes it possible to automatically extract points for improvement in store operations and generate high-quality presentation materials in a short time simply by having the user input data.

[0077] A "user input method" is an interface for users to provide store operation data to the system. Sales data, customer feedback, inventory data, etc., can be uploaded via a web application or mobile application.

[0078] A "data processing device" is a device that has the function of pre-processing data received from a user input device. By imputing missing values, removing outliers, and standardizing the data, it prepares the data to facilitate subsequent analysis.

[0079] "Artificial intelligence analysis tools" are used to analyze pre-processed data. Specifically, they use natural language processing models and machine learning models to extract trends in customer feedback and time-series patterns in sales data.

[0080] A "data extraction tool" is a device that extracts, organizes, and visualizes the results analyzed by an artificial intelligence analysis tool. It classifies the analysis results into categories and generates visual data such as line graphs and pie charts.

[0081] The "generation means" is a system that automatically generates PowerPoint presentations based on the organized and visualized data obtained from the data extraction means. It creates slides using templates and generates high-quality presentation materials.

[0082] The "download method" refers to a function that prepares the generated PPT file for the user to download. It sends a notification to the user, ensuring they can handle the file conveniently.

[0083] This invention is a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. The system includes user input means, data processing means, artificial intelligence analysis means, data extraction means, generation means, and download means.

[0084] User input means

[0085] The user input mechanism is an interface for users to provide store operation data to the system. Through this interface, users can upload data files such as:

[0086] Sales data (e.g., sales_data.csv)

[0087] Customer feedback (e.g., customer_feedback.xlsx)

[0088] Inventory data (e.g., inventory_data.csv)

[0089] The interface will be implemented as a web application or a mobile application.

[0090] Data processing means

[0091] The server preprocesses the data received from the user input. Specifically, it performs the following processing:

[0092] Imputation of missing values: If there are missing values ​​in the sales data, they will be imputed using the average value of past data.

[0093] Removing outliers: Using statistical methods to identify outliers in data and then removing or correcting them.

[0094] Data standardization: Converting data into a unified format.

[0095] Artificial intelligence analysis methods

[0096] The artificial intelligence analysis tools implemented on the server analyze the data in the following way:

[0097] Using natural language processing (NLP) models, we extract specific keywords and trends from customer feedback text data. For example, we detect trends such as "slow service" or "high prices."

[0098] We use machine learning (ML) models to perform time-series analysis of sales data to identify seasonality and trends. We also identify the causes of sudden increases and decreases in sales.

[0099] Data extraction means

[0100] The server extracts, organizes, and visualizes the analysis results of the artificial intelligence analysis tools as follows:

[0101] Category classification: Classified into categories such as "Points for increasing sales," "Points for improving customer service," and "Points for optimizing inventory management."

[0102] Graph generation: Generates line graphs, bar graphs, pie charts, etc., to visualize data.

[0103] generation means

[0104] The server automatically generates a PowerPoint presentation based on the organized and visualized data obtained from the data extraction method. Using a template, it creates slides like the following:

[0105] Title slide

[0106] Slides showing various analysis results

[0107] Proposal slides

[0108] For example, a slide titled "Areas for Improvement in Customer Service" would include graphs related to the analysis of customer feedback, while a slide titled "Key Points for Increasing Sales" would include sales data trends and their interpretations.

[0109] Download method

[0110] The server prepares the generated PPT file for the user to download and sends a notification. After receiving the notification, the user can download the generated presentation via the web application or mobile application.

[0111] Specific example

[0112] For example, if a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" via a web interface, the server receives this data and performs imputation of missing values ​​and correction of outliers. Next, an artificial intelligence analysis tool analyzes the data, extracts trends in customer feedback such as "slow service" and "high prices", and identifies seasonality and trends through time-series analysis of sales data. Subsequently, a data extraction tool organizes the analysis results and generates visualized data. Finally, a generation tool creates a PowerPoint file based on these results and makes it available for the user to download.

[0113] An example of a prompt message is: "Analyze the pre-processed sales data and customer feedback to identify areas for improvement in store operations, and then compile them into a PowerPoint presentation."

[0114] This system allows users to automatically extract areas for improvement in store operations simply by inputting data, and generate high-quality presentation materials in a short amount of time.

[0115] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0116] Step 1: User Input

[0117] Users provide store operation data, such as sales data, customer feedback, and inventory data, to the system via a web or mobile application. Specifically, users upload files such as "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" to the interface. The device receives these files and sends them to the server.

[0118] Input files: SalesData.csv, CustomerFeedback.xlsx, InventoryData.csv

[0119] Output: Data file sent to the server

[0120] Step 2: Data reception and preprocessing

[0121] The server receives data files sent by the user. The received data undergoes the following preprocessing:

[0122] Imputation of missing values: If there are missing values ​​in the sales data, the server will imputate them using the average value of past data.

[0123] Removing outliers: Use statistical methods to identify outliers in the data and remove or correct them as needed.

[0124] Data standardization: Converting data in different formats into a unified format.

[0125] Input: Sales data received from users.csv, Customer feedback.xlsx, Inventory data.csv

[0126] Output: Pre-processed sales data, customer feedback, inventory data

[0127] Step 3: Data Analysis

[0128] The artificial intelligence analysis tools implemented on the server analyze the pre-processed data. The following analysis is performed:

[0129] Using natural language processing (NLP) models, we extract specific keywords and trends from customer feedback text data. For example, we detect trends such as "slow service" and "high prices."

[0130] We use machine learning (ML) models to perform time-series analysis of sales data to identify seasonality and trends. We also identify the causes of increases and decreases in sales.

[0131] Input: Pre-processed sales data, customer feedback, inventory data

[0132] Output: Trends in analyzed sales data, trends in customer feedback

[0133] Step 4: Data Extraction and Visualization

[0134] The server extracts the analysis results from the artificial intelligence analysis tools and organizes them as follows:

[0135] Category classification: Classified into categories such as "Points for increasing sales," "Points for improving customer service," and "Points for optimizing inventory management."

[0136] Visualization: Graph the analysis results. For sales data, create line graphs or bar graphs; for customer feedback, create pie charts.

[0137] Input: Trends in analyzed sales data, trends in customer feedback

[0138] Output: Organized and visualized data (line graphs, bar graphs, pie charts)

[0139] Step 5: Generate PowerPoint

[0140] The server automatically generates a PowerPoint presentation based on the organized and visualized data obtained from the data extraction method. The following template is used to create the slides:

[0141] Title slide

[0142] Slides showing various analysis results

[0143] Proposal slides

[0144] For example, a slide titled "Areas for Improvement in Customer Service" would include graphs related to the analysis of customer feedback, while a slide titled "Key Points for Increasing Sales" would include sales data trends and their interpretations.

[0145] Input: Organized and visualized data

[0146] Output: Generated PPT file

[0147] Step 6: Download preparation and notification

[0148] The server prepares the generated PPT file for the user to download and sends a notification. The user receives the notification and can download the generated presentation via the web application or mobile application.

[0149] Input: Generated PPT file

[0150] Output: Downloadable PPT file, notification to the user

[0151] In this way, the system can automatically extract points for improvement in store operations and generate high-quality presentation materials in a short time, simply by the user inputting data.

[0152] (Application Example 1)

[0153] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0154] In store operations, there is a need to efficiently analyze large amounts of data and quickly identify areas for improvement. However, current systems have cumbersome data preprocessing and analysis methods, and there is a lack of means to provide the results to store managers and staff in a quick and easy-to-understand format. As a result, there is a challenge in that real-time response and improvement are difficult.

[0155] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0156] In this invention, the server includes a user input means for inputting store operation data, a server pre-processing means for pre-processing the data received from the user input means, an AI analysis means for analyzing the data pre-processed by the pre-processing means, a data extraction means for extracting the analysis results of the AI ​​analysis means, a PPT generation means for generating a PPT file based on the extraction results of the data extraction means, and a notification means for notifying smart glasses of the PPT file in real time. This enables store operators and staff to check areas for improvement in operations in real time during their daily work and respond quickly and effectively.

[0157] A "user input method" is an interface for providing store operation data to the system.

[0158] "Server preprocessing means" refers to a server component that has the function of preprocessing data received from user input means.

[0159] "AI analysis methods" refer to methods that use artificial intelligence technology to analyze pre-processed data and derive analysis results.

[0160] A "data extraction means" is a means that has the function of extracting and organizing the analysis results obtained by the AI ​​analysis means.

[0161] A "PPT generation means" is a means for automatically generating a PowerPoint (presentation) file based on data obtained from a data extraction means.

[0162] A "notification method" is a means that has the function of notifying store operators and staff of the generated PPT file in real time using their smart glasses.

[0163] The system for implementing the present invention automates a series of steps, including inputting and analyzing store operation data, extracting areas for improvement, and generating a presentation file. The system includes the following means:

[0164] 1. User Input Method: This is an interface for users to provide store operation data to the system. It is implemented as a web application or mobile application and allows users to upload sales data, customer feedback, inventory data, etc.

[0165] 2. Server preprocessing means: This means that the server has the function of preprocessing the data received from the user input means. Preprocessing includes imputing missing values, removing outliers, and standardizing the data. Specifically, it reads the data using the pandas library, imputes missing values ​​using sklearn.impute.SimpleImputer, and removes outliers.

[0166] 3. AI Analysis Methods: Pre-processed data is analyzed. Natural language processing models (using the transformers library) and machine learning models (using RandomForestRegressor) are used for the analysis. The natural language processing model analyzes text data of customer feedback and extracts specific keywords and trends. The machine learning model performs time-series analysis of sales data to identify seasonality and trends.

[0167] 4. Data Extraction Method: This method has the function of extracting and organizing the analysis results of the AI ​​analysis method. Specifically, it classifies the data into points for increasing sales, points for improving customer service, points for optimizing inventory management, etc., and generates graphs and charts for visualization.

[0168] 5. PPT Generation Method: Based on the results obtained from the data extraction method, a presentation in PowerPoint format is automatically generated. This uses the python-pptx library. The slides are generated using a pre-configured template and include a title slide, various analysis result slides, proposal slides, etc.

[0169] 6. Notification Method: The generated PPT file will be sent in real time to the smart glasses of store operators and staff. This will allow them to check for areas for improvement in operations in real time during their daily work and take quick action.

[0170] Specific example

[0171] For example, suppose a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and uses pandas and scikit-learn to impute and correct missing values ​​and outliers. Next, it analyzes the data using the transformers library and RandomForestRegressor to extract trends in customer feedback such as "slow service" or "high prices", and performs time-series analysis of the sales data. After that, it visualizes the analysis results in graphs and charts using pyplot and generates a PowerPoint file using python-pptx. Finally, this PowerPoint file is displayed in real time on smart glasses.

[0172] Example of a prompt

[0173] "Based on customer feedback text data from the first quarter of 2023, please identify the main customer complaints and areas for improvement."

[0174] "Use the sales data from the first quarter of 2023 to generate a sales forecast for the next quarter."

[0175] This system enables store operators and staff to efficiently analyze store operation data, quickly identify areas for improvement, and take action.

[0176] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0177] Step 1:

[0178] Users upload store operation data (e.g., sales data.csv, customer feedback.xlsx, inventory data.csv) through user input methods. This allows users to provide the necessary data to the system.

[0179] Step 2:

[0180] The server preprocesses the data received from the user input using its own preprocessing mechanism. This preprocessing involves reading the data using pandas, imputing missing values ​​(sklearn.impute.SimpleImputer), and removing outliers (interquartile range method). This results in clean data.

[0181] Step 3:

[0182] The server analyzes pre-processed data using AI analysis tools. Specifically, it uses the transformers library for natural language processing to extract keywords and trends from customer feedback. It also performs time-series analysis of sales data using a machine learning model (RandomForestRegressor). This allows for the identification of customer dissatisfactions and sales predictions.

[0183] Step 4:

[0184] The server extracts and organizes the analysis results from the AI ​​analysis using data extraction tools. The results are categorized into "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management," and graphs and charts are generated using pyplot for visualization. This results in data that is easy to understand visually.

[0185] Step 5:

[0186] The server generates a PowerPoint presentation file based on the data obtained from the data extraction means using a PowerPoint generation means. Using the python-pptx library, slides are automatically created according to a pre-prepared template. This provides a PowerPoint file that the user can use immediately.

[0187] Step 6:

[0188] The server uses a notification system to send generated PowerPoint files to the smart glasses of store operators and staff in real time. This allows users to check for operational improvements in real time during their daily work and take quick action.

[0189] By executing each step in this order, efficient analysis of store operation data and rapid improvement can be achieved.

[0190] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0191] This invention relates to a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. Furthermore, it aims to improve the user experience by combining it with an emotion engine that recognizes user emotions. The system for carrying out this invention includes a user input means, a server pre-processing means, an AI analysis means, a data extraction means, a PowerPoint generation means, and an emotion engine.

[0192] Overall system flow

[0193] User input means

[0194] The user input mechanism is an interface for users to provide store operation data to the system. Through this interface, users upload sales data, customer feedback, inventory data, and so on. This interface can be implemented, for example, as a web application or mobile application. It may also include voice recognition devices and cameras for inputting the user's voice and facial expressions.

[0195] Server Preprocessing Means

[0196] The server preprocessing mechanism has the function of preprocessing data received from the user input mechanism. Preprocessing includes imputing missing values, removing outliers, and standardizing data. For example, if there are missing values ​​in sales data, the server imputates the missing values ​​with the average value of past data. For outliers, statistical methods of data are used to identify the outliers, and the data is removed or corrected as necessary.

[0197] AI analysis means

[0198] AI analysis tools analyze pre-processed data. Natural language processing models and machine learning models are used for this analysis. The natural language processing model analyzes text data from customer feedback to extract specific keywords and trends. For example, it detects trends such as "slow service" and "high prices." The machine learning model performs time-series analysis of sales data to identify seasonality and trends. It also identifies the causes of sudden increases or decreases in sales.

[0199] Data extraction means

[0200] The data extraction tool has the function of extracting and organizing the analysis results of the AI ​​analysis tool. For example, it classifies the analysis results into categories such as "points for increasing sales," "areas for improvement in customer service," and "points for optimizing inventory management." Furthermore, it generates graphs and charts to visualize the data. For sales data, it creates line graphs and bar graphs, and for customer feedback, it generates pie charts showing the ratio of positive to negative feedback.

[0201] PPT generation means

[0202] The PPT generation means automatically generates a presentation in PowerPoint format based on the results obtained from the data extraction means. The slides are generated using pre-configured templates. The templates include title slides, various analysis result slides, proposal slides, etc. For example, the "Areas for Improvement in Customer Service" slide will contain the analysis results of customer feedback and related graphs, and the "Points for Increasing Sales" slide will contain sales data trends and their interpretations.

[0203] Emotional Engine

[0204] The emotion engine has the ability to analyze emotions from the user's voice and facial expressions. For example, it analyzes the tone of voice and facial expressions while the user is using the interface to understand the user's emotional state. Voice analysis and facial expression analysis are used for emotion recognition.

[0205] Furthermore, based on the analysis results of the emotion engine, it suggests recommended actions to improve the user experience. For example, if a user is experiencing stress, it provides simpler instructions or support information. Conversely, if a user is satisfied, it presents additional suggestions or promotional information.

[0206] Specific examples

[0207] For example, suppose a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and fills in or corrects missing or outlier values. Next, an AI analysis tool analyzes the data, extracts trends in customer feedback such as "slow service" and "high prices", and identifies seasonality and trends through time-series analysis of sales data. Subsequently, a data extraction tool organizes the analysis results and generates visualized data. Finally, a PPT generation tool creates a PPT file based on these results and makes it available for the user to download.

[0208] Furthermore, if the emotion engine analyzes that a user is experiencing stress while entering data, the system will provide the user with simple instructions and help information. On the other hand, if the system perceives that the user is satisfied, it will suggest additional features or relevant promotional information.

[0209] In this way, the system of the present invention can automatically extract points for improvement in store operations and generate materials that present concrete action plans simply by the user inputting data, and can also provide a better user experience by providing support that responds to the user's emotional state.

[0210] The following describes the processing flow.

[0211] Step 1:

[0212] Users upload store operation data to the system through an interface. The data, including sales data, customer feedback, and inventory data, is provided in CSV and Excel file formats. User voice data and facial expression data are also collected.

[0213] Step 2:

[0214] The server receives data files uploaded by users. During this process, it verifies the file format and performs security checks. It confirms that the file extension is CSV or XLSX and then performs a virus scan.

[0215] Step 3:

[0216] The server preprocesses the received data. Specifically, if missing values ​​exist, they are imputed using the mean or mode of past data. If outliers are detected, they are removed or corrected using statistical methods. In addition, the data is standardized to unify all data formats.

[0217] Step 4:

[0218] The server inputs pre-processed data into an AI model. Using a natural language processing model, it analyzes the text data of customer feedback and extracts specific keywords and trends. For example, it detects trends such as "slow service" and "high prices."

[0219] Step 5:

[0220] The server uses a machine learning model to perform time-series analysis of sales data. It identifies seasonality and trends from the data and pinpoints the causes of sudden increases or decreases in sales. Specifically, if a particular event was held on a day when sales surged, it extracts that information.

[0221] Step 6:

[0222] The server extracts the output results of the AI ​​model using data extraction methods. In this process, the analysis results are categorized into areas such as "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management." In addition, bar graphs, line graphs, pie charts, etc., are generated to visualize the analysis results.

[0223] Step 7:

[0224] The server generates the PPT file using a template. First, a title slide is created, followed by slides containing various analysis results and proposals. The "Areas for Improvement in Customer Service" slide contains analysis results of customer feedback and related graphs. The "Points for Increasing Sales" slide contains sales data trends and their interpretation.

[0225] Step 8:

[0226] The server uses an emotion engine to analyze the user's emotions. Based on the voice and facial expression data provided by the user during data entry, it performs speech recognition and facial expression analysis to identify the user's emotional state. For example, if the user is feeling stressed, that information is analyzed.

[0227] Step 9:

[0228] The server suggests actions to improve the user experience based on the analysis results of the emotion engine. If the user is experiencing stress, it provides simple instructions and help information. If the user is satisfied, it suggests additional features and relevant promotional information.

[0229] Step 10:

[0230] The server generates the final PPT file and saves it for the user to download. The file is either stored in cloud storage or provided directly to the user.

[0231] Step 11:

[0232] Users download PowerPoint files from the system and use them as reference material to understand specific areas for improvement in store operations and to develop necessary action plans.

[0233] Through the above processing steps, this system enables users to efficiently analyze store operation data, identify areas for improvement, and generate effective presentation materials. Furthermore, by providing support that responds to the user's emotional state, it can deliver an excellent user experience.

[0234] (Example 2)

[0235] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0236] Current store operations require a significant amount of time and effort to manually analyze large amounts of data, identify areas for improvement, and compile them into presentations. Furthermore, the emotional state of users when using the system is not considered, which can lead to stress. Therefore, there is a need for a system that efficiently and automatically analyzes store operation data, identifies areas for improvement, and provides support tailored to the emotional state of users.

[0237] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for inputting store operation data, a preprocessing means for preprocessing the data received from the input means, an analysis means for analyzing the data preprocessed by the preprocessing means, an extraction means for extracting the analysis results of the analysis means, a generation means for generating a presentation file based on the extraction results of the extraction means, and an emotion analysis means for recognizing the user's emotions. This enables efficient analysis of store operation data, extraction of areas for improvement, automatic generation of presentations, and support tailored to the user's emotional state.

[0238] "Store operation data" refers to all data related to store operations, such as sales data, customer feedback, and inventory data.

[0239] An "input method" is an interface for users to provide store operation data to the system, and is implemented as a web application or mobile application.

[0240] "Preprocessing means" refers to means of performing preprocessing on data received from input means, such as imputing missing values, removing outliers, and standardizing data.

[0241] "Analysis means" refers to means that include natural language processing models that analyze pre-processed data and extract specific keywords or trends, and machine learning models that perform time-series analysis of sales data.

[0242] "Extraction means" refers to means for extracting and organizing the analysis results of the analysis means, and includes category classification and the generation of graphs and charts for visualization.

[0243] The "generation means" refers to a means for automatically generating presentation files based on the results obtained from the extraction means, and has the function of automatically generating slides using templates.

[0244] "Emotional analysis methods" are means of analyzing a user's emotions from their voice and facial expressions, and then providing appropriate support and suggestions to improve the user experience based on the results.

[0245] This invention relates to a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a presentation file. Furthermore, it aims to provide a better user experience by combining it with an emotion engine that analyzes user emotions.

[0246] This system includes input means, preprocessing means, analysis means, extraction means, generation means, and sentiment analysis means. The specific implementation methods for each means are described below.

[0247] Input means

[0248] Users provide store operation data to the system using a web application or mobile application. This interface is implemented as a web application built with React or Vue.js, or as a mobile application developed with Flutter® or Kotlin. In addition, the system inputs the user's voice and facial expressions using a voice recognition device (e.g., a speech recognition device) or a camera.

[0249] Pretreatment means

[0250] The server preprocesses the data received from user input. Specifically, it uses Python and the Pandas library to read the data, impute missing values, remove outliers, and standardize the data. For example, missing values ​​are imputed with the mean of past data, and outliers are detected using Z-scores and corrected as needed.

[0251] Analysis means

[0252] The server analyzes pre-processed data using AI models. Text data from customer feedback is analyzed using natural language processing models (e.g., BERT model) to extract specific keywords and trends. Time series analysis of sales data uses machine learning models (e.g., Prophet model) to identify trends and seasonality.

[0253] extraction means

[0254] The server extracts and organizes the results of the analysis. Specifically, it categorizes the analysis results into categories such as "points for increasing sales" and "areas for improvement in customer service," and generates graphs and charts for visualization. Data visualization libraries such as Matplotlib and Seaborn are used for this task.

[0255] generation means

[0256] The server automatically generates presentation files based on the data obtained from the extraction method. The generation uses the Python python-pptx library, arranging the analysis results and visualizations into a pre-configured template. For example, the "Improvements in Customer Service" slide would include visualized customer feedback data and related suggestions.

[0257] Emotion analysis means

[0258] The server analyzes the user's emotions from their voice and facial expressions. It uses a speech analysis API for speech recognition and OpenCV for facial expression recognition. Based on the results of the emotion analysis, if the user is feeling stressed, it will provide simple instructions or help information; if the user is satisfied, it will display additional suggestions or promotional information.

[0259] Specific examples

[0260] For example, a user uploads files such as "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and imputes and corrects missing or outlier values. Next, an AI model is used to analyze the data, extracting trends in customer feedback such as "slow service" and "high prices," and identifying trends through time-series analysis of sales data. After that, the analysis results are organized and visualized data is generated. Finally, a presentation file is automatically generated and made available for the user to download.

[0261] Furthermore, if the sentiment analysis engine determines that the user is experiencing stress during user data entry, the system will provide the user with easy-to-follow instructions and help information. On the other hand, if the system recognizes that the user is satisfied, it will suggest additional features or relevant promotional information.

[0262] This system allows users to easily input data, automatically extract areas for improvement in store operations, and generate materials that present concrete action plans. Furthermore, by providing support tailored to the user's emotional state, it can deliver an excellent user experience.

[0263] Example of a prompt

[0264] Based on sales data, customer feedback, and inventory data, identify areas for improvement in store operations and generate a PowerPoint presentation. The data should also include trends in customer feedback such as "slow service" and "high prices." Furthermore, conduct user sentiment analysis to provide appropriate support.

[0265] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0266] Step 1:

[0267] The user opens the web or mobile application. The user selects sales data, customer feedback, and inventory data files and uploads them to the interface. For example, the user selects "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" and clicks the upload button. The input is a store operation data file, and the output is the upload of data into the system.

[0268] Step 2:

[0269] The server receives the uploaded data and stores it in temporary storage. For example, these files are stored using a cloud storage service (e.g., an AWS® S3 bucket). The input is the data file uploaded by the user, and the output is the temporary file stored on the server.

[0270] Step 3:

[0271] The server preprocesses the stored data. It uses Python and the Pandas library to read CSV and Excel files. The `fillna` method is used for missing value imputation, and Z-scores are used for anomaly detection. The input is a raw data file on the server, and the output is a preprocessed dataset.

[0272] Step 4:

[0273] The server analyzes pre-processed data using an AI model. Customer feedback text data is analyzed using a natural language processing model (e.g., BERT model) to extract trends and keywords. For time-series analysis of sales data, a machine learning model (e.g., Prophet model) is used to identify trends and seasonality. The input is pre-processed data, and the output is the analysis result.

[0274] Step 5:

[0275] The server extracts and organizes the results of the analysis. Specifically, it uses Matplotlib and Seaborn to visualize the analysis results and create graphs and charts. The analysis results are categorized into categories such as "points for increasing sales" and "areas for improvement in customer service." The input is the analysis results, and the output is the visualized data and the categorized results.

[0276] Step 6:

[0277] The server generates a presentation file based on the visualized data. Using the python-pptx library, slides are automatically created according to a pre-configured template. For example, the "Customer Service Improvements" slide will include a pie chart of customer feedback data and related suggestions. The input is the visualized data and classification results, and the output is a presentation file in PowerPoint format.

[0278] Step 7:

[0279] The server saves the generated presentation file and provides the user with a download link. Alternatively, the PPT file can be saved to a cloud storage service (e.g., an AWS S3 bucket), and the download link can be emailed to the user or displayed on a web application. The input is the generated presentation file, and the output is the download link to the user.

[0280] Step 8:

[0281] The server analyzes the emotion from the user's voice and expression. For voice recognition, an API for voice analysis (e.g., Google (registered trademark) Speech-to-Text) is used, and for expression recognition, OpenCV is used. Analyze the emotional state such as stress and satisfaction, and provide appropriate support information according to the result. The input is the user's voice and expression data, and the output is the emotion analysis result and the provided support information.

[0282] (Application Example 2)

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

[0284] Conventionally, analyzing store operation data and extracting improvement points have taken a huge amount of time and effort, and it has also been troublesome to create presentation materials to effectively utilize the analysis results. Furthermore, it has been impossible to grasp the user's emotion, and there has been a limit to improving the user experience. Therefore, it has been desired to provide a system that simultaneously realizes the efficiency improvement of store operation and the improvement of the user experience.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0286] In this invention, the server includes a user input means for inputting store operation data, a server preprocessing means for preprocessing the data received from the user input means, an AI analysis means for analyzing the data preprocessed by the preprocessing means, a data extraction means for extracting the analysis results of the AI analysis means, a PPT generation means for generating a PPT file based on the extraction results of the data extraction means, and an emotion engine for recognizing the user's emotion and presenting recommended actions for improving the user experience. As a result, it is possible to consistently perform from extracting improvement points from the analysis of store operation data to automatically generating presentation materials, and to provide support that reflects the user's emotion.

[0287] The "user input means" is an interface for the user to provide store operation data to the system, and has a function of uploading sales data, customer feedback, inventory data, etc. through a web application or a mobile application.

[0288] The "server preprocessing means" has a function of preprocessing the data received from the user input means, and performs functions such as complementing missing values, removing outliers, and normalizing data.

[0289] The "AI analysis means" analyzes the preprocessed data, extracts specific keywords and trends using a natural language processing model or a machine learning model, and has a function of performing time series analysis of sales data.

[0290] The "data extraction means" extracts the analysis results of the AI analysis means, classifies them into categories such as points for increasing sales, improvement points for customer service, and optimization points for inventory management, and further has a function of generating graphs and charts for visualizing the data.

[0291] The "PPT generation means" has a function of automatically generating a PPT-formatted presentation based on the results obtained from the data extraction means, and creates slides using a preset template.

[0292] An "emotion engine" is a system that analyzes a user's emotions from their voice and facial expressions and suggests recommended actions to improve the user experience. It uses voice analysis and facial expression analysis to understand the user's emotional state.

[0293] This invention is a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. The system includes a user input means, a server pre-processing means, an AI analysis means, a data extraction means, a PowerPoint generation means, and an emotion engine.

[0294] system

[0295] 1. User input means

[0296] The user input mechanism is an interface for users to provide store operation data to the system. Specifically, users upload sales data, customer feedback, inventory data, etc., using smartphones or personal computers. This interface is implemented as a web application or mobile application. It also includes voice recognition devices and cameras to capture the user's voice and facial expressions from resources.

[0297] 2. Server preprocessing means

[0298] The server preprocessing mechanism has the function of preprocessing data received from the user input mechanism. Preprocessing includes imputing missing values, removing outliers, and standardizing data. Specifically, if sales data contains missing values, the server imputates them with the average value of past data. For outliers, statistical methods are used to identify them, and the data is removed or corrected as necessary.

[0299] 3. AI analysis means

[0300] The AI ​​analysis tool has the ability to analyze pre-processed data. This analysis utilizes natural language processing models and machine learning models. The natural language processing model analyzes text data from customer feedback to extract specific keywords and trends. For example, it detects trends such as "slow service" and "high prices." The machine learning model performs time-series analysis of sales data to identify seasonality and trends. It also identifies the causes of sudden increases or decreases in sales.

[0301] 4. Data extraction means

[0302] The data extraction mechanism extracts and organizes the analysis results from the AI ​​analysis mechanism. This mechanism categorizes the analysis results into categories such as "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management." Furthermore, it generates graphs and charts to visualize the data. For sales data, it creates time-series graphs and bar graphs, and for customer feedback, it generates pie charts showing the ratio of negative to positive feedback.

[0303] 5. PPT generation means

[0304] The PPT generation means automatically generates a presentation in PowerPoint format based on the results obtained from the data extraction means. These slides are generated using a pre-configured template. The template includes a title slide, various analysis results slides, and proposal slides. For example, the "Areas for Improvement in Customer Service" slide contains the analysis results of customer feedback and related graphs, and the "Points for Increasing Sales" slide contains sales data trends and their interpretation.

[0305] 6. Emotional Engine

[0306] The emotion engine has the function of analyzing emotions from the user's voice and expressions. It uses voice analysis and facial expression analysis to grasp the user's emotional state. Based on the analysis results of the emotion engine, it presents recommended actions to improve the user experience. For example, when the user is feeling stressed, it provides easier operation methods and support information. Conversely, when the user is satisfied, it presents additional suggestions and promotion information.

[0307] Specific example

[0308] Example of prompt sentence

[0309] Suppose the user uploads "Sales data for the first quarter of 2023.csv", "Customer feedback.xlsx", and "Inventory data.csv" through the interface. The server receives these data and complements and corrects missing values and outliers. Next, the AI analysis means analyzes the data, extracts trends in customer feedback such as "The service is slow" and "The price is high", and identifies seasonality and trends through time series analysis of the sales data. Then, the data extraction means organizes the analysis results and generates visualized data. Finally, the PPT generation means creates a PPT file based on these results and makes it available for the user to download.

[0310] Also, when the emotion engine analyzes that the user is feeling stressed during data input, the system provides the user with easier operation methods and help information. On the other hand, when the system recognizes that the user is satisfied, it presents additional function suggestions and relevant promotion information. In this way, the system of the present invention can automatically extract improvement points for store operations and generate materials presenting specific action plans simply by the user inputting data, and can provide a better user experience by providing support corresponding to the user's emotional state.

[0311] The flow of the specific process in Application Example 2 will be described using FIG. 14.

[0312] Step 1: Users upload sales data, customer feedback, and inventory data to the system interface using their smartphones or personal computers.

[0313] Inputs: Sales data, customer feedback, inventory data

[0314] Output: Various data files sent to the server

[0315] Step 2: The server preprocessing device preprocesses the received data. Specifically, it imputes missing values ​​with the mean and identifies and removes outliers using statistical methods.

[0316] Input: Various data files sent to the server

[0317] Output: Preprocessed data with missing values ​​imputed and outliers removed.

[0318] Step 3: The server's AI analysis tools analyze the pre-processed data. A natural language processing model analyzes the text data of customer feedback, extracting specific keywords and trends. In addition, a machine learning model is used to perform time-series analysis of sales data to identify seasonality, trends, and the causes of sudden increases or decreases in sales.

[0319] Input: Preprocessed data

[0320] Output: Analysis results (keywords, trends, time series analysis results, etc.)

[0321] Step 4: The server's data extraction tool extracts the analysis results from the AI ​​analysis tool and categorizes them into points for increasing sales, areas for improving customer service, and points for optimizing inventory management. It also generates graphs and charts to visualize the data.

[0322] Input: Analysis results

[0323] Output: Classified analysis results, visualized graphs and charts

[0324] Step 5: The server's PPT generation means automatically generates a PPT file using a pre-configured template based on the results obtained from the data extraction means.

[0325] Input: Classified analysis results, visualized graphs and charts

[0326] Output: Presentation file in PPT format

[0327] Step 6: The emotion engine analyzes the voice and facial expressions of the user using the interface. It uses voice analysis and facial expression analysis to understand the user's emotional state.

[0328] Input: User voice data, facial expression data

[0329] Output: User's emotional state

[0330] Step 7: The server's emotion engine suggests actions based on the user's emotional state. For example, if the user is stressed, it provides simple instructions or help information; if the user is satisfied, it provides additional suggestions or promotional information.

[0331] Input: User's emotional state

[0332] Output: Recommended actions (simple instructions, help information, additional suggestions, promotional information, etc.)

[0333] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0334] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0335] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0336] [Second Embodiment]

[0337] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0338] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0339] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0340] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0341] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0342] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0343] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0344] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0345] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0346] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0347] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0348] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0349] This document describes a specific example of a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. The system for implementing the present invention includes a user input means, a server pre-processing means, an AI analysis means, a data extraction means, and a PowerPoint generation means.

[0350] Overall system flow

[0351] User input means

[0352] The user input mechanism is an interface for users to provide store operation data to the system. Through this interface, users upload sales data, customer feedback, inventory data, and so on. This interface can be implemented, for example, as a web application or a mobile application.

[0353] Server Preprocessing Means

[0354] The server preprocessing mechanism has the function of preprocessing data received from the user input mechanism. Preprocessing includes imputing missing values, removing outliers, and standardizing data. For example, if there are missing values ​​in sales data, the server imputates the missing values ​​with the average value of past data. For outliers, statistical methods of data are used to identify the outliers, and the data is removed or corrected as necessary.

[0355] AI analysis means

[0356] AI analysis tools analyze pre-processed data. Natural language processing models and machine learning models are used for this analysis. The natural language processing model analyzes text data from customer feedback to extract specific keywords and trends. For example, it detects trends such as "slow service" and "high prices." The machine learning model performs time-series analysis of sales data to identify seasonality and trends. It also identifies the causes of sudden increases or decreases in sales.

[0357] Data extraction means

[0358] The data extraction tool has the function of extracting and organizing the analysis results of the AI ​​analysis tool. For example, it classifies the analysis results into categories such as "points for increasing sales," "areas for improvement in customer service," and "points for optimizing inventory management." Furthermore, it generates graphs and charts to visualize the data. For sales data, it creates line graphs and bar graphs, and for customer feedback, it generates pie charts showing the ratio of positive to negative feedback.

[0359] PPT generation means

[0360] The PPT generation means automatically generates a presentation in PowerPoint format based on the results obtained from the data extraction means. The slides are generated using pre-configured templates. The templates include title slides, various analysis result slides, proposal slides, etc. For example, the "Areas for Improvement in Customer Service" slide will contain the analysis results of customer feedback and related graphs, and the "Points for Increasing Sales" slide will contain sales data trends and their interpretations.

[0361] Specific examples

[0362] For example, suppose a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and fills in or corrects missing or outlier values. Next, an AI analysis tool analyzes the data, extracts trends in customer feedback such as "the service is slow" or "the price is high," and identifies seasonality and trends through time-series analysis of sales data. Subsequently, a data extraction tool organizes the analysis results and generates visualized data. Finally, a PPT generation tool creates a PPT file based on these results and makes it available for the user to download.

[0363] In this way, the system of the present invention can automatically extract points for improvement in store operations and generate materials that present concrete action plans simply by having the user input data. This enables the streamlining and optimization of store operations.

[0364] The following describes the processing flow.

[0365] Step 1:

[0366] Users upload store operation data to the system through an interface. The data, including sales data, customer feedback, and inventory data, is provided in CSV and Excel file formats.

[0367] Step 2:

[0368] The server receives data files uploaded by users. During this process, it also verifies the file format and performs security checks. For example, it checks if the file extension is CSV or XLSX and then performs a virus scan.

[0369] Step 3:

[0370] The server preprocesses the received data. Specifically, if missing values ​​exist, they are imputed using the mean or mode of past data. If outliers are detected, they are removed or corrected using statistical methods.

[0371] Step 4:

[0372] The server inputs pre-processed data into the AI ​​model. Natural language processing (NLP) and machine learning (ML) models are applied to store operation data. For example, the NLP model analyzes text data of customer feedback to extract specific trends and patterns. The ML model performs time-series analysis of sales data to identify seasonality and trends.

[0373] Step 5:

[0374] The server extracts the output results of the AI ​​model using data extraction methods. In this process, important analysis results are categorized into "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management." In addition, bar graphs, line graphs, pie charts, etc., are generated to visualize the analysis results.

[0375] Step 6:

[0376] The server uses a template to generate a PowerPoint file. Each slide in the PowerPoint file contains extracted data and visualizations. For example, "Areas for Improvement in Customer Service" displays customer feedback trends and related graphs, while "Points for Increasing Sales" includes sales data trend graphs and detailed analysis.

[0377] Step 7:

[0378] The server generates the final PPT file and saves it for the user to download. The file is either stored in cloud storage or provided directly to the user.

[0379] Step 8:

[0380] Users can download PowerPoint files from the system and use them as reference material to understand specific areas for improvement in store operations and to develop necessary action plans.

[0381] Through the above processing steps, this system enables users to efficiently analyze store operation data, identify areas for improvement, and generate effective presentation materials.

[0382] (Example 1)

[0383] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0384] Analyzing traditional store operation data, identifying areas for improvement, and compiling them into presentations was a manual process that required considerable effort and time. Furthermore, the accuracy of the analysis and the quality of the result visualization depended heavily on the skills of the person performing the analysis, leading to significant inconsistencies. This resulted in a challenge in achieving sufficient efficiency and optimization of store operations.

[0385] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0386] In this invention, the server includes a user input means for inputting store operation data, a data processing means for pre-processing the data received from the user input means, an artificial intelligence analysis means for analyzing the data pre-processed by the data processing means, a data extraction means for extracting, organizing, and visualizing the analysis results of the artificial intelligence analysis means, a generation means for automatically generating a presentation in PowerPoint format based on the organized and visualized results of the data extraction means, and a means for enabling the user to download the PowerPoint file generated by the generation means. This makes it possible to automatically extract points for improvement in store operations and generate high-quality presentation materials in a short time simply by having the user input data.

[0387] A "user input method" is an interface for users to provide store operation data to the system. Sales data, customer feedback, inventory data, etc., can be uploaded via a web application or mobile application.

[0388] A "data processing device" is a device that has the function of pre-processing data received from a user input device. By imputing missing values, removing outliers, and standardizing the data, it prepares the data to facilitate subsequent analysis.

[0389] "Artificial intelligence analysis tools" are used to analyze pre-processed data. Specifically, they use natural language processing models and machine learning models to extract trends in customer feedback and time-series patterns in sales data.

[0390] A "data extraction tool" is a device that extracts, organizes, and visualizes the results analyzed by an artificial intelligence analysis tool. It classifies the analysis results into categories and generates visual data such as line graphs and pie charts.

[0391] The "generation means" is a system that automatically generates PowerPoint presentations based on the organized and visualized data obtained from the data extraction means. It creates slides using templates and generates high-quality presentation materials.

[0392] The "download method" refers to a function that prepares the generated PPT file for the user to download. It sends a notification to the user, ensuring they can handle the file conveniently.

[0393] This invention is a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. The system includes user input means, data processing means, artificial intelligence analysis means, data extraction means, generation means, and download means.

[0394] User input means

[0395] The user input mechanism is an interface for users to provide store operation data to the system. Through this interface, users can upload data files such as:

[0396] Sales data (e.g., sales_data.csv)

[0397] Customer feedback (e.g., customer_feedback.xlsx)

[0398] Inventory data (e.g., inventory_data.csv)

[0399] The interface will be implemented as a web application or a mobile application.

[0400] Data processing means

[0401] The server preprocesses the data received from the user input. Specifically, it performs the following processing:

[0402] Imputation of missing values: If there are missing values ​​in the sales data, they will be imputed using the average value of past data.

[0403] Removing outliers: Using statistical methods to identify outliers in data and then removing or correcting them.

[0404] Data standardization: Converting data into a unified format.

[0405] Artificial intelligence analysis methods

[0406] The artificial intelligence analysis tools implemented on the server analyze the data in the following way:

[0407] Using natural language processing (NLP) models, we extract specific keywords and trends from customer feedback text data. For example, we detect trends such as "slow service" or "high prices."

[0408] We use machine learning (ML) models to perform time-series analysis of sales data to identify seasonality and trends. We also identify the causes of sudden increases and decreases in sales.

[0409] Data extraction means

[0410] The server extracts, organizes, and visualizes the analysis results of the artificial intelligence analysis tools as follows:

[0411] Category classification: Classified into categories such as "Points for increasing sales," "Points for improving customer service," and "Points for optimizing inventory management."

[0412] Graph generation: Generates line graphs, bar graphs, pie charts, etc., to visualize data.

[0413] generation means

[0414] The server automatically generates a PowerPoint presentation based on the organized and visualized data obtained from the data extraction method. Using a template, it creates slides like the following:

[0415] Title slide

[0416] Slides showing various analysis results

[0417] Proposal slides

[0418] For example, a slide titled "Areas for Improvement in Customer Service" would include graphs related to the analysis of customer feedback, while a slide titled "Key Points for Increasing Sales" would include sales data trends and their interpretations.

[0419] Download method

[0420] The server prepares the generated PPT file for the user to download and sends a notification. After receiving the notification, the user can download the generated presentation via the web application or mobile application.

[0421] Specific example

[0422] For example, if a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" via a web interface, the server receives this data and performs imputation of missing values ​​and correction of outliers. Next, an artificial intelligence analysis tool analyzes the data, extracts trends in customer feedback such as "slow service" and "high prices", and identifies seasonality and trends through time-series analysis of sales data. Subsequently, a data extraction tool organizes the analysis results and generates visualized data. Finally, a generation tool creates a PowerPoint file based on these results and makes it available for the user to download.

[0423] An example of a prompt message is: "Analyze the pre-processed sales data and customer feedback to identify areas for improvement in store operations, and then compile them into a PowerPoint presentation."

[0424] This system allows users to automatically extract areas for improvement in store operations simply by inputting data, and generate high-quality presentation materials in a short amount of time.

[0425] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0426] Step 1: User Input

[0427] Users provide store operation data, such as sales data, customer feedback, and inventory data, to the system via a web or mobile application. Specifically, users upload files such as "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" to the interface. The device receives these files and sends them to the server.

[0428] Input files: SalesData.csv, CustomerFeedback.xlsx, InventoryData.csv

[0429] Output: Data file sent to the server

[0430] Step 2: Data reception and preprocessing

[0431] The server receives data files sent by the user. The received data undergoes the following preprocessing:

[0432] Imputation of missing values: If there are missing values ​​in the sales data, the server will imputate them using the average value of past data.

[0433] Removing outliers: Use statistical methods to identify outliers in the data and remove or correct them as needed.

[0434] Data standardization: Converting data in different formats into a unified format.

[0435] Input: Sales data received from users.csv, Customer feedback.xlsx, Inventory data.csv

[0436] Output: Pre-processed sales data, customer feedback, inventory data

[0437] Step 3: Data Analysis

[0438] The artificial intelligence analysis tools implemented on the server analyze the pre-processed data. The following analysis is performed:

[0439] Using natural language processing (NLP) models, we extract specific keywords and trends from customer feedback text data. For example, we detect trends such as "slow service" and "high prices."

[0440] We use machine learning (ML) models to perform time-series analysis of sales data to identify seasonality and trends. We also identify the causes of increases and decreases in sales.

[0441] Input: Pre-processed sales data, customer feedback, inventory data

[0442] Output: Trends in analyzed sales data, trends in customer feedback

[0443] Step 4: Data Extraction and Visualization

[0444] The server extracts the analysis results from the artificial intelligence analysis tools and organizes them as follows:

[0445] Category classification: Classified into categories such as "Points for increasing sales," "Points for improving customer service," and "Points for optimizing inventory management."

[0446] Visualization: Graph the analysis results. For sales data, create line graphs or bar graphs; for customer feedback, create pie charts.

[0447] Input: Trends in analyzed sales data, trends in customer feedback

[0448] Output: Organized and visualized data (line graphs, bar graphs, pie charts)

[0449] Step 5: Generate PowerPoint

[0450] The server automatically generates a PowerPoint presentation based on the organized and visualized data obtained from the data extraction method. The following template is used to create the slides:

[0451] Title slide

[0452] Slides showing various analysis results

[0453] Proposal slides

[0454] For example, a slide titled "Areas for Improvement in Customer Service" would include graphs related to the analysis of customer feedback, while a slide titled "Key Points for Increasing Sales" would include sales data trends and their interpretations.

[0455] Input: Organized and visualized data

[0456] Output: Generated PPT file

[0457] Step 6: Download preparation and notification

[0458] The server prepares the generated PPT file for the user to download and sends a notification. The user receives the notification and can download the generated presentation via the web application or mobile application.

[0459] Input: Generated PPT file

[0460] Output: Downloadable PPT file, notification to the user

[0461] In this way, the system can automatically extract points for improvement in store operations and generate high-quality presentation materials in a short time, simply by the user inputting data.

[0462] (Application Example 1)

[0463] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0464] In store operations, there is a need to efficiently analyze large amounts of data and quickly identify areas for improvement. However, current systems have cumbersome data preprocessing and analysis methods, and there is a lack of means to provide the results to store managers and staff in a quick and easy-to-understand format. As a result, there is a challenge in that real-time response and improvement are difficult.

[0465] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0466] In this invention, the server includes a user input means for inputting store operation data, a server pre-processing means for pre-processing the data received from the user input means, an AI analysis means for analyzing the data pre-processed by the pre-processing means, a data extraction means for extracting the analysis results of the AI ​​analysis means, a PPT generation means for generating a PPT file based on the extraction results of the data extraction means, and a notification means for notifying smart glasses of the PPT file in real time. This enables store operators and staff to check areas for improvement in operations in real time during their daily work and respond quickly and effectively.

[0467] A "user input method" is an interface for providing store operation data to the system.

[0468] "Server preprocessing means" refers to a server component that has the function of preprocessing data received from user input means.

[0469] "AI analysis methods" refer to methods that use artificial intelligence technology to analyze pre-processed data and derive analysis results.

[0470] A "data extraction means" is a means that has the function of extracting and organizing the analysis results obtained by the AI ​​analysis means.

[0471] A "PPT generation means" is a means for automatically generating a PowerPoint (presentation) file based on data obtained from a data extraction means.

[0472] A "notification method" is a means that has the function of notifying store operators and staff of the generated PPT file in real time using their smart glasses.

[0473] The system for implementing the present invention automates a series of steps, including inputting and analyzing store operation data, extracting areas for improvement, and generating a presentation file. The system includes the following means:

[0474] 1. User Input Method: This is an interface for users to provide store operation data to the system. It is implemented as a web application or mobile application and allows users to upload sales data, customer feedback, inventory data, etc.

[0475] 2. Server preprocessing means: This means that the server has the function of preprocessing the data received from the user input means. Preprocessing includes imputing missing values, removing outliers, and standardizing the data. Specifically, it reads the data using the pandas library, imputes missing values ​​using sklearn.impute.SimpleImputer, and removes outliers.

[0476] 3. AI Analysis Methods: Pre-processed data is analyzed. Natural language processing models (using the transformers library) and machine learning models (using RandomForestRegressor) are used for the analysis. The natural language processing model analyzes text data of customer feedback and extracts specific keywords and trends. The machine learning model performs time-series analysis of sales data to identify seasonality and trends.

[0477] 4. Data Extraction Method: This method has the function of extracting and organizing the analysis results of the AI ​​analysis method. Specifically, it classifies the data into points for increasing sales, points for improving customer service, points for optimizing inventory management, etc., and generates graphs and charts for visualization.

[0478] 5. PPT Generation Method: Based on the results obtained from the data extraction method, a presentation in PowerPoint format is automatically generated. This uses the python-pptx library. The slides are generated using a pre-configured template and include a title slide, various analysis result slides, proposal slides, etc.

[0479] 6. Notification Method: The generated PPT file will be sent in real time to the smart glasses of store operators and staff. This will allow them to check for areas for improvement in operations in real time during their daily work and take quick action.

[0480] Specific example

[0481] For example, suppose a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and uses pandas and scikit-learn to impute and correct missing values ​​and outliers. Next, it analyzes the data using the transformers library and RandomForestRegressor to extract trends in customer feedback such as "slow service" or "high prices", and performs time-series analysis of the sales data. After that, it visualizes the analysis results in graphs and charts using pyplot and generates a PowerPoint file using python-pptx. Finally, this PowerPoint file is displayed in real time on smart glasses.

[0482] Example of a prompt

[0483] "Based on customer feedback text data from the first quarter of 2023, please identify the main customer complaints and areas for improvement."

[0484] "Use the sales data from the first quarter of 2023 to generate a sales forecast for the next quarter."

[0485] This system enables store operators and staff to efficiently analyze store operation data, quickly identify areas for improvement, and take action.

[0486] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0487] Step 1:

[0488] Users upload store operation data (e.g., sales data.csv, customer feedback.xlsx, inventory data.csv) through user input methods. This allows users to provide the necessary data to the system.

[0489] Step 2:

[0490] The server preprocesses the data received from the user input using its own preprocessing mechanism. This preprocessing involves reading the data using pandas, imputing missing values ​​(sklearn.impute.SimpleImputer), and removing outliers (interquartile range method). This results in clean data.

[0491] Step 3:

[0492] The server analyzes pre-processed data using AI analysis tools. Specifically, it uses the transformers library for natural language processing to extract keywords and trends from customer feedback. It also performs time-series analysis of sales data using a machine learning model (RandomForestRegressor). This allows for the identification of customer dissatisfactions and sales predictions.

[0493] Step 4:

[0494] The server extracts and organizes the analysis results from the AI ​​analysis using data extraction tools. The results are categorized into "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management," and graphs and charts are generated using pyplot for visualization. This results in data that is easy to understand visually.

[0495] Step 5:

[0496] The server generates a PowerPoint presentation file based on the data obtained from the data extraction means using a PowerPoint generation means. Using the python-pptx library, slides are automatically created according to a pre-prepared template. This provides a PowerPoint file that the user can use immediately.

[0497] Step 6:

[0498] The server uses a notification system to send generated PowerPoint files to the smart glasses of store operators and staff in real time. This allows users to check for operational improvements in real time during their daily work and take quick action.

[0499] By executing each step in this order, efficient analysis of store operation data and rapid improvement can be achieved.

[0500] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0501] This invention relates to a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. Furthermore, it aims to improve the user experience by combining it with an emotion engine that recognizes user emotions. The system for carrying out this invention includes a user input means, a server pre-processing means, an AI analysis means, a data extraction means, a PowerPoint generation means, and an emotion engine.

[0502] Overall system flow

[0503] User input means

[0504] The user input mechanism is an interface for users to provide store operation data to the system. Through this interface, users upload sales data, customer feedback, inventory data, and so on. This interface can be implemented, for example, as a web application or mobile application. It may also include voice recognition devices and cameras for inputting the user's voice and facial expressions.

[0505] Server Preprocessing Means

[0506] The server preprocessing mechanism has the function of preprocessing data received from the user input mechanism. Preprocessing includes imputing missing values, removing outliers, and standardizing data. For example, if there are missing values ​​in sales data, the server imputates the missing values ​​with the average value of past data. For outliers, statistical methods of data are used to identify the outliers, and the data is removed or corrected as necessary.

[0507] AI analysis means

[0508] AI analysis tools analyze pre-processed data. Natural language processing models and machine learning models are used for this analysis. The natural language processing model analyzes text data from customer feedback to extract specific keywords and trends. For example, it detects trends such as "slow service" and "high prices." The machine learning model performs time-series analysis of sales data to identify seasonality and trends. It also identifies the causes of sudden increases or decreases in sales.

[0509] Data extraction means

[0510] The data extraction tool has the function of extracting and organizing the analysis results of the AI ​​analysis tool. For example, it classifies the analysis results into categories such as "points for increasing sales," "areas for improvement in customer service," and "points for optimizing inventory management." Furthermore, it generates graphs and charts to visualize the data. For sales data, it creates line graphs and bar graphs, and for customer feedback, it generates pie charts showing the ratio of positive to negative feedback.

[0511] PPT generation means

[0512] The PPT generation means automatically generates a presentation in PowerPoint format based on the results obtained from the data extraction means. The slides are generated using pre-configured templates. The templates include title slides, various analysis result slides, proposal slides, etc. For example, the "Areas for Improvement in Customer Service" slide will contain the analysis results of customer feedback and related graphs, and the "Points for Increasing Sales" slide will contain sales data trends and their interpretations.

[0513] Emotional Engine

[0514] The emotion engine has the ability to analyze emotions from the user's voice and facial expressions. For example, it analyzes the tone of voice and facial expressions while the user is using the interface to understand the user's emotional state. Voice analysis and facial expression analysis are used for emotion recognition.

[0515] Furthermore, based on the analysis results of the emotion engine, it suggests recommended actions to improve the user experience. For example, if a user is experiencing stress, it provides simpler instructions or support information. Conversely, if a user is satisfied, it presents additional suggestions or promotional information.

[0516] Specific examples

[0517] For example, suppose a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and fills in or corrects missing or outlier values. Next, an AI analysis tool analyzes the data, extracts trends in customer feedback such as "slow service" and "high prices", and identifies seasonality and trends through time-series analysis of sales data. Subsequently, a data extraction tool organizes the analysis results and generates visualized data. Finally, a PPT generation tool creates a PPT file based on these results and makes it available for the user to download.

[0518] Furthermore, if the emotion engine analyzes that a user is experiencing stress while entering data, the system will provide the user with simple instructions and help information. On the other hand, if the system perceives that the user is satisfied, it will suggest additional features or relevant promotional information.

[0519] In this way, the system of the present invention can automatically extract points for improvement in store operations and generate materials that present concrete action plans simply by the user inputting data, and can also provide a better user experience by providing support that responds to the user's emotional state.

[0520] The following describes the processing flow.

[0521] Step 1:

[0522] Users upload store operation data to the system through an interface. The data, including sales data, customer feedback, and inventory data, is provided in CSV and Excel file formats. User voice data and facial expression data are also collected.

[0523] Step 2:

[0524] The server receives data files uploaded by users. During this process, it verifies the file format and performs security checks. It confirms that the file extension is CSV or XLSX and then performs a virus scan.

[0525] Step 3:

[0526] The server preprocesses the received data. Specifically, if missing values ​​exist, they are imputed using the mean or mode of past data. If outliers are detected, they are removed or corrected using statistical methods. In addition, the data is standardized to unify all data formats.

[0527] Step 4:

[0528] The server inputs pre-processed data into an AI model. Using a natural language processing model, it analyzes the text data of customer feedback and extracts specific keywords and trends. For example, it detects trends such as "slow service" and "high prices."

[0529] Step 5:

[0530] The server uses a machine learning model to perform time-series analysis of sales data. It identifies seasonality and trends from the data and pinpoints the causes of sudden increases or decreases in sales. Specifically, if a particular event was held on a day when sales surged, it extracts that information.

[0531] Step 6:

[0532] The server extracts the output results of the AI ​​model using data extraction methods. In this process, the analysis results are categorized into areas such as "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management." In addition, bar graphs, line graphs, pie charts, etc., are generated to visualize the analysis results.

[0533] Step 7:

[0534] The server generates the PPT file using a template. First, a title slide is created, followed by slides containing various analysis results and proposals. The "Areas for Improvement in Customer Service" slide contains analysis results of customer feedback and related graphs. The "Points for Increasing Sales" slide contains sales data trends and their interpretation.

[0535] Step 8:

[0536] The server uses an emotion engine to analyze the user's emotions. Based on the voice and facial expression data provided by the user during data entry, it performs speech recognition and facial expression analysis to identify the user's emotional state. For example, if the user is feeling stressed, that information is analyzed.

[0537] Step 9:

[0538] The server suggests actions to improve the user experience based on the analysis results of the emotion engine. If the user is experiencing stress, it provides simple instructions and help information. If the user is satisfied, it suggests additional features and relevant promotional information.

[0539] Step 10:

[0540] The server generates the final PPT file and saves it for the user to download. The file is either stored in cloud storage or provided directly to the user.

[0541] Step 11:

[0542] Users download PowerPoint files from the system and use them as reference material to understand specific areas for improvement in store operations and to develop necessary action plans.

[0543] Through the above processing steps, this system enables users to efficiently analyze store operation data, identify areas for improvement, and generate effective presentation materials. Furthermore, by providing support that responds to the user's emotional state, it can deliver an excellent user experience.

[0544] (Example 2)

[0545] Next, we will describe Example 2. 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".

[0546] Current store operations require a significant amount of time and effort to manually analyze large amounts of data, identify areas for improvement, and compile them into presentations. Furthermore, the emotional state of users when using the system is not considered, which can lead to stress. Therefore, there is a need for a system that efficiently and automatically analyzes store operation data, identifies areas for improvement, and provides support tailored to the emotional state of users.

[0547] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for inputting store operation data, a preprocessing means for preprocessing the data received from the input means, an analysis means for analyzing the data preprocessed by the preprocessing means, an extraction means for extracting the analysis results of the analysis means, a generation means for generating a presentation file based on the extraction results of the extraction means, and an emotion analysis means for recognizing the user's emotions. This enables efficient analysis of store operation data, extraction of areas for improvement, automatic generation of presentations, and support tailored to the user's emotional state.

[0548] "Store operation data" refers to all data related to store operations, such as sales data, customer feedback, and inventory data.

[0549] An "input method" is an interface for users to provide store operation data to the system, and is implemented as a web application or mobile application.

[0550] "Preprocessing means" refers to means of performing preprocessing on data received from input means, such as imputing missing values, removing outliers, and standardizing data.

[0551] "Analysis means" refers to means that include natural language processing models that analyze pre-processed data and extract specific keywords or trends, and machine learning models that perform time-series analysis of sales data.

[0552] "Extraction means" refers to means for extracting and organizing the analysis results of the analysis means, and includes category classification and the generation of graphs and charts for visualization.

[0553] The "generation means" refers to a means for automatically generating presentation files based on the results obtained from the extraction means, and has the function of automatically generating slides using templates.

[0554] "Emotional analysis methods" are means of analyzing a user's emotions from their voice and facial expressions, and then providing appropriate support and suggestions to improve the user experience based on the results.

[0555] This invention relates to a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a presentation file. Furthermore, it aims to provide a better user experience by combining it with an emotion engine that analyzes user emotions.

[0556] This system includes input means, preprocessing means, analysis means, extraction means, generation means, and sentiment analysis means. The specific implementation methods for each means are described below.

[0557] Input means

[0558] Users provide store operation data to the system using a web application or mobile application. This interface is implemented as a web application built with React or Vue.js, or as a mobile application developed with Flutter or Kotlin. In addition, the system inputs the user's voice and facial expressions using a voice recognition device (e.g., a speech recognition device) or a camera.

[0559] Pretreatment means

[0560] The server preprocesses the data received from user input. Specifically, it uses Python and the Pandas library to read the data, impute missing values, remove outliers, and standardize the data. For example, missing values ​​are imputed with the mean of past data, and outliers are detected using Z-scores and corrected as needed.

[0561] Analysis means

[0562] The server analyzes pre-processed data using AI models. Text data from customer feedback is analyzed using natural language processing models (e.g., BERT model) to extract specific keywords and trends. Time series analysis of sales data uses machine learning models (e.g., Prophet model) to identify trends and seasonality.

[0563] extraction means

[0564] The server extracts and organizes the results of the analysis. Specifically, it categorizes the analysis results into categories such as "points for increasing sales" and "areas for improvement in customer service," and generates graphs and charts for visualization. Data visualization libraries such as Matplotlib and Seaborn are used for this task.

[0565] generation means

[0566] The server automatically generates presentation files based on the data obtained from the extraction method. The generation uses the Python python-pptx library, arranging the analysis results and visualizations into a pre-configured template. For example, the "Improvements in Customer Service" slide would include visualized customer feedback data and related suggestions.

[0567] Emotion analysis means

[0568] The server analyzes the user's emotions from their voice and facial expressions. It uses a speech analysis API for speech recognition and OpenCV for facial expression recognition. Based on the results of the emotion analysis, if the user is feeling stressed, it will provide simple instructions or help information; if the user is satisfied, it will display additional suggestions or promotional information.

[0569] Specific examples

[0570] For example, a user uploads files such as "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and imputes and corrects missing or outlier values. Next, an AI model is used to analyze the data, extracting trends in customer feedback such as "slow service" and "high prices," and identifying trends through time-series analysis of sales data. After that, the analysis results are organized and visualized data is generated. Finally, a presentation file is automatically generated and made available for the user to download.

[0571] Furthermore, if the sentiment analysis engine determines that the user is experiencing stress during user data entry, the system will provide the user with easy-to-follow instructions and help information. On the other hand, if the system recognizes that the user is satisfied, it will suggest additional features or relevant promotional information.

[0572] This system allows users to easily input data, automatically extract areas for improvement in store operations, and generate materials that present concrete action plans. Furthermore, by providing support tailored to the user's emotional state, it can deliver an excellent user experience.

[0573] Example of a prompt

[0574] Based on sales data, customer feedback, and inventory data, identify areas for improvement in store operations and generate a PowerPoint presentation. The data should also include trends in customer feedback such as "slow service" and "high prices." Furthermore, conduct user sentiment analysis to provide appropriate support.

[0575] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0576] Step 1:

[0577] The user opens the web or mobile application. The user selects sales data, customer feedback, and inventory data files and uploads them to the interface. For example, the user selects "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" and clicks the upload button. The input is a store operation data file, and the output is the upload of data into the system.

[0578] Step 2:

[0579] The server receives the uploaded data and stores it in temporary storage. For example, it might use a cloud storage service (e.g., an AWS S3 bucket) to store these files. The input is the data file uploaded by the user, and the output is the temporary file stored on the server.

[0580] Step 3:

[0581] The server preprocesses the stored data. It uses Python and the Pandas library to read CSV and Excel files. The `fillna` method is used for missing value imputation, and Z-scores are used for anomaly detection. The input is a raw data file on the server, and the output is a preprocessed dataset.

[0582] Step 4:

[0583] The server analyzes pre-processed data using an AI model. Customer feedback text data is analyzed using a natural language processing model (e.g., BERT model) to extract trends and keywords. For time-series analysis of sales data, a machine learning model (e.g., Prophet model) is used to identify trends and seasonality. The input is pre-processed data, and the output is the analysis result.

[0584] Step 5:

[0585] The server extracts and organizes the results of the analysis. Specifically, it uses Matplotlib and Seaborn to visualize the analysis results and create graphs and charts. The analysis results are categorized into categories such as "points for increasing sales" and "areas for improvement in customer service." The input is the analysis results, and the output is the visualized data and the categorized results.

[0586] Step 6:

[0587] The server generates a presentation file based on the visualized data. Using the python-pptx library, slides are automatically created according to a pre-configured template. For example, the "Customer Service Improvements" slide will include a pie chart of customer feedback data and related suggestions. The input is the visualized data and classification results, and the output is a presentation file in PowerPoint format.

[0588] Step 7:

[0589] The server saves the generated presentation file and provides the user with a download link. Alternatively, the PPT file can be saved to a cloud storage service (e.g., an AWS S3 bucket), and the download link can be emailed to the user or displayed on a web application. The input is the generated presentation file, and the output is the download link to the user.

[0590] Step 8:

[0591] The server analyzes the user's emotions from their voice and facial expressions. It uses a speech analysis API (e.g., Google Speech-to-Text) for speech recognition and OpenCV for facial expression recognition. It analyzes emotional states such as stress and satisfaction, and provides appropriate support information based on the results. Input is the user's voice and facial expression data, and output is the emotion analysis results and the provided support information.

[0592] (Application Example 2)

[0593] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0594] Traditionally, analyzing store operation data and identifying areas for improvement required a tremendous amount of time and effort, and creating presentation materials to effectively utilize the analysis results was also time-consuming. Furthermore, it was impossible to grasp user emotions, limiting the potential for improving the user experience. Therefore, there was a strong demand for a system that could simultaneously achieve both increased efficiency in store operations and improved user experience.

[0595] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0596] In this invention, the server includes a user input means for inputting store operation data, a server pre-processing means for pre-processing the data received from the user input means, an AI analysis means for analyzing the data pre-processed by the pre-processing means, a data extraction means for extracting the analysis results of the AI ​​analysis means, a PPT generation means for generating a PPT file based on the extraction results of the data extraction means, and an emotion engine that recognizes the user's emotions and suggests recommended actions to improve the user experience. This enables a consistent process from analyzing store operation data to extracting areas for improvement and automatically generating presentation materials, as well as providing support that reflects the user's emotions.

[0597] A "user input method" is an interface for users to provide store operation data to the system, and it has the function of uploading sales data, customer feedback, inventory data, etc., through web applications or mobile applications.

[0598] A "server preprocessing means" is a device that has the function of preprocessing data received from a user input means, and performs tasks such as imputing missing values, removing outliers, and standardizing data.

[0599] "AI analysis tools" are those that analyze pre-processed data, extract specific keywords and trends using natural language processing models and machine learning models, and perform time-series analysis of sales data.

[0600] A "data extraction tool" is a tool that extracts the analysis results from an AI analysis tool, classifies them into categories such as points for increasing sales, areas for improving customer service, and points for optimizing inventory management, and further generates graphs and charts to visualize that data.

[0601] The "PPT generation means" has the function of automatically generating a presentation in PowerPoint format based on the results obtained from the data extraction means, and creates slides using a pre-configured template.

[0602] An "emotion engine" is a system that analyzes a user's emotions from their voice and facial expressions and suggests recommended actions to improve the user experience. It uses voice analysis and facial expression analysis to understand the user's emotional state.

[0603] This invention is a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. The system includes a user input means, a server pre-processing means, an AI analysis means, a data extraction means, a PowerPoint generation means, and an emotion engine.

[0604] system

[0605] 1. User input means

[0606] The user input mechanism is an interface for users to provide store operation data to the system. Specifically, users upload sales data, customer feedback, inventory data, etc., using smartphones or personal computers. This interface is implemented as a web application or mobile application. It also includes voice recognition devices and cameras to capture the user's voice and facial expressions from resources.

[0607] 2. Server preprocessing means

[0608] The server preprocessing mechanism has the function of preprocessing data received from the user input mechanism. Preprocessing includes imputing missing values, removing outliers, and standardizing data. Specifically, if sales data contains missing values, the server imputates them with the average value of past data. For outliers, statistical methods are used to identify them, and the data is removed or corrected as necessary.

[0609] 3. AI analysis means

[0610] The AI ​​analysis tool has the ability to analyze pre-processed data. This analysis utilizes natural language processing models and machine learning models. The natural language processing model analyzes text data from customer feedback to extract specific keywords and trends. For example, it detects trends such as "slow service" and "high prices." The machine learning model performs time-series analysis of sales data to identify seasonality and trends. It also identifies the causes of sudden increases or decreases in sales.

[0611] 4. Data extraction means

[0612] The data extraction mechanism extracts and organizes the analysis results from the AI ​​analysis mechanism. This mechanism categorizes the analysis results into categories such as "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management." Furthermore, it generates graphs and charts to visualize the data. For sales data, it creates time-series graphs and bar graphs, and for customer feedback, it generates pie charts showing the ratio of negative to positive feedback.

[0613] 5. PPT generation means

[0614] The PPT generation means automatically generates a presentation in PowerPoint format based on the results obtained from the data extraction means. These slides are generated using a pre-configured template. The template includes a title slide, various analysis results slides, and proposal slides. For example, the "Areas for Improvement in Customer Service" slide contains the analysis results of customer feedback and related graphs, and the "Points for Increasing Sales" slide contains sales data trends and their interpretation.

[0615] 6. Emotional Engine

[0616] The emotion engine has the ability to analyze emotions from the user's voice and facial expressions. It uses voice analysis and facial expression analysis to understand the user's emotional state. Based on the results of the emotion engine's analysis, it suggests actions to improve the user experience. For example, if the user is feeling stressed, it provides simpler instructions or support information. Conversely, if the user is satisfied, it presents additional suggestions or promotional information.

[0617] Specific example

[0618] Example of a prompt

[0619] Let's assume a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and fills in and corrects missing values ​​and outliers. Next, an AI analysis tool analyzes the data, extracting trends in customer feedback such as "slow service" and "high prices," and identifies seasonality and trends through time-series analysis of sales data. After that, a data extraction tool organizes the analysis results and generates visualized data. Finally, a PPT generation tool creates a PPT file based on these results and makes it available for the user to download.

[0620] Furthermore, if the emotion engine analyzes that the user is experiencing stress while entering data, the system provides the user with simple instructions and help information. On the other hand, if the system recognizes that the user is satisfied, it presents additional feature suggestions and relevant promotional information. In this way, the system of the present invention can automatically extract points for improvement in store operations and generate materials that present concrete action plans simply by having the user enter data, and can provide a better user experience by providing support that corresponds to the user's emotional state.

[0621] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0622] Step 1: Users upload sales data, customer feedback, and inventory data to the system interface using their smartphones or personal computers.

[0623] Inputs: Sales data, customer feedback, inventory data

[0624] Output: Various data files sent to the server

[0625] Step 2: The server preprocessing device preprocesses the received data. Specifically, it imputes missing values ​​with the mean and identifies and removes outliers using statistical methods.

[0626] Input: Various data files sent to the server

[0627] Output: Preprocessed data with missing values ​​imputed and outliers removed.

[0628] Step 3: The server's AI analysis tools analyze the pre-processed data. A natural language processing model analyzes the text data of customer feedback, extracting specific keywords and trends. In addition, a machine learning model is used to perform time-series analysis of sales data to identify seasonality, trends, and the causes of sudden increases or decreases in sales.

[0629] Input: Preprocessed data

[0630] Output: Analysis results (keywords, trends, time series analysis results, etc.)

[0631] Step 4: The server's data extraction tool extracts the analysis results from the AI ​​analysis tool and categorizes them into points for increasing sales, areas for improving customer service, and points for optimizing inventory management. It also generates graphs and charts to visualize the data.

[0632] Input: Analysis results

[0633] Output: Classified analysis results, visualized graphs and charts

[0634] Step 5: The server's PPT generation means automatically generates a PPT file using a pre-configured template based on the results obtained from the data extraction means.

[0635] Input: Classified analysis results, visualized graphs and charts

[0636] Output: Presentation file in PPT format

[0637] Step 6: The emotion engine analyzes the voice and facial expressions of the user using the interface. It uses voice analysis and facial expression analysis to understand the user's emotional state.

[0638] Input: User voice data, facial expression data

[0639] Output: User's emotional state

[0640] Step 7: The server's emotion engine suggests actions based on the user's emotional state. For example, if the user is stressed, it provides simple instructions or help information; if the user is satisfied, it provides additional suggestions or promotional information.

[0641] Input: User's emotional state

[0642] Output: Recommended actions (simple instructions, help information, additional suggestions, promotional information, etc.)

[0643] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0644] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0645] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0646] [Third Embodiment]

[0647] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0648] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0649] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0650] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0651] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0652] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0653] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0654] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0655] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0656] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0657] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0658] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0659] This document describes a specific example of a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. The system for implementing the present invention includes a user input means, a server pre-processing means, an AI analysis means, a data extraction means, and a PowerPoint generation means.

[0660] Overall system flow

[0661] User input means

[0662] The user input mechanism is an interface for users to provide store operation data to the system. Through this interface, users upload sales data, customer feedback, inventory data, and so on. This interface can be implemented, for example, as a web application or a mobile application.

[0663] Server Preprocessing Means

[0664] The server preprocessing mechanism has the function of preprocessing data received from the user input mechanism. Preprocessing includes imputing missing values, removing outliers, and standardizing data. For example, if there are missing values ​​in sales data, the server imputates the missing values ​​with the average value of past data. For outliers, statistical methods of data are used to identify the outliers, and the data is removed or corrected as necessary.

[0665] AI analysis means

[0666] AI analysis tools analyze pre-processed data. Natural language processing models and machine learning models are used for this analysis. The natural language processing model analyzes text data from customer feedback to extract specific keywords and trends. For example, it detects trends such as "slow service" and "high prices." The machine learning model performs time-series analysis of sales data to identify seasonality and trends. It also identifies the causes of sudden increases or decreases in sales.

[0667] Data extraction means

[0668] The data extraction tool has the function of extracting and organizing the analysis results of the AI ​​analysis tool. For example, it classifies the analysis results into categories such as "points for increasing sales," "areas for improvement in customer service," and "points for optimizing inventory management." Furthermore, it generates graphs and charts to visualize the data. For sales data, it creates line graphs and bar graphs, and for customer feedback, it generates pie charts showing the ratio of positive to negative feedback.

[0669] PPT generation means

[0670] The PPT generation means automatically generates a presentation in PowerPoint format based on the results obtained from the data extraction means. The slides are generated using pre-configured templates. The templates include title slides, various analysis result slides, proposal slides, etc. For example, the "Areas for Improvement in Customer Service" slide will contain the analysis results of customer feedback and related graphs, and the "Points for Increasing Sales" slide will contain sales data trends and their interpretations.

[0671] Specific examples

[0672] For example, suppose a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and fills in or corrects missing or outlier values. Next, an AI analysis tool analyzes the data, extracts trends in customer feedback such as "the service is slow" or "the price is high," and identifies seasonality and trends through time-series analysis of sales data. Subsequently, a data extraction tool organizes the analysis results and generates visualized data. Finally, a PPT generation tool creates a PPT file based on these results and makes it available for the user to download.

[0673] In this way, the system of the present invention can automatically extract points for improvement in store operations and generate materials that present concrete action plans simply by having the user input data. This enables the streamlining and optimization of store operations.

[0674] The following describes the processing flow.

[0675] Step 1:

[0676] Users upload store operation data to the system through an interface. The data, including sales data, customer feedback, and inventory data, is provided in CSV and Excel file formats.

[0677] Step 2:

[0678] The server receives data files uploaded by users. During this process, it also verifies the file format and performs security checks. For example, it checks if the file extension is CSV or XLSX and then performs a virus scan.

[0679] Step 3:

[0680] The server preprocesses the received data. Specifically, if missing values ​​exist, they are imputed using the mean or mode of past data. If outliers are detected, they are removed or corrected using statistical methods.

[0681] Step 4:

[0682] The server inputs pre-processed data into the AI ​​model. Natural language processing (NLP) and machine learning (ML) models are applied to store operation data. For example, the NLP model analyzes text data of customer feedback to extract specific trends and patterns. The ML model performs time-series analysis of sales data to identify seasonality and trends.

[0683] Step 5:

[0684] The server extracts the output results of the AI ​​model using data extraction methods. In this process, important analysis results are categorized into "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management." In addition, bar graphs, line graphs, pie charts, etc., are generated to visualize the analysis results.

[0685] Step 6:

[0686] The server uses a template to generate a PowerPoint file. Each slide in the PowerPoint file contains extracted data and visualizations. For example, "Areas for Improvement in Customer Service" displays customer feedback trends and related graphs, while "Points for Increasing Sales" includes sales data trend graphs and detailed analysis.

[0687] Step 7:

[0688] The server generates the final PPT file and saves it for the user to download. The file is either stored in cloud storage or provided directly to the user.

[0689] Step 8:

[0690] Users can download PowerPoint files from the system and use them as reference material to understand specific areas for improvement in store operations and to develop necessary action plans.

[0691] Through the above processing steps, this system enables users to efficiently analyze store operation data, identify areas for improvement, and generate effective presentation materials.

[0692] (Example 1)

[0693] Next, we will describe Example 1. 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."

[0694] Analyzing traditional store operation data, identifying areas for improvement, and compiling them into presentations was a manual process that required considerable effort and time. Furthermore, the accuracy of the analysis and the quality of the result visualization depended heavily on the skills of the person performing the analysis, leading to significant inconsistencies. This resulted in a challenge in achieving sufficient efficiency and optimization of store operations.

[0695] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0696] In this invention, the server includes a user input means for inputting store operation data, a data processing means for pre-processing the data received from the user input means, an artificial intelligence analysis means for analyzing the data pre-processed by the data processing means, a data extraction means for extracting, organizing, and visualizing the analysis results of the artificial intelligence analysis means, a generation means for automatically generating a presentation in PowerPoint format based on the organized and visualized results of the data extraction means, and a means for enabling the user to download the PowerPoint file generated by the generation means. This makes it possible to automatically extract points for improvement in store operations and generate high-quality presentation materials in a short time simply by having the user input data.

[0697] A "user input method" is an interface for users to provide store operation data to the system. Sales data, customer feedback, inventory data, etc., can be uploaded via a web application or mobile application.

[0698] A "data processing device" is a device that has the function of pre-processing data received from a user input device. By imputing missing values, removing outliers, and standardizing the data, it prepares the data to facilitate subsequent analysis.

[0699] "Artificial intelligence analysis tools" are used to analyze pre-processed data. Specifically, they use natural language processing models and machine learning models to extract trends in customer feedback and time-series patterns in sales data.

[0700] A "data extraction tool" is a device that extracts, organizes, and visualizes the results analyzed by an artificial intelligence analysis tool. It classifies the analysis results into categories and generates visual data such as line graphs and pie charts.

[0701] The "generation means" is a system that automatically generates PowerPoint presentations based on the organized and visualized data obtained from the data extraction means. It creates slides using templates and generates high-quality presentation materials.

[0702] The "download method" refers to a function that prepares the generated PPT file for the user to download. It sends a notification to the user, ensuring they can handle the file conveniently.

[0703] This invention is a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. The system includes user input means, data processing means, artificial intelligence analysis means, data extraction means, generation means, and download means.

[0704] User input means

[0705] The user input mechanism is an interface for users to provide store operation data to the system. Through this interface, users can upload data files such as:

[0706] Sales data (e.g., sales_data.csv)

[0707] Customer feedback (e.g., customer_feedback.xlsx)

[0708] Inventory data (e.g., inventory_data.csv)

[0709] The interface will be implemented as a web application or a mobile application.

[0710] Data processing means

[0711] The server preprocesses the data received from the user input. Specifically, it performs the following processing:

[0712] Imputation of missing values: If there are missing values ​​in the sales data, they will be imputed using the average value of past data.

[0713] Removing outliers: Using statistical methods to identify outliers in data and then removing or correcting them.

[0714] Data standardization: Converting data into a unified format.

[0715] Artificial intelligence analysis methods

[0716] The artificial intelligence analysis tools implemented on the server analyze the data in the following way:

[0717] Using natural language processing (NLP) models, we extract specific keywords and trends from customer feedback text data. For example, we detect trends such as "slow service" or "high prices."

[0718] We use machine learning (ML) models to perform time-series analysis of sales data to identify seasonality and trends. We also identify the causes of sudden increases and decreases in sales.

[0719] Data extraction means

[0720] The server extracts, organizes, and visualizes the analysis results of the artificial intelligence analysis tools as follows:

[0721] Category classification: Classified into categories such as "Points for increasing sales," "Points for improving customer service," and "Points for optimizing inventory management."

[0722] Graph generation: Generates line graphs, bar graphs, pie charts, etc., to visualize data.

[0723] generation means

[0724] The server automatically generates a PowerPoint presentation based on the organized and visualized data obtained from the data extraction method. Using a template, it creates slides like the following:

[0725] Title slide

[0726] Slides showing various analysis results

[0727] Proposal slides

[0728] For example, a slide titled "Areas for Improvement in Customer Service" would include graphs related to the analysis of customer feedback, while a slide titled "Key Points for Increasing Sales" would include sales data trends and their interpretations.

[0729] Download method

[0730] The server prepares the generated PPT file for the user to download and sends a notification. After receiving the notification, the user can download the generated presentation via the web application or mobile application.

[0731] Specific example

[0732] For example, if a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" via a web interface, the server receives this data and performs imputation of missing values ​​and correction of outliers. Next, an artificial intelligence analysis tool analyzes the data, extracts trends in customer feedback such as "slow service" and "high prices", and identifies seasonality and trends through time-series analysis of sales data. Subsequently, a data extraction tool organizes the analysis results and generates visualized data. Finally, a generation tool creates a PowerPoint file based on these results and makes it available for the user to download.

[0733] An example of a prompt message is: "Analyze the pre-processed sales data and customer feedback to identify areas for improvement in store operations, and then compile them into a PowerPoint presentation."

[0734] This system allows users to automatically extract areas for improvement in store operations simply by inputting data, and generate high-quality presentation materials in a short amount of time.

[0735] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0736] Step 1: User Input

[0737] Users provide store operation data, such as sales data, customer feedback, and inventory data, to the system via a web or mobile application. Specifically, users upload files such as "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" to the interface. The device receives these files and sends them to the server.

[0738] Input files: SalesData.csv, CustomerFeedback.xlsx, InventoryData.csv

[0739] Output: Data file sent to the server

[0740] Step 2: Data reception and preprocessing

[0741] The server receives data files sent by the user. The received data undergoes the following preprocessing:

[0742] Imputation of missing values: If there are missing values ​​in the sales data, the server will imputate them using the average value of past data.

[0743] Removing outliers: Use statistical methods to identify outliers in the data and remove or correct them as needed.

[0744] Data standardization: Converting data in different formats into a unified format.

[0745] Input: Sales data received from users.csv, Customer feedback.xlsx, Inventory data.csv

[0746] Output: Pre-processed sales data, customer feedback, inventory data

[0747] Step 3: Data Analysis

[0748] The artificial intelligence analysis tools implemented on the server analyze the pre-processed data. The following analysis is performed:

[0749] Using natural language processing (NLP) models, we extract specific keywords and trends from customer feedback text data. For example, we detect trends such as "slow service" and "high prices."

[0750] We use machine learning (ML) models to perform time-series analysis of sales data to identify seasonality and trends. We also identify the causes of increases and decreases in sales.

[0751] Input: Pre-processed sales data, customer feedback, inventory data

[0752] Output: Trends in analyzed sales data, trends in customer feedback

[0753] Step 4: Data Extraction and Visualization

[0754] The server extracts the analysis results from the artificial intelligence analysis tools and organizes them as follows:

[0755] Category classification: Classified into categories such as "Points for increasing sales," "Points for improving customer service," and "Points for optimizing inventory management."

[0756] Visualization: Graph the analysis results. For sales data, create line graphs or bar graphs; for customer feedback, create pie charts.

[0757] Input: Trends in analyzed sales data, trends in customer feedback

[0758] Output: Organized and visualized data (line graphs, bar graphs, pie charts)

[0759] Step 5: Generate PowerPoint

[0760] The server automatically generates a PowerPoint presentation based on the organized and visualized data obtained from the data extraction method. The following template is used to create the slides:

[0761] Title slide

[0762] Slides showing various analysis results

[0763] Proposal slides

[0764] For example, a slide titled "Areas for Improvement in Customer Service" would include graphs related to the analysis of customer feedback, while a slide titled "Key Points for Increasing Sales" would include sales data trends and their interpretations.

[0765] Input: Organized and visualized data

[0766] Output: Generated PPT file

[0767] Step 6: Download preparation and notification

[0768] The server prepares the generated PPT file for the user to download and sends a notification. The user receives the notification and can download the generated presentation via the web application or mobile application.

[0769] Input: Generated PPT file

[0770] Output: Downloadable PPT file, notification to the user

[0771] In this way, the system can automatically extract points for improvement in store operations and generate high-quality presentation materials in a short time, simply by the user inputting data.

[0772] (Application Example 1)

[0773] Next, we will explain Application Example 1. In the following explanation, 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."

[0774] In store operations, there is a need to efficiently analyze large amounts of data and quickly identify areas for improvement. However, current systems have cumbersome data preprocessing and analysis methods, and there is a lack of means to provide the results to store managers and staff in a quick and easy-to-understand format. As a result, there is a challenge in that real-time response and improvement are difficult.

[0775] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0776] In this invention, the server includes a user input means for inputting store operation data, a server pre-processing means for pre-processing the data received from the user input means, an AI analysis means for analyzing the data pre-processed by the pre-processing means, a data extraction means for extracting the analysis results of the AI ​​analysis means, a PPT generation means for generating a PPT file based on the extraction results of the data extraction means, and a notification means for notifying smart glasses of the PPT file in real time. This enables store operators and staff to check areas for improvement in operations in real time during their daily work and respond quickly and effectively.

[0777] A "user input method" is an interface for providing store operation data to the system.

[0778] "Server preprocessing means" refers to a server component that has the function of preprocessing data received from user input means.

[0779] "AI analysis methods" refer to methods that use artificial intelligence technology to analyze pre-processed data and derive analysis results.

[0780] A "data extraction means" is a means that has the function of extracting and organizing the analysis results obtained by the AI ​​analysis means.

[0781] A "PPT generation means" is a means for automatically generating a PowerPoint (presentation) file based on data obtained from a data extraction means.

[0782] A "notification method" is a means that has the function of notifying store operators and staff of the generated PPT file in real time using their smart glasses.

[0783] The system for implementing the present invention automates a series of steps, including inputting and analyzing store operation data, extracting areas for improvement, and generating a presentation file. The system includes the following means:

[0784] 1. User Input Method: This is an interface for users to provide store operation data to the system. It is implemented as a web application or mobile application and allows users to upload sales data, customer feedback, inventory data, etc.

[0785] 2. Server preprocessing means: This means that the server has the function of preprocessing the data received from the user input means. Preprocessing includes imputing missing values, removing outliers, and standardizing the data. Specifically, it reads the data using the pandas library, imputes missing values ​​using sklearn.impute.SimpleImputer, and removes outliers.

[0786] 3. AI Analysis Methods: Pre-processed data is analyzed. Natural language processing models (using the transformers library) and machine learning models (using RandomForestRegressor) are used for the analysis. The natural language processing model analyzes text data of customer feedback and extracts specific keywords and trends. The machine learning model performs time-series analysis of sales data to identify seasonality and trends.

[0787] 4. Data Extraction Method: This method has the function of extracting and organizing the analysis results of the AI ​​analysis method. Specifically, it classifies the data into points for increasing sales, points for improving customer service, points for optimizing inventory management, etc., and generates graphs and charts for visualization.

[0788] 5. PPT Generation Method: Based on the results obtained from the data extraction method, a presentation in PowerPoint format is automatically generated. This uses the python-pptx library. The slides are generated using a pre-configured template and include a title slide, various analysis result slides, proposal slides, etc.

[0789] 6. Notification Method: The generated PPT file will be sent in real time to the smart glasses of store operators and staff. This will allow them to check for areas for improvement in operations in real time during their daily work and take quick action.

[0790] Specific example

[0791] For example, suppose a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and uses pandas and scikit-learn to impute and correct missing values ​​and outliers. Next, it analyzes the data using the transformers library and RandomForestRegressor to extract trends in customer feedback such as "slow service" or "high prices", and performs time-series analysis of the sales data. After that, it visualizes the analysis results in graphs and charts using pyplot and generates a PowerPoint file using python-pptx. Finally, this PowerPoint file is displayed in real time on smart glasses.

[0792] Example of a prompt

[0793] "Based on customer feedback text data from the first quarter of 2023, please identify the main customer complaints and areas for improvement."

[0794] "Use the sales data from the first quarter of 2023 to generate a sales forecast for the next quarter."

[0795] This system enables store operators and staff to efficiently analyze store operation data, quickly identify areas for improvement, and take action.

[0796] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0797] Step 1:

[0798] Users upload store operation data (e.g., sales data.csv, customer feedback.xlsx, inventory data.csv) through user input methods. This allows users to provide the necessary data to the system.

[0799] Step 2:

[0800] The server preprocesses the data received from the user input using its own preprocessing mechanism. This preprocessing involves reading the data using pandas, imputing missing values ​​(sklearn.impute.SimpleImputer), and removing outliers (interquartile range method). This results in clean data.

[0801] Step 3:

[0802] The server analyzes pre-processed data using AI analysis tools. Specifically, it uses the transformers library for natural language processing to extract keywords and trends from customer feedback. It also performs time-series analysis of sales data using a machine learning model (RandomForestRegressor). This allows for the identification of customer dissatisfactions and sales predictions.

[0803] Step 4:

[0804] The server extracts and organizes the analysis results from the AI ​​analysis using data extraction tools. The results are categorized into "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management," and graphs and charts are generated using pyplot for visualization. This results in data that is easy to understand visually.

[0805] Step 5:

[0806] The server generates a PowerPoint presentation file based on the data obtained from the data extraction means using a PowerPoint generation means. Using the python-pptx library, slides are automatically created according to a pre-prepared template. This provides a PowerPoint file that the user can use immediately.

[0807] Step 6:

[0808] The server uses a notification system to send generated PowerPoint files to the smart glasses of store operators and staff in real time. This allows users to check for operational improvements in real time during their daily work and take quick action.

[0809] By executing each step in this order, efficient analysis of store operation data and rapid improvement can be achieved.

[0810] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0811] This invention relates to a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. Furthermore, it aims to improve the user experience by combining it with an emotion engine that recognizes user emotions. The system for carrying out this invention includes a user input means, a server pre-processing means, an AI analysis means, a data extraction means, a PowerPoint generation means, and an emotion engine.

[0812] Overall system flow

[0813] User input means

[0814] The user input mechanism is an interface for users to provide store operation data to the system. Through this interface, users upload sales data, customer feedback, inventory data, and so on. This interface can be implemented, for example, as a web application or mobile application. It may also include voice recognition devices and cameras for inputting the user's voice and facial expressions.

[0815] Server Preprocessing Means

[0816] The server preprocessing mechanism has the function of preprocessing data received from the user input mechanism. Preprocessing includes imputing missing values, removing outliers, and standardizing data. For example, if there are missing values ​​in sales data, the server imputates the missing values ​​with the average value of past data. For outliers, statistical methods of data are used to identify the outliers, and the data is removed or corrected as necessary.

[0817] AI analysis means

[0818] AI analysis tools analyze pre-processed data. Natural language processing models and machine learning models are used for this analysis. The natural language processing model analyzes text data from customer feedback to extract specific keywords and trends. For example, it detects trends such as "slow service" and "high prices." The machine learning model performs time-series analysis of sales data to identify seasonality and trends. It also identifies the causes of sudden increases or decreases in sales.

[0819] Data extraction means

[0820] The data extraction tool has the function of extracting and organizing the analysis results of the AI ​​analysis tool. For example, it classifies the analysis results into categories such as "points for increasing sales," "areas for improvement in customer service," and "points for optimizing inventory management." Furthermore, it generates graphs and charts to visualize the data. For sales data, it creates line graphs and bar graphs, and for customer feedback, it generates pie charts showing the ratio of positive to negative feedback.

[0821] PPT generation means

[0822] The PPT generation means automatically generates a presentation in PowerPoint format based on the results obtained from the data extraction means. The slides are generated using pre-configured templates. The templates include title slides, various analysis result slides, proposal slides, etc. For example, the "Areas for Improvement in Customer Service" slide will contain the analysis results of customer feedback and related graphs, and the "Points for Increasing Sales" slide will contain sales data trends and their interpretations.

[0823] Emotional Engine

[0824] The emotion engine has the ability to analyze emotions from the user's voice and facial expressions. For example, it analyzes the tone of voice and facial expressions while the user is using the interface to understand the user's emotional state. Voice analysis and facial expression analysis are used for emotion recognition.

[0825] Furthermore, based on the analysis results of the emotion engine, it suggests recommended actions to improve the user experience. For example, if a user is experiencing stress, it provides simpler instructions or support information. Conversely, if a user is satisfied, it presents additional suggestions or promotional information.

[0826] Specific examples

[0827] For example, suppose a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and fills in or corrects missing or outlier values. Next, an AI analysis tool analyzes the data, extracts trends in customer feedback such as "slow service" and "high prices", and identifies seasonality and trends through time-series analysis of sales data. Subsequently, a data extraction tool organizes the analysis results and generates visualized data. Finally, a PPT generation tool creates a PPT file based on these results and makes it available for the user to download.

[0828] Furthermore, if the emotion engine analyzes that a user is experiencing stress while entering data, the system will provide the user with simple instructions and help information. On the other hand, if the system perceives that the user is satisfied, it will suggest additional features or relevant promotional information.

[0829] In this way, the system of the present invention can automatically extract points for improvement in store operations and generate materials that present concrete action plans simply by the user inputting data, and can also provide a better user experience by providing support that responds to the user's emotional state.

[0830] The following describes the processing flow.

[0831] Step 1:

[0832] Users upload store operation data to the system through an interface. The data, including sales data, customer feedback, and inventory data, is provided in CSV and Excel file formats. User voice data and facial expression data are also collected.

[0833] Step 2:

[0834] The server receives data files uploaded by users. During this process, it verifies the file format and performs security checks. It confirms that the file extension is CSV or XLSX and then performs a virus scan.

[0835] Step 3:

[0836] The server preprocesses the received data. Specifically, if missing values ​​exist, they are imputed using the mean or mode of past data. If outliers are detected, they are removed or corrected using statistical methods. In addition, the data is standardized to unify all data formats.

[0837] Step 4:

[0838] The server inputs pre-processed data into an AI model. Using a natural language processing model, it analyzes the text data of customer feedback and extracts specific keywords and trends. For example, it detects trends such as "slow service" and "high prices."

[0839] Step 5:

[0840] The server uses a machine learning model to perform time-series analysis of sales data. It identifies seasonality and trends from the data and pinpoints the causes of sudden increases or decreases in sales. Specifically, if a particular event was held on a day when sales surged, it extracts that information.

[0841] Step 6:

[0842] The server extracts the output results of the AI ​​model using data extraction methods. In this process, the analysis results are categorized into areas such as "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management." In addition, bar graphs, line graphs, pie charts, etc., are generated to visualize the analysis results.

[0843] Step 7:

[0844] The server generates the PPT file using a template. First, a title slide is created, followed by slides containing various analysis results and proposals. The "Areas for Improvement in Customer Service" slide contains analysis results of customer feedback and related graphs. The "Points for Increasing Sales" slide contains sales data trends and their interpretation.

[0845] Step 8:

[0846] The server uses an emotion engine to analyze the user's emotions. Based on the voice and facial expression data provided by the user during data entry, it performs speech recognition and facial expression analysis to identify the user's emotional state. For example, if the user is feeling stressed, that information is analyzed.

[0847] Step 9:

[0848] The server suggests actions to improve the user experience based on the analysis results of the emotion engine. If the user is experiencing stress, it provides simple instructions and help information. If the user is satisfied, it suggests additional features and relevant promotional information.

[0849] Step 10:

[0850] The server generates the final PPT file and saves it for the user to download. The file is either stored in cloud storage or provided directly to the user.

[0851] Step 11:

[0852] Users download PowerPoint files from the system and use them as reference material to understand specific areas for improvement in store operations and to develop necessary action plans.

[0853] Through the above processing steps, this system enables users to efficiently analyze store operation data, identify areas for improvement, and generate effective presentation materials. Furthermore, by providing support that responds to the user's emotional state, it can deliver an excellent user experience.

[0854] (Example 2)

[0855] Next, we will describe Example 2. 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."

[0856] Current store operations require a significant amount of time and effort to manually analyze large amounts of data, identify areas for improvement, and compile them into presentations. Furthermore, the emotional state of users when using the system is not considered, which can lead to stress. Therefore, there is a need for a system that efficiently and automatically analyzes store operation data, identifies areas for improvement, and provides support tailored to the emotional state of users.

[0857] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for inputting store operation data, a preprocessing means for preprocessing the data received from the input means, an analysis means for analyzing the data preprocessed by the preprocessing means, an extraction means for extracting the analysis results of the analysis means, a generation means for generating a presentation file based on the extraction results of the extraction means, and an emotion analysis means for recognizing the user's emotions. This enables efficient analysis of store operation data, extraction of areas for improvement, automatic generation of presentations, and support tailored to the user's emotional state.

[0858] "Store operation data" refers to all data related to store operations, such as sales data, customer feedback, and inventory data.

[0859] An "input method" is an interface for users to provide store operation data to the system, and is implemented as a web application or mobile application.

[0860] "Preprocessing means" refers to means of performing preprocessing on data received from input means, such as imputing missing values, removing outliers, and standardizing data.

[0861] "Analysis means" refers to means that include natural language processing models that analyze pre-processed data and extract specific keywords or trends, and machine learning models that perform time-series analysis of sales data.

[0862] "Extraction means" refers to means for extracting and organizing the analysis results of the analysis means, and includes category classification and the generation of graphs and charts for visualization.

[0863] The "generation means" refers to a means for automatically generating presentation files based on the results obtained from the extraction means, and has the function of automatically generating slides using templates.

[0864] "Emotional analysis methods" are means of analyzing a user's emotions from their voice and facial expressions, and then providing appropriate support and suggestions to improve the user experience based on the results.

[0865] This invention relates to a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a presentation file. Furthermore, it aims to provide a better user experience by combining it with an emotion engine that analyzes user emotions.

[0866] This system includes input means, preprocessing means, analysis means, extraction means, generation means, and sentiment analysis means. The specific implementation methods for each means are described below.

[0867] Input means

[0868] Users provide store operation data to the system using a web application or mobile application. This interface is implemented as a web application built with React or Vue.js, or as a mobile application developed with Flutter or Kotlin. In addition, the system inputs the user's voice and facial expressions using a voice recognition device (e.g., a speech recognition device) or a camera.

[0869] Pretreatment means

[0870] The server preprocesses the data received from user input. Specifically, it uses Python and the Pandas library to read the data, impute missing values, remove outliers, and standardize the data. For example, missing values ​​are imputed with the mean of past data, and outliers are detected using Z-scores and corrected as needed.

[0871] Analysis means

[0872] The server analyzes pre-processed data using AI models. Text data from customer feedback is analyzed using natural language processing models (e.g., BERT model) to extract specific keywords and trends. Time series analysis of sales data uses machine learning models (e.g., Prophet model) to identify trends and seasonality.

[0873] extraction means

[0874] The server extracts and organizes the results of the analysis. Specifically, it categorizes the analysis results into categories such as "points for increasing sales" and "areas for improvement in customer service," and generates graphs and charts for visualization. Data visualization libraries such as Matplotlib and Seaborn are used for this task.

[0875] generation means

[0876] The server automatically generates presentation files based on the data obtained from the extraction method. The generation uses the Python python-pptx library, arranging the analysis results and visualizations into a pre-configured template. For example, the "Improvements in Customer Service" slide would include visualized customer feedback data and related suggestions.

[0877] Emotion analysis means

[0878] The server analyzes the user's emotions from their voice and facial expressions. It uses a speech analysis API for speech recognition and OpenCV for facial expression recognition. Based on the results of the emotion analysis, if the user is feeling stressed, it will provide simple instructions or help information; if the user is satisfied, it will display additional suggestions or promotional information.

[0879] Specific examples

[0880] For example, a user uploads files such as "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and imputes and corrects missing or outlier values. Next, an AI model is used to analyze the data, extracting trends in customer feedback such as "slow service" and "high prices," and identifying trends through time-series analysis of sales data. After that, the analysis results are organized and visualized data is generated. Finally, a presentation file is automatically generated and made available for the user to download.

[0881] Furthermore, if the sentiment analysis engine determines that the user is experiencing stress during user data entry, the system will provide the user with easy-to-follow instructions and help information. On the other hand, if the system recognizes that the user is satisfied, it will suggest additional features or relevant promotional information.

[0882] This system allows users to easily input data, automatically extract areas for improvement in store operations, and generate materials that present concrete action plans. Furthermore, by providing support tailored to the user's emotional state, it can deliver an excellent user experience.

[0883] Example of a prompt

[0884] Based on sales data, customer feedback, and inventory data, identify areas for improvement in store operations and generate a PowerPoint presentation. The data should also include trends in customer feedback such as "slow service" and "high prices." Furthermore, conduct user sentiment analysis to provide appropriate support.

[0885] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0886] Step 1:

[0887] The user opens the web or mobile application. The user selects sales data, customer feedback, and inventory data files and uploads them to the interface. For example, the user selects "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" and clicks the upload button. The input is a store operation data file, and the output is the upload of data into the system.

[0888] Step 2:

[0889] The server receives the uploaded data and stores it in temporary storage. For example, it might use a cloud storage service (e.g., an AWS S3 bucket) to store these files. The input is the data file uploaded by the user, and the output is the temporary file stored on the server.

[0890] Step 3:

[0891] The server preprocesses the stored data. It uses Python and the Pandas library to read CSV and Excel files. The `fillna` method is used for missing value imputation, and Z-scores are used for anomaly detection. The input is a raw data file on the server, and the output is a preprocessed dataset.

[0892] Step 4:

[0893] The server analyzes pre-processed data using an AI model. Customer feedback text data is analyzed using a natural language processing model (e.g., BERT model) to extract trends and keywords. For time-series analysis of sales data, a machine learning model (e.g., Prophet model) is used to identify trends and seasonality. The input is pre-processed data, and the output is the analysis result.

[0894] Step 5:

[0895] The server extracts and organizes the results of the analysis. Specifically, it uses Matplotlib and Seaborn to visualize the analysis results and create graphs and charts. The analysis results are categorized into categories such as "points for increasing sales" and "areas for improvement in customer service." The input is the analysis results, and the output is the visualized data and the categorized results.

[0896] Step 6:

[0897] The server generates a presentation file based on the visualized data. Using the python-pptx library, slides are automatically created according to a pre-configured template. For example, the "Customer Service Improvements" slide will include a pie chart of customer feedback data and related suggestions. The input is the visualized data and classification results, and the output is a presentation file in PowerPoint format.

[0898] Step 7:

[0899] The server saves the generated presentation file and provides the user with a download link. Alternatively, the PPT file can be saved to a cloud storage service (e.g., an AWS S3 bucket), and the download link can be emailed to the user or displayed on a web application. The input is the generated presentation file, and the output is the download link to the user.

[0900] Step 8:

[0901] The server analyzes the user's emotions from their voice and facial expressions. It uses a speech analysis API (e.g., Google Speech-to-Text) for speech recognition and OpenCV for facial expression recognition. It analyzes emotional states such as stress and satisfaction, and provides appropriate support information based on the results. Input is the user's voice and facial expression data, and output is the emotion analysis results and the provided support information.

[0902] (Application Example 2)

[0903] Next, we will explain application example 2. In the following explanation, 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."

[0904] Traditionally, analyzing store operation data and identifying areas for improvement required a tremendous amount of time and effort, and creating presentation materials to effectively utilize the analysis results was also time-consuming. Furthermore, it was impossible to grasp user emotions, limiting the potential for improving the user experience. Therefore, there was a strong demand for a system that could simultaneously achieve both increased efficiency in store operations and improved user experience.

[0905] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0906] In this invention, the server includes a user input means for inputting store operation data, a server pre-processing means for pre-processing the data received from the user input means, an AI analysis means for analyzing the data pre-processed by the pre-processing means, a data extraction means for extracting the analysis results of the AI ​​analysis means, a PPT generation means for generating a PPT file based on the extraction results of the data extraction means, and an emotion engine that recognizes the user's emotions and suggests recommended actions to improve the user experience. This enables a consistent process from analyzing store operation data to extracting areas for improvement and automatically generating presentation materials, as well as providing support that reflects the user's emotions.

[0907] A "user input method" is an interface for users to provide store operation data to the system, and it has the function of uploading sales data, customer feedback, inventory data, etc., through web applications or mobile applications.

[0908] A "server preprocessing means" is a device that has the function of preprocessing data received from a user input means, and performs tasks such as imputing missing values, removing outliers, and standardizing data.

[0909] "AI analysis tools" are those that analyze pre-processed data, extract specific keywords and trends using natural language processing models and machine learning models, and perform time-series analysis of sales data.

[0910] A "data extraction tool" is a tool that extracts the analysis results from an AI analysis tool, classifies them into categories such as points for increasing sales, areas for improving customer service, and points for optimizing inventory management, and further generates graphs and charts to visualize that data.

[0911] The "PPT generation means" has the function of automatically generating a presentation in PowerPoint format based on the results obtained from the data extraction means, and creates slides using a pre-configured template.

[0912] An "emotion engine" is a system that analyzes a user's emotions from their voice and facial expressions and suggests recommended actions to improve the user experience. It uses voice analysis and facial expression analysis to understand the user's emotional state.

[0913] This invention is a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. The system includes a user input means, a server pre-processing means, an AI analysis means, a data extraction means, a PowerPoint generation means, and an emotion engine.

[0914] system

[0915] 1. User input means

[0916] The user input mechanism is an interface for users to provide store operation data to the system. Specifically, users upload sales data, customer feedback, inventory data, etc., using smartphones or personal computers. This interface is implemented as a web application or mobile application. It also includes voice recognition devices and cameras to capture the user's voice and facial expressions from resources.

[0917] 2. Server preprocessing means

[0918] The server preprocessing mechanism has the function of preprocessing data received from the user input mechanism. Preprocessing includes imputing missing values, removing outliers, and standardizing data. Specifically, if sales data contains missing values, the server imputates them with the average value of past data. For outliers, statistical methods are used to identify them, and the data is removed or corrected as necessary.

[0919] 3. AI analysis means

[0920] The AI ​​analysis tool has the ability to analyze pre-processed data. This analysis utilizes natural language processing models and machine learning models. The natural language processing model analyzes text data from customer feedback to extract specific keywords and trends. For example, it detects trends such as "slow service" and "high prices." The machine learning model performs time-series analysis of sales data to identify seasonality and trends. It also identifies the causes of sudden increases or decreases in sales.

[0921] 4. Data extraction means

[0922] The data extraction mechanism extracts and organizes the analysis results from the AI ​​analysis mechanism. This mechanism categorizes the analysis results into categories such as "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management." Furthermore, it generates graphs and charts to visualize the data. For sales data, it creates time-series graphs and bar graphs, and for customer feedback, it generates pie charts showing the ratio of negative to positive feedback.

[0923] 5. PPT generation means

[0924] The PPT generation means automatically generates a presentation in PowerPoint format based on the results obtained from the data extraction means. These slides are generated using a pre-configured template. The template includes a title slide, various analysis results slides, and proposal slides. For example, the "Areas for Improvement in Customer Service" slide contains the analysis results of customer feedback and related graphs, and the "Points for Increasing Sales" slide contains sales data trends and their interpretation.

[0925] 6. Emotional Engine

[0926] The emotion engine has the ability to analyze emotions from the user's voice and facial expressions. It uses voice analysis and facial expression analysis to understand the user's emotional state. Based on the results of the emotion engine's analysis, it suggests actions to improve the user experience. For example, if the user is feeling stressed, it provides simpler instructions or support information. Conversely, if the user is satisfied, it presents additional suggestions or promotional information.

[0927] Specific example

[0928] Example of a prompt

[0929] Let's assume a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and fills in and corrects missing values ​​and outliers. Next, an AI analysis tool analyzes the data, extracting trends in customer feedback such as "slow service" and "high prices," and identifies seasonality and trends through time-series analysis of sales data. After that, a data extraction tool organizes the analysis results and generates visualized data. Finally, a PPT generation tool creates a PPT file based on these results and makes it available for the user to download.

[0930] Furthermore, if the emotion engine analyzes that the user is experiencing stress while entering data, the system provides the user with simple instructions and help information. On the other hand, if the system recognizes that the user is satisfied, it presents additional feature suggestions and relevant promotional information. In this way, the system of the present invention can automatically extract points for improvement in store operations and generate materials that present concrete action plans simply by having the user enter data, and can provide a better user experience by providing support that corresponds to the user's emotional state.

[0931] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0932] Step 1: Users upload sales data, customer feedback, and inventory data to the system interface using their smartphones or personal computers.

[0933] Inputs: Sales data, customer feedback, inventory data

[0934] Output: Various data files sent to the server

[0935] Step 2: The server preprocessing device preprocesses the received data. Specifically, it imputes missing values ​​with the mean and identifies and removes outliers using statistical methods.

[0936] Input: Various data files sent to the server

[0937] Output: Preprocessed data with missing values ​​imputed and outliers removed.

[0938] Step 3: The server's AI analysis tools analyze the pre-processed data. A natural language processing model analyzes the text data of customer feedback, extracting specific keywords and trends. In addition, a machine learning model is used to perform time-series analysis of sales data to identify seasonality, trends, and the causes of sudden increases or decreases in sales.

[0939] Input: Preprocessed data

[0940] Output: Analysis results (keywords, trends, time series analysis results, etc.)

[0941] Step 4: The server's data extraction tool extracts the analysis results from the AI ​​analysis tool and categorizes them into points for increasing sales, areas for improving customer service, and points for optimizing inventory management. It also generates graphs and charts to visualize the data.

[0942] Input: Analysis results

[0943] Output: Classified analysis results, visualized graphs and charts

[0944] Step 5: The server's PPT generation means automatically generates a PPT file using a pre-configured template based on the results obtained from the data extraction means.

[0945] Input: Classified analysis results, visualized graphs and charts

[0946] Output: Presentation file in PPT format

[0947] Step 6: The emotion engine analyzes the voice and facial expressions of the user using the interface. It uses voice analysis and facial expression analysis to understand the user's emotional state.

[0948] Input: User voice data, facial expression data

[0949] Output: User's emotional state

[0950] Step 7: The server's emotion engine suggests actions based on the user's emotional state. For example, if the user is stressed, it provides simple instructions or help information; if the user is satisfied, it provides additional suggestions or promotional information.

[0951] Input: User's emotional state

[0952] Output: Recommended actions (simple instructions, help information, additional suggestions, promotional information, etc.)

[0953] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0954] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0955] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0956] [Fourth Embodiment]

[0957] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0958] As shown in Figure 7, the 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.

[0959] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0960] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0961] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0962] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0963] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0964] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0965] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0966] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0967] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0968] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0969] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0970] This document describes a specific example of a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. The system for implementing the present invention includes a user input means, a server pre-processing means, an AI analysis means, a data extraction means, and a PowerPoint generation means.

[0971] Overall system flow

[0972] User input means

[0973] The user input mechanism is an interface for users to provide store operation data to the system. Through this interface, users upload sales data, customer feedback, inventory data, and so on. This interface can be implemented, for example, as a web application or a mobile application.

[0974] Server Preprocessing Means

[0975] The server preprocessing mechanism has the function of preprocessing data received from the user input mechanism. Preprocessing includes imputing missing values, removing outliers, and standardizing data. For example, if there are missing values ​​in sales data, the server imputates the missing values ​​with the average value of past data. For outliers, statistical methods of data are used to identify the outliers, and the data is removed or corrected as necessary.

[0976] AI analysis means

[0977] AI analysis tools analyze pre-processed data. Natural language processing models and machine learning models are used for this analysis. The natural language processing model analyzes text data from customer feedback to extract specific keywords and trends. For example, it detects trends such as "slow service" and "high prices." The machine learning model performs time-series analysis of sales data to identify seasonality and trends. It also identifies the causes of sudden increases or decreases in sales.

[0978] Data extraction means

[0979] The data extraction tool has the function of extracting and organizing the analysis results of the AI ​​analysis tool. For example, it classifies the analysis results into categories such as "points for increasing sales," "areas for improvement in customer service," and "points for optimizing inventory management." Furthermore, it generates graphs and charts to visualize the data. For sales data, it creates line graphs and bar graphs, and for customer feedback, it generates pie charts showing the ratio of positive to negative feedback.

[0980] PPT generation means

[0981] The PPT generation means automatically generates a presentation in PowerPoint format based on the results obtained from the data extraction means. The slides are generated using pre-configured templates. The templates include title slides, various analysis result slides, proposal slides, etc. For example, the "Areas for Improvement in Customer Service" slide will contain the analysis results of customer feedback and related graphs, and the "Points for Increasing Sales" slide will contain sales data trends and their interpretations.

[0982] Specific examples

[0983] For example, suppose a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and fills in or corrects missing or outlier values. Next, an AI analysis tool analyzes the data, extracts trends in customer feedback such as "the service is slow" or "the price is high," and identifies seasonality and trends through time-series analysis of sales data. Subsequently, a data extraction tool organizes the analysis results and generates visualized data. Finally, a PPT generation tool creates a PPT file based on these results and makes it available for the user to download.

[0984] In this way, the system of the present invention can automatically extract points for improvement in store operations and generate materials that present concrete action plans simply by having the user input data. This enables the streamlining and optimization of store operations.

[0985] The following describes the processing flow.

[0986] Step 1:

[0987] Users upload store operation data to the system through an interface. The data, including sales data, customer feedback, and inventory data, is provided in CSV and Excel file formats.

[0988] Step 2:

[0989] The server receives data files uploaded by users. During this process, it also verifies the file format and performs security checks. For example, it checks if the file extension is CSV or XLSX and then performs a virus scan.

[0990] Step 3:

[0991] The server preprocesses the received data. Specifically, if missing values ​​exist, they are imputed using the mean or mode of past data. If outliers are detected, they are removed or corrected using statistical methods.

[0992] Step 4:

[0993] The server inputs pre-processed data into the AI ​​model. Natural language processing (NLP) and machine learning (ML) models are applied to store operation data. For example, the NLP model analyzes text data of customer feedback to extract specific trends and patterns. The ML model performs time-series analysis of sales data to identify seasonality and trends.

[0994] Step 5:

[0995] The server extracts the output results of the AI ​​model using data extraction methods. In this process, important analysis results are categorized into "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management." In addition, bar graphs, line graphs, pie charts, etc., are generated to visualize the analysis results.

[0996] Step 6:

[0997] The server uses a template to generate a PowerPoint file. Each slide in the PowerPoint file contains extracted data and visualizations. For example, "Areas for Improvement in Customer Service" displays customer feedback trends and related graphs, while "Points for Increasing Sales" includes sales data trend graphs and detailed analysis.

[0998] Step 7:

[0999] The server generates the final PPT file and saves it for the user to download. The file is either stored in cloud storage or provided directly to the user.

[1000] Step 8:

[1001] Users can download PowerPoint files from the system and use them as reference material to understand specific areas for improvement in store operations and to develop necessary action plans.

[1002] Through the above processing steps, this system enables users to efficiently analyze store operation data, identify areas for improvement, and generate effective presentation materials.

[1003] (Example 1)

[1004] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1005] Analyzing traditional store operation data, identifying areas for improvement, and compiling them into presentations was a manual process that required considerable effort and time. Furthermore, the accuracy of the analysis and the quality of the result visualization depended heavily on the skills of the person performing the analysis, leading to significant inconsistencies. This resulted in a challenge in achieving sufficient efficiency and optimization of store operations.

[1006] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1007] In this invention, the server includes a user input means for inputting store operation data, a data processing means for pre-processing the data received from the user input means, an artificial intelligence analysis means for analyzing the data pre-processed by the data processing means, a data extraction means for extracting, organizing, and visualizing the analysis results of the artificial intelligence analysis means, a generation means for automatically generating a presentation in PowerPoint format based on the organized and visualized results of the data extraction means, and a means for enabling the user to download the PowerPoint file generated by the generation means. This makes it possible to automatically extract points for improvement in store operations and generate high-quality presentation materials in a short time simply by having the user input data.

[1008] A "user input method" is an interface for users to provide store operation data to the system. Sales data, customer feedback, inventory data, etc., can be uploaded via a web application or mobile application.

[1009] A "data processing device" is a device that has the function of pre-processing data received from a user input device. By imputing missing values, removing outliers, and standardizing the data, it prepares the data to facilitate subsequent analysis.

[1010] "Artificial intelligence analysis tools" are used to analyze pre-processed data. Specifically, they use natural language processing models and machine learning models to extract trends in customer feedback and time-series patterns in sales data.

[1011] A "data extraction tool" is a device that extracts, organizes, and visualizes the results analyzed by an artificial intelligence analysis tool. It classifies the analysis results into categories and generates visual data such as line graphs and pie charts.

[1012] The "generation means" is a system that automatically generates PowerPoint presentations based on the organized and visualized data obtained from the data extraction means. It creates slides using templates and generates high-quality presentation materials.

[1013] The "download method" refers to a function that prepares the generated PPT file for the user to download. It sends a notification to the user, ensuring they can handle the file conveniently.

[1014] This invention is a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. The system includes user input means, data processing means, artificial intelligence analysis means, data extraction means, generation means, and download means.

[1015] User input means

[1016] The user input mechanism is an interface for users to provide store operation data to the system. Through this interface, users can upload data files such as:

[1017] Sales data (e.g., sales_data.csv)

[1018] Customer feedback (e.g., customer_feedback.xlsx)

[1019] Inventory data (e.g., inventory_data.csv)

[1020] The interface will be implemented as a web application or a mobile application.

[1021] Data processing means

[1022] The server preprocesses the data received from the user input. Specifically, it performs the following processing:

[1023] Imputation of missing values: If there are missing values ​​in the sales data, they will be imputed using the average value of past data.

[1024] Removing outliers: Using statistical methods to identify outliers in data and then removing or correcting them.

[1025] Data standardization: Converting data into a unified format.

[1026] Artificial intelligence analysis methods

[1027] The artificial intelligence analysis tools implemented on the server analyze the data in the following way:

[1028] Using natural language processing (NLP) models, we extract specific keywords and trends from customer feedback text data. For example, we detect trends such as "slow service" or "high prices."

[1029] We use machine learning (ML) models to perform time-series analysis of sales data to identify seasonality and trends. We also identify the causes of sudden increases and decreases in sales.

[1030] Data extraction means

[1031] The server extracts, organizes, and visualizes the analysis results of the artificial intelligence analysis tools as follows:

[1032] Category classification: Classified into categories such as "Points for increasing sales," "Points for improving customer service," and "Points for optimizing inventory management."

[1033] Graph generation: Generates line graphs, bar graphs, pie charts, etc., to visualize data.

[1034] generation means

[1035] The server automatically generates a PowerPoint presentation based on the organized and visualized data obtained from the data extraction method. Using a template, it creates slides like the following:

[1036] Title slide

[1037] Slides showing various analysis results

[1038] Proposal slides

[1039] For example, a slide titled "Areas for Improvement in Customer Service" would include graphs related to the analysis of customer feedback, while a slide titled "Key Points for Increasing Sales" would include sales data trends and their interpretations.

[1040] Download method

[1041] The server prepares the generated PPT file for the user to download and sends a notification. After receiving the notification, the user can download the generated presentation via the web application or mobile application.

[1042] Specific example

[1043] For example, if a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" via a web interface, the server receives this data and performs imputation of missing values ​​and correction of outliers. Next, an artificial intelligence analysis tool analyzes the data, extracts trends in customer feedback such as "slow service" and "high prices", and identifies seasonality and trends through time-series analysis of sales data. Subsequently, a data extraction tool organizes the analysis results and generates visualized data. Finally, a generation tool creates a PowerPoint file based on these results and makes it available for the user to download.

[1044] An example of a prompt message is: "Analyze the pre-processed sales data and customer feedback to identify areas for improvement in store operations, and then compile them into a PowerPoint presentation."

[1045] This system allows users to automatically extract areas for improvement in store operations simply by inputting data, and generate high-quality presentation materials in a short amount of time.

[1046] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1047] Step 1: User Input

[1048] Users provide store operation data, such as sales data, customer feedback, and inventory data, to the system via a web or mobile application. Specifically, users upload files such as "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" to the interface. The device receives these files and sends them to the server.

[1049] Input files: SalesData.csv, CustomerFeedback.xlsx, InventoryData.csv

[1050] Output: Data file sent to the server

[1051] Step 2: Data reception and preprocessing

[1052] The server receives data files sent by the user. The received data undergoes the following preprocessing:

[1053] Imputation of missing values: If there are missing values ​​in the sales data, the server will imputate them using the average value of past data.

[1054] Removing outliers: Use statistical methods to identify outliers in the data and remove or correct them as needed.

[1055] Data standardization: Converting data in different formats into a unified format.

[1056] Input: Sales data received from users.csv, Customer feedback.xlsx, Inventory data.csv

[1057] Output: Pre-processed sales data, customer feedback, inventory data

[1058] Step 3: Data Analysis

[1059] The artificial intelligence analysis tools implemented on the server analyze the pre-processed data. The following analysis is performed:

[1060] Using natural language processing (NLP) models, we extract specific keywords and trends from customer feedback text data. For example, we detect trends such as "slow service" and "high prices."

[1061] We use machine learning (ML) models to perform time-series analysis of sales data to identify seasonality and trends. We also identify the causes of increases and decreases in sales.

[1062] Input: Pre-processed sales data, customer feedback, inventory data

[1063] Output: Trends in analyzed sales data, trends in customer feedback

[1064] Step 4: Data Extraction and Visualization

[1065] The server extracts the analysis results from the artificial intelligence analysis tools and organizes them as follows:

[1066] Category classification: Classified into categories such as "Points for increasing sales," "Points for improving customer service," and "Points for optimizing inventory management."

[1067] Visualization: Graph the analysis results. For sales data, create line graphs or bar graphs; for customer feedback, create pie charts.

[1068] Input: Trends in analyzed sales data, trends in customer feedback

[1069] Output: Organized and visualized data (line graphs, bar graphs, pie charts)

[1070] Step 5: Generate PowerPoint

[1071] The server automatically generates a PowerPoint presentation based on the organized and visualized data obtained from the data extraction method. The following template is used to create the slides:

[1072] Title slide

[1073] Slides showing various analysis results

[1074] Proposal slides

[1075] For example, a slide titled "Areas for Improvement in Customer Service" would include graphs related to the analysis of customer feedback, while a slide titled "Key Points for Increasing Sales" would include sales data trends and their interpretations.

[1076] Input: Organized and visualized data

[1077] Output: Generated PPT file

[1078] Step 6: Download preparation and notification

[1079] The server prepares the generated PPT file for the user to download and sends a notification. The user receives the notification and can download the generated presentation via the web application or mobile application.

[1080] Input: Generated PPT file

[1081] Output: Downloadable PPT file, notification to the user

[1082] In this way, the system can automatically extract points for improvement in store operations and generate high-quality presentation materials in a short time, simply by the user inputting data.

[1083] (Application Example 1)

[1084] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1085] In store operations, there is a need to efficiently analyze large amounts of data and quickly identify areas for improvement. However, current systems have cumbersome data preprocessing and analysis methods, and there is a lack of means to provide the results to store managers and staff in a quick and easy-to-understand format. As a result, there is a challenge in that real-time response and improvement are difficult.

[1086] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1087] In this invention, the server includes a user input means for inputting store operation data, a server pre-processing means for pre-processing the data received from the user input means, an AI analysis means for analyzing the data pre-processed by the pre-processing means, a data extraction means for extracting the analysis results of the AI ​​analysis means, a PPT generation means for generating a PPT file based on the extraction results of the data extraction means, and a notification means for notifying smart glasses of the PPT file in real time. This enables store operators and staff to check areas for improvement in operations in real time during their daily work and respond quickly and effectively.

[1088] A "user input method" is an interface for providing store operation data to the system.

[1089] "Server preprocessing means" refers to a server component that has the function of preprocessing data received from user input means.

[1090] "AI analysis methods" refer to methods that use artificial intelligence technology to analyze pre-processed data and derive analysis results.

[1091] A "data extraction means" is a means that has the function of extracting and organizing the analysis results obtained by the AI ​​analysis means.

[1092] A "PPT generation means" is a means for automatically generating a PowerPoint (presentation) file based on data obtained from a data extraction means.

[1093] A "notification method" is a means that has the function of notifying store operators and staff of the generated PPT file in real time using their smart glasses.

[1094] The system for implementing the present invention automates a series of steps, including inputting and analyzing store operation data, extracting areas for improvement, and generating a presentation file. The system includes the following means:

[1095] 1. User Input Method: This is an interface for users to provide store operation data to the system. It is implemented as a web application or mobile application and allows users to upload sales data, customer feedback, inventory data, etc.

[1096] 2. Server preprocessing means: This means that the server has the function of preprocessing the data received from the user input means. Preprocessing includes imputing missing values, removing outliers, and standardizing the data. Specifically, it reads the data using the pandas library, imputes missing values ​​using sklearn.impute.SimpleImputer, and removes outliers.

[1097] 3. AI Analysis Methods: Pre-processed data is analyzed. Natural language processing models (using the transformers library) and machine learning models (using RandomForestRegressor) are used for the analysis. The natural language processing model analyzes text data of customer feedback and extracts specific keywords and trends. The machine learning model performs time-series analysis of sales data to identify seasonality and trends.

[1098] 4. Data Extraction Method: This method has the function of extracting and organizing the analysis results of the AI ​​analysis method. Specifically, it classifies the data into points for increasing sales, points for improving customer service, points for optimizing inventory management, etc., and generates graphs and charts for visualization.

[1099] 5. PPT Generation Method: Based on the results obtained from the data extraction method, a presentation in PowerPoint format is automatically generated. This uses the python-pptx library. The slides are generated using a pre-configured template and include a title slide, various analysis result slides, proposal slides, etc.

[1100] 6. Notification Method: The generated PPT file will be sent in real time to the smart glasses of store operators and staff. This will allow them to check for areas for improvement in operations in real time during their daily work and take quick action.

[1101] Specific example

[1102] For example, suppose a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and uses pandas and scikit-learn to impute and correct missing values ​​and outliers. Next, it analyzes the data using the transformers library and RandomForestRegressor to extract trends in customer feedback such as "slow service" or "high prices", and performs time-series analysis of the sales data. After that, it visualizes the analysis results in graphs and charts using pyplot and generates a PowerPoint file using python-pptx. Finally, this PowerPoint file is displayed in real time on smart glasses.

[1103] Example of a prompt

[1104] "Based on customer feedback text data from the first quarter of 2023, please identify the main customer complaints and areas for improvement."

[1105] "Use the sales data from the first quarter of 2023 to generate a sales forecast for the next quarter."

[1106] This system enables store operators and staff to efficiently analyze store operation data, quickly identify areas for improvement, and take action.

[1107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1108] Step 1:

[1109] Users upload store operation data (e.g., sales data.csv, customer feedback.xlsx, inventory data.csv) through user input methods. This allows users to provide the necessary data to the system.

[1110] Step 2:

[1111] The server preprocesses the data received from the user input using its own preprocessing mechanism. This preprocessing involves reading the data using pandas, imputing missing values ​​(sklearn.impute.SimpleImputer), and removing outliers (interquartile range method). This results in clean data.

[1112] Step 3:

[1113] The server analyzes pre-processed data using AI analysis tools. Specifically, it uses the transformers library for natural language processing to extract keywords and trends from customer feedback. It also performs time-series analysis of sales data using a machine learning model (RandomForestRegressor). This allows for the identification of customer dissatisfactions and sales predictions.

[1114] Step 4:

[1115] The server extracts and organizes the analysis results from the AI ​​analysis using data extraction tools. The results are categorized into "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management," and graphs and charts are generated using pyplot for visualization. This results in data that is easy to understand visually.

[1116] Step 5:

[1117] The server generates a PowerPoint presentation file based on the data obtained from the data extraction means using a PowerPoint generation means. Using the python-pptx library, slides are automatically created according to a pre-prepared template. This provides a PowerPoint file that the user can use immediately.

[1118] Step 6:

[1119] The server uses a notification system to send generated PowerPoint files to the smart glasses of store operators and staff in real time. This allows users to check for operational improvements in real time during their daily work and take quick action.

[1120] By executing each step in this order, efficient analysis of store operation data and rapid improvement can be achieved.

[1121] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1122] This invention relates to a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. Furthermore, it aims to improve the user experience by combining it with an emotion engine that recognizes user emotions. The system for carrying out this invention includes a user input means, a server pre-processing means, an AI analysis means, a data extraction means, a PowerPoint generation means, and an emotion engine.

[1123] Overall system flow

[1124] User input means

[1125] The user input mechanism is an interface for users to provide store operation data to the system. Through this interface, users upload sales data, customer feedback, inventory data, and so on. This interface can be implemented, for example, as a web application or mobile application. It may also include voice recognition devices and cameras for inputting the user's voice and facial expressions.

[1126] Server Preprocessing Means

[1127] The server preprocessing mechanism has the function of preprocessing data received from the user input mechanism. Preprocessing includes imputing missing values, removing outliers, and standardizing data. For example, if there are missing values ​​in sales data, the server imputates the missing values ​​with the average value of past data. For outliers, statistical methods of data are used to identify the outliers, and the data is removed or corrected as necessary.

[1128] AI analysis means

[1129] AI analysis tools analyze pre-processed data. Natural language processing models and machine learning models are used for this analysis. The natural language processing model analyzes text data from customer feedback to extract specific keywords and trends. For example, it detects trends such as "slow service" and "high prices." The machine learning model performs time-series analysis of sales data to identify seasonality and trends. It also identifies the causes of sudden increases or decreases in sales.

[1130] Data extraction means

[1131] The data extraction tool has the function of extracting and organizing the analysis results of the AI ​​analysis tool. For example, it classifies the analysis results into categories such as "points for increasing sales," "areas for improvement in customer service," and "points for optimizing inventory management." Furthermore, it generates graphs and charts to visualize the data. For sales data, it creates line graphs and bar graphs, and for customer feedback, it generates pie charts showing the ratio of positive to negative feedback.

[1132] PPT generation means

[1133] The PPT generation means automatically generates a presentation in PowerPoint format based on the results obtained from the data extraction means. The slides are generated using pre-configured templates. The templates include title slides, various analysis result slides, proposal slides, etc. For example, the "Areas for Improvement in Customer Service" slide will contain the analysis results of customer feedback and related graphs, and the "Points for Increasing Sales" slide will contain sales data trends and their interpretations.

[1134] Emotional Engine

[1135] The emotion engine has the ability to analyze emotions from the user's voice and facial expressions. For example, it analyzes the tone of voice and facial expressions while the user is using the interface to understand the user's emotional state. Voice analysis and facial expression analysis are used for emotion recognition.

[1136] Furthermore, based on the analysis results of the emotion engine, it suggests recommended actions to improve the user experience. For example, if a user is experiencing stress, it provides simpler instructions or support information. Conversely, if a user is satisfied, it presents additional suggestions or promotional information.

[1137] Specific examples

[1138] For example, suppose a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and fills in or corrects missing or outlier values. Next, an AI analysis tool analyzes the data, extracts trends in customer feedback such as "slow service" and "high prices", and identifies seasonality and trends through time-series analysis of sales data. Subsequently, a data extraction tool organizes the analysis results and generates visualized data. Finally, a PPT generation tool creates a PPT file based on these results and makes it available for the user to download.

[1139] Furthermore, if the emotion engine analyzes that a user is experiencing stress while entering data, the system will provide the user with simple instructions and help information. On the other hand, if the system perceives that the user is satisfied, it will suggest additional features or relevant promotional information.

[1140] In this way, the system of the present invention can automatically extract points for improvement in store operations and generate materials that present concrete action plans simply by the user inputting data, and can also provide a better user experience by providing support that responds to the user's emotional state.

[1141] The following describes the processing flow.

[1142] Step 1:

[1143] Users upload store operation data to the system through an interface. The data, including sales data, customer feedback, and inventory data, is provided in CSV and Excel file formats. User voice data and facial expression data are also collected.

[1144] Step 2:

[1145] The server receives data files uploaded by users. During this process, it verifies the file format and performs security checks. It confirms that the file extension is CSV or XLSX and then performs a virus scan.

[1146] Step 3:

[1147] The server preprocesses the received data. Specifically, if missing values ​​exist, they are imputed using the mean or mode of past data. If outliers are detected, they are removed or corrected using statistical methods. In addition, the data is standardized to unify all data formats.

[1148] Step 4:

[1149] The server inputs pre-processed data into an AI model. Using a natural language processing model, it analyzes the text data of customer feedback and extracts specific keywords and trends. For example, it detects trends such as "slow service" and "high prices."

[1150] Step 5:

[1151] The server uses a machine learning model to perform time-series analysis of sales data. It identifies seasonality and trends from the data and pinpoints the causes of sudden increases or decreases in sales. Specifically, if a particular event was held on a day when sales surged, it extracts that information.

[1152] Step 6:

[1153] The server extracts the output results of the AI ​​model using data extraction methods. In this process, the analysis results are categorized into areas such as "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management." In addition, bar graphs, line graphs, pie charts, etc., are generated to visualize the analysis results.

[1154] Step 7:

[1155] The server generates the PPT file using a template. First, a title slide is created, followed by slides containing various analysis results and proposals. The "Areas for Improvement in Customer Service" slide contains analysis results of customer feedback and related graphs. The "Points for Increasing Sales" slide contains sales data trends and their interpretation.

[1156] Step 8:

[1157] The server uses an emotion engine to analyze the user's emotions. Based on the voice and facial expression data provided by the user during data entry, it performs speech recognition and facial expression analysis to identify the user's emotional state. For example, if the user is feeling stressed, that information is analyzed.

[1158] Step 9:

[1159] The server suggests actions to improve the user experience based on the analysis results of the emotion engine. If the user is experiencing stress, it provides simple instructions and help information. If the user is satisfied, it suggests additional features and relevant promotional information.

[1160] Step 10:

[1161] The server generates the final PPT file and saves it for the user to download. The file is either stored in cloud storage or provided directly to the user.

[1162] Step 11:

[1163] Users download PowerPoint files from the system and use them as reference material to understand specific areas for improvement in store operations and to develop necessary action plans.

[1164] Through the above processing steps, this system enables users to efficiently analyze store operation data, identify areas for improvement, and generate effective presentation materials. Furthermore, by providing support that responds to the user's emotional state, it can deliver an excellent user experience.

[1165] (Example 2)

[1166] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1167] Current store operations require a significant amount of time and effort to manually analyze large amounts of data, identify areas for improvement, and compile them into presentations. Furthermore, the emotional state of users when using the system is not considered, which can lead to stress. Therefore, there is a need for a system that efficiently and automatically analyzes store operation data, identifies areas for improvement, and provides support tailored to the emotional state of users.

[1168] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for inputting store operation data, a preprocessing means for preprocessing the data received from the input means, an analysis means for analyzing the data preprocessed by the preprocessing means, an extraction means for extracting the analysis results of the analysis means, a generation means for generating a presentation file based on the extraction results of the extraction means, and an emotion analysis means for recognizing the user's emotions. This enables efficient analysis of store operation data, extraction of areas for improvement, automatic generation of presentations, and support tailored to the user's emotional state.

[1169] "Store operation data" refers to all data related to store operations, such as sales data, customer feedback, and inventory data.

[1170] An "input method" is an interface for users to provide store operation data to the system, and is implemented as a web application or mobile application.

[1171] "Preprocessing means" refers to means of performing preprocessing on data received from input means, such as imputing missing values, removing outliers, and standardizing data.

[1172] "Analysis means" refers to means that include natural language processing models that analyze pre-processed data and extract specific keywords or trends, and machine learning models that perform time-series analysis of sales data.

[1173] "Extraction means" refers to means for extracting and organizing the analysis results of the analysis means, and includes category classification and the generation of graphs and charts for visualization.

[1174] The "generation means" refers to a means for automatically generating presentation files based on the results obtained from the extraction means, and has the function of automatically generating slides using templates.

[1175] "Emotional analysis methods" are means of analyzing a user's emotions from their voice and facial expressions, and then providing appropriate support and suggestions to improve the user experience based on the results.

[1176] This invention relates to a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a presentation file. Furthermore, it aims to provide a better user experience by combining it with an emotion engine that analyzes user emotions.

[1177] This system includes input means, preprocessing means, analysis means, extraction means, generation means, and sentiment analysis means. The specific implementation methods for each means are described below.

[1178] Input means

[1179] Users provide store operation data to the system using a web application or mobile application. This interface is implemented as a web application built with React or Vue.js, or as a mobile application developed with Flutter or Kotlin. In addition, the system inputs the user's voice and facial expressions using a voice recognition device (e.g., a speech recognition device) or a camera.

[1180] Pretreatment means

[1181] The server preprocesses the data received from user input. Specifically, it uses Python and the Pandas library to read the data, impute missing values, remove outliers, and standardize the data. For example, missing values ​​are imputed with the mean of past data, and outliers are detected using Z-scores and corrected as needed.

[1182] Analysis means

[1183] The server analyzes pre-processed data using AI models. Text data from customer feedback is analyzed using natural language processing models (e.g., BERT model) to extract specific keywords and trends. Time series analysis of sales data uses machine learning models (e.g., Prophet model) to identify trends and seasonality.

[1184] extraction means

[1185] The server extracts and organizes the results of the analysis. Specifically, it categorizes the analysis results into categories such as "points for increasing sales" and "areas for improvement in customer service," and generates graphs and charts for visualization. Data visualization libraries such as Matplotlib and Seaborn are used for this task.

[1186] generation means

[1187] The server automatically generates presentation files based on the data obtained from the extraction method. The generation uses the Python python-pptx library, arranging the analysis results and visualizations into a pre-configured template. For example, the "Improvements in Customer Service" slide would include visualized customer feedback data and related suggestions.

[1188] Emotion analysis means

[1189] The server analyzes the user's emotions from their voice and facial expressions. It uses a speech analysis API for speech recognition and OpenCV for facial expression recognition. Based on the results of the emotion analysis, if the user is feeling stressed, it will provide simple instructions or help information; if the user is satisfied, it will display additional suggestions or promotional information.

[1190] Specific examples

[1191] For example, a user uploads files such as "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and imputes and corrects missing or outlier values. Next, an AI model is used to analyze the data, extracting trends in customer feedback such as "slow service" and "high prices," and identifying trends through time-series analysis of sales data. After that, the analysis results are organized and visualized data is generated. Finally, a presentation file is automatically generated and made available for the user to download.

[1192] Furthermore, if the sentiment analysis engine determines that the user is experiencing stress during user data entry, the system will provide the user with easy-to-follow instructions and help information. On the other hand, if the system recognizes that the user is satisfied, it will suggest additional features or relevant promotional information.

[1193] This system allows users to easily input data, automatically extract areas for improvement in store operations, and generate materials that present concrete action plans. Furthermore, by providing support tailored to the user's emotional state, it can deliver an excellent user experience.

[1194] Example of a prompt

[1195] Based on sales data, customer feedback, and inventory data, identify areas for improvement in store operations and generate a PowerPoint presentation. The data should also include trends in customer feedback such as "slow service" and "high prices." Furthermore, conduct user sentiment analysis to provide appropriate support.

[1196] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1197] Step 1:

[1198] The user opens the web or mobile application. The user selects sales data, customer feedback, and inventory data files and uploads them to the interface. For example, the user selects "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" and clicks the upload button. The input is a store operation data file, and the output is the upload of data into the system.

[1199] Step 2:

[1200] The server receives the uploaded data and stores it in temporary storage. For example, it might use a cloud storage service (e.g., an AWS S3 bucket) to store these files. The input is the data file uploaded by the user, and the output is the temporary file stored on the server.

[1201] Step 3:

[1202] The server preprocesses the stored data. It uses Python and the Pandas library to read CSV and Excel files. The `fillna` method is used for missing value imputation, and Z-scores are used for anomaly detection. The input is a raw data file on the server, and the output is a preprocessed dataset.

[1203] Step 4:

[1204] The server analyzes pre-processed data using an AI model. Customer feedback text data is analyzed using a natural language processing model (e.g., BERT model) to extract trends and keywords. For time-series analysis of sales data, a machine learning model (e.g., Prophet model) is used to identify trends and seasonality. The input is pre-processed data, and the output is the analysis result.

[1205] Step 5:

[1206] The server extracts and organizes the results of the analysis. Specifically, it uses Matplotlib and Seaborn to visualize the analysis results and create graphs and charts. The analysis results are categorized into categories such as "points for increasing sales" and "areas for improvement in customer service." The input is the analysis results, and the output is the visualized data and the categorized results.

[1207] Step 6:

[1208] The server generates a presentation file based on the visualized data. Using the python-pptx library, slides are automatically created according to a pre-configured template. For example, the "Customer Service Improvements" slide will include a pie chart of customer feedback data and related suggestions. The input is the visualized data and classification results, and the output is a presentation file in PowerPoint format.

[1209] Step 7:

[1210] The server saves the generated presentation file and provides the user with a download link. Alternatively, the PPT file can be saved to a cloud storage service (e.g., an AWS S3 bucket), and the download link can be emailed to the user or displayed on a web application. The input is the generated presentation file, and the output is the download link to the user.

[1211] Step 8:

[1212] The server analyzes the user's emotions from their voice and facial expressions. It uses a speech analysis API (e.g., Google Speech-to-Text) for speech recognition and OpenCV for facial expression recognition. It analyzes emotional states such as stress and satisfaction, and provides appropriate support information based on the results. Input is the user's voice and facial expression data, and output is the emotion analysis results and the provided support information.

[1213] (Application Example 2)

[1214] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1215] Traditionally, analyzing store operation data and identifying areas for improvement required a tremendous amount of time and effort, and creating presentation materials to effectively utilize the analysis results was also time-consuming. Furthermore, it was impossible to grasp user emotions, limiting the potential for improving the user experience. Therefore, there was a strong demand for a system that could simultaneously achieve both increased efficiency in store operations and improved user experience.

[1216] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1217] In this invention, the server includes a user input means for inputting store operation data, a server pre-processing means for pre-processing the data received from the user input means, an AI analysis means for analyzing the data pre-processed by the pre-processing means, a data extraction means for extracting the analysis results of the AI ​​analysis means, a PPT generation means for generating a PPT file based on the extraction results of the data extraction means, and an emotion engine that recognizes the user's emotions and suggests recommended actions to improve the user experience. This enables a consistent process from analyzing store operation data to extracting areas for improvement and automatically generating presentation materials, as well as providing support that reflects the user's emotions.

[1218] A "user input method" is an interface for users to provide store operation data to the system, and it has the function of uploading sales data, customer feedback, inventory data, etc., through web applications or mobile applications.

[1219] A "server preprocessing means" is a device that has the function of preprocessing data received from a user input means, and performs tasks such as imputing missing values, removing outliers, and standardizing data.

[1220] "AI analysis tools" are those that analyze pre-processed data, extract specific keywords and trends using natural language processing models and machine learning models, and perform time-series analysis of sales data.

[1221] A "data extraction tool" is a tool that extracts the analysis results from an AI analysis tool, classifies them into categories such as points for increasing sales, areas for improving customer service, and points for optimizing inventory management, and further generates graphs and charts to visualize that data.

[1222] The "PPT generation means" has the function of automatically generating a presentation in PowerPoint format based on the results obtained from the data extraction means, and creates slides using a pre-configured template.

[1223] An "emotion engine" is a system that analyzes a user's emotions from their voice and facial expressions and suggests recommended actions to improve the user experience. It uses voice analysis and facial expression analysis to understand the user's emotional state.

[1224] This invention is a system that automatically analyzes store operation data, extracts areas for improvement, and compiles them into a PowerPoint presentation. The system includes a user input means, a server pre-processing means, an AI analysis means, a data extraction means, a PowerPoint generation means, and an emotion engine.

[1225] system

[1226] 1. User input means

[1227] The user input mechanism is an interface for users to provide store operation data to the system. Specifically, users upload sales data, customer feedback, inventory data, etc., using smartphones or personal computers. This interface is implemented as a web application or mobile application. It also includes voice recognition devices and cameras to capture the user's voice and facial expressions from resources.

[1228] 2. Server preprocessing means

[1229] The server preprocessing mechanism has the function of preprocessing data received from the user input mechanism. Preprocessing includes imputing missing values, removing outliers, and standardizing data. Specifically, if sales data contains missing values, the server imputates them with the average value of past data. For outliers, statistical methods are used to identify them, and the data is removed or corrected as necessary.

[1230] 3. AI analysis means

[1231] The AI ​​analysis tool has the ability to analyze pre-processed data. This analysis utilizes natural language processing models and machine learning models. The natural language processing model analyzes text data from customer feedback to extract specific keywords and trends. For example, it detects trends such as "slow service" and "high prices." The machine learning model performs time-series analysis of sales data to identify seasonality and trends. It also identifies the causes of sudden increases or decreases in sales.

[1232] 4. Data extraction means

[1233] The data extraction mechanism extracts and organizes the analysis results from the AI ​​analysis mechanism. This mechanism categorizes the analysis results into categories such as "points for increasing sales," "areas for improving customer service," and "points for optimizing inventory management." Furthermore, it generates graphs and charts to visualize the data. For sales data, it creates time-series graphs and bar graphs, and for customer feedback, it generates pie charts showing the ratio of negative to positive feedback.

[1234] 5. PPT generation means

[1235] The PPT generation means automatically generates a presentation in PowerPoint format based on the results obtained from the data extraction means. These slides are generated using a pre-configured template. The template includes a title slide, various analysis results slides, and proposal slides. For example, the "Areas for Improvement in Customer Service" slide contains the analysis results of customer feedback and related graphs, and the "Points for Increasing Sales" slide contains sales data trends and their interpretation.

[1236] 6. Emotional Engine

[1237] The emotion engine has the ability to analyze emotions from the user's voice and facial expressions. It uses voice analysis and facial expression analysis to understand the user's emotional state. Based on the results of the emotion engine's analysis, it suggests actions to improve the user experience. For example, if the user is feeling stressed, it provides simpler instructions or support information. Conversely, if the user is satisfied, it presents additional suggestions or promotional information.

[1238] Specific example

[1239] Example of a prompt

[1240] Let's assume a user uploads "2023 Q1 Sales Data.csv", "Customer Feedback.xlsx", and "Inventory Data.csv" through the interface. The server receives this data and fills in and corrects missing values ​​and outliers. Next, an AI analysis tool analyzes the data, extracting trends in customer feedback such as "slow service" and "high prices," and identifies seasonality and trends through time-series analysis of sales data. After that, a data extraction tool organizes the analysis results and generates visualized data. Finally, a PPT generation tool creates a PPT file based on these results and makes it available for the user to download.

[1241] Furthermore, if the emotion engine analyzes that the user is experiencing stress while entering data, the system provides the user with simple instructions and help information. On the other hand, if the system recognizes that the user is satisfied, it presents additional feature suggestions and relevant promotional information. In this way, the system of the present invention can automatically extract points for improvement in store operations and generate materials that present concrete action plans simply by having the user enter data, and can provide a better user experience by providing support that corresponds to the user's emotional state.

[1242] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1243] Step 1: Users upload sales data, customer feedback, and inventory data to the system interface using their smartphones or personal computers.

[1244] Inputs: Sales data, customer feedback, inventory data

[1245] Output: Various data files sent to the server

[1246] Step 2: The server preprocessing device preprocesses the received data. Specifically, it imputes missing values ​​with the mean and identifies and removes outliers using statistical methods.

[1247] Input: Various data files sent to the server

[1248] Output: Preprocessed data with missing values ​​imputed and outliers removed.

[1249] Step 3: The server's AI analysis tools analyze the pre-processed data. A natural language processing model analyzes the text data of customer feedback, extracting specific keywords and trends. In addition, a machine learning model is used to perform time-series analysis of sales data to identify seasonality, trends, and the causes of sudden increases or decreases in sales.

[1250] Input: Preprocessed data

[1251] Output: Analysis results (keywords, trends, time series analysis results, etc.)

[1252] Step 4: The server's data extraction tool extracts the analysis results from the AI ​​analysis tool and categorizes them into points for increasing sales, areas for improving customer service, and points for optimizing inventory management. It also generates graphs and charts to visualize the data.

[1253] Input: Analysis results

[1254] Output: Classified analysis results, visualized graphs and charts

[1255] Step 5: The server's PPT generation means automatically generates a PPT file using a pre-configured template based on the results obtained from the data extraction means.

[1256] Input: Classified analysis results, visualized graphs and charts

[1257] Output: Presentation file in PPT format

[1258] Step 6: The emotion engine analyzes the voice and facial expressions of the user using the interface. It uses voice analysis and facial expression analysis to understand the user's emotional state.

[1259] Input: User voice data, facial expression data

[1260] Output: User's emotional state

[1261] Step 7: The server's emotion engine suggests actions based on the user's emotional state. For example, if the user is stressed, it provides simple instructions or help information; if the user is satisfied, it provides additional suggestions or promotional information.

[1262] Input: User's emotional state

[1263] Output: Recommended actions (simple instructions, help information, additional suggestions, promotional information, etc.)

[1264] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1265] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1266] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1267] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1268] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1269] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1270] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1271] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1272] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1273] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1274] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1275] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1276] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1277] 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.

[1278] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1279] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1280] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1281] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1282] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1283] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1284] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1285] The following is further disclosed regarding the embodiments described above.

[1286] (Claim 1)

[1287] A user input method for entering store operation data,

[1288] A server preprocessing means that preprocesses the data received from the user input means,

[1289] An AI analysis means for analyzing the data preprocessed by the aforementioned preprocessing means,

[1290] A data extraction means for extracting the analysis results of the aforementioned AI analysis means,

[1291] A PPT generation means that generates a PPT file based on the extraction results of the data extraction means,

[1292] A system that includes this.

[1293] (Claim 2)

[1294] The system according to claim 1, characterized in that the PPT generation means has a function to automatically generate slides using a template.

[1295] (Claim 3)

[1296] The system according to claim 1, characterized in that the AI ​​analysis means has the function of analyzing data using a natural language processing model and a machine learning model.

[1297] "Example 1"

[1298] (Claim 1)

[1299] A user input method for entering store operation data,

[1300] A data processing means for pre-processing data received from the user input means,

[1301] An artificial intelligence analysis means for analyzing data preprocessed by the aforementioned data processing means,

[1302] A data extraction means for extracting, organizing, and visualizing the analysis results of the artificial intelligence analysis means,

[1303] A generation means that automatically generates a presentation in PowerPoint format based on the organized and visualized results of the data extraction means,

[1304] Means for enabling the user to download the PPT file generated by the generation means,

[1305] A system that includes this.

[1306] (Claim 2)

[1307] The system according to claim 1, characterized in that the generation means has a function to automatically generate slides using a template.

[1308] (Claim 3)

[1309] The system according to claim 1, characterized in that the artificial intelligence analysis means has the function of analyzing data using a natural language processing model and a machine learning model.

[1310] "Application Example 1"

[1311] (Claim 1)

[1312] A user input method for entering store operation data,

[1313] A server preprocessing means that preprocesses the data received from the user input means,

[1314] An AI analysis means for analyzing the data preprocessed by the aforementioned preprocessing means,

[1315] A data extraction means for extracting the analysis results of the aforementioned AI analysis means,

[1316] A PPT generation means that generates a PPT file based on the extraction results of the data extraction means,

[1317] A notification means for notifying smart glasses of the aforementioned PPT file in real time,

[1318] A system that includes this.

[1319] (Claim 2)

[1320] The system according to claim 1, characterized in that the PPT generation means has a function to automatically generate slides using a template.

[1321] (Claim 3)

[1322] The system according to claim 1, characterized in that the AI ​​analysis means has the function of analyzing data using a natural language processing model and a machine learning model.

[1323] "Example 2 of combining an emotion engine"

[1324] (Claim 1)

[1325] Input method for entering store operation data,

[1326] A preprocessing means for preprocessing the data received from the input means,

[1327] An analysis means for analyzing the data preprocessed by the aforementioned preprocessing means,

[1328] An extraction means for extracting the analysis results of the aforementioned analysis means,

[1329] A generation means that generates a presentation file based on the extraction results of the extraction means,

[1330] A means of analyzing user emotions,

[1331] A system that includes this.

[1332] (Claim 2)

[1333] The system according to claim 1, characterized in that the generation means has a function to automatically generate slides using a template.

[1334] (Claim 3)

[1335] The system according to claim 1, characterized in that the analysis means has the function of analyzing data using a natural language processing model and a machine learning model.

[1336] "Application example 2 when combining with an emotional engine"

[1337] (Claim 1)

[1338] A user input method for entering store operation data,

[1339] A server preprocessing means that preprocesses the data received from the user input means,

[1340] An AI analysis means for analyzing the data preprocessed by the aforementioned preprocessing means,

[1341] A data extraction means for extracting the analysis results of the aforementioned AI analysis means,

[1342] A PPT generation means that generates a PPT file based on the extraction results of the data extraction means,

[1343] An emotion engine that recognizes user emotions and suggests actions to improve the user experience,

[1344] A system that includes this.

[1345] (Claim 2)

[1346] The system according to claim 1, characterized in that the PPT generation means has a function to automatically generate slides using a template.

[1347] (Claim 3)

[1348] The system according to claim 1, characterized in that the AI ​​analysis means has the function of analyzing data using a natural language processing model and a machine learning model. [Explanation of Symbols]

[1349] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A user input method for entering store operation data, A server preprocessing means that preprocesses the data received from the user input means, An AI analysis means for analyzing the data preprocessed by the aforementioned preprocessing means, A data extraction means for extracting the analysis results of the aforementioned AI analysis means, A PPT generation means that generates a PPT file based on the extraction results of the data extraction means, A system that includes this.

2. The system according to claim 1, characterized in that the PPT generation means has a function to automatically generate slides using a template.

3. The system according to claim 1, characterized in that the AI ​​analysis means has the function of analyzing data using a natural language processing model and a machine learning model.

Images